JP2023035896A - Method, system, and computer program for dynamically providing sub-item recommendation list for each item included in search result by search query - Google Patents

Abstract

To provide a method, a system, and a computer program for dynamically providing a sub-item recommendation list for each item included in search results by a search query.SOLUTION: A search result providing method includes a step of providing items corresponding to a search query as search results. The providing step includes recommending, for each item included in the search results, sub-items corresponding to the search query among sub-items belonging to the pertinent item.SELECTED DRAWING: Figure 4

Description

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

Various evaluation systems such as star reviews, text reviews, and photo reviews are used as user reviews for various items.

A review service that uses places as items uses a place reservation function, a receipt authentication function, etc. to authenticate a place visited or used by a user, and then submits the authenticated place information together with a review.

For example, Patent Literature 1 (published January 6, 2020) discloses a technique for creating sales floor review information using augmented reality.

User reviews of places may be displayed in conjunction with other services that provide place information, such as search services and map services, as well as place review services.

Korean Patent Publication No. 10-2020-0000925

An object of the present invention is to dynamically compose and provide a subordinate item recommendation list for each item included in a search result according to a search query based on the relationship between an item and subordinate items possessed by the corresponding item.

A method of providing search results performed in a computer system, said computer system including at least one processor configured to execute computer readable instructions contained in a memory, said method of providing search results comprising: providing an item corresponding to a search query as a search result by the at least one processor, wherein the providing step includes sub-items belonging to the item for each item included in the search result. A search result providing method is provided, characterized by recommending subordinate items corresponding to the search query.

According to one aspect, the method for providing search results further includes searching for sub-items corresponding to the search query by the at least one processor, and providing includes: as the item search result.

According to another aspect, the method for providing search results comprises: searching, by the at least one processor, sub-items corresponding to the search query; and by the at least one processor, among reviews registered for each item, retrieving a review corresponding to the search query from the search query, wherein the providing step selects an item to which the retrieved sub-item belongs and an item to which the retrieved review is registered as an item search result. may contain

According to another aspect, the step of providing comprises: selecting an item to which the subordinate item corresponding to the search query belongs as a candidate item; selecting the part as the final item.

According to another aspect, the step of providing includes: using at least one of attribute information of the final item, candidate items attached to the final item, and reviews registered for the final item; A step of ranking the items may be included.

According to yet another aspect, the step of providing includes ranking the final item using a matching rate with attribute information of the final item for the search query, and ranking the final item for the search query. A step of boosting the ranking of the final item using at least one of a matching rate with the candidate item and a matching rate with the review registered for the final item may be included.

According to another aspect, in the step of providing, for each item included in the search result, reviews corresponding to the search query among reviews registered for the corresponding item are selected as sub-items corresponding to the search query. can be recommended with

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

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

According to yet another aspect, the step of providing ranks the selected reviews using at least one of text length, recency, popularity, and author rating of the selected reviews. may further include the step of:

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

1. A computer system comprising at least one processor configured to execute computer readable instructions contained in a memory, said at least one processor providing as search results items corresponding to a search query. a result providing unit, wherein the search result providing unit recommends a subordinate item corresponding to the search query among the subordinate items attached to the corresponding item for each item included in the search result; Provide a computer system.

According to an embodiment of the present invention, a subordinate item recommendation list is dynamically constructed and provided for each item included in a search result according to a search query based on the relationship between the item and subordinate items possessed by the corresponding item. By doing so, it is possible to improve the search results so that they are closer to the user's search intent.

1 is a diagram showing an example of a network environment in one embodiment of the present invention; FIG. 1 is a block diagram illustrating an example of a computer system in one embodiment of the invention; FIG. FIG. 2 illustrates an example of components that a processor of a computer system may include in one embodiment of the present invention; 2 is a flowchart illustrating an example of a method that may be performed by a computer system in accordance with one embodiment of the present invention; It is the figure which showed an example of the item search result screen in one Embodiment of this invention. It is the figure which showed an example of the item search result screen in one Embodiment of this invention. It is the figure which showed an example of the item search result screen in one Embodiment of this invention. 4 is a flow chart for explaining an example of the process of ranking item search results in one embodiment of the present invention. FIG. 4 is a diagram showing an example of features utilized for review ranking in one embodiment of the present invention; 4 is a flowchart for explaining an example of a process of ranking review recommendation results in one embodiment of the present invention.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Embodiments of the present invention relate to techniques for providing item search results that match the intent of a query.

