Method and system for displaying product search result

Abstract

Disclosed are a method for displaying a product search result and a system to which the method is applied. The method for displaying a product search result according to an embodiment of the present disclosure may comprise the steps of: receiving a first search word from a user terminal; determining, on the basis of a predefined dictionary, a keyword to be highlighted included in the first search word; and transmitting, to the user terminal, data for configuring a first interface including the product name of a first product corresponding to the first search word. The data for configuring the first interface may include information related to applying a different highlight effect to each region in which the keyword to be highlighted included in the first search word is displayed.

Description

Product search results display method and system

[0001] A method for displaying product search results is disclosed. More specifically, the present disclosure relates to a method for highlighting keywords included in the product name of a product corresponding to a search term entered by a user, and a system employing the method.

[0002] When purchasing products through online commerce, online commerce services generally include a search function to enable users to specify the product they wish to purchase among multiple products registered with the online commerce service.

[0003] To identify products within the same category with desired attributes, users typically enter search terms that include the product name and keywords related to the product's attributes. However, to ensure users receive accurate information on desired products, online commerce services typically structure their SRP (Search Results Page) to include information about products unrelated to the attributes of the product they're looking for.

[0004] In the case of the above-mentioned conventional technology, there is a problem in that the product list corresponding to the search word entered by the user is randomly mixed with products having the attributes desired by the user and products that do not, making it difficult for the user to accurately identify the product he or she wishes to purchase from the displayed product list. Therefore, improvement of this inefficiency is required.

[0005] A technical problem to be achieved through some embodiments of the present disclosure is to provide a method for separating a product name and a keyword expressing an attribute of the product from a search word entered by a user.

[0006] Another technical problem to be achieved through some embodiments of the present disclosure is to provide a method for displaying attribute information of a product entered by a user in a product list corresponding to a search word entered by the user in a manner different from the product name.

[0007] Another technical problem to be achieved through some embodiments of the present disclosure is to provide a method for highlighting attribute keywords of products that have been searched by multiple users in a product list corresponding to a search term entered by a user.

[0008] Another technical problem to be achieved through some embodiments of the present disclosure is to provide a method for displaying product names and product attribute information differently in an area where product names of multiple products displayed in a product list corresponding to a search word entered by a user are displayed.

[0009] The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0010] In order to solve the above technical problem, a product search result display method according to one embodiment of the present disclosure may include the steps of receiving a first search word from a user terminal, the step of determining a highlight target keyword included in the first search word based on a predefined dictionary, and the step of transmitting data for constructing a first interface including a product name of a first product corresponding to the first search word to the user terminal. The data for constructing the first interface may include information related to applying different highlight effects to each area where highlight target keywords included in the first search word are displayed.

[0011] In some embodiments, the first search term may include a main keyword and a property keyword, the main keyword of the first search term may be a keyword that is a brand name of a product included in the first search term, the property keyword of the first search term may be a keyword corresponding to a property of the product included in the first search term, and the data for configuring the first interface may include information related to applying a first highlight effect to the main keyword of the first search term and applying a highlight effect different from the first highlight effect to the property keyword of the first search term.

[0012] In some embodiments, the data for configuring the first interface may include information related to applying different highlight effects to attribute keywords of the first category and attribute keywords of the second category, respectively, when there are multiple attribute keywords of the first search term.

[0013] In some embodiments, the attribute keywords of the first category may be keywords related to product specification information, and the attribute keywords of the second category may be keywords related to product quantity information.

[0014] In some embodiments, the method may further include the steps of tokenizing the first search term to obtain a first token and a second token, determining the first token as the main keyword of the first search term if the first token corresponds to a brand name included in the predefined dictionary, obtaining information related to a plurality of products related to the first token, and determining the second token as the attribute keyword of the first search term if the second token is included in the information related to a plurality of products related to the first token by a threshold value or more.

[0015] In some embodiments, the method may further include the steps of tokenizing the first search term to obtain a first token and a second token, identifying in a previously generated knowledge graph that the first token is a node having at least one subordinate node, identifying in the knowledge graph that the second token is a subordinate node of the first token, and determining the first token as the main keyword of the first search term and determining the second token as the attribute keyword of the first search term.

[0016] In some embodiments, the method may further include the steps of performing semantic analysis on the first search term, using the results of the semantic analysis, determining a proper noun of a product included in the first search term as a main keyword of the first search term, and using the results of the semantic analysis, determining a keyword corresponding to an attribute of a product included in the first search term as an attribute keyword of the first search term.

[0017] In some embodiments, the data for configuring the first interface may include information related to applying a highlight effect different from the first highlight effect to an area where the image of the first product is displayed, when the image of the first product includes a feature associated with a keyword included in the first search term.

[0018] In some embodiments, the first interface may include information regarding applying a highlight effect different from the first highlight effect to an area where an object associated with a keyword included in the first search term of the image of the first product is displayed.

