JP7492994B2 - Search result providing method, system, and computer program - Google Patents

Description

The following description relates to techniques for providing item search results that match the intent of a query.

A variety of rating systems are used for user reviews of various items, including star reviews, text reviews, and photo reviews.

In a review service that uses locations as items, the locations a user has visited or used are authenticated using functions such as location reservation and receipt authentication, and the authenticated location information is then submitted along with the review.

For example, Patent Document 1 (published on January 6, 2020) discloses a technology that uses augmented reality to create sales floor review information.

User reviews of places may be displayed not only by the place review service, but also in conjunction with other services that provide place information, such as search services and map services.

Korean Patent Publication No. 10-2020-0000925

The purpose is to dynamically construct and provide a list of recommended subitems for each item included in the search results based on the relationship between the item and the subitems it possesses.

A method for providing search results executed in a computer system, the computer system including at least one processor configured to execute computer-readable instructions stored in a memory, the method for providing search results including a step of providing items corresponding to a search query as search results by the at least one processor, the step of providing including, for each item included in the search results, recommending sub-items corresponding to the search query among sub-items attached to the corresponding item.

According to one aspect, the search result providing method further includes a step of searching for subitems corresponding to the search query by the at least one processor, and the providing step may include a step of selecting an item to which the searched subitem belongs as an item search result.

According to another aspect, the method for providing search results further includes a step of searching, by the at least one processor, for lower-level items corresponding to the search query, and a step of searching, by the at least one processor, for reviews corresponding to the search query from among reviews registered for each item, and the providing step may include a step of selecting, as item search results, an item to which the searched lower-level items belong and an item in which the searched reviews are registered.

In another aspect, the providing step may include a step of selecting items to which subordinate items corresponding to the search query belong as candidate items, and a step of selecting some of the candidate items as final items using the popularity of the candidate items.

In another aspect, the providing step may include a step of ranking the final items using at least one of attribute information of the final items, candidate items associated with the final items, and reviews registered for the final items.

In another aspect, the providing step may include ranking the final item using a matching rate between the search query and attribute information of the final item, and boosting the ranking of the final item using at least one of a matching rate between the search query and candidate items attached to the final item and a matching rate between the search query and reviews registered for the final item.

In another aspect, the providing step may include, for each item included in the search results, recommending reviews that correspond to the search query from among reviews registered for the corresponding item, together with sub-items that correspond to the search query.

In another aspect, the providing step may include selecting reviews corresponding to the search query using an embedding similarity with the search query.

In another aspect, the providing step may further include ranking the selected reviews based on positive/negative scoring of the selected reviews.

In yet another aspect, the providing step may further include a step of ranking the selected reviews using at least one of the length of the selected reviews, recency, popularity, and author rating.

A computer program is provided to cause a computer to execute the search result providing method.

A computer system is provided that includes at least one processor configured to execute computer-readable instructions included in a memory, the at least one processor including a search result providing unit that provides items corresponding to a search query as search results, and the search result providing unit processes, for each item included in the search results, recommending sub-items that correspond to the search query from among sub-items attached to the corresponding item.

According to an embodiment of the present invention, a subitem recommendation list is dynamically constructed and provided for each item included in the search results based on the relationship between the item and the subitems it possesses, thereby improving the search results to be closer to the user's search intent.

FIG. 1 illustrates an example of a network environment in accordance with an embodiment of the present invention. FIG. 1 is a block diagram illustrating an example computer system according to an embodiment of the present invention. FIG. 2 illustrates example components that may be included in a processor of a computer system in accordance with one embodiment of the present invention. 4 is a flow chart illustrating an example of a method that may be performed by a computer system in accordance with an embodiment of the present invention. FIG. 13 is a diagram showing an example of an item search result screen in the embodiment of the present invention. FIG. 13 is a diagram showing an example of an item search result screen in the embodiment of the present invention. FIG. 13 is a diagram showing an example of an item search result screen in the embodiment of the present invention. 11 is a flowchart illustrating an example of a process for ranking item search results in accordance with an embodiment of the present invention. FIG. 13 is a diagram showing an example of features utilized for review ranking in one embodiment of the present invention. 10 is a flowchart illustrating an example of a process for ranking review recommendation results in an embodiment of the present invention.

