Apparatus and method for recommending store based on congestion level

Abstract

The present invention relates to a store recommendation method based on congestion, and the store recommendation method based on congestion may include the steps of receiving preferred store information including preferred congestion from a user terminal, calculating store-specific congestion based on store-specific noise level information, selecting at least one recommended store that satisfies the preferred congestion based on the store-specific congestion, and transmitting information about the at least one recommended store to the user terminal.

Description

Technology Field

[0001] The present invention relates to a store recommendation device and method based on congestion level. Background Technology

[0002] Recently, domestic coffee and cafe consumption has been increasing, leading to a rise in the number of specialty coffee shops and establishments selling coffee menus. Furthermore, for modern people, cafes are being utilized beyond simply being places to drink tea to engage in leisure activities, study, work, view interiors, and experience new food and beverages; consequently, the atmospheres and concepts of cafes are becoming increasingly diverse.

[0003] Meanwhile, when users select a cafe based on their purpose of visit or preferences, the existence of numerous cafes and the lack of information about them can make it difficult for users to find and visit the cafe they want. Furthermore, popular cafes may have limited seating, and it may be difficult to gauge the level of congestion based solely on review information consisting of photos and text. Consequently, even if a user searches for and visits a cafe they desire, there may be disadvantages such as being unable to use the cafe or having an unsatisfactory experience.

[0004] In addition, small and medium-sized cafes operated by individual business owners are increasing alongside franchises, and these small and medium-sized cafes face difficulties in establishing systems to provide information about the cafe due to cost and time constraints.

[0005] The technology forming the background of the present invention is disclosed in Korean Published Patent Application No. 10-2021-003706. The problem to be solved

[0006] The present invention aims to solve the problems of the aforementioned prior art by providing a congestion-based store recommendation device and method that can provide the congestion level of a store to the user in near real-time by calculating the congestion level of the cafe based on the noise level of the cafe measured through a user terminal using the cafe, thereby supporting the user in searching for and visiting a store suitable for their purpose of visiting and preferred tastes.

[0007] The present invention aims to solve the problems of the aforementioned prior art by providing a congestion-based store recommendation device and method that facilitates the verification and management of store lists for each user by providing a metaverse-based user-customized store map that includes store lists such as recommended stores, visited stores, and preferred stores.

[0008] However, the technical problems that the embodiments of the present invention aim to solve are not limited to the technical problems described above, and other technical problems may exist. means of solving the problem

[0009] As a technical means for achieving the above-mentioned technical problem, a congestion-based store recommendation method according to one embodiment of the present invention may include the steps of receiving preferred store information including preferred congestion from a user terminal, calculating a store-specific congestion level based on store-specific noise level information, selecting at least one recommended store that satisfies the preferred congestion level based on the store-specific congestion level, and transmitting information about the at least one recommended store to the user terminal.

[0010] According to one embodiment of the present invention, the method further includes the step of receiving order information from a store terminal, and the step of calculating the congestion level may calculate the congestion level for each store by further considering the order information.

[0011] According to one embodiment of the present invention, the method further includes the step of receiving sound data measured at the store currently used by each of the plurality of users among the plurality of stores from each of the user terminals of the plurality of users using the plurality of stores, and the step of calculating the congestion level may be to generate noise level information for each store based on the sound data.

[0012] According to one embodiment of the present invention, the preferred store information further includes preferred mood information and condition information, and the step of selecting at least one recommended store may involve selecting at least one recommended store by further considering the preferred mood information and the condition information.

[0013] According to one embodiment of the present invention, the method further includes the step of generating a user-customized store map that displays a list of at least one of the at least one recommended store, a visited store where a user corresponding to the user terminal has a visit history, and a preferred store already stored in the user terminal, and the step of transmitting to the user terminal may be to output the user-customized store map through the user terminal.

[0014] According to one embodiment of the present invention, the user-customized store map is generated in the form of a metaverse-based map that is virtually simulated based on actual environmental information of each store included in the store list, and the step of generating the user-customized store map may include the step of generating a metaverse-based virtual object that is movable on the user-customized store map based on user information received by the user terminal.

[0015] According to one embodiment of the present invention, the step of generating the user-customized store map may involve setting different display forms for a plurality of stores included in the store list, each store including at least one of color, shape, and size based on importance.