[0019] In some embodiments, the method may further include, after receiving the first search term from the user terminal, the step of receiving a second search term, and the step of transmitting data for configuring a second interface including a product name of a second product corresponding to the second search term to the user terminal. The data for configuring the second interface may include information related to applying a highlight effect to an area where the first keyword is displayed when the first keyword included in the first search term is present in the product name of the second product.

[0020] In some embodiments, the data for configuring the first interface may include information related to applying a highlight effect to an area where keywords that are not included in the first search term but are included in a plurality of search terms related to the first product received by a criterion or more are displayed.

[0021] A product search result providing system according to another embodiment of the present disclosure for solving the above-described technical problem may include one or more processors and a memory storing a computer program executed by the one or more processors. The computer program may include instructions that cause the processor to perform the steps of: receiving a first search term from a user terminal; determining a highlight target keyword included in the first search term based on a predefined dictionary; and transmitting data for constructing a first interface including a product name of a first product corresponding to the first search term to the user terminal. Here, the data for constructing the first interface may include information related to applying different highlight effects to each area where highlight target keywords included in the first search term are displayed.

[0022] In some embodiments, the first search term may include a main keyword and a property keyword, the main keyword of the first search term may be a keyword that is a brand name of a product included in the first search term, the property keyword of the first search term may be a keyword corresponding to a property of the product included in the first search term, and the data for configuring the first interface may include information related to applying a first highlight effect to the main keyword of the first search term and applying a highlight effect different from the first highlight effect to the property keyword of the first search term.

[0023] In some embodiments, the data for configuring the first interface may include information related to applying different highlight effects to attribute keywords of the first category and attribute keywords of the second category, respectively, when there are multiple attribute keywords of the first search term.

[0024] In some embodiments, the computer program may further include instructions to cause the processor to perform the steps of: tokenizing the first search term to obtain a first token and a second token; determining the first token as the main keyword of the first search term if the first token corresponds to a brand name included in the predefined dictionary; obtaining information related to a plurality of products related to the first token; and determining the second token as the attribute keyword of the first search term if the second token is included in the information related to the plurality of products related to the first token by a threshold value or more.

[0025] In some embodiments, the computer program may further include instructions that cause the processor to perform the steps of: tokenizing the first search term to obtain a first token and a second token; identifying in a previously generated knowledge graph that the first token is a node having at least one subordinate node; identifying in the knowledge graph that the second token is a subordinate node of the first token; and determining the first token as the main keyword of the first search term and determining the second token as the attribute keyword of the first search term.

[0026] In some embodiments, the computer program may further include instructions that cause the processor to perform a step of performing a semantic analysis on the first search term, a step of determining a proper noun of a product included in the first search term as a main keyword of the first search term using a result of the semantic analysis, and a step of determining a keyword corresponding to an attribute of a product included in the first search term as an attribute keyword of the first search term using a result of the semantic analysis.

[0027] In some embodiments, the data for configuring the first interface may include information related to applying a highlight effect different from the first highlight effect to an area where the image of the first product is displayed, when the image of the first product includes a feature associated with a keyword included in the first search term.

[0028] FIG. 1 illustrates an exemplary environment in which a product search result provision system according to one embodiment of the present disclosure can be applied.

[0029] FIG. 2 is a flowchart of a product search result display method according to another embodiment of the present disclosure.

[0030] FIG. 3 is a diagram for exemplarily explaining a step of determining a highlight target keyword included in the first search term based on a predefined dictionary that can be performed in some embodiments of the present disclosure.

[0031] Figure 4 is a flowchart for explaining in detail some of the operations described with reference to Figure 2.

[0032] FIG. 5 is a diagram for exemplarily explaining a step of specifying an attribute keyword corresponding to an attribute category included in a search term that can be performed in some embodiments of the present disclosure.

[0033] Figure 6 is a flowchart for explaining in detail some of the operations described with reference to Figure 2.

[0034] FIG. 7 is a diagram for exemplarily explaining a step of specifying attribute keywords of a search term based on the frequency with which a specific keyword included in the search term is included in a product name associated with the search term, which can be performed in some embodiments of the present disclosure.

[0035] Figure 8 is a flowchart for explaining in detail some of the operations described with reference to Figure 2.

[0036] FIG. 9 is a diagram for exemplarily explaining a step of specifying attribute keywords of a search term based on a pre-generated knowledge graph that can be performed in some embodiments of the present disclosure.

[0037] FIG. 10 is a diagram for exemplarily explaining a step of transmitting data to a user terminal for configuring an interface including a highlight effect on a product image based on an attribute keyword included in a search word that can be performed in some embodiments of the present disclosure.

[0038] FIG. 11 is a diagram for exemplarily explaining a step of transmitting data to a user terminal for configuring an interface including a highlight effect for a product name corresponding to a search word based on a search word input history that can be performed in some embodiments of the present disclosure.

[0039] FIG. 12 is a diagram for exemplarily explaining a step of transmitting data to a user terminal for configuring an interface including a highlight effect for a product name corresponding to a search term based on search term input history of other users that can be performed in some embodiments of the present disclosure.

[0040] FIG. 13 is a hardware configuration diagram of a product search result provision system according to another embodiment of the present disclosure.

