Electronic device and item information management method thereof

Abstract

Disclosed is an item information management method of an electronic device. The item information management method may comprise the steps of: acquiring information related to a plurality of items including information related to a plurality of images; acquiring hash values of the plurality of images on the basis of a hash algorithm; generating a plurality of item sets corresponding to respective hash values among the hash values of the plurality of images; identifying one or more item sets satisfying a first condition that has been set from among the plurality of item sets; and generating one or more item subsets on the basis of the similarity between the items included in the one or more item sets.

Description

Electronic devices and methods for managing their item information

[0001] The present disclosure relates to an electronic device and a control method thereof for classifying images related to items into several classes and effectively grouping a plurality of items by utilizing similarities between images of each class.

[0002] As internet use becomes more widespread, the e-commerce market is expanding. In particular, interest in e-commerce / online shopping, which allows for non-face-to-face product purchases, is rapidly increasing. Furthermore, the increasing number of sellers offering the same type of item has enabled users to compare similar items and purchase items that best suit their preferences.

[0003] However, even if two items are of the same type, there is a problem that the two items may be determined to be of different types if the seller selling the items enters incorrect information or selects a representative image without any separate criteria.

[0004] The disclosed embodiments provide an electronic device and a method for managing item information thereof. More specifically, the present invention provides an electronic device and a control method thereof that classifies images related to items into multiple classes and effectively groups multiple items by utilizing similarities between images in each class.

[0005] The technical tasks to be achieved by this embodiment are not limited to the technical tasks described above, and other technical tasks can be inferred from the following embodiments.

[0006] One aspect of the present disclosure may provide a method for managing item information, comprising: obtaining information about a plurality of items including information about a plurality of images; obtaining hash values ​​of the plurality of images based on a hash algorithm; generating a plurality of item sets corresponding to each of the plurality of hash values ​​among the hash values ​​of the plurality of images; identifying at least one item set satisfying a set first condition among the plurality of item sets; and generating at least one item subset based on similarity between items included in the at least one item set.

[0007] In addition, in one embodiment of the present disclosure, a method for managing item information may be provided, wherein information about a first item among the plurality of items includes information about one or more images, the one or more images are displayed on a page about the first item provided to a user, and a hash value of the one or more images corresponds to the first item.

[0008] In addition, in one embodiment of the present disclosure, the method for managing item information may further include a step of confirming that type information corresponding to an item included in a first item subset among the one or more item subsets is first type information; and a step of determining the type of an item included in the first item subset as the first type.

[0009] In addition, in one embodiment of the present disclosure, the step of generating the plurality of sets of items may include the step of: identifying a first hash value among hash values ​​of the plurality of images; identifying one or more items corresponding to the first hash value among the plurality of items; and generating a first set of items including the one or more items and corresponding to the first hash value. A method for managing item information may be provided.

[0010] In addition, in one embodiment of the present disclosure, the step of verifying the one or more item sets may include the step of verifying the one or more first item sets by removing the item sets, the number of items included in which are greater than or equal to a first threshold value, from among the plurality of item sets; and the step of verifying the one or more item sets by removing the item sets, the brand information corresponding to the items included in which are two or more, from among the one or more first item sets.

[0011] In addition, in one embodiment of the present disclosure, the step of verifying the one or more item sets may further include the step of verifying that the type information corresponding to an item included in a second item set among the one or more item sets is the same as the second type information; and the step of determining the type of an item included in the second item set as the second type. A method for managing item information may be provided.

[0012] In addition, in one embodiment of the present disclosure, the step of generating one or more item subsets may include: checking whether a similarity between a second item and a third item included in a third item set among the one or more item sets satisfies a set second condition; determining, if the similarity between the second item and the third item satisfies the set second condition, that the second item and the third item are items of the same type; and generating a second item subset including the second item and the third item based on whether an item subset corresponding to the second item or the third item exists in a database.

[0013] In addition, in one embodiment of the present disclosure, the step of checking whether the similarity between the second item and the third item satisfies the set second condition may include the step of comparing a hash value of a first main image corresponding to the second item, a hash value of one or more first detailed images corresponding to the second item, and a hash value of one or more first content images corresponding to the second item with a hash value of a second main image corresponding to the third item, a hash value of one or more second detailed images corresponding to the third item, and a hash value of one or more second content images corresponding to the third item, thereby obtaining a comparison result value; and the step of inputting the comparison result value into a learned model, and determining that the set second condition is satisfied when the output value is a first value, and inputting the comparison result value into the learned model, and determining that the set second condition is not satisfied when the output value is a second value.

[0014] In addition, in one embodiment of the present disclosure, the comparison result value includes: a first comparison result value indicating whether a hash value of the first main image matches a hash value of the second main image; a second comparison result value indicating whether a hash value of the first main image matches a hash value of the one or more second detailed images; a third comparison result value indicating whether a hash value of the second main image matches a hash value of the one or more first detailed images; a fourth comparison result value indicating whether a hash value of the first main image matches a hash value of the one or more second content images; a fifth comparison result value indicating whether a hash value of the second main image matches a hash value of the one or more first content images; at least one sixth comparison result value indicating whether a hash value of the one or more first detailed images matches a hash value of the one or more second detailed images; at least one seventh comparison result value indicating whether a hash value of the one or more first detailed images matches a hash value of the one or more second content images; A method for managing item information may be provided, comprising: at least one eighth comparison result value indicating whether a hash value of the one or more second detailed images matches with a hash value of the one or more first content images; and at least one ninth comparison result value indicating whether a hash value of the one or more first content images matches with a hash value of the one or more second content images.

[0015] In addition, in one embodiment of the present disclosure, the step of checking whether the similarity between the second item and the third item satisfies the set second condition may include the step of comparing a hash value of a first main image corresponding to the second item, a hash value of one or more first detailed images corresponding to the second item, and a hash value of one or more first content images corresponding to the second item with a hash value of a second main image corresponding to the third item, a hash value of one or more second detailed images corresponding to the third item, and a hash value of one or more second content images corresponding to the third item, thereby obtaining a comparison result value; and the step of checking that the set second condition is satisfied when the ratio of pairs of items determined to be items of the same type among pairs of items corresponding to the comparison result values ​​is equal to or greater than a second threshold value.

[0016] In addition, in one embodiment of the present disclosure, the comparison result value includes: a first comparison result value indicating whether a hash value of the first main image matches a hash value of the second main image; a second comparison result value indicating whether a hash value of the first main image matches a hash value of the one or more second detailed images; a third comparison result value indicating whether a hash value of the second main image matches a hash value of the one or more first detailed images; a fourth comparison result value indicating whether a hash value of the first main image matches a hash value of the one or more second content images; a fifth comparison result value indicating whether a hash value of the second main image matches a hash value of the one or more first content images; at least one sixth comparison result value indicating whether a hash value of the one or more first detailed images matches a hash value of the one or more second detailed images; at least one seventh comparison result value indicating whether a hash value of the one or more first detailed images matches a hash value of the one or more second content images; A method for managing item information may be provided, comprising: at least one eighth comparison result value indicating whether a hash value of the one or more second detailed images matches with a hash value of the one or more first content images; and at least one ninth comparison result value indicating whether a hash value of the one or more first content images matches with a hash value of the one or more second content images.

[0017] In addition, in one embodiment of the present disclosure, the step of checking whether the similarity between the second item and the third item satisfies the set second condition may include the step of checking attribute information, brand information, and item name information corresponding to each of the second item and the third item; and the step of inputting the attribute information, the brand information, and the item name information into a learned model and checking that the set second condition is satisfied when the output value is greater than or equal to a third threshold value. A method for managing item information may be provided.

[0018] In addition, in one embodiment of the present disclosure, the step of creating the second item subset may include one of the following steps: if there is no item subset corresponding to the second item and the third item in the database, creating the second item subset and including the second item and the third item in the second item subset; if there is only the second item subset corresponding to the second item in the database, including the third item in the second item subset; if there is only the second item subset corresponding to the third item in the database, including the second item in the second item subset; and if there is an item subset corresponding to each of the second item and the third item in the database, merging the item subsets corresponding to each of the second item and the third item to create the second item subset.