The following describes in detail an embodiment of the present invention with reference to the attached drawings.

Embodiments of the present invention relate to a technology that provides item search results that match the intent of a query.

Embodiments including those specifically disclosed herein may dynamically construct and provide a subitem recommendation list for each item included in search results from a search query based on the relationship between the item and the subitems it possesses.

In this specification, an item may refer to a search or recommendation target inclusively. As an example, an item may include a target that allows a user to review the user's experience by visiting, using, purchasing, etc. Also, a subitem may refer to a target that is owned by an item, in other words, that belongs secondarily to the item. User reviews may include individual reviews of each of the subitems as well as reviews of the item.

Representative examples of items include places such as restaurants, shops, famous places, and hot places. In the case of a restaurant, the menu items sold at the restaurant may correspond to the sub-items, and in the case of a shop, the items sold at the shop may correspond to the sub-items.

The search result providing system according to the embodiment of the present invention may be realized by at least one computer system, and the search result providing method according to the embodiment of the present invention may be executed by at least one computer system included in the search result providing system. In this case, a computer program according to an embodiment of the present invention may be installed and executed in the computer system, and the computer system may execute the search result providing method according to the embodiment of the present invention according to the control of the executed computer program. The above-mentioned computer program may be recorded on a computer-readable recording medium in combination with the computer system to cause the computer to execute the search result providing method.

Figure 1 is a diagram showing an example of a network environment in one embodiment of the present invention. The network environment in Figure 1 shows an example including multiple electronic devices 110, 120, 130, 140, multiple servers 150, 160, and a network 170. Figure 1 is merely an example for explaining the invention, and the number of electronic devices and the number of servers are not limited to those shown in Figure 1. Furthermore, the network environment in Figure 1 is merely an example of an environment applicable to this embodiment, and the environment applicable to this embodiment is not limited to the network environment in Figure 1.

The electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals realized by computer devices. Examples of the electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, personal computers (PCs), notebook PCs, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), tablets, game consoles, wearable devices, internet of things (IoT) devices, virtual reality (VR) devices, and augmented reality (AR) devices. As an example, FIG. 1 shows a smartphone as an example of the electronic device 110, but in an embodiment of the present invention, the electronic device 110 may refer to one of a variety of physical computer devices that can communicate with other electronic devices 120, 130, 140 and/or servers 150, 160 via a network 170 using a substantially wireless or wired communication method.

The communication method is not limited, and may include not only a communication method using a communication network that the network 170 can include (for example, a mobile communication network, a wired Internet, a wireless Internet, or a broadcast network), but also short-range wireless communication between devices. For example, the network 170 may include any one or more of a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), the Internet, and the like. Furthermore, the network 170 may include any one or more of a network topology including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network.

Each of the servers 150 and 160 may be realized by one or more computer devices that communicate with the multiple electronic devices 110, 120, 130, and 140 via the network 170 to provide instructions, codes, files, content, services, and the like. For example, the server 150 may be a system that provides a first service to the multiple electronic devices 110, 120, 130, and 140 connected via the network 170, and the server 160 may be a system that provides a second service to the multiple electronic devices 110, 120, 130, and 140 connected via the network 170. As a more specific example, the server 150 may provide a service (such as an item review service, for example) targeted by an application, which is a computer program installed and executed on the multiple electronic devices 110, 120, 130, and 140, as a first service to the multiple electronic devices 110, 120, 130, and 140. As another example, the server 160 may provide, as the second service, a service of distributing files for installing and executing the above-mentioned application to multiple electronic devices 110, 120, 130, and 140.