[0041] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the attached drawings. The advantages and features of the present invention, and methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the attached drawings. However, the technical spirit of the present invention is not limited to the following embodiments and may be implemented in various different forms. The following embodiments are provided only to complete the technical spirit of the present invention and to fully inform those skilled in the art of the present invention of the scope of the present invention, and the technical spirit of the present invention is defined only by the scope of the claims.

[0042] In describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description will be omitted.

[0043] Unless otherwise defined, the terms (including technical and scientific terms) used in the following examples may be used with meanings commonly understood by those of ordinary skill in the art to which this disclosure pertains; however, this may vary depending on the intentions of engineers working in the relevant field, precedents, the emergence of new technologies, etc. The terminology used in this disclosure is for the purpose of describing the embodiments and is not intended to limit the scope of this disclosure.

[0044] In the following examples, singular expressions include plural concepts unless the context clearly specifies that they are singular. Furthermore, plural expressions include singular concepts unless the context clearly specifies that they are plural.

[0045] In addition, terms such as first, second, A, B, (a), (b), etc. used in the following embodiments are only used to distinguish certain components from other components, and the nature, order, or sequence of the components are not limited by the terms.

[0046] Before describing various embodiments of the present disclosure, the terms used in the following embodiments will be clarified.

[0047] In some of the examples below, the "main keyword" may refer to the common noun of the product included in a specific search term. For example, in the search term "1000ml low-fat milk," "milk" is the only common noun, so the search term "1000ml low-fat milk" may include the main keyword "milk."

[0048] For another example, in the search term '1000ml of so-and-so brand milk', since the brand name is a proper noun, 'milk' alone may be determined as the main keyword.

[0049] In some other embodiments, the 'main keyword' may mean a keyword that exists as a brand name category in a pre-stored dictionary among keywords included in a specific search term.

[0050] In some other embodiments, the "main keyword" may refer to a keyword included in a specific search term that exists in a previously stored keyword table. For example, if the first keyword table includes "milk," "smartphone," and "camera," the main keyword for the search term "1000ml milk" may be determined to be "milk."

[0051] In some other embodiments, the 'main keyword' may mean the model name of a product included in a specific search term.

[0052] In some other embodiments, the "main keyword" may refer to a trademark or brand name included in a specific search term. In this case, the results of a semantic analysis performed on the specific search term may be used to determine that the trademark or brand name included in the specific search term is the main keyword for the specific search term.

[0053] In some other embodiments, a 'main keyword' may mean a keyword corresponding to a node having at least one subnode in a pre-stored knowledge graph that is included in a specific search term.

[0054] In some embodiments below, an "attribute keyword" may refer to a keyword that specifies an attribute of a common noun of a product included in a specific search term. For example, the attribute keyword may refer to a keyword associated with at least one of the following information: quantity, brand, color, capacity, size, applicable target, specifications, specifications, standard, price, manufacturing date, seller, and purpose of the product.

[0055] In some other embodiments, 'attribute keyword' may mean any keyword other than the main keyword included in a particular search term.

[0056] In some other embodiments, an 'attribute keyword' may mean a keyword corresponding to a lowest node in a previously stored knowledge graph that does not have at least one lower node included in a specific search term.

[0057] In the examples below, "category of attribute keywords" may refer to the category of each attribute keyword associated with a specific product. For example, in the search term "1000ml milk," "1000ml" may be an attribute keyword corresponding to the category of capacity.

[0058] In the following embodiments, 'highlight effect' may mean displaying specific text differently from other text in order to visually distinguish the specific text from other text displayed on the screen.

[0059] For example, the highlight effect may include displaying specific text in bold, underlining specific text, or displaying a highlighter pen effect on specific text.

[0060] For another example, the first keyword of the first attribute and the second keyword of the second attribute included in the first search term are highlighted in a visually distinct manner. That is, the first keyword may be highlighted in the first manner, and the second keyword may be highlighted in the second manner.

[0061] In the following embodiments, a "dictionary" may refer to a string array pre-stored in a specific computing system. In another embodiment, the dictionary may be implemented in a graph form using each string included in the string array. In other words, the dictionary may be understood as pre-defined data including multiple string data, and is not limited to being implemented as a single data structure.

[0062] Hereinafter, some embodiments of the present disclosure will be described with reference to the drawings.

[0063] FIG. 1 illustrates an exemplary environment in which a product search result provision system (100) according to one embodiment of the present disclosure can be applied.

[0064] The user terminal (300) illustrated in FIG. 1 may be a laptop, desktop, laptop, smartphone, tablet, etc., but is not limited thereto and may include all types of devices equipped with computing functions.

[0065] Meanwhile, each component illustrated in Fig. 1 may mean software or hardware such as a Field Programmable Gate Array (FPGA) or an Application-Specific Integrated Circuit (ASIC). However, the components are not limited to software or hardware, and may be configured to reside in an addressable storage medium or configured to execute one or more processors. The functions provided within the components may be implemented by more detailed components, or multiple components may be combined to form a single component that performs a specific function.