[0016] According to one embodiment of the present invention, the method may further include the step of providing a community that displays at least one of a plurality of stores included in the store list on the user-customized store map to share with other users, and provides a communication function between a plurality of user terminals regarding the shared store map.

[0017] As a technical means for achieving the above-mentioned technical problem, a congestion-based store recommendation device according to one embodiment of the present invention may include a receiving unit that receives preferred store information including preferred congestion level from a user terminal, a calculating unit that calculates a store-specific congestion level based on store-specific noise level information, a selecting unit that selects at least one recommended store satisfying the preferred congestion level based on the store-specific congestion level, and a transmitting unit that transmits information about the at least one recommended store to the user terminal.

[0018] According to one embodiment of the present invention, the receiving unit receives order information from a store terminal, and the calculating unit may calculate the congestion level for each store by further considering the order information.

[0019] According to one embodiment of the present invention, the receiving unit receives sound data measured at the store currently used by each of the plurality of users among the plurality of stores from each of the user terminals of the plurality of users using the plurality of stores, and the congestion level calculation unit may generate noise level information for each store based on the sound data.

[0020] According to one embodiment of the present invention, the preferred store information further includes preferred mood information and condition information, and the selection unit may select the at least one recommended store by further considering the preferred mood information and the condition information.

[0021] According to one embodiment of the present invention, the system further includes a map generating unit that generates a user-customized store map displaying a list of at least one of the following: at least one recommended store, a visited store where a user corresponding to the user terminal has a visit history, and a preferred store already stored in the user terminal; and the transmitting unit may output the user-customized store map through the user terminal.

[0022] According to one embodiment of the present invention, the user-customized store map is generated in the form of a metaverse-based map that is virtually simulated based on actual environmental information of each store included in the store list, and the map generation unit may generate a metaverse-based virtual object that is movable on the user-customized store map based on user information received by the user terminal.

[0023] According to one embodiment of the present invention, the map generating unit may set different display forms for a plurality of stores included in the store list, each store including at least one of color, shape, and size, based on importance.

[0024] According to one embodiment of the present invention, the system may further include a community providing unit that displays at least one of a plurality of stores included in the store list on the user-customized store map to share with other users, and provides a community that provides a communication function between a plurality of user terminals regarding the shared store map.

[0025] The means for solving the problem described above are merely exemplary and should not be interpreted as intended to limit the present invention. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and the detailed description of the invention. Effects of the invention

[0026] According to the solution to the problem of the present invention described above, by calculating the level of congestion of a cafe based on the noise level of the cafe measured through a user terminal using the cafe, the level of congestion of the store can be provided to the user in near real-time, thereby supporting the user in searching for and visiting a store suitable for their purpose of visiting and preferred tastes.

[0027] According to the solution to the problem of the present invention described above, by providing a metaverse-based user-customized store map that includes store lists such as recommended stores, visited stores, and preferred stores, it is possible to easily provide verification and management of store lists for each user.

[0028] However, the effects obtainable from this invention are not limited to those described above, and other effects may exist. Brief explanation of the drawing

[0029] FIG. 1 is a schematic diagram of a congestion-based store recommendation system according to one embodiment of the present invention. Figure 2 is a diagram illustrating an exemplary filter selection interface in which user input regarding preferred store information is authorized. Figure 3 is a diagram illustrating an exemplary noise level display interface that displays measured acoustic data. FIG. 4 is a diagram illustrating an exemplary map display interface that displays a metaverse-based user-customized store map and an information provision interface that allows user input for the selection of a store displayed on the user-customized store map and displays information about the store based on the user input. FIG. 5 is a diagram illustrating an exemplary community selection interface in which user input regarding mood information and condition information for selecting a desired community is authorized, and a user information display interface that displays user-specific usage history. FIG. 6 is a diagram illustrating an event information display interface that provides event information and an order information display interface that provides order information and allows user input for order information. FIG. 7 is a schematic block diagram of a congestion-based store recommendation device according to one embodiment of the present invention. FIG. 8 is a flowchart of an operation for a store recommendation method based on congestion according to one embodiment of the present invention. Specific details for implementing the invention

[0030] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0031] Throughout this specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected," but also cases where they are "electrically connected" or "indirectly connected" with other elements interposed between them.