Embodiments including matters specifically disclosed in the present specification recommend subordinate items for each item included in a search result according to a search query based on the relationship between the item and subordinate items possessed by the corresponding item. Lists can be dynamically constructed and served.

In this specification, an item may mean a search or recommendation target. By way of example, items may include subjects that can be reviewed for user experience with visits, uses, purchases, and the like. In addition, a lower item may mean an object possessed by an item, in other words, an object belonging to the item secondarily. User reviews may include individual reviews for each sub-item as well as reviews for the item.

A place such as a restaurant, a store, a famous place, a hotplace, etc. can be given as a representative example of the item. In the case of a restaurant, menus sold at the restaurant may correspond to the lower items, and in the case of the store, the items sold at the store may correspond to the lower items.

A search result providing system according to an embodiment of the present invention may be implemented by at least one computer system, and a search result providing method according to an embodiment of the present invention may be implemented by at least one computer system included in the search result providing system. may be executed. At this time, 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 provide search results according to an embodiment of the present invention under control of the executed computer program. the method may be carried out. The computer program described above may be recorded in a computer-readable recording medium in order to combine with a computer system and cause the computer to execute the method of providing search results.

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

The plurality of electronic devices 110, 120, 130, 140 may be fixed terminals or mobile terminals implemented by computing devices. Examples of the plurality of electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, PCs (personal computers), notebook PCs, digital broadcasting terminals, PDAs (Personal Digital Assistants), and PMPs (Portable Multimedia Players). ), tablets, game consoles, wearable devices, IoT (internet of things) devices, VR (virtual reality) devices, AR (augmented reality) devices, and the like. As an example, FIG. 1 shows a smart phone as an example of the electronic device 110, but in embodiments of the present invention, the electronic device 110 substantially utilizes a wireless or wired communication scheme and communicates with other devices via the network 170. may refer to one of a variety of physical computing devices capable of communicating with the electronic devices 120, 130, 140 and/or servers 150, 160 of the server.

The communication method is not limited, and not only the communication method using the communication network that can be included in the network 170 (eg, mobile communication network, wired Internet, wireless Internet, broadcasting network), but also the short distance between devices. Wireless communication may be included. For example, the network 170 includes a PAN (personal area network), a LAN (local area network), a CAN (campus area network), a MAN (metropolitan area network), a WAN (wide area network), a BBN (broadband network), and the Internet. Any one or more of the networks may be included. Additionally, network 170 may include any one or more of network topologies including, but not limited to, bus networks, star networks, ring networks, mesh networks, star-bus networks, tree or hierarchical networks, and the like. will not be

Each of servers 150, 160 is implemented by one or more computing devices that communicate with a plurality of electronic devices 110, 120, 130, 140 over network 170 to provide instructions, code, files, content, services, etc. good. For example, the server 150 may be a system that provides a first service to a plurality of electronic devices 110, 120, 130, 140 connected via the network 170, and the server 160 may also be a system that provides a plurality of electronic devices connected via the network 170. It may be a system that provides the second service to the electronic devices 110 , 120 , 130 , 140 . As a more specific example, the server 150 provides services (for example, item review service, etc.) may be provided to a plurality of electronic devices 110, 120, 130, 140 as a first service. As another example, the server 160 may provide, as a second service, a service of distributing files for installing and executing the applications described above to the plurality of electronic devices 110, 120, 130, and 140. FIG.

FIG. 2 is a block diagram illustrating an example computing device, in accordance with one embodiment of the present invention. Each of the plurality of 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 FIG.