[0066] In some embodiments, the product search result providing system (100) may communicate with other components via a network. The network may be implemented as any type of wired / wireless network, such as a Local Area Network (LAN), a Wide Area Network (WAN), a mobile radio communication network, or Wibro (Wireless Broadband Internet).

[0067] In addition, with respect to the configuration of the product search result providing system (100) and the user terminal (300) described above, the hardware configuration of FIG. 12, which will be described later, may be referred to. That is, the product search result providing system (100) and the user terminal (300) may have the hardware configuration described with reference to FIG. 12. In addition, the technical concepts that can be understood through several embodiments of the present disclosure described below may be applied to the product search result providing system (100) described above, even without separate description.

[0068] Below, the operations that each component illustrated in Fig. 1 can perform are described.

[0069] A product search result provision system (100) according to one embodiment of the present disclosure can receive a first search word from a user terminal (300).

[0070] A product search result provision system (100) according to another embodiment of the present disclosure can specify a highlight target keyword of the first search term.

[0071] In some embodiments of the present disclosure, keywords included in the first search term and included in a predefined dictionary may be determined to be highlight target keywords.

[0072] In some embodiments of the present disclosure, the first search term may include a main keyword and an attribute keyword. Here, the main keyword and the attribute keyword may be highlighted using different highlight effects, but it may be understood that both are keywords subject to highlighting.

[0073] In some other embodiments of the present disclosure, the main keyword of the first search term may be a keyword that is a brand name of a product included in the first search term.

[0074] In some other embodiments of the present disclosure, the attribute keyword of the first search term may be a keyword corresponding to an attribute of a product included in the first search term.

[0075] In some other embodiments of the present disclosure, the product search result providing system (100) may transmit the first search term to an artificial neural network server (400), receive an output of an artificial neural network of the artificial neural network server (400) from the artificial neural network server (400), and determine a main keyword and attribute keyword of the first search term based on the output of the artificial neural network.

[0076] Hereinafter, the method by which the product search result provision system (100) specifies the main keyword and attribute keyword included in the first search word will be described in detail.

[0077] A product search result provision system (100) according to another embodiment of the present disclosure can transmit data for configuring a first interface including a product name of a first product corresponding to the first search word to a user terminal (300).

[0078] In some embodiments of the present disclosure, the information related to the first product may be received from the product information management system (200) illustrated in FIG. 1.

[0079] In some other embodiments of the present disclosure, the data for configuring the first interface may include information related to applying a highlight effect to an area where a highlight target keyword included in the first search word is displayed.

[0080] In some other embodiments of the present disclosure, the user terminal (300) may render the first interface using data for configuring the first interface and display the first interface on the screen.

[0081] So far, with reference to FIG. 1, the configuration and operation of the product search result provision system (100) and an exemplary environment to which the product search result provision system (100) can be applied have been described. The product search result provision system (100) and the product information management system (200) may be understood to operate according to a server-client model. However, in some embodiments, the system may be configured in a stand-alone client manner without the need for a server. In this case, the operations performed by the product search result provision system (100) may be understood to be performed by the product information management system (200).

[0082] In some other embodiments, the product search result provision system (100) and the artificial neural network server (400) may be configured as a stand-alone system.

[0083] Next, a product search result display method according to another embodiment of the present disclosure will be described with reference to FIGS. 2 to 11. The product search result display method according to the present embodiment may be performed by one or more computing systems. In addition, the product search result display method according to the present embodiment may perform some operations by a first computing device, and the remaining operations by a second computing device. For example, some operations of the product search result display method according to the present embodiment may be performed by an on-premise physical server, and the remaining operations by a cloud compute instance. In addition, for example, some operations of the product search result display method according to the present embodiment may be performed by a product search result providing system (100), and the remaining operations by a user terminal (300). Hereinafter, if the performing entity of each operation is omitted, it will be understood that the performing entity is the computing system.

[0084] FIG. 2 is a flowchart illustrating a process of a product search result display method according to another embodiment of the present disclosure.

[0085] In step S100, the product search result provision system (100) can receive a first search word from a user terminal (300).

[0086] In step S200, the product search result provision system (100) can determine a highlight target keyword included in the first search word.

[0087] In step S300, the product search result provision system (100) can transmit data for configuring the first interface to the user terminal (300).

[0088] Hereinafter, some embodiments related to steps S200 and S300 will be described with reference to FIGS. 3 to 11.

[0089] In some embodiments related to step S200, the product search result providing system (100) may determine a highlight target keyword included in the first search term based on a predefined dictionary.

[0090] In some embodiments related to steps S200 and S300, referring to FIG. 3, the product search result providing system (100) receives a first search word (30) from a user terminal (300), and when the 1-1 keyword (31) included in the first search word (30) exists in the brand name column (35) of the first dictionary (34), the 1-2 keyword (32) exists in the color column (36) of the first dictionary (34), and the 1-3 keyword (33) exists in the quantity column (37) of the first dictionary (34), the 1-1 keyword to the 1-3 keyword (31, 32, 33) may be determined as highlight target keywords, respectively.