[0019] In addition, in one embodiment of the present disclosure, a method for managing item information may be provided, wherein a hash value of a first image among the plurality of images includes a value obtained by concatenating a second hash value obtained based on a first hash algorithm, a third hash value obtained based on the second hash algorithm, and a fourth hash value obtained based on the third hash algorithm, and a length of the second hash value is longer than a length of the third hash value, and a length of the third hash value is longer than a length of the fourth hash value.

[0020] In addition, in one embodiment of the present disclosure, the method for managing item information may further include the steps of: obtaining a request for information regarding a first item among the plurality of items; identifying at least one item determined to be of the same type as the first item, and identifying information regarding one or more images included in information regarding the first item; and providing a first page on which information regarding the at least one item and at least one of the one or more images are displayed.

[0021] Another aspect of the present disclosure may provide an electronic device comprising a transceiver, a memory, and a processor, wherein the processor obtains information about a plurality of items including information about a plurality of images, obtains hash values ​​of the plurality of images based on a hash algorithm, generates a plurality of item sets corresponding to each of the plurality of hash values ​​among the hash values ​​of the plurality of images, identifies one or more item sets satisfying a set first condition among the plurality of item sets, and generates one or more item subsets based on similarities between items included in the one or more item sets.

[0022] Another aspect of the present disclosure may provide a computer-readable recording medium having recorded thereon a program for implementing a method performed by an electronic device.

[0023] Specific details of other embodiments are included in the detailed description and drawings.

[0024] According to the proposed embodiment, one or more of the following effects can be expected.

[0025] According to an embodiment of the present specification, an electronic device can more accurately and effectively determine whether two items are of the same type of item by utilizing all images corresponding to an item, not just one image corresponding to an item, to determine whether two items are of the same type of item.

[0026] Additionally, according to the embodiment of the present specification, the electronic device can more accurately and effectively determine whether two items are of the same type by effectively filtering images commonly displayed on the detailed description pages of all items.

[0027] Additionally, according to an embodiment of the present disclosure, by providing information about items of the same type as a specific item, the electronic device allows the user to compare information about items of the same type and purchase the cheapest item.

[0028] The effects of the invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

[0029] Figure 1 illustrates a system according to one embodiment.

[0030] FIG. 2 illustrates a user interface provided by an electronic device according to one embodiment.

[0031] FIG. 3 is a diagram illustrating a process in which an electronic device manages item information and provides item information to a user according to one embodiment.

[0032] FIG. 4 is a diagram illustrating a process in which an electronic device generates a set of items according to one embodiment.

[0033] FIG. 5 is a diagram illustrating a process in which an electronic device compares hash values ​​of images corresponding to each of two items to obtain a comparison result numerical value according to one embodiment.

[0034] FIGS. 6A to 6C are diagrams for explaining a process for an electronic device to check whether similarity between items satisfies a set condition according to one embodiment.

[0035] FIGS. 7A to 7C are diagrams illustrating a process in which an electronic device generates a subset of items according to one embodiment.

[0036] FIGS. 8A and 8B illustrate a user interface provided by an electronic device according to one embodiment.

[0037] FIG. 9 illustrates a flowchart of a method for managing item information of an electronic device according to one embodiment.

[0038] Figure 10 shows a block diagram of an electronic device according to one embodiment.

[0039] The terms used in the embodiments have been selected from widely used and common terms, taking into account the functions of the present disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, in which case their meanings will be described in detail in the relevant description. Therefore, the terms used in this disclosure should not be defined simply as names of terms, but rather based on the meanings of the terms and the overall content of the present disclosure.

[0040] When a part of a specification is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise stated.

[0041] The expression "at least one of a, b, and c" described throughout the specification may encompass 'a alone', 'b alone', 'c alone', 'a and b', 'a and c', 'b and c', or 'all of a, b, and c'.

[0042] The "terminal" mentioned below may be implemented as a computer or portable terminal that can connect to a server or other terminal via a network. Here, the computer includes, for example, a notebook, desktop, laptop, etc. equipped with a web browser, and the portable terminal may include, for example, a wireless communication device that guarantees portability and mobility, and may include all types of handheld-based wireless communication devices such as communication-based terminals such as IMT (International Mobile Telecommunication), CDMA (Code Division Multiple Access), W-CDMA (W-Code Division Multiple Access), LTE (Long Term Evolution), smartphones, tablet PCs, etc.

[0043] Below, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein.

[0044] In the present disclosure, two items being of the same type may mean that the two items are the same product or merchandise sold by different sellers. For example, if the first item is a "500ml Coke of the First Brand" product sold by the first seller and the second item is a "500ml Coke of the First Brand" product sold by the second seller, the first and second items may be determined to be of the same type. Alternatively, if the first item is a "500ml Coke of the First Brand, 48 Count" product sold by the first seller and the second item is a "500ml Coke of the First Brand, 48 Count" product sold by the second seller, the first and second items may be determined to be of the same type. However, the above examples are merely exemplary, and the two items may be determined to be of the same type based on information other than brand information, capacity information, and quantity information.

[0045] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0046] Figure 1 illustrates a system according to one embodiment.

[0047] Referring to FIG. 1, the system may include at least one of an electronic device (100), a user terminal (120), a seller terminal (140), a database (160), and a network (180). Meanwhile, the system illustrated in FIG. 1 only illustrates components related to the present embodiment. Therefore, those skilled in the art will appreciate that, in addition to the components illustrated in FIG. 1, other general-purpose components may be included.

[0048] An electronic device (100) is a device that configures and provides various information. The electronic device (100) may provide the configured information as a web page or application screen, or may provide the information in a form that can be displayed as a web page or application screen on a receiving terminal.

[0049] According to one embodiment, the electronic device (100) may group a plurality of items based on the similarity of images corresponding to each of the plurality of items. For example, the electronic device (100) may obtain information about a plurality of items including information about a plurality of images, obtain hash values ​​of the plurality of images based on a hash algorithm, and generate a plurality of item sets corresponding to each of the plurality of hash values ​​among the hash values ​​of the plurality of images. Thereafter, the electronic device (100) may identify one or more item sets that satisfy a set first condition among the plurality of item sets, and generate one or more item subsets based on the similarity between items included in the one or more item sets.

[0050] The user terminal (120) is a terminal used by each user, and the user can access the service provided by the network (180) using their respective terminals (120). For example, the electronic device (100) may provide the user terminal (120) with an application for providing information related to ordering various items. The user can use the application installed on the respective terminal (120) to check and order items corresponding to the searched keyword. In addition, the user can use the application installed on the respective terminal (120) to compare information on items of the same type sold by multiple sellers and order items that suit their preferences.

[0051] The seller terminal (140) is a terminal used by each seller, and the seller can access the service provided by the network (180) using their respective terminals (140). For example, the electronic device (100) may provide the seller terminal (140) with an application for registering information about an item to be sold. The seller may input one or more images to be displayed on the detailed page of the item to be sold using the application installed on their respective terminals (140). In addition, the seller may input type information, name information, brand information, or attribute information of the item to be sold using the application installed on their respective terminals (140).

[0052] The database (160) is a data structure implemented in a predetermined storage space, and may include a relational database such as MySQL, Oracle, Mssql, a non-relational database such as Redis, MongoDB, CouchDB, an open source search engine such as Elasticsearch, and a combination thereof. For example, the database (160) may store information about items registered by sellers. Alternatively, the database (160) may store a correspondence between items and item subsets. Meanwhile, although FIG. 1 illustrates that the database (160) exists outside the electronic device (100), this is only one embodiment, and the database (160) may be included in the electronic device (100).

[0053] The user terminal (120), the seller terminal (140), the database (160), and the electronic device (100) can communicate with each other within the network (180). The network (180) includes a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and a combination thereof, and is a comprehensive data communication network that enables each network component illustrated in FIG. 1 to communicate smoothly with each other, and may include wired Internet, wireless Internet, and a mobile radio communication network. Wireless communication may include, but is not limited to, wireless LAN (Wi-Fi), Bluetooth, Bluetooth low energy, Zigbee, Wi-Fi Direct (WFD), ultra wideband (UWB), infrared communication (IrDA, infrared Data Association), NFC (Near Field Communication), etc., for example.

[0054] FIG. 2 illustrates a user interface provided by an electronic device (100) according to one embodiment.