Figure 2 is a block diagram showing an example of a computer device in one embodiment of the present invention. Each of the multiple electronic devices 110, 120, 130, and 140 and each of the servers 150 and 160 described above may be realized by the computer device 200 shown in Figure 2.

Such a computing device 200 may include a memory 210, a processor 220, a communication interface 230, and an input/output interface 240, as shown in FIG. 2.

The memory 210 is a computer-readable recording medium and may include a RAM (random access memory), a ROM (read only memory), and a permanent mass storage device such as a disk drive. Here, a permanent mass storage device such as a ROM or a disk drive may be included in the computer device 200 as a separate permanent storage device separate from the memory 210. In addition, an operating system and at least one program code may be recorded in the memory 210. Such software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, a memory card, etc. In another embodiment, the software components may be loaded into the memory 210 through the communication interface 230, which is not a computer-readable recording medium. For example, the software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received via the network 170.

The processor 220 may be configured to process computer program instructions by performing basic arithmetic, logic, and input/output operations. The instructions may be provided to the processor 220 by the memory 210 or the communication interface 230. For example, the processor 220 may be configured to execute instructions received according to program code recorded in a recording device such as the memory 210.

The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (for example, the above-mentioned recording device) via the network 170. As an example, requests, commands, data, files, etc. generated by the processor 220 of the computer device 200 according to program code recorded in a recording device such as the memory 210 may be transmitted to other devices via the network 170 under the control of the communication interface 230. Conversely, signals, commands, data, files, etc. from other devices may be received by the computer device 200 through the communication interface 230 of the computer device 200 via the network 170. The signals, commands, data, etc. received through the communication interface 230 may be transmitted to the processor 220 or the memory 210, and the files, etc. may be recorded on a recording medium (the above-mentioned permanent recording device) that the computer device 200 may further include.

The input/output interface 240 may be a means for interfacing with the input/output device 250. For example, the input device may include devices such as a microphone, keyboard, or mouse, and the output device may include devices such as a display and a speaker. As another example, the input/output interface 240 may be a means for interfacing with a device in which functions for input and output are integrated into one, such as a touch screen. The input/output device 250 may be configured as a single device together with the computer device 200.

Also, in other embodiments, computer device 200 may include fewer or more components than those of FIG. 2. However, most prior art components need not be explicitly shown in the figures. For example, computer device 200 may be implemented to include at least some of the input/output devices 250 described above, and may further include other components such as a transceiver, a database, etc.

The following describes specific embodiments of a method and system for dynamically providing subitem recommendation lists for each item included in search results based on a search query.

Figure 3 is a block diagram showing an example of components that may be included in a processor of a computer system in one embodiment of the present invention, and Figure 4 is a flowchart showing an example of a method for providing search results that may be executed by a computer system in one embodiment of the present invention.

The computer system 200 according to this embodiment may provide an item review service to a client through a dedicated application installed on the client or through a connection to a web/mobile site associated with the computer system 200.

The computer system 200 may provide a review space for items through a user's personal service page, and may authenticate items visited or used by the user through a linking function with a reservation/order service or a receipt authentication function in relation to the items, and then register the authenticated item information in association with reviews created by the user. A user may create reviews not only for an item, but also by identifying subitems within an item. In this case, reviews for subitems may be managed in association with the subitems and the item to which the subitems belong.

The computer system 200 may provide an item-based search and recommendation environment for users. In this case, reviews of items may be shared based on users following each other.

The processor 220 of the computer system 200 may include an item search unit 310 and a search result providing unit 320 as components for executing the search result providing method described below, as shown in FIG. 3. Depending on the embodiment, the components of the processor 220 may be selectively included or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or combined to express the functions of the processor 220.

Such processor 220 and components of processor 220 may control computer system 200 to execute steps included in the search result providing method described below. For example, processor 220 and components of processor 220 may be implemented to execute instructions from operating system code and at least one program code contained in memory 210.