[0091] In addition, in step S300, the product search result provision system (100) transmits data for configuring a first interface to be transmitted to the user terminal (300), and the data for configuring the first interface may include information related to applying different highlight effects to areas where each of the first to third keywords (31, 32, 33) is displayed. However, in some other embodiments, the same highlight effect may be applied to the first to third keywords (31, 32, 33).

[0092] In some other embodiments related to steps S200 and S300, referring to FIG. 3, the product search result providing system (100) may determine the 1-1 keyword (31) included in the first search term (30) as the main keyword of the first search term (30) based on information that the 1-1 keyword (31) exists in the brand name column (35) of the first dictionary (34), and may determine the 1-2 keyword and the 1-3 keyword (32, 33) corresponding to keywords existing in columns other than the brand name column (35) as attribute keywords of the first search term (30).

[0093] As described above, as the roles of each of the first to third keywords (31, 32, 33) are determined, in step S300, the product search result provision system (100) can transmit data for configuring a first interface including information related to applying a highlight effect corresponding to a main keyword to the first keyword (31) and applying a highlight effect corresponding to an attribute keyword to the first to second and third keywords (32, 33) to the user terminal (300).

[0094] In some other embodiments, based on the judgment that the first-second keyword and the first-third keyword (32, 33) are attribute keywords of different categories, the data for configuring the first interface may include information related to applying highlight effects corresponding to different attribute keywords to each of the first-second keyword and the first-third keyword (32, 33).

[0095] Hereinafter, with reference to FIG. 4, an embodiment will be described in which a product search result provision system (100) identifies a category of an attribute keyword included in a first search term and highlights and displays a keyword corresponding to the category of an attribute keyword included in the first search term on the first interface.

[0096] In step S201 illustrated in FIG. 4, the product search result provision system (100) can determine the category of the attribute keyword included in the first search word.

[0097] In some embodiments related to step S201, referring to FIG. 5, the product search result providing system (100) receives a second search word (41) from a user terminal (300), performs semantic analysis on the second search word (41) by transmitting the second search word (41) to an artificial neural network server (400), receives an output of the artificial neural network from the artificial neural network server (400), and determines a second-second keyword (43) included in the second search word (41) as a main keyword of the second search word (41) using the output of the artificial neural network.

[0098] However, in some other embodiments, the semantic analysis for the second search term (41) may be performed by the product search result providing system (100) through its own processing without transmitting the second search term (41) to the artificial neural network server (400).

[0099] In some other embodiments related to step S201, the product search result providing system (100) may use the output of the artificial neural network to determine the 2-1 keyword (42) included in the second search term as an attribute keyword of the brand category, and determine the 2-3 keyword (44) as an attribute keyword of the viscosity category.

[0100] In step S202, the product search result providing system (100) can identify a keyword corresponding to a category in the product name of the first product included in the SRP corresponding to the first search word and an attribute keyword included in the first search word.

[0101] In some embodiments related to steps S202 and S300, referring to FIG. 5, the product search result providing system (100) may determine that the brand category keyword (42-1), the viscosity category keyword (44-1) and the second-second keyword (43) of the product corresponding to the second search word (41) illustrated in FIG. 5 are highlight target keywords, and may transmit data for configuring a first interface including information related to applying different highlight effects to each highlight target keyword to the user terminal (300).

[0102] Hereinafter, with reference to FIG. 6, an embodiment in which a product search result provision system (100) determines a keyword included in product information related to a first search term more than a standard value as an attribute keyword of the first search term will be described.

[0103] In step S211 illustrated in FIG. 6, the product search result providing system (100) may tokenize the first search term. As a result, in step S212, the product search result providing system (100) may obtain multiple tokens contained in the first search term. In the following examples, tokenization will be exemplified as being performed based on spaces contained in a string. However, it should be noted that the tokenization criteria are not limited.

[0104] In some embodiments related to steps S211 and S212, the product search result providing system (100) may tokenize the third search word (61) and separate the third search word (61) into a third-first keyword (62), a third-second keyword (63), a third-third keyword (64), and a third-fourth keyword (65).

[0105] In step S213, the product search result provision system (100) can determine any one of the tokens included in the first search word as the main keyword.

[0106] In some other embodiments related to step S213, referring to FIG. 7, the product search result providing system (100) may determine the 3-2 keyword (63) as the main keyword of the 3rd search term (61) based on the judgment that the 3-2 keyword (63) among the tokens (62-65) included in the 3rd search term (61) is a word included in the predefined 2nd dictionary (60). Here, the 2nd dictionary (60) may be understood as a dictionary that stores a plurality of proper nouns of products.

[0107] In step S214, the product search result provision system (100) can obtain information on multiple products related to the main keyword from the product information management system (200).

[0108] In step S215, the product search result provision system (100) can determine one of the plurality of tokens as an attribute keyword based on information on a plurality of products related to the acquired main keyword.