[0055] According to one embodiment, the electronic device (100) may provide a page according to a user's request for detailed information. More specifically, upon receiving a request for detailed information regarding a first item from a user terminal (120), the electronic device (100) may identify one or more images corresponding to the first item. Thereafter, the electronic device (100) may transmit information, including information regarding one or more images, to the user terminal (120) in a form that can be displayed as a web page or application screen, such as a detailed description page of the first item. Based on the received information, the user terminal (120) may display a detailed description page of the first item including one or more images on its display.

[0056] For example, the user terminal (120) may obtain a user's input for selecting a first item from among a plurality of items displayed on a search result page, and transmit a request for detailed information about the first item to the electronic device (100). The electronic device (100) may check one or more images (220, 240, 260, 280) corresponding to the first item, and transmit information about a detailed description page (200) of the first item including information about the one or more images (220, 240, 260, 280) to the user terminal (120). Thereafter, referring to FIG. 2, the user terminal (120) may display a detailed description page (200) of the first item, in which one or more images (220, 240, 260, 280) are displayed at a set location, based on the received information.

[0057] At this time, one or more images displayed on the detailed description page of the first item may represent one of a main image, a detailed image, and a content image, depending on the content of the image and the setting information entered by the seller selling the first item. More specifically, the main image may represent an image set by the seller as a representative image of the first item, the detailed image may represent an image containing detailed information about the first item, and the content image may represent an image containing information such as a photo or video about the first item.

[0058] For example, referring to FIG. 2, image (220) may represent a main image representing a first item, image (240) may represent a content image including photographic information about the first item, image (260) may represent a detailed image including nutritional information about the first item, and image (280) may represent a detailed image including return / exchange information about the first item.

[0059] However, the types of user interface components, names of image types, and specific examples of images described above are merely examples, and it is obvious to a person skilled in the art to which the present disclosure pertains that the present disclosure can be implemented with examples different from those described above.

[0060] Meanwhile, a method was previously used to determine whether two items were of the same type based on the similarity between the main images corresponding to each item. However, it was difficult to establish consistent criteria for selecting the main image, which resulted in sellers having to select one of several images corresponding to the item as the main image based on their personal preferences. As a result, even though two items were of the same type, cases frequently occurred where different images were selected as the main images, resulting in them being judged as different types of items. Therefore, to solve this problem, there is a need to utilize all images corresponding to an item, not just the main image, to determine whether two items are of the same type. However, in the case of garbage images commonly displayed on the detailed description pages of all items, such as image (280) of FIG. 2, they cannot be used to determine whether two items are of the same type. Therefore, a method for effectively filtering out garbage images must also be considered.

[0061] FIG. 3 is a diagram for explaining a process in which an electronic device (100) manages item information and provides item information to a user according to one embodiment.

[0062] In step S300, the electronic device (100) may obtain information about a plurality of items including information about a plurality of images from the database (160) according to an embodiment. For example, a plurality of sellers may input information about one or more images to be displayed on a detail page of an item to be sold through their respective seller terminals (140), as well as type information, name information, brand information, or attribute information of the item to be sold, and the information entered by the sellers may be stored in the database (160). Accordingly, the electronic device (100) may check information about a plurality of items including information about a plurality of images, type information, name information, brand information, and attribute information of the plurality of items stored in the database (160).

[0063] In step S305, the electronic device (100) may obtain hash values ​​of a plurality of images based on a hash algorithm according to an embodiment. More specifically, the electronic device (100) may obtain p-hash values ​​of each of the plurality of images using a p-hash (perceptual hash) algorithm.

[0064] For example, the electronic device (100) may obtain 16-bit p-hash values ​​of each of the plurality of images using a first p-hash algorithm. Alternatively, the electronic device (100) may obtain 12-bit p-hash values ​​of each of the plurality of images using a second p-hash algorithm. The electronic device (100) may obtain 8-bit p-hash values ​​of each of the plurality of images using a third p-hash algorithm. However, this is only one embodiment, and the electronic device (100) may obtain at least two of the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of the image, or may obtain hash values ​​of different bit lengths using a different hash algorithm than the above.

[0065] In step S310, the electronic device (100) may generate a plurality of item sets corresponding to each of the plurality of hash values ​​among the hash values ​​of the plurality of images according to an embodiment. For example, the electronic device (100) may identify a first hash value among the hash values ​​of the plurality of images, and identify one or more items corresponding to the first hash value among the plurality of items. Thereafter, the electronic device (100) may generate a first item set including one or more items and corresponding to the first hash value. The electronic device (100) may generate a plurality of item sets by performing the above-described process for each of the hash values ​​of the plurality of images.

[0066] At this time, the item set refers to a collection of items corresponding to the same hash value, and may be referred to as a p-hash bucket, etc., but the referring term is not limited to the above.

[0067] Meanwhile, a specific example of an electronic device (100) generating a plurality of item sets corresponding to each of a plurality of hash values ​​among the hash values ​​of a plurality of images will be described in more detail with reference to FIG. 4.

[0068] In step S315, the electronic device (100) may identify one or more item sets that satisfy a first condition set among a plurality of item sets according to an embodiment. More specifically, the electronic device (100) may identify one or more first item sets by removing item sets whose number of items included is greater than or equal to a first threshold value among the plurality of item sets, and may identify one or more item sets by removing item sets whose brand information corresponding to items included in the one or more first item sets is two or more.

[0069] For example, the electronic device (100) may filter out item sets corresponding to garbage images commonly displayed on detailed description pages of all items by removing item sets that include 100 or more items from among a plurality of item sets or by removing 5000 item sets that include the largest number of items from among a plurality of item sets. Thereafter, the electronic device (100) may filter out item sets that include different types of items by removing item sets that include 2 or more brand information corresponding to the items included from among the remaining item sets.

[0070] However, the number of items included or the top ranking based on the number of items included, which serves as a criterion for filtering garbage images, may be set differently from the above-described method. Furthermore, the electronic device (100) may, differently from the above-described method, remove a set of items whose number of included items is greater than or equal to a first threshold value after removing a set of items whose brand information corresponding to the included items is two or more.

[0071] According to one embodiment, the electronic device (100) may determine the type of an item included in an item set, skipping subsequent steps based on the type information of the items included in the item set. For example, the electronic device (100) may confirm that the type information corresponding to an item included in a first item set among one or more item sets is identical to the first type information. Accordingly, the electronic device (100) may determine the type of all items included in the item set as the first type.

[0072] At step S320, the electronic device (100) may, according to one embodiment, pair items included in one or more item sets and determine whether the similarity between the items satisfies a second condition set. More specifically, the electronic device (100) may determine whether the similarity between the items satisfies the second condition set by using the hash value of the image corresponding to the item or by using attribute information, brand information, and item name information.

[0073] For example, the electronic device (100) may obtain a comparison result value by comparing a hash value of a first main image corresponding to a first item included in a first item set among one or more item sets, a hash value of one or more first detailed images corresponding to the first item, a hash value of one or more first content images corresponding to the first item, a hash value of a second main image corresponding to a second item, a hash value of one or more second detailed images corresponding to the second item, and a hash value of one or more second content images corresponding to the second item. Thereafter, the electronic device (100) may input the comparison result value into a learned model, and if the output value is the first value, determine that the set second condition is satisfied, and if the output value is the second value, determine that the set second condition is not satisfied.

[0074] For another example, the electronic device (100) may obtain a comparison result numerical value by comparing a hash value of a first main image corresponding to a first item included in a first item set among one or more item sets, a hash value of one or more first detailed images corresponding to the first item, a hash value of one or more first content images corresponding to the first item, a hash value of a second main image corresponding to a second item, a hash value of one or more second detailed images corresponding to the second item, and a hash value of one or more second content images corresponding to the second item. Thereafter, the electronic device (100) may determine that the set second condition is satisfied when the ratio of pairs of items determined to be items of the same type among pairs of items corresponding to the comparison result numerical value is equal to or greater than a second threshold value.

[0075] For another example, the electronic device (100) can verify attribute information, brand information, and item name information corresponding to each of the first and second items among one or more sets of items. Thereafter, the electronic device (100) inputs the attribute information, brand information, and item name information into the learned model, and if the output value is greater than or equal to a third threshold value, it can determine that the established second condition is satisfied.