[0032] Throughout the entire specification, when a component is described as being located "on," "on top," "on top," "under," "on bottom," or "on bottom" of another component, this includes not only cases where the component is in contact with the other component but also cases where another component exists between the two components.

[0033] Throughout this specification, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0034] The present invention relates to a store recommendation device based on congestion. The multiple stores described herein may refer to multiple franchise stores linked to the store recommendation device based on congestion of the present invention, and the stores described herein may be, for example, cafes, but are not limited thereto.

[0035] FIG. 1 is a schematic diagram of a congestion-based store recommendation system according to one embodiment of the present invention.

[0036] Referring to FIG. 1, a store recommendation system based on congestion (10) (hereinafter referred to as the 'store recommendation system (10)') according to one embodiment of the present invention may include a store recommendation device based on congestion (100) (hereinafter referred to as the 'store recommendation device (100)') according to one embodiment of the present invention, a user terminal (200), a user terminal (300), and a store terminal (400).

[0037] The store recommendation device (100), user terminal (200), customer terminal (300), and store terminal (400) can communicate with each other through a network. A network refers to a connection structure that enables information exchange between each node, such as terminals and servers. Examples of such networks may include, but are not limited to, a 3GPP (3rd Generation Partnership Project) network, an LTE (Long Term Evolution) network, a 5G network, a WIMAX (World Interoperability for Microwave Access) network, a wired / wireless internet (Internet), a LAN (Local Area Network), a Wireless LAN (Wireless Local Area Network), a WAN (Wide Area Network), a PAN (Personal Area Network), a Bluetooth network, a Wi-Fi network, a NFC (Near Field Communication) network, a satellite broadcasting network, an analog broadcasting network, and a DMB (Digital Multimedia Broadcasting) network.

[0038] In addition, in the description of the embodiments of the present invention, the terminal including the user terminal (200), customer terminal (300), and store terminal (400) is a device that is linked with the store recommendation device (100) through a network, and may be, for example, a smartphone, smart pad, tablet PC, wearable device, etc., and all kinds of wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, and a fixed terminal such as a desktop computer and a smart TV.

[0039] According to one embodiment of the present invention, a store recommendation device (100) receives preferred store information from a user terminal (200) and, based on the preferred store information, selects a recommended store based on the store-specific congestion level and provides it to the user terminal (200). At this time, the store recommendation device (100) may generate store-specific noise level information used to calculate the congestion level based on acoustic data measured through the user terminal (300) of a user of each store.

[0040] That is, the user corresponding to the user terminal (300) may also be a user using the store recommendation device (100), but for convenience of explanation, the terminal of the user receiving the recommended store is specified as the user terminal (200), and the terminal of the user (user) who uses the store and measures sound data through the terminal may be specified as the user terminal (300).

[0041] Additionally, the store recommendation device (100) may calculate the store-specific congestion level by taking into account order information received from the store terminal (400) when calculating the store-specific congestion level. In this regard, the store recommendation device (100) may calculate the store-specific congestion level by taking into account store-specific review information.

[0042] Additionally, the store recommendation device (100) may provide a list of stores including selected recommended stores to a user terminal (200) by displaying it on a metaverse-based user-customized store map that is virtually simulated based on actual environmental information for each store.

[0043] Hereinafter, with reference to FIGS. 2 to 6, a user-customized store recommendation process based on congestion through a store recommendation system (10), a user-customized store map provision process, and a related additional service provision process will be described in detail.

[0044] Figure 2 is a diagram illustrating an exemplary filter selection interface in which user input regarding preferred store information is authorized.

[0045] Referring to FIG. 2, the store recommendation device (100) may display a plurality of options for preferred store information through a user terminal (200) and receive a selection input for at least one of the plurality of options. In other words, the store recommendation device (100) may receive preferred store information from the user terminal (200).

[0046] At this time, the preferred store information may include preferred congestion level, preferred mood information, and condition information. Specifically, the preferred congestion level may be expressed as a noise level as exemplified in FIG. 2, but is not limited thereto, and may be expressed as a level of congestion (e.g., level 1, level 2, etc., or reading room level, general conversation level, downtown street level, etc.) arbitrarily classified by the store recommendation device (100).