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

The memory 210 is a computer-readable storage medium and may include random access memory (RAM), read only memory (ROM), and permanent mass storage devices such as disk drives. Here, a permanent mass storage device such as a ROM or disk drive may be included in computer device 200 as a separate permanent storage device separate from memory 210 . Also stored in memory 210 may be an operating system and at least one program code. Such software components may be loaded into memory 210 from a computer-readable medium separate from memory 210 . Such other computer-readable recording media may include computer-readable recording media such as floppy drives, disks, tapes, DVD/CD-ROM drives, memory cards, and the like. In other embodiments, software components may be loaded into memory 210 through communication interface 230 that is not a computer-readable medium. For example, software components may be loaded into memory 210 of computing device 200 based on computer programs installed by files received over network 170 .

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

Communication interface 230 may provide functionality for computer device 200 to communicate with other devices (eg, the recording device described above) via network 170 . As an example, processor 220 of computing device 200 can transmit requests, commands, data, files, etc. generated according to program code recorded in a recording device such as memory 210 to other devices via network 170 under the control of communication interface 230 . device. Conversely, signals, instructions, data, files, etc. from other devices may be received by computing device 200 through communication interface 230 of computing device 200 over network 170 . Signals, instructions, data, etc. received through the communication interface 230 may be transmitted to the processor 220 and the memory 210, and files may be stored in a recording medium (the permanent recording device described above) that the computing device 200 may further include. may be recorded.

Input/output interface 240 may be a means for interfacing with input/output device 250 . For example, input devices may include devices such as a microphone, keyboard, or mouse, and output devices may include devices such as displays, speakers, and the like. As another example, input/output interface 240 may be a means for interfacing with a device that integrates functionality for input and output, such as a touch screen. Input/output device 250 may be one device with computing device 200 .

Also, in other embodiments, computing device 200 may include fewer or more components than the components of FIG. However, most prior art components need not be explicitly shown in the figures. For example, computing device 200 may be implemented to include at least some of the input/output devices 250 described above, and may also include other components such as transceivers, databases, and the like.

Hereinafter, specific embodiments of a method and system for dynamically providing a sub-item recommendation list for each item included in search results according to a search query will be described.

FIG. 3 is a block diagram illustrating exemplary components that a processor of a computer system may include in accordance with one embodiment of the present invention, and FIG. 4 illustrates the components executed by the computer system in accordance with one embodiment of the present invention. It is the flowchart which showed an example of the search result provision method which can be performed.

The computer system 200 according to the present embodiment may provide an item review service for clients through a dedicated application installed on the client or by connecting 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 authenticate the items visited or used by the user through a function of interlocking with the reservation/order service or a receipt authentication function in relation to the item. After that, the authenticated item information and the review created by the user may be associated and registered. The user can create a review by specifying not only the item but also sub-items within the item. At this time, the review for the subordinate item may be managed in association with the subordinate item and the item to which the subordinate item belongs.

Computer system 200 may provide an item-based search and recommendation environment for users. At this time, 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 shown in FIG. 3 as components for executing the search result providing method described below. Depending on the embodiment, components of processor 220 may be selectively included or excluded from processor 220 . Also, depending on the embodiment, the components of processor 220 may be separated or merged to represent the functionality of processor 220 .

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

Here, the components of processor 220 may represent different functions performed by processor 220 according to instructions provided by program code recorded in computer system 200 . For example, item retriever 310 may be utilized as a functional representation of processor 220 that controls computer system 200 according to the instructions described above such that computer system 200 retrieves items corresponding to a search query.

Processor 220 may read the necessary instructions from memory 210 loaded with instructions associated with controlling computer system 200 . In this case, the read instructions may include instructions for controlling processor 220 to perform the search result providing method described below.