[0076] Meanwhile, a specific example of an electronic device (100) pairing items included in one or more item sets and checking whether the items satisfy a second condition in which similarity between the items is set will be described in more detail with reference to FIGS. 5 and 6a to 6c.

[0077] In step S325, the electronic device (100) may determine, according to an embodiment, that a pair of items among the item pairs that satisfy a second condition in which a similarity between the items is set is an item of the same type. For example, the electronic device (100) may determine that a first item and a second item included in a first item set among one or more item sets satisfy a second condition in which a similarity is set, and determine that the first item and the second item are items of the same type.

[0078] In step S330, the electronic device (100) may, according to one embodiment, determine whether a subset of items corresponding to the pair of items exists in the database (160). For example, if it is determined that the first item and the second item are of the same type of item, the electronic device (100) may determine whether information regarding the subset of items corresponding to each of the first item and the second item is stored in the database (160).

[0079] In step S335, the electronic device (100) may generate one or more item subsets based on the verification result according to one embodiment. More specifically, the electronic device (100) may generate one or more item subsets based on the number of item subsets corresponding to the item pairs stored in the database (160).

[0080] For example, if an item subset corresponding to the first item and the second item does not exist in the database (160), the electronic device (100) may create a new item subset and include the first item and the second item in the newly created item subset.

[0081] For another example, the electronic device (100) may include the second item in the item subset corresponding to the first item if only a subset of items corresponding to the first item exists in the database (160).

[0082] For another example, the electronic device (100) may include the first item in the item subset corresponding to the second item if only a subset of items corresponding to the second item exists in the database (160).

[0083] For another example, if there are item subsets corresponding to each of the first item and the second item in the database (160), the electronic device (100) can merge the item subsets corresponding to each of the first item and the second item to create a new item subset.

[0084] At this time, the item subset refers to a set of items determined to be of the same type, and may be referred to as a product bucket, etc., but the referring term is not limited to the above.

[0085] Meanwhile, a specific example of an electronic device (100) generating one or more item subsets based on the number of item subsets corresponding to item pairs stored in a database (160) will be described in more detail with reference to FIGS. 7A to 7C.

[0086] In step S340, the electronic device (100) may determine the type of an item based on type information corresponding to an item included in one or more item subsets according to an embodiment. For example, the electronic device (100) may confirm that the type information corresponding to an item included in a first item subset among one or more item subsets is first type information, and may determine the types of all items included in the first item subset to be the first type.

[0087] At step S345, the electronic device (100) may receive a request for information about a first item from a user terminal (120) according to one embodiment.

[0088] For example, the user terminal (120) may obtain a user's input for selecting a first item among items displayed on a search results page and transmit a request for detailed information about the first item to the electronic device (100).

[0089] For another example, the user terminal (120) may obtain a user's input of entering a keyword into a search box and transmit a search result request corresponding to the entered keyword to the electronic device (100).

[0090] As another example, the user terminal (120) may obtain a user input returning to a search results page from a detailed description page for a first item, and transmit a request for information about an item of the same type as the first item to the electronic device (100).

[0091] At step S350, the electronic device (100) can check at least one of information about at least one item determined to be of the same type as the first item and one or more images included in the information about the first item according to one embodiment.

[0092] For example, the electronic device (100) can verify that the type of the first item is the first type and can verify at least one item of the first type. In addition, the electronic device (100) can verify one or more images corresponding to the first item.

[0093] For another example, the electronic device (100) can identify items corresponding to a keyword received from the user terminal (120). Thereafter, the electronic device (100) can identify that the type of the first item among the identified items is the first type, and identify at least one item of the first type.

[0094] In step S355, the electronic device (100) may transmit information about a first page including at least one of information about at least one item and information about one or more images to the user terminal (120), according to one embodiment.

[0095] For example, the electronic device (100) may transmit information in a form that can be displayed as a web page or application screen, such as a detailed description page of a first item, including information about at least one item and information about one or more images, to the user terminal (120).

[0096] For another example, the electronic device (100) may transmit information in a form that can be displayed as a web page or application screen, such as a search result page corresponding to a keyword, including information about at least one item, to the user terminal (120).

[0097] At step S360, the user terminal (120) may provide the first page to the user according to one embodiment.

[0098] For example, the user terminal (120) may display a detailed description page of a first item including information about at least one item and information about one or more images based on information received from the electronic device (100).

[0099] For another example, the user terminal (120) may display a search results page including information about at least one item based on information received from the electronic device (100).

[0100] FIG. 4 is a diagram for explaining a process in which an electronic device (100) generates an item set according to one embodiment.

[0101] According to one embodiment, the electronic device (100) may generate a plurality of sets of items, each corresponding to a plurality of hash values ​​among the hash values ​​of a plurality of images. More specifically, the electronic device (100) may identify a specific hash value among the hash values ​​of the plurality of images, and identify one or more items corresponding to the specific hash value among the plurality of items. Thereafter, the electronic device (100) may generate an item set including one or more items and corresponding to the specific hash value.

[0102] For example, referring to FIG. 4, the electronic device (100) can check a first hash value among hash values ​​of a plurality of images, and can check that a first item (400), a second item (410), a third item (420), a fifth item, a sixth item, a seventh item, etc. correspond to the first hash value. Thereafter, the electronic device (100) can generate a first item set (440) that includes the first item (400), the second item (410), the third item (420), the fifth item, the sixth item, the seventh item, etc., and corresponds to the first hash value.

[0103] For another example, referring to FIG. 4, the electronic device (100) can check a second hash value among hash values ​​of a plurality of images, and can check that the first item (400), the second item (410), the third item (420), the fourth item (430), the seventh item, and the eighth item, etc. correspond to the second hash value. Thereafter, the electronic device (100) can generate a second item set (450) that includes the first item (400), the second item (410), the third item (420), the fourth item (430), the seventh item, and the eighth item, etc., and corresponds to the second hash value.

[0104] For another example, referring to FIG. 4, the electronic device (100) can check a third hash value among hash values ​​of a plurality of images and confirm that the first item (400), the third item (420), the sixth item, the ninth item, the tenth item, and the eleventh item correspond to the first hash value. Thereafter, the electronic device (100) can generate a third item set (460) that includes the first item (400), the third item (420), the sixth item, the ninth item, the tenth item, and the eleventh item and corresponds to the third hash value.

[0105] FIG. 5 is a diagram for explaining a process in which an electronic device (100) compares hash values ​​of images corresponding to each of two items to obtain a comparison result numerical value according to one embodiment.

[0106] According to one embodiment, the electronic device (100) may obtain hash values ​​of a plurality of images based on a hash algorithm. More specifically, the electronic device (100) may obtain a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of a plurality of images using a p-hash algorithm.

[0107] For example, the electronic device (100) can obtain a 16-bit p-hash value (ba19c8ab5fa05a59), a 12-bit p-hash value (ccea7d304a59), and an 8-bit p-hash value (c42eb3db) of the main image of the first item using the p-hash algorithm. In addition, the electronic device (100) can obtain a 16-bit p-hash value (ba19c8ab5fa05a59), a 12-bit p-hash value (cfabbc004a49), and an 8-bit p-hash value (c42eb3db) of the main image of the second item using the p-hash algorithm. Similarly, the electronic device (100) can obtain a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of each of n detailed images and n' content images of the first item using a p-hash algorithm, and can obtain a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of each of m detailed images and m' content images of the second item.

[0108] According to one embodiment, the electronic device (100) can obtain a comparison result value by comparing the hash values ​​of the main images corresponding to each of the items. More specifically, the electronic device (100) can compare a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of the main images corresponding to two items, and assign 1 if the hash values ​​match, and assign 0 if they do not match. Thereafter, the electronic device (100) can obtain a comparison result value between the hash values ​​of the main images of the two items by concatenating a result value (H16) of comparing the 16-bit p-hash values, a result value (H12) of comparing the 12-bit p-hash values, and a result value (H8) of comparing the 8-bit p-hash values.