[0047] Additionally, preferred mood information may include modern, kitsch, antique, minimal, vintage, retro, good for working, good for conversation, etc., and condition information may include dessert hotspots, coffee hotspots, brunch sales, no-kids zones, yes-kids zones, pet-friendly, pet-prohibited, etc., but is not limited thereto, and preferred mood information and condition information may include various other examples in addition to the above examples, and as illustrated in FIG. 2, preferred mood information and condition information may be displayed on the user terminal (200) without distinction from each other.

[0048] Referring to FIG. 2, the store recommendation device (100) may further provide the user terminal (200) with options for sorting criteria for a list of recommended stores through the filter selection interface shown in FIG. 2. The sorting criteria, exemplified by referring to FIG. 2, may include order of popularity, high acidity, low acidity, low price, order of many reviews, distance, recommendation, etc., and filter criteria may include open, franchise, non-franchise, discount promotion, etc. At this time, high acidity, low acidity, low price, etc., may be divided based on criteria such as Americano when the store is a cafe, but are not limited thereto.

[0049] According to one embodiment of the present invention, a store recommendation device (100) can select at least one recommended store from a plurality of stores by considering preferred store information received from a user terminal (200). At this time, the store recommendation device (100) can calculate store-specific congestion information for each of the plurality of stores in order to select a store that satisfies the preferred congestion included in the preferred store information as a recommended store.

[0050] Figure 3 is a diagram illustrating an exemplary noise level display interface that displays measured acoustic data.

[0051] Referring to FIG. 3, the store recommendation device (100) can receive sound data measured at the store currently used by each of the multiple customers among the multiple stores from each of the multiple customers' terminals (300) that use multiple stores.

[0052] Specifically, the store recommendation device (100) may provide an icon to which an input for measuring sound data of the store can be authorized to be performed on the user terminal (300), and when the user's input for the icon is received, the sound data of the store currently visited by the user may be obtained through the user terminal (300).

[0053] At this time, the store recommendation device (100) may determine whether the user has actually visited the store by considering the location information of the user terminal (300), and if the user's location is the same as the location of the store, allow the measurement of sound data of the user terminal (300). Additionally, the store recommendation device (100) may receive the measured sound data from the user terminal (300) when the measurement of sound data of the user terminal (300) is allowed and the sound data is measured.

[0054] Referring to FIG. 3, the store recommendation device (100) may provide the customer terminal (300) with an interface indicating that sound data is being measured (see FIG. 3 (a)) when sound data is being measured through the customer terminal (300). Additionally, the store recommendation device (100) may provide the customer terminal (300) with an interface that displays the measured sound data (e.g., measurement results in decibel (dB) units, exemplified by FIG. 3) and a comparison of living noise and facial expression icons for the measured sound data together to help with easy identification and determination of the degree of the measured sound data (see FIG. 3 (b), (c), and (d)).

[0055] According to one embodiment of the present invention, a store recommendation device (100) can generate noise level information for each store based on measured acoustic data. Specifically, the store recommendation device (100) may remove the sound of conversation of a user from acoustic data measured through a user terminal (300), identify a non-conversational section suitable for evaluating the noise level within the store among the measurement sections, and generate noise level information for the corresponding store using acoustic data in the identified non-conversational section.

[0056] For example, the store recommendation device (100) may use a user terminal (300) to measure sound data during a preset measurement time, analyze the sound of the entire measurement section to remove noise sections such as the sound of the user’s conversation, specify a section within the entire measurement section that contains a minimum amount of unnecessary sound parts such as the sound of the user’s conversation and noise generated by the user’s body contacting the user terminal (300) as a non-conversation section, and generate noise level information for the corresponding store using only the sound data of the specified non-conversation section.

[0057] As another example, the store recommendation device (100) may measure acoustic data using a user terminal (300), continue measuring the acoustic data for a period of time until a non-conversational section greater than the minimum section required for generating noise level information is measured, and stop measuring the acoustic data when a non-conversational section greater than the minimum section is measured.

[0058] In other words, the non-expansion period may be a period of longer than the minimum period required for generating noise level information, and in this regard, the store recommendation device (100) may generate accurate noise level information as the non-expansion period is longer.

[0059] Additionally, the store recommendation device (100) may acquire sound data through the store terminal (400) as well as the user terminal (300). At this time, the store terminal (400) may include a router, kiosk, and POS machine installed in each store, but is not limited thereto.