Here, the components of the processor 220 may represent different functions executed by the processor 220 according to instructions provided by the program code recorded in the computer system 200. For example, the item search unit 310 may be used as a functional representation of the processor 220 that controls the computer system 200 according to the above-mentioned instructions so that the computer system 200 searches for items corresponding to the search query.

The processor 220 may read the necessary instructions from the memory 210, which is loaded with instructions related to the control of the computer system 200. In this case, the read instructions may include instructions for controlling the processor 220 to execute the search result providing method described below.

The steps included in the search result providing method described below may be performed in an order different from that shown in the figures, some of the steps may be omitted, or additional processes may be included.

Referring to FIG. 4, in step 410, when a search query is received, the item search unit 310 may search for items corresponding to the search query and provide subitems attached to the item and reviews registered for the item as information about the searched item. The item search unit 310 may search for subitems corresponding to the search query and reviews corresponding to the search query in order to provide search results that fit the context.

Each item and subitem has its own attribute information. For example, if the item is a restaurant, the attribute information may include the restaurant's location, business name, business category, phone number, description, rating, reviews, photos, reservation information, etc. Subitems of a restaurant may include the menu items sold at the restaurant, and each menu item has attribute information including the menu item name, price, description, photos, rating, reviews, etc.

Reviews are user feedback for items and subitems and may include review content created in a variety of review formats, such as star reviews, keyword reviews, text reviews, and photo reviews.

The item search unit 310 may select, from among sub-items and reviews, sub-items that have attribute information that matches the search query, and reviews that contain content that matches the search query or content that is similar in meaning to the search query.

In step 420, the search result providing unit 320 may provide item search results for the search query using the subitem search results and the review search results. The search result providing unit 320 may select items to which subitems included in the subitem search results belong and items to which reviews included in the review search results are linked as item search results or may use them for ranking the item search results.

In step 410, the search result providing unit 320 may select items selected as search results in both subitems and reviews for the search query as item search results. In other words, items that are commonly present in the subitem search results and the review search results may be selected. In some embodiments, items selected as search results in either the subitems or reviews may be selected as item search results.

The search result providing unit 320 may provide a list of items selected as item search results as final search results corresponding to the search query. In this case, for each item included in the item search results, at least a portion of the sub-item search results and review search results searched in step 410 may be provided as a recommendation list for the search query.

In other words, the search result providing unit 320 can dynamically configure and provide a list of subitems and review recommendations for each item included in the search results based on the search query, thereby providing search results that fit the context based on the interrelationships between items and subitems. For each item included in the search results, a list of subitems and reviews belonging to the corresponding item can be displayed, and in particular, subitems and reviews that fit the search query can be displayed higher in the list than other subitems and reviews while taking into account the user's search intent.

Figure 5 shows an example of an item search results screen in one embodiment of the present invention.

Referring to FIG. 5, the processor 220 may provide an item list 510 as final search results corresponding to the search query 501 via an item search results screen 500.

At this time, the item list 510 may be determined based on the sub-item search results and review search results corresponding to the search query 501. The item list 510 may be composed of items to which sub-items having attribute information matching the search query 501 belong, items to which reviews containing content matching the search query 501 or content similar in meaning to the search query 501 are registered, items that belong to the two conditions mentioned above, etc.

The processor 220 may provide both a sub-item recommendation list 520 and a review recommendation list 530 for each item included in the item list 510 via the item search results screen 500.

The sub-item recommendation list 520 may be composed of sub-item search results corresponding to the search query 501, and the review recommendation list 530 may be composed of review search results corresponding to the search query 501.

In other words, the processor 220 can dynamically construct and provide a sub-item recommendation list 520 and a review recommendation list 530 for each item included in the search results by the search query 501.

For example, if a user uses restaurant menu keywords as a search query, even if the same restaurant appears in the search results, information about that restaurant will be displayed differently depending on the search query.

Referring to Figure 6, assume that the search results include the item <Restaurant I>.