[0109] For example, referring to FIG. 5, the electronic device (100) may determine H16 as 1 upon confirming that the 16-bit p-hash value (ba19c8ab5fa05a59) of the main image of the first item and the 16-bit p-hash value (ba19c8ab5fa05a59) of the main image of the second item match, may determine H12 as 0 upon confirming that the 12-bit p-hash value (ccea7d304a59) of the main image of the first item and the 12-bit p-hash value (cfabbc004a49) of the main image of the second item do not match, and may determine H8 as 1 upon confirming that the 8-bit p-hash value (c42eb3db) of the main image of the first item and the 8-bit p-hash value (c42eb3db) of the main image of the second item match. Thereafter, the electronic device (100) can determine the first comparison result value (500) as 101 (=5) by connecting H16, H12, and H8.

[0110] According to one embodiment, the electronic device (100) can obtain a comparison result value by comparing a hash value of a main image corresponding to each of the items with a hash value of at least one detailed image. More specifically, the electronic device (100) can obtain H16, H12, and H8 by comparing a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of the main images corresponding to two items with a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of at least one detailed image. Thereafter, the electronic device (100) can obtain at least one comparison result value by connecting H16, H12, and H8, and check a largest comparison result value among the at least one comparison result value.

[0111] For example, referring to FIG. 5, the electronic device (100) may obtain m comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of the main image of the first item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of the m detailed images of the second item. Thereafter, the electronic device (100) may determine the largest value among the m comparison result values ​​as the second comparison result value (510).

[0112] For another example, referring to FIG. 5, the electronic device (100) may obtain n comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of the main image of the second item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of n detailed images of the first item. Thereafter, the electronic device (100) may determine the largest value among the n comparison result values ​​as the third comparison result value (520).

[0113] According to one embodiment, the electronic device (100) can obtain a comparison result value by comparing a hash value of a main image corresponding to each of the items with a hash value of at least one content image. More specifically, the electronic device (100) can obtain H16, H12, and H8 by comparing a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of the main images corresponding to two items with a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of at least one content image. Thereafter, the electronic device (100) can obtain at least one comparison result value by connecting H16, H12, and H8, and check a largest comparison result value among the at least one comparison result value.

[0114] For example, referring to FIG. 5, the electronic device (100) may obtain m comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of the main image of the first item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of the m' content images of the second item. Thereafter, the electronic device (100) may determine the largest value among the m' comparison result values ​​as the fourth comparison result value (530).

[0115] For another example, referring to FIG. 5, the electronic device (100) may obtain n comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of the main image of the second item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of the n' content images of the first item. Thereafter, the electronic device (100) may determine the largest value among the n' comparison result values ​​as the fifth comparison result value (540).

[0116] According to one embodiment, the electronic device (100) can obtain at least one comparison result value by comparing the hash values ​​of at least one detailed image corresponding to each of the items. More specifically, the electronic device (100) can obtain H16, H12, and H8 by comparing a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of at least one detailed image corresponding to two items. Thereafter, the electronic device (100) can obtain at least one comparison result value by connecting H16, H12, and H8, and can check three largest comparison result values, a median comparison result value, and a smallest comparison result value among the at least one comparison result value.

[0117] For example, referring to FIG. 5, the electronic device (100) may obtain n*m comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of n detailed images of the first item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of m detailed images of the second item. Thereafter, the electronic device (100) may determine the three largest comparison result values, the median comparison result value, and the smallest comparison result value among the n*m ​​comparison result values ​​as at least one sixth comparison result value (550).

[0118] According to one embodiment, the electronic device (100) can obtain at least one comparison result value by comparing a hash value of at least one detailed image corresponding to each of the items with a hash value of at least one content image. More specifically, the electronic device (100) can obtain H16, H12, and H8 by comparing a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of at least one detailed image corresponding to two items with a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of at least one content image. Thereafter, the electronic device (100) can obtain at least one comparison result value by connecting H16, H12, and H8, and can check three largest comparison result values, a median comparison result value, and a smallest comparison result value among the at least one comparison result values.

[0119] For example, referring to FIG. 5, the electronic device (100) may obtain n*m' comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of n detailed images of the first item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of m' content images of the second item. Thereafter, the electronic device (100) may determine the three largest comparison result values, the median comparison result value, and the smallest comparison result value among the n*m' comparison result values ​​as at least one seventh comparison result value (560).

[0120] For another example, referring to FIG. 5, the electronic device (100) may obtain n'*m comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of the n' content images of the first item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of the m detailed images of the second item. Thereafter, the electronic device (100) may determine the three largest comparison result values, the median comparison result value, and the smallest comparison result value among the n'*m comparison result values ​​as at least one eighth comparison result value (570).

[0121] According to one embodiment, the electronic device (100) can obtain at least one comparison result value by comparing the hash values ​​of at least one content image corresponding to each of the items. More specifically, the electronic device (100) can obtain H16, H12, and H8 by comparing a 16-bit p-hash value, a 12-bit p-hash value, and an 8-bit p-hash value of at least one content image corresponding to two items. Thereafter, the electronic device (100) can obtain at least one comparison result value by connecting H16, H12, and H8, and can check three largest comparison result values, a median comparison result value, and a smallest comparison result value among the at least one comparison result value.

[0122] For example, referring to FIG. 5, the electronic device (100) may obtain n'*m' comparison result values ​​by comparing the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of the n' content images of the first item with the 16-bit p-hash value, the 12-bit p-hash value, and the 8-bit p-hash value of each of the m' content images of the second item. Thereafter, the electronic device (100) may determine the three largest comparison result values, the median comparison result value, and the smallest comparison result value among the n'*m' comparison result values ​​as at least one ninth comparison result value (580).

[0123] According to one embodiment, the electronic device (100) may obtain a comparison result numerical value based on the result values ​​obtained by comparing the main image, at least one detailed image, and at least one content image corresponding to each of two items. More specifically, the electronic device (100) may obtain a comparison result numerical value by connecting the comparison result values ​​obtained by comparing the main image, at least one detailed image, and at least one content image corresponding to each of two items in a set order.

[0124] For example, referring to FIG. 5, the electronic device (100) can obtain a comparison result value of 25 bytes by connecting a first comparison result value (500) of 1 byte size, a second comparison result value (510) of 1 byte size, a third comparison result value (520) of 1 byte size, a fourth comparison result value (530) of 1 byte size, a fifth comparison result value (540) of 1 byte size, at least one sixth comparison result value (550) of 5 bytes size, at least one seventh comparison result value (560) of 5 bytes size, at least one eighth comparison result value (570) of 5 bytes size, and at least one ninth comparison result value (580) of 5 bytes size.

[0125] Meanwhile, the comparison results obtained in this manner can be input into a learned model or rule judgment module and used to determine whether two items are similar. Specific examples related to this will be described in more detail with reference to Figures 6a through 6c.

[0126] FIGS. 6A to 6C are diagrams for explaining a process in which an electronic device (100) checks whether the similarity between items satisfies a set condition according to one embodiment.

[0127] According to one embodiment, the electronic device (100) can pair items included in one or more item sets and determine whether the similarity between the items satisfies a set condition. More specifically, the electronic device (100) can compare the hash values ​​of images corresponding to two items to obtain a comparison result value, and input the comparison result value into a trained model, thereby determining whether the set condition is satisfied based on the output value.

[0128] For example, referring to FIG. 6A, the electronic device (100) can compare images corresponding to each of the first item and the second item included in the first item set (600) to obtain a comparison result numerical value of 25 bytes in size. Thereafter, the electronic device (100) can input the comparison result numerical value into the first model (640), and if the obtained value is the first value or True, it can determine that the set condition is satisfied, and if the obtained value is the second value or False, it can determine that the set condition is not satisfied. Similarly, the electronic device (100) can compare all items included in the first item set (600) and the second item set (620) in pairs to check whether the similarity between all pairs of items satisfies the set condition.

[0129] According to one embodiment, the electronic device (100) can pair items included in one or more item sets and determine whether the similarity between the items satisfies a set condition. More specifically, the electronic device (100) can compare the hash values ​​of images corresponding to two items to obtain a comparison result value, and input the comparison result value into a rule judgment module, thereby determining whether the set condition is satisfied based on the output value.