The steps included in the search results providing method described below may be performed in a different order than shown in the figures, some of the steps may be omitted, or additional steps may be included. may

Referring to FIG. 4, in step 410, when a search query is received, the item search unit 310 searches for an item corresponding to the search query, and registers sub-items attached to the item and the item as information on the searched item. You may provide written reviews. The item searcher 310 may search for sub-items corresponding to the search query and reviews corresponding to the search query to provide contextual search results.

Items and sub-items have respective 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, and the like. A menu item sold at a restaurant may correspond to a sub-item of a restaurant, and each menu has attribute information including a menu name, price, description, photo, rating, review, and the like.

Reviews are user feedback on items and subitems, and may include review content created in various review schemes such as star reviews, keyword reviews, text reviews, and photo reviews.

The item search unit 310 selects sub-items having attribute information that matches the search query, and reviews that include content that matches the search query or content that is similar in meaning to the search query, targeting sub-items and reviews. good.

In operation 420, the search result providing unit 320 may provide an item search result for the search query using the lower item search result and the review search result. The search result providing unit 320 selects, as an item search result, an item to which the lower item included in the lower item search result belongs and the review included in the review search result is linked, or uses it for ranking of the item search result. good.

In step 410, the search result providing unit 320 may select, as item search results, items selected as search results for both sub-items and reviews for the search query. In other words, items that are common to both the lower item search results and the review search results may be selected. Depending on the embodiment, an item selected as a search result from either one of the lower item and the review may be selected as the item search result.

The search result providing unit 320 may provide the item list selected as the item search result as the final search result corresponding to the search query. At this time, for each item included in the item search result, at least a part of the lower item search result and the review search result retrieved in step 410 may be provided as a recommendation list for the search query.

In other words, the search result providing unit 320 dynamically configures and provides sub-items and a review recommendation list for each item included in the search results according to the search query, thereby providing context based on the interrelationship between the items and sub-items. It is possible to provide search results that match For each item included in the search results, the subordinate item list and review list belonging to that item can be displayed. May appear higher in the list than other subordinate items and reviews.

FIG. 5 is a diagram showing an example of an item search result screen in one embodiment of the present invention.

Referring to FIG. 5 , processor 220 may provide item list 510 as final search results corresponding to search query 501 through 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 includes items to which sub-items having attribute information matching the search query 501 belong, content matching the search query 501, or content similar in meaning to the search query 501. It may consist of items for which reviews have been registered, items that belong to the two conditions described above, and the like.

The processor 220 may provide both a lower item recommendation list 520 and a review recommendation list 530 for each item included in the item list 510 through the item search result screen 500 .

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

In other words, the processor 220 may dynamically configure and provide the lower item recommendation list 520 and the review recommendation list 530 for each item included in the search results according to the search query 501 .

For example, when a user uses a restaurant menu keyword as a search query, even if the same restaurant is displayed in the search results, information about the restaurant may be displayed differently depending on the search query.

Referring to FIG. 6, it is assumed that <Restaurant I> corresponding to the item is included in the search result.

If 'Gangnam Pasta' is entered as a search query, the recommendation information related to <Restaurant I> may consist of the pasta menus sold at <Restaurant I>, or the pasta menus may be displayed at the top (for example, , displayed at a position that is easy for the user to recognize, such as the leftmost or topmost position of the list), and furthermore, content related to pasta in the review for <Restaurant I> may be provided. and a review recommendation list 631 in which the reviews registered in the <Restaurant I> pasta menu are displayed at the top.

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

In other words, the lower item recommendation lists 621 and 622 and the review recommendation lists 631 and 632 can be configured differently for the same item <Restaurant I> according to the search query.

For example, as shown in FIG. 7, when "Shinjuku pasta" is input as a search query, a lower item recommendation list 721 that displays pasta menus in the menu of <restaurant X> and a review list of <restaurant X> are displayed. A review recommendation list 731 may be provided that ranks the reviews associated with the pasta menu within. On the other hand, when "Shinjuku Pizza" is input as a search query, a lower item recommendation list 722 that displays pizza menus among the menus of <restaurant X> and a list of items related to pizza menus among reviews of <restaurant X>. A review recommendation list 732 may be provided that ranks the reviews to be reviewed.