When "Gangnam Pasta" is entered as a search query, the recommendation information related to <Restaurant I> may consist of pasta menu items sold at <Restaurant I>, or a sub-item recommendation list 621 may be provided in which the pasta menu items are displayed at the top (for example, in a position that is easy for the user to recognize, such as the leftmost or topmost position of the list). In addition, a review recommendation list 631 may be provided in which reviews of <Restaurant I> that contain content related to pasta and reviews registered for the pasta menu items of <Restaurant I> are displayed at the top.

On the other hand, when "Gangnam Pizza" is entered as a search query, the recommendation information related to <Restaurant I> may consist of the pizza menu sold at <Restaurant I>, or a sub-item recommendation list 622 may be provided in which the pizza menu is displayed at the top (for example, in a position that is easy for the user to recognize, such as the leftmost or topmost position of the list), and a review recommendation list 632 may be provided in which reviews of <Restaurant I> that include content related to pizza or reviews registered for the pizza menu of <Restaurant I> are displayed at the top.

In other words, for the same item <Restaurant I>, the sub-item recommendation lists 621, 622 and the review recommendation lists 631, 632 can be configured differently depending on the search query.

For example, as shown in FIG. 7, when "Shinjuku pasta" is input as a search query, a sub-item recommendation list 721 that displays pasta dishes at the top of the menu of <Restaurant X> and a review recommendation list 731 that displays reviews related to the pasta dishes at the top of the reviews of <Restaurant X> may be provided. On the other hand, when "Shinjuku pizza" is input as a search query, a sub-item recommendation list 722 that displays pizza dishes at the top of the menu of <Restaurant X> and a review recommendation list 732 that displays reviews related to the pizza dishes at the top of the reviews of <Restaurant X> may be provided.

A visual indication may be added to search results for keywords that match the search query, for example by displaying the text in red or highlighting it using highlighting.

The processor 220 can provide a context-appropriate item list as search results by determining item search results using subitem search results and review search results corresponding to the search query.

Furthermore, the processor 220 may provide context-appropriate recommendation information among information about the items by displaying a list of subitems and reviews corresponding to the search query for each item included in the search results. In this case, the processor 220 may preferentially display subitems that match the search query among the subitems attached to the item, and reviews that match the search query among the reviews registered for the item.

Figure 8 is a flowchart illustrating an example of a process for ranking item search results in one embodiment of the present invention.

The processor 220 may rank the item search results using each item's attribute information, subitems, and reviews.

Referring to FIG. 8, in step 801, the processor 220 may select candidate items using subitem search results corresponding to the search query and review search results corresponding to the search query. As an example, the processor 220 may select an item to which a subitem corresponding to the search query belongs as the candidate item. As another example, the processor 220 may select an item to which a subitem corresponding to the search query belongs and to which a review corresponding to the search query is registered, i.e., an item that exists in common in the subitem search results and the review search results, as the candidate item.

In step 802, the processor 220 may use the popularity of the items to select a certain number or percentage of the top candidate items as the final items. Here, popularity may refer to a user feedback score, and for example, the higher the number of likes or ratings, the more shares, or the more registered reviews, the higher the score may be calculated. In other words, the processor 220 may apply a popularity ranking based on the user feedback score of each item.

In step 803, the processor 220 may rank the item search results configured as the final items using a query-customized relevance feature using at least one of the attribute information, subitems, and reviews of each item. As an example, the processor 220 may use at least one of the matching rate between the search query and the attribute information, the matching rate between the search query and the subitems, and the matching rate between the search query and the reviews as the query-customized relevance feature.

The processor 220 may calculate a matching rate with a search query based on the attribute information present in the item database, such as the item's name, description, category, as well as theme keywords related to the item, and use the calculated matching rate as a query-customized relevance feature for ranking search results.