[0130] For example, referring to FIG. 6B, the electronic device (100) can compare images corresponding to each of the first and second items included in the first item set (600) to obtain a comparison result numerical value of 25 bytes in size. Thereafter, the electronic device (100) can input the comparison result numerical value into the rule judgment module (660) to determine whether the ratio (statistical value) of item pairs determined to be items of the same type among the item pairs corresponding to the comparison result numerical value is greater than or equal to a first threshold value. If the ratio is greater than or equal to the first threshold value, the electronic device (100) can determine that the set condition is satisfied, and if the ratio is less than the first threshold value, the set condition is not satisfied. Similarly, the electronic device (100) can compare all items included in the first item set (600) and the second item set (620) in pairs to determine whether the similarity between all item pairs satisfies the set condition.

[0131] According to one embodiment, the electronic device (100) can pair items included in one or more item sets and determine whether the similarity between the items satisfies a set condition. More specifically, the electronic device (100) can input attribute information, brand information, and item name information corresponding to two items into a learned model and determine whether the set condition is satisfied based on the output values.

[0132] For example, referring to FIG. 6C, the electronic device (100) can check attribute information, brand information, and item name information corresponding to each of the first and second items included in the first item set (600). Thereafter, the electronic device (100) can input attribute information, brand information, and item name information corresponding to each of the first and second items into the second model (680) and check whether the obtained score is equal to or greater than a second threshold value. If the score is equal to or greater than the second threshold value, the electronic device (100) can check that the set condition is satisfied, and if the score is less than the second threshold value, the set condition is not satisfied. Similarly, the electronic device (100) can compare all items included in the first item set (600) and the second item set (620) in pairs to check whether the similarity between all pairs of items satisfies the set condition.

[0133] According to one embodiment, the electronic device (100) may omit the process of checking whether the similarity between some pairs of items satisfies the set condition based on whether the similarity between specific pairs of items satisfies the set condition. More specifically, if the similarity between specific pairs of items satisfies the set condition, the electronic device (100) may omit the process of checking whether the similarity between some pairs of items satisfies the set condition by adaptively selecting two items to be compared.

[0134] For example, referring to FIGS. 6A to 6C, the electronic device (100) can confirm that the similarity between the first item and the second item included in the first item set (600) satisfies the set condition, and can confirm that the similarity between the first item and the third item satisfies the set condition. Accordingly, the electronic device (100) can determine that the similarity between the second item and the third item satisfies the set condition, and can omit the process of confirming whether the similarity between the second item and the third item satisfies the set condition.

[0135] For another example, referring to FIGS. 6A to 6C, the electronic device (100) can confirm that the similarity between the first item and the second item included in the second item set (620) satisfies the set condition, confirm that the similarity between the fourth item and the sixth item satisfies the set condition, and confirm that the similarity between the first item and the fourth item satisfies the set condition. Accordingly, the electronic device (100) can determine that the similarity between the first item and the sixth item, the similarity between the second item and the fourth item, and the similarity between the second item and the sixth item satisfy the set condition, and can omit the process of confirming whether the similarity between the first item and the sixth item, the similarity between the second item and the fourth item, and the similarity between the second item and the sixth item satisfy the set condition.

[0136] For another example, referring to FIGS. 6A to 6C, the electronic device (100) can confirm that the similarity between the first item and the second item included in the first item set (600) satisfies the set condition. Accordingly, the electronic device (100) can omit the process of confirming whether the similarity between the first item and the second item included in the second item set (620) satisfies the set condition.

[0137] According to one embodiment, the electronic device (100) may determine whether two items are of the same type based on whether the similarity between the two items satisfies a set condition. For example, if the similarity between the two items satisfies the set condition, the electronic device (100) may determine that the two items are of the same type. Alternatively, if the similarity between the two items does not satisfy the set condition, the electronic device (100) may determine that the two items are of different types.

[0138] Meanwhile, if two items are determined to be of the same type, the electronic device (100) can check whether an item subset corresponding to the two items exists in the database (160) and, based on the check result, create an item subset including the two items. Related specific examples will be described in more detail with reference to FIGS. 7A to 7C .

[0139] FIGS. 7A to 7C are diagrams for explaining a process in which an electronic device (100) generates an item subset according to one embodiment.

[0140] According to one embodiment, the electronic device (100) can check whether a subset of items corresponding to a pair of items exists in the database (160). For example, if it is determined that a first item and a second item are items of the same type, the electronic device (100) can check whether information regarding a subset of items corresponding to each of the first item and the second item is stored in the database (160).

[0141] According to one embodiment, the electronic device (100) may generate one or more item subsets based on the verification result. More specifically, the electronic device (100) may generate one or more item subsets based on the number of item subsets corresponding to the item pairs stored in the database (160).

[0142] For example, referring to FIG. 7A, the electronic device (100) may determine that a correspondence between the first item and the second item and the item subset is not stored in the database (160). Accordingly, the electronic device (100) may create a new second item subset and include the first item and the second item in the second item subset.

[0143] For another example, referring to FIG. 7B, the electronic device (100) can verify that only the correspondence between the first item and the first item subset is stored in the database (160). Accordingly, the electronic device (100) can include the second item in the first item subset.

[0144] For another example, referring to FIG. 7c, the electronic device (100) can confirm that the database (160) stores a correspondence between a first item and a first item subset and a correspondence between a second item and a second item subset. Accordingly, the electronic device (100) can merge the first item subset and the second item subset to create a new third item subset.

[0145] FIGS. 8A and 8B illustrate a user interface provided by an electronic device (100) according to one embodiment.

[0146] According to one embodiment, the electronic device (100) may provide a page according to a user's request for detailed information. More specifically, upon receiving a request for detailed information regarding a first item from a user terminal (120), the electronic device (100) may identify one or more images corresponding to the first item. Thereafter, the electronic device (100) may transmit information, including information regarding one or more images, to the user terminal (120) in a form that can be displayed as a web page or application screen, such as a detailed description page of the first item. Based on the received information, the user terminal (120) may display a detailed description page of the first item including one or more images on its display.

[0147] For example, the user terminal (120) may obtain a user's input for selecting a first item from among a plurality of items displayed on a search results page, and transmit a request for detailed information about the first item to the electronic device (100). The electronic device (100) may identify one or more images corresponding to the first item, and transmit information about a detailed description page (800) of the first item including information about the one or more images to the user terminal (120). Thereafter, referring to FIG. 2, the user terminal (120) may display, on the display, a detailed description page (800) of the first item, in which one or more images are displayed at a set location, based on the received information.

[0148] According to one embodiment, the electronic device (100) may provide information regarding at least one item of the same type as the first item. More specifically, upon receiving a request for information regarding an item of the same type as the first item from the user terminal (120), the electronic device (100) may identify at least one item determined to be of the same type as the first item. Thereafter, the electronic device (100) may transmit information to the user terminal (120) in a form that can display a page including information regarding at least one item, such as a web page or an application screen. The user terminal (120) may display a page including information regarding at least one item on the display based on the received information.

[0149] For example, referring to FIG. 8A, the user terminal (120) may obtain a user input for selecting a view other sellers icon (820) on a first page (800), and transmit a request for information on items of the same type as the first item to the electronic device (100). The electronic device (100) may confirm a second item, a third item, a fourth item, and a fifth item determined to be of the same type as the first item, and transmit information on a page (840) including information on the second item, the third item, the fourth item, and the fifth item to the user terminal (120). Referring to FIG. 8B, the user terminal (120) may display a page (840) including information on the first item, the second item, the third item, the fourth item, and the fifth item on the display based on the received information.

[0150] In this way, by providing information about items of the same type as the first item, the user can compare information about items of the same type and purchase the cheapest fifth item.

[0151] Meanwhile, the specific examples of the types of user interface components, information about items, and images described above are merely examples, and it is obvious to a person skilled in the art to which the present disclosure pertains that the present disclosure can be implemented with examples different from those described above.

[0152] Figure 9 illustrates a flowchart of a method for managing item information in an electronic device according to one embodiment. The above description may apply to overlapping content.

[0153] At step S900, the electronic device can obtain information about a plurality of items, including information about a plurality of images.

[0154] According to one embodiment, information about a first item among a plurality of items includes information about one or more images, the one or more images are displayed on a page about the first item provided to the user, and a hash value of the one or more images may correspond to the first item.

[0155] At step S920, the electronic device can obtain hash values ​​of multiple images based on a hash algorithm.