[0109] In some embodiments related to steps S214 and S215, the product search result providing system (100) receives information (63-1) of a plurality of products related to the 3-2 keyword (63), which is a main keyword, from the product information management system (200), and when it is identified that the 3-1 keyword (62) and the 3-3 keyword (64) are included in the information (63-1) of a plurality of products related to the 3-2 keyword (63) in amounts greater than a reference value, it may determine that the 3-1 keyword (62) and the 3-3 keyword (64) of the 3rd search term (61) are attribute keywords.

[0110] In addition, it can be understood that the 3rd-4th keyword (65) is not included in the plurality of product information (63-1), and therefore is not determined as an attribute keyword of the 3rd search term (61).

[0111] In some other embodiments related to step S300, the product search result providing system (100) may determine that the 3-1 keyword (62), the 3-2 keyword (63), and the 3-3 keyword (64) are keywords to be highlighted, and may transmit data for configuring a first interface including information related to applying different highlight effects to areas corresponding to the 3-1 keyword (62), the 3-2 keyword (63), and the 3-3 keyword (64) to the user terminal (300).

[0112] That is, in the SRP related to the third search term (61), it can be understood that keywords identical to the 3-1 keyword (62), the 3-2 keyword (63), and the 3-3 keyword (64) are all displayed with a highlight effect added.

[0113] Hereinafter, a method for determining a highlight target keyword included in a first search term by using relationship information between nodes included in a predefined knowledge graph is described with reference to FIG. 8.

[0114] In step S211 illustrated in FIG. 8, the product search result provision system (100) can tokenize the first search word.

[0115] In step S212, the product search result provision system (100) can obtain multiple tokens as a result of tokenizing the first search word.

[0116] In some embodiments related to steps S211 and S212, referring to FIG. 9, the product search result providing system (100) may tokenize the third search word (61) and separate the third search word (61) into a third-first keyword (62), a third-second keyword (63), a third-third keyword (64), and a third-fourth keyword (65).

[0117] In step S221, the product search result provision system (100) can identify relationships within a knowledge graph between multiple tokens. Furthermore, in step S222, the main keyword and attribute keywords of the first search term can be determined based on the relationships within the knowledge graph between the multiple tokens.

[0118] In some embodiments related to steps S221 and S222, referring to the knowledge graph (81) of FIG. 9, the product search result provision system (100) may determine the 3-2 keyword (63) as the main keyword of the 3rd search term (61) when the 3-2 keyword (63) corresponds to a first node (82) having one or more subordinate nodes.

[0119] In some other embodiments related to steps S221 and S222, referring to the knowledge graph (81) of FIG. 9, the product search result providing system (100) may determine that the 3-1 keyword (62) and the 3-3 keyword (64) are attribute keywords of the 3rd search term (61) when the 3-1 keyword (62) and the 3-3 keyword (64) correspond to the 2nd node (83) and the 3rd node (84), which are subordinate nodes of the 1st node (82) corresponding to the 3-2 keyword (63), respectively.

[0120] Also, referring to FIG. 9, it can be understood that the 3rd-4th keyword (65) is not included in the knowledge graph (81), and therefore cannot be determined as an attribute keyword of the 3rd search term (61).

[0121] In some other embodiments related to steps S221 and S222, referring to FIG. 9, the product search result providing system (100) can determine the category of each of the 3-1 keyword (62) and the 3-3 keyword (64), which are attribute keywords, according to predefined relationship information between nodes of the knowledge graph (81).

[0122] In some other embodiments related to step S300, the product search result providing system (100) may transmit information related to applying different highlight effects to keywords included in the product information corresponding to the 3-2 keyword (63), which is a main keyword, and the 3-1 keyword (62) and the 3-3 keyword (64), which are attribute keywords, in the first interface including a plurality of product information related to the 3rd search term (61).

[0123] Hereinafter, with reference to FIG. 10, an embodiment in which a product search result provision system (100) determines that a highlight effect is applied to an image of a product corresponding to a first search word will be described.

[0124] In some other embodiments related to steps S200 and S300, the product search result providing system (100) may determine that the 4-1 keyword (92) included in the 4th search word (91) is a main keyword, and transmit data for configuring a first interface including information related to applying a highlight effect to a first product image (94) and a second product image (95) including an object corresponding to the 4-1 keyword (92) in a plurality of product lists (90) corresponding to the 4th search word (91) to the user terminal (300).

[0125] In some further embodiments related to steps S200 and S300, the product search result providing system (100) may determine that the 4-1 keyword (92) included in the 4th search term (91) is a main keyword, determine that the 4-2 keyword (93) is an attribute keyword, and transmit data to the user terminal (300) for configuring a first interface including information related to applying a highlight effect to an area (96) in which an object corresponding to the 4-2 keyword (93) of a product image including an object corresponding to the 4-1 keyword (92) is displayed, in a plurality of product lists (90) corresponding to the 4th search term (91).

[0126] Hereinafter, an embodiment in which a product search result provision system (100) transmits data for configuring a first interface related to applying a highlight effect to a product name corresponding to a search word based on a search word input history of a specific user to a user terminal (300) is described.