Keywords that match the search query in the content included in the search results may be visually indicated, for example, by displaying the text color in red or by adding highlighting. you can

The processor 220 can utilize the sub-item search results and the review search results corresponding to the search query to determine the item search results, thereby providing a contextual list of items as search results.

In addition, the processor 220 provides contextual recommendation information among the information about the item by displaying both the sub-item list and the review list corresponding to the search query for each item included in the search result. can do. At this time, the processor 220 preferentially displays sub-items matching the search query among sub-items attached to the item and reviews matching the search query among reviews registered in the item as targets. good.

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

The processor 220 may rank the item search results using attribute information of each item and sub-items and reviews.

Referring to FIG. 8, at step 801, processor 220 may select candidate items utilizing sub-item search results corresponding to the search query and review search results corresponding to the search query. As an example, processor 220 may select items to which subordinate items corresponding to the search query belong as candidate items. As another example, the processor 220 selects an item to which the lower item corresponding to the search query belongs and to which the review corresponding to the search query is registered, that is, the item that exists in common between the lower item search result and the review search result. May be selected as a candidate item.

At step 802, the processor 220 may select a certain number or percentage of the top candidate items as final items using the popularity of the items. Here, the degree of popularity may mean a user feedback score, and for example, a higher score may be calculated as the number of "likes" or ratings, the number of times of sharing, or the number of registered reviews increases. In other words, processor 220 may apply a popularity ranking based on each item's user feedback score.

At step 803, the processor 220 ranks the item search results configured as final items using query custom type relevance features using at least one of attribute information of each item and sub-items and reviews. You can As an example, the processor 220 uses at least one of a search query and attribute information matching rate, a search query and sub-item matching rate, and a search query and review matching rate as the query custom type relevance feature. good.

The processor 220 calculates the matching rate with the search query based on the name, description, category, etc. of the item as well as the theme keyword related to the item as the attribute information existing in the item database, and uses the query for ranking the search result. May be used as a custom relevance feature.

Theme keywords include keywords related to subordinate items and keywords unrelated to subordinate items. In the case of restaurants, theme keywords may be classified into menu keywords and non-menu keywords. The restaurant theme keyword can be extracted from a predetermined theme keyword dictionary as well as restaurant attribute information such as business category and menu name.

The processor 220 may rank the item search results by combining the matching rate with the attribute information, the matching rate with lower items attached to the item, the matching rate with reviews registered for the item, and the like.

The processor 220 maintains popularity rankings for search results based on user feedback scores for each item, but may also rerank item search results using matching rates with attribute information for search queries. The processor 220 also utilizes the sub-item matching rate and/or the review matching rate to complement each other to address inaccuracies in attribute information by boosting search result reranking. any ranking logic may be applied.

Additionally, time keywords such as "morning", "lunch", "dinner", etc., and time keywords such as "drinking party", "date", "gathering", "with family", "with friends", etc. For a query containing a target keyword indicating a purpose, a definition for each keyword may be given based on review data obtained by receipt authentication, and used for ranking logic.

The present embodiment can dynamically compose and display a subordinate item recommendation list according to a search query for the same item included in the search result.

FIG. 9 is a diagram showing an example of features utilized for review ranking in one embodiment of the present invention.

For each item included in the search results, the processor 220 may recommend contextual reviews among the reviews registered for the item. At this time, reviews that are more meaningful and relevant to the search query may be preferentially displayed.

Referring to FIG. 9, the processor 220 determines 1) the length of the review text, 2) the text quality including the sentimental score by 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 under the high quality level, 5) the date the review was created, 6) the difference between the date the review was created and the date recently consumed, etc. 7) review author's abuse rating, 8) user's real name authentication status, 9) user's total number of review creations, 10) user's follower number, 11) user's visit authentication number, etc. Popularity, including user rating, 12) review score, 13) cumulative number of review "likes", etc., may be used to rank review recommendation results.