[0156] According to one embodiment, a hash value of a first image among a plurality of images includes a value obtained by concatenating a second hash value obtained based on a first hash algorithm, a third hash value obtained based on the second hash algorithm, and a fourth hash value obtained based on the third hash algorithm, wherein a length of the second hash value may be longer than a length of the third hash value, and a length of the third hash value may be longer than a length of the fourth hash value.

[0157] At step S940, the electronic device can generate a plurality of item sets corresponding to each of the plurality of hash values ​​among the plurality of images.

[0158] According to one embodiment, when generating a plurality of sets of items, a first hash value among hash values ​​of a plurality of images may be identified, one or more items corresponding to the first hash value among the plurality of items may be identified, and a first set of items including one or more items and corresponding to the first hash value may be generated.

[0159] At step S960, the electronic device can identify one or more sets of items that satisfy a set first condition among a plurality of sets of items.

[0160] According to one embodiment, when verifying one or more sets of items, the electronic device can verify one or more sets of first items by removing sets of items whose number of items included is greater than or equal to a first threshold value from among the plurality of sets of items, and can verify one or more sets of items by removing sets of items whose brand information corresponding to items included is two or more from among the one or more sets of first items.

[0161] According to one embodiment, when checking one or more sets of items, the electronic device can check that type information corresponding to an item included in a second set of items among the one or more sets of items is the same as second type information, and determine the type of the item included in the second set of items as the second type.

[0162] At step S980, the electronic device can generate one or more item subsets based on similarity between items included in one or more item sets.

[0163] According to one embodiment, the electronic device can determine that type information corresponding to an item included in a first item subset among one or more item subsets is first type information, and determine the type of the item included in the first item subset as the first type.

[0164] According to one embodiment, when generating one or more item subsets, the electronic device may determine whether a similarity between a second item and a third item included in a third item set among the one or more item sets satisfies a second condition, and if the similarity between the second item and the third item satisfies the second condition, determine that the second item and the third item are items of the same type, and generate a second item subset including the second item and the third item based on whether an item subset corresponding to the second item or the third item exists in a database.

[0165] According to one embodiment, when determining whether the similarity between the second item and the third item satisfies the set second condition, the electronic device may compare a hash value of a first main image corresponding to the second item, a hash value of one or more first detailed images corresponding to the second item, a hash value of one or more first content images corresponding to the second item, a hash value of a second main image corresponding to the third item, a hash value of one or more second detailed images corresponding to the third item, and a hash value of one or more second content images corresponding to the third item, thereby obtaining a comparison result value, and inputting the comparison result value into a learned model, and if the output value is the first value, determining that the set second condition is satisfied, and inputting the comparison result value into the learned model, and if the output value is the second value, determining that the set second condition is not satisfied.

[0166] According to one embodiment, when determining whether the similarity between the second item and the third item satisfies the set second condition, the electronic device may compare a hash value of a first main image corresponding to the second item, a hash value of one or more first detailed images corresponding to the second item, a hash value of one or more first content images corresponding to the second item, a hash value of a second main image corresponding to the third item, a hash value of one or more second detailed images corresponding to the third item, and a hash value of one or more second content images corresponding to the third item to obtain a comparison result value, and when a ratio of pairs of items determined to be items of the same type among pairs of items corresponding to the comparison result values ​​is equal to or greater than a second threshold value, it may be determined that the set second condition is satisfied.

[0167] According to one embodiment, the comparison result value includes a first comparison result value indicating whether there is a match between a hash value of a first main image and a hash value of a second main image, a second comparison result value indicating whether there is a match between a hash value of the first main image and a hash value of one or more second detailed images, a third comparison result value indicating whether there is a match between a hash value of a second main image and a hash value of one or more first detailed images, a fourth comparison result value indicating whether there is a match between a hash value of a first main image and a hash value of one or more second content images, a fifth comparison result value indicating whether there is a match between a hash value of a second main image and a hash value of one or more first content images, at least one sixth comparison result value indicating whether there is a match between a hash value of a first detailed image and a hash value of one or more second detailed images, at least one seventh comparison result value indicating whether there is a match between a hash value of a first detailed image and a hash value of one or more second content images, and a match between a hash value of a second detailed image and a hash value of one or more first content images. It may include at least one eighth comparison result value indicating whether there is a match between the hash values ​​of one or more first content images and the hash values ​​of one or more second content images.

[0168] According to one embodiment, when checking whether the similarity between the second item and the third item satisfies the set second condition, the electronic device checks attribute information, brand information, and item name information corresponding to each of the second item and the third item, and inputs the attribute information, brand information, and item name information into the learned model. If the output value is greater than or equal to the third threshold value, the set second condition can be determined to be satisfied.

[0169] According to one embodiment, when generating a second item subset, if there is no item subset corresponding to the second item and the third item in the database, the electronic device may generate a second item subset and include the second item and the third item in the second item subset, if there is only a second item subset corresponding to the second item in the database, the electronic device may include the third item in the second item subset, if there is only a second item subset corresponding to the third item in the database, the electronic device may include the second item in the second item subset, and if there is an item subset corresponding to each of the second item and the third item in the database, the electronic device may merge the item subsets corresponding to each of the second item and the third item to generate the second item subset.

[0170] According to one embodiment, the electronic device may obtain a request for information regarding a first item among a plurality of items, identify at least one item determined to be of the same type as the first item, identify information regarding one or more images included in the information regarding the first item, and provide a first page displaying at least one of the information regarding the at least one item and the one or more images.

[0171] FIG. 10 shows a block diagram of an electronic device (100) according to one embodiment.

[0172] According to an embodiment, the electronic device (100) may include a transceiver (1020), a memory (1040), and a processor (1060). The electronic device (100) illustrated in FIG. 10 only includes components related to the present embodiment. Therefore, it will be understood by those skilled in the art that the electronic device (100) may further include general-purpose components in addition to the components illustrated in FIG. 10. In the embodiment, the transceiver (1020) may be included in a communication device. Additionally, in the embodiment, the processor (1060) may be included in a controller.

[0173] The transceiver (1020) is a device for performing wired / wireless communication and can communicate with external electronic devices. The external electronic devices may be terminals or servers. In addition, communication technologies used by the transceiver (1020) may include GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), LTE (Long Term Evolution), 5G, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Bluetooth (Bluetooth), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), ZigBee, NFC (Near Field Communication), etc.

[0174] The processor (1060) can control the overall operation of the electronic device (100) and process data and signals. The processor (1060) can be composed of at least one hardware unit. In addition, the processor (1060) can operate by one or more software modules generated by executing program codes stored in the memory (1040). The processor (1060) can include a memory, and the processor (1060) can control the overall operation of the electronic device (100) and process data and signals by executing program codes stored in the memory.

[0175] The processor (1060) may obtain information about a plurality of items including information about a plurality of images, obtain hash values ​​of the plurality of images based on a hash algorithm, generate a plurality of item sets corresponding to each of the plurality of hash values ​​among the hash values ​​of the plurality of images, identify one or more item sets that satisfy a set first condition among the plurality of item sets, and generate one or more item subsets based on similarity between items included in the one or more item sets.

[0176] The electronic device according to the above-described embodiments may include a processor, a memory for storing and executing program data, permanent storage such as a disk drive, a communication port for communicating with an external device, a user interface device such as a touch panel, a key, a button, etc. The methods implemented as software modules or algorithms may be stored on a computer-readable recording medium as computer-readable codes or program instructions executable on the processor. Here, the computer-readable recording medium includes a magnetic storage medium (e.g., read-only memory (ROM), random-access memory (RAM), floppy disk, hard disk, etc.) and an optical reading medium (e.g., CD-ROM, DVD: Digital Versatile Disc)). The computer-readable recording medium may be distributed to computer systems connected to a network, so that the computer-readable code may be stored and executed in a distributed manner. The medium may be readable by a computer, stored in a memory, and executed by a processor.

[0177] The present embodiment may be represented by functional block configurations and various processing steps. These functional blocks may be implemented by various hardware and / or software configurations that perform specific functions. For example, the embodiment may employ integrated circuit configurations such as memory, processing, logic, look-up tables, etc., which may perform various functions under the control of one or more microprocessors or other control devices. Similarly, the present embodiment may be implemented in a programming or scripting language such as C, C++, Java, assembler, etc., including various algorithms implemented as a combination of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms that execute on one or more processors. Furthermore, the present embodiment may employ conventional techniques for electronic configuration, signal processing, and / or data processing. Terms such as "mechanism," "element," "means," and "composition" can be used broadly and are not limited to mechanical or physical structures. These terms can also encompass a series of software routines, such as those associated with a processor.