[0127] In some other embodiments related to steps S200 and S300, referring to FIG. 11, when the product search result providing system (100) receives a fifth search term (101) after receiving a fourth search term (91) from a specific user terminal (300), even if the 5-1 keyword (102) and the 5-2 keyword (103) included in the fifth search term (101) do not include the 4-2 keyword (93), it may determine that a highlight effect is to be applied to the keyword (105) corresponding to the 4-2 keyword (93) in a plurality of product lists (104) related to the 5th search term (101).

[0128] Hereinafter, with reference to FIG. 12, an embodiment will be described in which a product search result provision system (100) determines that a highlight effect is applied to a product name corresponding to a search word received from a user terminal (300) based on the search word input history of other users, and transmits data for configuring a first interface including the result of the above determination to the user terminal (300).

[0129] In some other embodiments related to steps S200 and S300, referring to FIG. 12, when the product search result providing system (100) receives a sixth search term (111) including a main keyword (112) of a monitor from a user terminal (300), based on information that the first attribute keyword (113) is included in the search term input history including the main keyword (112) of the monitor received from a first user terminal (114), a second user terminal (115), a third user terminal (116), and a fourth user terminal (117) different from the plurality of user terminals (300) more than a reference value, even if the first attribute keyword (113) is not included in the sixth search term (111), it may determine that a highlight effect is to be applied to a keyword corresponding to the first attribute keyword (113) in a plurality of product lists (118) related to the sixth search term (111).

[0130] So far, a product search result display method according to another embodiment of the present disclosure has been described with reference to FIGS. 2 through 12. It should be understood that the embodiments described above are exemplary in all respects and are not limiting.

[0131] FIG. 13 is a hardware configuration diagram of a product search result providing system according to some embodiments of the present disclosure. The product search result providing system (1000) of FIG. 13 may include one or more processors (1100), a system bus (1600), a communication interface (1200), a memory (1400) for loading a computer program (1500) executed by the processor (1100), and a storage (1300) for storing the computer program (1500).

[0132] The processor (1100) controls the overall operation of each component of the computing system (1000). The processor (1100) can perform operations for at least one application or program for executing methods / operations according to various embodiments of the present disclosure. The memory (1400) stores various data, commands, and / or information. The memory (1400) can load one or more computer programs (1500) from the storage (1300) to execute methods / operations according to various embodiments of the present disclosure. The storage (1300) can non-temporarily store one or more computer programs (1500).

[0133] The computer program (1500) may include one or more instructions implementing methods / operations according to various embodiments of the present disclosure. When the computer program (1500) is loaded into the memory (1400), the processor (1100) may execute the one or more instructions to perform the methods / operations according to various embodiments of the present disclosure.

[0134] For example, the product search result providing system (1000) of FIG. 13 may be the product search result providing system (100) described with reference to FIG. 1. At this time, the product search result providing system (1000) described with reference to FIG. 13 may be configured using one or more physical servers included in a server farm based on cloud technology such as a virtual machine. In this case, at least some of the processor (1100), memory (1400), and storage (1300) among the components illustrated in FIG. 13 may be virtual hardware, and the communication interface (1200) may also be configured with a virtualized networking element such as a virtual switch.

[0135] At this time, the computer program (1500) may include instructions that cause the processor (1100) to perform the steps of receiving a first search word from a user terminal, determining a highlight target keyword included in the first search word based on a predefined dictionary, and transmitting data for configuring a first interface including a product name of a first product corresponding to the first search word to the user terminal.

[0136] Although the operations are depicted in a particular order in the drawings, this should not be construed as requiring that the operations be performed in the particular order depicted, or in any sequential order, or that all depicted operations must be performed to achieve the desired results. In certain situations, multitasking and parallel processing may be advantageous.

[0137] Although the embodiments of the present disclosure have been described with reference to the attached drawings, those skilled in the art will appreciate that the present disclosure can be implemented in other specific forms without changing the technical concepts or essential features thereof. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within a scope equivalent thereto should be interpreted as being included within the scope of the technical ideas defined by the present disclosure.

Claims

1. In a method performed by a computing system, A step of receiving a first search word from a user terminal; A step of determining a highlight target keyword included in the first search word based on a predefined dictionary; and A step of transmitting data for configuring a first interface including a product name of a first product corresponding to the first search word to the user terminal, The data for configuring the above first interface is: Including information related to applying different highlight effects to each area where the highlight target keyword included in the first search word is displayed, How to display product search results.

2. In paragraph 1, The above first search term includes a main keyword and a property keyword, The main keyword of the first search term above is a keyword that is the brand name of the product included in the first search term. The attribute keyword of the first search term is a keyword corresponding to the attribute of the product included in the first search term, The data for configuring the above first interface is: Including information related to applying a first highlight effect to the main keyword of the first search term and applying a highlight effect different from the first highlight effect to the attribute keyword of the first search term. How to display product search results.

3. In paragraph 2, The data for configuring the above first interface is: In the case where there are multiple attribute keywords of the first search term, information related to applying different highlight effects to each of the attribute keywords of the first category and the attribute keywords of the second category is included. How to display product search results.