Theme keywords include keywords related to subitems and keywords unrelated to subitems. In the case of a restaurant, the theme keywords may be divided into menu keywords and non-menu keywords. Theme keywords for a restaurant can be extracted from a predefined theme keyword dictionary as well as from restaurant attribute information such as business category and menu name.

The processor 220 may rank the item search results by taking into account not only the matching rate with the attribute information, but also the matching rate with subordinate items attached to the item, the matching rate with reviews registered for the item, and the like.

The processor 220 maintains a popularity ranking for the search results based on each item's user feedback score, but may also rerank the item search results using a matching rate with the attribute information for the search query. The processor 220 may also apply complementary ranking logic to address inaccuracies in the attribute information by boosting the search result reranking using a matching rate with lower ranking items and/or a matching rate with reviews.

Additionally, for queries that include time keywords indicating a time period, such as "morning," "lunch," or "dinner," or purpose keywords indicating a purpose, such as "drinking party," "date," "get-together," "with family," or "with friends," a definition for each keyword may be added based on review data obtained through receipt authentication and used in the ranking logic.

In this embodiment, for the same item included in the search results, a sub-item recommendation list can be dynamically constructed and displayed based on the search query.

Figure 9 shows an example of features used for review ranking in one embodiment of the present invention.

For each item included in the search results, the processor 220 may recommend context-appropriate reviews from among the reviews registered for the item, giving priority to reviews that are more meaningful and relevant to the search query.

Referring to FIG. 9, the processor 220 may rank the review recommendation results using 1) the length of the review text, 2) text quality including a sentimental score based on positive/negative scoring of the review text, 3) the number of images included in the review, 4) image quality including the number of images included in the review that fall into a high quality level, 5) the review creation date, 6) recency including the difference between the review creation date and the most recent consumption date, 7) abuse rating of the user who created the review, 8) the user's real name authentication status, 9) the total number of reviews created by the user, 10) the number of followers of the user, 11) user rating including the number of visits authenticated by the user, 12) review score, and 13) popularity including the cumulative number of "likes" of the review.

1) Review text length, 2) emotion score, 3) number of images, 4) number of high-quality images, etc. are criteria for selecting reviews with substantial content, while 5) review creation date, 6) difference between the review creation date and the most recent consumption date, etc. are criteria for selecting reviews with a high level of recentness. In addition, 7) abuse rating, 8) real name authentication status, etc. are criteria for selecting reviews with low malicious intent, while 9) total number of reviews created, 10) number of followers, 11) number of visits authenticated, etc. are criteria for selecting reviews written by experts. Furthermore, 12) rating, 13) cumulative number of "likes", etc. are criteria for selecting popular reviews.

The features listed above are merely examples, and can be expanded to any feature that can be used as a weighting factor for review rankings.

Figure 10 is a flowchart illustrating an example of a process for ranking review recommendation results in one embodiment of the present invention.

Referring to FIG. 10, in step 1001, the processor 220 may select a review to be recommended as a search result by using a similarity between the search query and the review content. The processor 220 may calculate the similarity with the search query by segmenting the review into meaningful sentence units and extracting the probability of a keyword corresponding to the search query occurring from the segmented sentence. An embedding-based semantic review matching technique may be used to match reviews with content similar to the search query as well as reviews with keywords matching the search query. Semantic review matching is a method of matching reviews with semantically similar content in addition to reviews that exactly include the search query. As an example, a cosine similarity between the search query and a distributed representation of the review by Doc2Vec embedding may be extracted and reflected in the recommendation score. For example, if the search query is "pasta", a review containing content semantically related to "pasta" may be selected as a recommendation target even if "pasta" is not directly mentioned.

In step 1002, the processor 220 may rank the review recommendation results based on scoring using at least one of text quality (emotion score), image quality, recency, user rating, and popularity, in addition to similarity to the search query, which are used as review selection criteria.