1) Length of review text, 2) Sentiment score, 3) Number of images, 4) Number of high quality images, etc. are the criteria for selecting reviews with substantial content, 5) Review creation date, 6) Review creation Differences such as the difference between the date of consumption and the recent consumption date are criteria for selecting up-to-date reviews. In addition, 7) Abuse grade, 8) Real name authentication status, etc. are the criteria for selecting reviews with low malicious intentions. It serves as the basis for selecting expert-authored reviews. Furthermore, 12) the score, 13) the cumulative number of "likes", etc., are criteria for selecting popular reviews.

The features described above are merely exemplary, and can be extended to any feature that can serve as a weighted value for review ranking.

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

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

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

As an example, the processor 220 may calculate a sentiment score based on positive wording using a ridge-based keyword-based sentiment dictionary, and may assign a ranking weight accordingly. The sentiment score, which is one of the features that indicate text quality, is obtained by extracting positive words that are important variables by a Ridge Logistic Regression method that classifies positive and negative from sentences created as reviews, and extracting these positive words. It is a score of coefficient values. The more positive the review text, the higher the positive value, and the more negative the review text, the lower the negative value. Such sentiment scores may be used to increase the impact of review displays containing positive wording.

As another example, the processor 220 may determine review rankings based on review text length, recency, ratings, cumulative number of likes, and the like. The processor 220 may assign higher ranking weights to reviews that have been recently written, reviews that have been written at a reasonable length, reviews that have accumulated a large number of "likes", and reviews that have received high ratings.

The present embodiment can dynamically construct and display a review recommendation list for the same item included in search results according to a search query.

As described above, according to the embodiment of the present invention, based on the relationship between the item and the sub-item owned by the corresponding item, the sub-item and the review recommendation list are moved for each item included in the search result according to the search query. By constructing and providing search results in a systematic manner, it is possible to improve search results by bringing them closer to the user's search intent.

The apparatus described above 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 include processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable gate arrays (FPGAs), programmable logic units (PLUs), microprocessors, Or may be implemented using one or more general purpose or special purpose computers, such as various devices capable of executing and responding to instructions. The processing unit may run an operating system (OS) and one or more software applications that run on the OS. The processor may also access, record, manipulate, process, and generate data in response to executing software. For convenience of understanding, a single processing device may be described as being used, but those skilled in the art will appreciate that a processing device may include multiple processing elements and/or multiple types of processing elements. You can understand that. For example, a processing unit may include multiple processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include computer programs, code, instructions, or a combination of one or more of these, to configure a processor to operate at its discretion or to independently or collectively instruct a processor. You can Software and/or data may be embodied in any kind of machine, component, physical device, computer storage medium, or device for interpretation by, or for providing instructions or data to, a processing device. good. The software may be stored and executed in a distributed fashion over computer systems linked by a network. Software and data may be recorded on one or more computer-readable recording media.

The method according to the embodiments may be embodied in the form of program instructions executable by various computer means and recorded on a computer-readable medium. Here, the medium may record the computer-executable program continuously or temporarily record it for execution or download. In addition, the medium may be various recording means or storage means in the form of a combination of single or multiple hardware, and is not limited to a medium that is directly connected to a computer system, but is distributed over a network. It may exist in Examples of media 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 ROM, RAM, flash memory, etc., and may be configured to store program instructions. Other examples of media include recording media or storage media managed by application stores that distribute applications, sites that supply or distribute various software, and servers.

As described above, the embodiments have been described based on the limited embodiments and drawings, but those skilled in the art will be able to make various modifications and variations based on the above description. For example, the techniques described may be performed in a different order than in the manner described and/or components such as systems, structures, devices, circuits, etc. described may be performed in a manner different from the manner described. Appropriate results may be achieved when combined or combined, opposed or substituted by other elements or equivalents.

Accordingly, different embodiments that are equivalent to the claims should still fall within the scope of the appended claims.