4. In paragraph 3, The attribute keywords of the above first category are keywords related to the product specification information, The attribute keywords of the above second category are keywords related to the quantity information of the product. How to display product search results.

5. In paragraph 2, A step of tokenizing the first search term to obtain a first token and a second token; A step of determining the first token as the main keyword of the first search term, if the first token corresponds to a brand name included in the pre-defined dictionary; A step of obtaining information related to a plurality of products associated with the first token; and If the second token is included in information related to a plurality of products related to the first token by a threshold value or more, further comprising a step of determining the second token as the attribute keyword of the first search term. How to display product search results.

6. In paragraph 2, A step of tokenizing the first search term to obtain a first token and a second token; A step of identifying that the first token is a node having at least one subnode in the generated knowledge graph; A step of identifying that the second token is a subnode of the first token in the knowledge graph; and Further comprising a step of determining the first token as the main keyword of the first search term and determining the second token as the attribute keyword of the first search term. How to display product search results.

7. In paragraph 2, A step of performing semantic analysis on the first search term; A step of determining a proper noun of a product included in the first search term as the main keyword of the first search term using the result of the above semantic analysis; and Using the result of the above semantic analysis, further comprising a step of determining a keyword corresponding to an attribute of a product included in the first search term as an attribute keyword of the first search term. How to display product search results.

8. In paragraph 2, The data for configuring the above first interface is: Including an image of the first product, and when the image of the first product includes a feature associated with a keyword included in the first search term, including information related to applying a highlight effect different from the first highlight effect to an area where the image of the first product is displayed. How to display product search results.

9. In paragraph 8, The above first interface is, Including information related to applying a highlight effect different from the first highlight effect to an area where an object related to a keyword included in the first search word of the image of the first product is displayed, How to display product search results.

10. In paragraph 1, A step of receiving a second search term after receiving the first search term from the user terminal; Further comprising a step of transmitting data for configuring a second interface including the product name of the second product corresponding to the second search word to the user terminal, The data for configuring the above second interface is: Including information related to applying a highlight effect to an area where the first keyword is displayed when the first keyword included in the first search word exists in the product name of the second product. How to display product search results.

11. In paragraph 1, The data for configuring the above first interface is: Including information related to applying a highlight effect to an area where keywords that are not included in the first search term but are included in a plurality of search terms related to the first product received above are displayed, How to display product search results.

12. One or more processors; and A memory storing a computer program executed by one or more processors, The above computer program causes the processor to: A step of receiving a first search word from a user terminal; A step of determining a highlight target keyword included in the first search word based on a predefined dictionary; and Includes instructions for performing a step of transmitting data for configuring a first interface including a product name of a first product corresponding to the first search word to the user terminal, The data for configuring the above first interface is: Including information related to applying different highlight effects to each area where the highlight target keyword included in the first search word is displayed, Product search results provision system.

13. In paragraph 12, The above first search term includes a main keyword and a property keyword, The main keyword of the first search term above is a keyword that is the brand name of the product included in the first search term. The attribute keyword of the first search term is a keyword corresponding to the attribute of the product included in the first search term, The data for configuring the above first interface is: Including information related to applying a first highlight effect to the main keyword of the first search term and applying a highlight effect different from the first highlight effect to the attribute keyword of the first search term. Product search results provision system.

14. In paragraph 13, The data for configuring the above first interface is: In the case where there are multiple attribute keywords of the first search term, information related to applying different highlight effects to each of the attribute keywords of the first category and the attribute keywords of the second category is included. Product search results provision system.

15. In paragraph 13, The above computer program causes the processor to: A step of tokenizing the first search term to obtain a first token and a second token; A step of determining the first token as the main keyword of the first search term, if the first token corresponds to a brand name included in the pre-defined dictionary; A step of obtaining information related to a plurality of products associated with the first token; and Further comprising instructions for performing a step of determining the second token as the attribute keyword of the first search term when the second token is included in information related to a plurality of products related to the first token exceeding a reference value. Product search results provision system.

16. In paragraph 13, The above computer program causes the processor to: A step of tokenizing the first search term to obtain a first token and a second token; A step of identifying that the first token is a node having at least one subnode in the generated knowledge graph; A step of identifying that the second token is a subnode of the first token in the knowledge graph; and Further comprising instructions for performing a step of determining the first token as the main keyword of the first search term and determining the second token as the attribute keyword of the first search term. Product search results provision system.

17. In paragraph 13, The above computer program causes the processor to: A step of performing semantic analysis on the first search term; A step of determining a proper noun of a product included in the first search term as the main keyword of the first search term using the result of the above semantic analysis; and Further comprising instructions for performing a step of determining a keyword corresponding to an attribute of a product included in the first search term as an attribute keyword of the first search term by using the result of the semantic analysis. Product search results provision system.

18. In paragraph 13, The data for configuring the above first interface is: Including an image of the first product, and when the image of the first product includes a feature associated with a keyword included in the first search term, including information related to applying a highlight effect different from the first highlight effect to an area where the image of the first product is displayed. Product search results provision system.

Images