As an example, the processor 220 may use a Ridge-based keyword-specific sentiment dictionary to calculate sentiment scores based on positive wording and may assign ranking weights based on the sentiment scores. The sentiment score, one of the features indicating text quality, is obtained by extracting positive words, which are important variables, using a Ridge Logistic Regression method that classifies a review sentence into positive or negative, and then scoring the coefficient values of these words. The more positive the review sentence, the higher the positive value, and the more negative the review sentence, the lower the negative value. Using such sentiment scores, the influence of reviews containing positive wording may be increased.

As another example, the processor 220 may determine review rankings based on the length and recency of the review text, the review score, the cumulative number of "likes," etc. The processor 220 may assign a higher ranking weighting to reviews that were created recently, reviews that are of an appropriate length, reviews with a large number of cumulative "likes," and reviews with high scores.

This embodiment can dynamically construct and display a review recommendation list for the same item included in the search results based on the search query.

In this way, according to an embodiment of the present invention, by dynamically constructing and providing subitems and review recommendation lists for each item included in the search results based on the relationship between the item and the subitems it possesses, it is possible to improve the search results by bringing them closer to the user's search intent.

The above-described devices may be realized by hardware components, software components, and/or a combination of hardware and software components. For example, the devices and components described in the embodiments may be realized using one or more general-purpose or special-purpose computers, such as a processor, controller, arithmetic logic unit (ALU), digital signal processor, microcomputer, field programmable gate array (FPGA), programmable logic unit (PLU), microprocessor, or various devices capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications that run on the OS. The processing device may also respond to the execution of the software and access, record, manipulate, process, and generate data. For ease of understanding, the description may be given as if one processing device is used, but one skilled in the art will understand that the processing device may include multiple processing elements and/or multiple types of processing elements. For example, a processing unit may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

The software may include computer programs, codes, instructions, or a combination of one or more of these, and may configure or instruct the processing device to operate as desired, either independently or collectively. The software and/or data may be embodied in any type of machine, component, physical device, computer storage medium, or device to be interpreted based on the processing device or to provide instructions or data to the processing device. The software may be distributed and stored or executed in a distributed manner on computer systems connected by a network. The software and data may be stored on one or more computer-readable storage media.

The method according to the embodiment may be realized in the form of program instructions executable by various computer means and recorded on a computer-readable medium. Here, the medium may be one that continuously records the computer-executable program or one that temporarily records it for execution or download. The medium may be one of various recording means or storage means in the form of a single or multiple hardware combined, and is not limited to a medium directly connected to a certain computer system, but may be one that is distributed over a network. Examples of the medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROMs, RAMs, flash memories, etc., configured to record program instructions. Other examples of the medium include recording media or storage media managed by application stores that distribute applications, or sites, servers, etc. that supply or distribute various other software.

Although the embodiments have been described above based on limited embodiments and drawings, those skilled in the art will appreciate that various modifications and variations can be made from the above description. For example, the described techniques may be performed in an order different from that described, and/or the components of the described systems, structures, devices, circuits, etc. may be combined or combined in a manner different from that described, or may be counterbalanced or replaced by other components or equivalents, and still achieve suitable results.

Therefore, different embodiments that are equivalent to the scope of the claims are within the scope of the attached claims.

220: Processor 310: Item search unit 320: Search result providing unit

Claims (18)