[0178] The above-described embodiments are merely examples, and other embodiments may be implemented within the scope of the claims set forth below.

Claims

1. In a method for managing item information of an electronic device, A step of obtaining information about a plurality of items including information about a plurality of images; A step of obtaining hash values ​​of the plurality of images based on a hash algorithm; A step of generating a plurality of item sets corresponding to each of a plurality of hash values ​​among the hash values ​​of the plurality of images; A step of checking one or more item sets that satisfy a first condition set among the plurality of item sets; and A method for managing item information, comprising the step of generating one or more item subsets based on similarity between items included in one or more item sets.

2. In paragraph 1, Information about a first item among the plurality of items includes information about one or more images, The one or more images are displayed on a page relating to the first item provided to the user, A method for managing item information, wherein the hash value of the one or more images corresponds to the first item.

3. In the first paragraph, the item information management method, A step of confirming that the type information corresponding to an item included in a first item subset among the one or more item subsets is first type information: and An item information management method further comprising a step of determining the type of an item included in the first item subset as the first type.

4. In the first paragraph, the step of generating the plurality of item sets is: A step of verifying a first hash value among the hash values ​​of the above plurality of images; A step of verifying one or more items corresponding to the first hash value among the plurality of items; and A method for managing item information, comprising the step of generating a first item set including one or more items and corresponding to the first hash value.

5. In the first paragraph, the step of verifying one or more sets of items comprises: A step of identifying one or more first item sets by removing item sets whose number of items included in the plurality of item sets is greater than or equal to a first threshold value; and An item information management method comprising a step of verifying one or more sets of items by removing sets of items having two or more brand information corresponding to items included in one or more sets of first items.

6. In the fifth paragraph, the step of verifying one or more sets of items comprises: A step of confirming that the type information corresponding to an item included in a second item set among the one or more item sets is the same as the second type information; and An item information management method further comprising a step of determining the type of an item included in the second item set as a second type.

7. In the first paragraph, the step of generating one or more item subsets comprises: A step of checking whether the similarity between the second item and the third item included in the third item set among the one or more item sets satisfies the second condition set; A step of determining that the second item and the third item are items of the same type when the similarity between the second item and the third item satisfies the second condition set above; and A method for managing item information, comprising the step of generating a second item subset including the second item and the third item based on whether an item subset corresponding to the second item or the third item exists in a database.

8. In the 7th paragraph, the step of checking whether the similarity between the second item and the third item satisfies the set second condition is as follows: A step of obtaining a comparison result value by comparing a hash value of a first main image corresponding to the second item, a hash value of one or more first detailed images corresponding to the second item, a hash value of one or more first content images corresponding to the second item, a hash value of a second main image corresponding to the third item, a hash value of one or more second detailed images corresponding to the third item, and a hash value of one or more second content images corresponding to the third item; and An item information management method comprising a step of inputting the comparison result value into the learned model and confirming that the set second condition is satisfied if the output value is the first value, and inputting the comparison result value into the learned model and confirming that the set second condition is not satisfied if the output value is the second value.

9. In paragraph 8, the comparison result value is, A first comparison result value indicating whether there is a match between the hash value of the first main image and the hash value of the second main image; A second comparison result value indicating whether there is a match between the hash value of the first main image and the hash value of the one or more second detailed images; A third comparison result value indicating whether there is a match between the hash value of the second main image and the hash value of the one or more first detailed images; A fourth comparison result value indicating whether there is a match between the hash value of the first main image and the hash value of the one or more second content images; A fifth comparison result value indicating whether there is a match between the hash value of the second main image and the hash value of the one or more first content images; At least one sixth comparison result value indicating whether there is a match between the hash value of the one or more first detailed images and the hash value of the one or more second detailed images; At least one seventh comparison result value indicating whether there is a match between the hash value of the one or more first detailed images and the hash value of the one or more second content images; At least one eighth comparison result value indicating whether there is a match between the hash value of the one or more second detailed images and the hash value of the one or more first content images; and An item information management method comprising at least one ninth comparison result value indicating whether there is a match between a hash value of the one or more first content images and a hash value of the one or more second content images.

10. In the 7th paragraph, the step of checking whether the similarity between the second item and the third item satisfies the set second condition is as follows: A step of obtaining a comparison result value by comparing a hash value of a first main image corresponding to the second item, a hash value of one or more first detailed images corresponding to the second item, a hash value of one or more first content images corresponding to the second item, a hash value of a second main image corresponding to the third item, a hash value of one or more second detailed images corresponding to the third item, and a hash value of one or more second content images corresponding to the third item; and An item information management method, comprising a step of confirming that the second condition set is satisfied when the ratio of item pairs determined to be items of the same type among the item pairs corresponding to the above comparison result numerical value is greater than or equal to the second threshold value.

11. In the 10th paragraph, the comparison result value is, A first comparison result value indicating whether there is a match between the hash value of the first main image and the hash value of the second main image; A second comparison result value indicating whether there is a match between the hash value of the first main image and the hash value of the one or more second detailed images; A third comparison result value indicating whether there is a match between the hash value of the second main image and the hash value of the one or more first detailed images; A fourth comparison result value indicating whether there is a match between the hash value of the first main image and the hash value of the one or more second content images; A fifth comparison result value indicating whether there is a match between the hash value of the second main image and the hash value of the one or more first content images; At least one sixth comparison result value indicating whether there is a match between the hash value of the one or more first detailed images and the hash value of the one or more second detailed images; At least one seventh comparison result value indicating whether there is a match between the hash value of the one or more first detailed images and the hash value of the one or more second content images; At least one eighth comparison result value indicating whether there is a match between the hash value of the one or more second detailed images and the hash value of the one or more first content images; and An item information management method comprising at least one ninth comparison result value indicating whether there is a match between a hash value of the one or more first content images and a hash value of the one or more second content images.

12. In the 7th paragraph, the step of checking whether the similarity between the second item and the third item satisfies the set second condition is as follows: A step of checking attribute information, brand information, and item name information corresponding to each of the second item and the third item; and An item information management method, comprising a step of inputting the above attribute information, the above brand information, and the above item name information into a learned model and confirming that the set second condition is satisfied when the output value is greater than or equal to a third threshold value.

13. In the 7th paragraph, the step of generating the second item subset is: If an item subset corresponding to the second item and the third item does not exist in the database, a step of creating the second item subset and including the second item and the third item in the second item subset; A step of including the third item in the second item subset, if only the second item subset corresponding to the second item exists in the database; If only the second item subset corresponding to the third item exists in the database, a step of including the second item in the second item subset; and A method for managing item information, comprising one of the steps of: generating the second item subset by merging the item subsets corresponding to the second item and the third item, if an item subset corresponding to each of the second item and the third item exists in the database.

14. In paragraph 1, The hash value of the first image among the plurality of images includes a value obtained by concatenating a second hash value obtained based on a first hash algorithm, a third hash value obtained based on a second hash algorithm, and a fourth hash value obtained based on a third hash algorithm, A method for managing item information, wherein the length of the second hash value is longer than the length of the third hash value, and the length of the third hash value is longer than the length of the fourth hash value.

15. In the first paragraph, the item information management method, A step of obtaining a request for information regarding a first item among the plurality of items; A step of confirming at least one item determined to be of the same type as the first item, and confirming information about one or more images included in the information about the first item; and A method for managing item information, further comprising the step of providing a first page displaying information about at least one item and at least one of the one or more images.

16. A non-transitory computer-readable recording medium having recorded thereon a program for executing the method of paragraph 1 on a computer.

17. As an electronic device, transceiver; memory; and A processor comprising: Obtain information about a plurality of items that include information about a plurality of images, Based on a hash algorithm, the hash values ​​of the plurality of images are obtained, Generate a plurality of item sets corresponding to each of the plurality of hash values ​​among the hash values ​​of the plurality of images, Check one or more item sets that satisfy the first condition among the above multiple item sets, An electronic device that generates one or more item subsets based on similarity between items included in the one or more item sets.

Images