220: Processor 310: Item Search Unit 320: Search Result Providing Unit

Claims (20)

A search results providing method executed by a computer system, comprising:
The computer system includes at least one processor configured to execute computer readable instructions contained in memory;
The search result providing method includes:
providing, by the at least one processor, items corresponding to a search query as search results;
The providing step includes:
A method for providing search results, comprising: recommending a subordinate item corresponding to the search query among subitems attached to the corresponding item for each item included in the search result. The search result providing method includes:
retrieving, by the at least one processor, sub-items corresponding to the search query;
The providing step includes:
The method of claim 1, further comprising: selecting an item to which the searched lower item belongs as an item search result. The search result providing method includes:
searching for sub-items corresponding to the search query by the at least one processor; and searching reviews registered for each item for reviews corresponding to the search query by the at least one processor. further includes
The providing step includes:
2. The method of claim 1, further comprising: selecting an item to which the searched sub-item belongs and an item to which the searched review is registered as an item search result. The providing step includes:
selecting items to which subordinate items corresponding to the search query belong as candidate items; and selecting some of the candidate items as final items using popularity of the candidate items. 1. The method for providing search results according to 1. The providing step includes:
5. The step of ranking the final item using at least one of attribute information of the final item, candidate items attached to the final item, and reviews registered for the final item. method of providing search results. The providing step includes:
ranking the final item using a matching rate of the attribute information of the final item with respect to the search query; and 5. The method of claim 4, comprising: boosting the ranking of the final item using at least one of matching rates with reviewed reviews. The providing step includes:
2. The method according to claim 1, wherein for each item included in the search result, a review corresponding to the search query among reviews registered for the corresponding item is recommended together with a lower item corresponding to the search query. How to provide search results as described. The providing step includes:
The method of claim 7, comprising selecting reviews corresponding to the search query using embedded similarity with the search query. The providing step includes:
9. The method of claim 8, further comprising: ranking the selected reviews based on positive/negative scoring of the selected reviews. The providing step includes:
9. The search of claim 8, further comprising ranking the selected reviews using at least one of text length, recency, popularity, author rating of the selected reviews. How to provide results. A computer program for causing a computer to execute the search result providing method according to any one of claims 1 to 10. a computer system,
at least one processor configured to execute computer readable instructions contained in memory;
The at least one processor
including a search results provider that provides search results for items corresponding to the search query;
The search result providing unit
A computer system for recommending sub-items corresponding to the search query among sub-items attached to each item included in the search result. The at least one processor
a search unit that searches for sub-items corresponding to the search query;
The search result providing unit
13. The computer system according to claim 12, wherein an item to which the searched sub-item belongs is selected as an item search result. The at least one processor
a search unit that searches for subordinate items corresponding to the search query, and searches reviews registered for each item for reviews corresponding to the search query;
The search result providing unit
13. The computer system according to claim 12, wherein an item to which the searched lower item belongs and an item to which the searched review is registered are selected as item search results. The search result providing unit
selecting an item to which the subordinate item corresponding to the search query belongs as a candidate item;
13. The computer system of claim 12, wherein the popularity of the candidate items is used to select some of the candidate items as final items. The search result providing unit
The final item is ranked using at least one of attribute information of the final item, candidate items attached to the final item, and reviews registered for the final item. the computer system described in . The search result providing unit
ranking the final item using a matching rate with the attribute information of the final item for the search query;
boosting the ranking of the final item using at least one of a matching rate with candidate items attached to the final item for the search query and a matching rate with reviews registered for the final item. 16. A computer system as in claim 15, characterized by: The search result providing unit
13. The method according to claim 12, wherein for each item included in the search result, reviews corresponding to the search query among reviews registered for the corresponding item are recommended together with lower items corresponding to the search query. The described computer system. The search result providing unit
19. The computer system of claim 18, wherein embedded similarities with the search query are used to select reviews corresponding to the search query. The search result providing unit
ranking the selected reviews using at least one of a positive/negative scoring of the selected reviews, length of text, recency, popularity, and author rating. Item 20. The computer system according to Item 19.

Images