A method for providing search results executed on a computer system, comprising:
The computer system includes at least one processor configured to execute computer-readable instructions contained in a memory;
The search result providing method includes:
searching, by the at least one processor, for items corresponding to a search query and sub-items corresponding to the search query;
a step of searching reviews corresponding to the search query among reviews registered for each item by the at least one processor; and a step of providing items corresponding to the search query as search results by the at least one processor,
The providing step comprises:
A method for providing search results, comprising: recommending lower-level items corresponding to the search query from among lower-level items attached to an item corresponding to the search query included in the search results; and selecting reviews corresponding to the search query by performing semantic review matching based on embedding similarity with the search query, thereby associating reviews related to the lower-level items corresponding to the search query from among reviews registered for the item corresponding to the search query searched in the searching step with the lower-level items corresponding to the search query and displaying them together. The search result providing method includes:
searching, by the at least one processor, for subordinate items corresponding to the search query;
The providing step comprises:
The method of claim 1 , further comprising: selecting an item to which the searched subordinate item belongs as an item search result. The step of searching for the item and sub-items corresponding to the search query includes:
The method of claim 1 , further comprising: searching for an item to which the searched sub-item belongs and an item for which the searched review is registered as the item search result. The providing step comprises:
The method of claim 1 , further comprising: selecting items to which subordinate items corresponding to the search query belong as candidate items; and selecting a portion of the candidate items as final items using popularity of the candidate items. The providing step comprises:
The method of claim 4 , further comprising: ranking the final items using at least one of attribute information of the final items, candidate items attached to the final items, and reviews registered on the final items. The providing step comprises:
5. The method of claim 4, further comprising: ranking the final item using a matching rate between the search query and attribute information of the final item; and boosting the ranking of the final item using at least one of a matching rate between the search query and candidate items attached to the final item and a matching rate between the search query and reviews registered on the final item. The providing step comprises:
providing a subitem recommendation list including subitems corresponding to the search query;
the subitem recommendation list includes an image representing each subitem;
The method for providing search results according to claim 1 , wherein reviews related to the lower-level items are displayed together in association with the lower-level item recommendation list. The providing step comprises:
The method of claim 1 , further comprising: ranking the selected reviews based on positive/negative scoring of the selected reviews. The providing step comprises:
The method of claim 1 , further comprising: ranking the selected reviews using at least one of a length of text, recency, popularity, and creator rating of the selected reviews. A computer program for causing a computer to execute the search result providing method according to any one of claims 1 to 9 . 1. A computer system comprising:
at least one processor configured to execute computer readable instructions contained in a memory;
The at least one processor
a search unit that searches for items corresponding to a search query and subordinate items corresponding to the search query, and searches reviews registered for each item for reviews corresponding to the search query; and a search result providing unit that provides the items corresponding to the search query as search results,
The search result providing unit is
recommending a sub-item corresponding to the search query among sub-items attached to the item corresponding to the search query included in the search result;
A computer system that processes: selecting reviews corresponding to the search query by performing semantic review matching based on embedding similarity with the search query, and displaying reviews related to lower-level items corresponding to the search query among reviews registered for an item corresponding to the search query searched by the search unit in association with the lower-level items corresponding to the search query. The at least one processor
a search unit for searching for subordinate items corresponding to the search query;
The search result providing unit is
The computer system according to claim 11 , further comprising: selecting an item to which the searched subordinate item belongs as an item search result. The search result providing unit is
The computer system according to claim 11 , wherein the item search results include an item to which the searched lower item belongs and an item for which the searched review has been registered. The search result providing unit is
Selecting items to which subordinate items corresponding to the search query belong as candidate items;
The computer system of claim 11 , further comprising: a popularity level of the candidate items being utilized to select some of the candidate items as final items. The search result providing unit is
The computer system according to claim 14, further comprising: ranking the final items using at least one of attribute information of the final items, candidate items attached to the final items, and reviews registered for the final items. The search result providing unit is
ranking the final items using a matching rate between the search query and attribute information of the final items;
The computer system of claim 14, further comprising: boosting a ranking of the final item by using at least one of a matching rate between the search query and candidate items attached to the final item and a matching rate between the search query and reviews registered for the final item. The search result providing unit is
providing a sub-item recommendation list including sub-items corresponding to the search query;
the subitem recommendation list includes an image representing each subitem;
12. The computer system of claim 11 , wherein reviews related to the subitems are displayed in association with the subitem recommendation list. The search result providing unit is
20. The computer system of claim 17, further comprising: ranking the selected reviews using at least one of the following: positive / negative scoring, length, recency, popularity, and author rating of the selected reviews.