[0060] Specifically, the store recommendation device (100) may transmit request information to the store terminal (400) of the store to request measurement of sound data in order to acquire additional sound data when at least one of the amount of sound data and the accuracy of sound data measured in real time through the customer terminal (300) does not reach a preset threshold. Additionally, when the store recommendation device (100) receives an acceptance input for the request information from the store terminal (400), it may measure the sound data through the store terminal (400).

[0061] Accordingly, the store recommendation device (100) may generate multiple first noise level information using acoustic data measured from each of the multiple user terminals (300), generate second noise level information using acoustic data measured from the store terminal (400), and generate final noise level information for the corresponding store by combining the generated multiple first noise level information and second noise level information. At this time, the process of generating each noise level information may be the same as the process of generating noise level information for acoustic data measured through the user terminal (300). In addition, the final noise level information may be the average of the generated multiple first noise level information and second noise level information, but is not limited thereto, and may be generated by assigning respective weights based on their respective accuracy.

[0062] According to one embodiment of the present invention, a store recommendation device (100) can calculate the level of congestion for each store based on noise level information for each store. The store recommendation device (100) can calculate that the higher the noise level according to the noise level information for each store, the higher the level of congestion for the corresponding store.

[0063] Additionally, the store recommendation device (100) may receive more order information from the store terminal (400) and calculate the congestion level for each store by taking the received order information into account. In this case, the order information may include the total order volume by time period, the takeout order volume, and the in-store order volume. The store recommendation device (100) may calculate the congestion level of the corresponding store as higher when the total order volume is higher and when the in-store order volume is higher relative to the takeout order volume by taking the order information into account.

[0064] Additionally, the store recommendation device (100) can record and store the calculated store-specific congestion level and generate statistical information on the previously recorded and stored congestion level based on temporal factors such as time of day, day of the week, and weather. The store recommendation device (100) calculates the store-specific congestion level by further considering the generated statistical information, specifically, it may obtain the average congestion level of the corresponding time period based on statistical information regarding the time period corresponding to the current time period for calculating the congestion level, and calculate the current congestion level by considering the obtained average congestion level of the corresponding time period.

[0065] Additionally, statistical information generated as described above can be provided to a user terminal (300) and a store terminal (400), and the store recommendation device (100) can be provided so that a user corresponding to the user terminal (300) and a store employee corresponding to the store terminal (400) can check when the congestion level is high and low by time of day, day of the week, and weather, and can support the user in predicting the current congestion level by store from a statistical perspective without calculating the congestion level in real time.

[0066] Additionally, the store recommendation device (100) may calculate the store-specific congestion level by further considering store-specific review information. Specifically, the store recommendation device (100) may collect store-specific review information, derive a sentence containing keywords regarding season, date, time, purpose of store visit, number of users, atmosphere, store space size and number of tables, etc. from the collected review information, and calculate the congestion level using a learned model trained to calculate the expected congestion level using the derived sentence as input.

[0067] For example, the store recommendation device (100) may derive sentences such as ‘I studied well today, perhaps because I studied at a cafe for the first time in a while,’ ‘It was difficult to order because there were too many people since it was past lunchtime,’ and ‘The cafe was very spacious, so it was good to chat and play with friends without any pressure’ from collected review information, and may use a learning model to predict the level of congestion for the store by time of day, or estimate the mood and space size of the store and further consider these factors to predict the level of congestion, but is not limited thereto.

[0068] Such learning models may include, for example, deep learning models, machine learning models, neural network models (artificial neural network models), neuro-fuzzy models, etc. As for the artificial intelligence models considered herein, various neural network models for machine learning that are already known in the past or will be developed in the future, such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Deep Neural Networks, may be applied.

[0069] According to one embodiment of the present invention, a store recommendation device (100) can calculate the store-specific congestion level based on the assigned weights by assigning weights to each of the store-specific noise level information, order information, statistical information, and review information, taking into account the amount and accuracy of each of the store-specific noise level information, order information, statistical information, and review information.

[0070] Specifically, the store recommendation device (100) may assign a higher weight to information among store-specific noise level information, order information, statistical information, and review information, as the amount of information is greater and the accuracy is higher. For example, if the amount of acoustic data measured for a specific store is insufficient, the store-specific congestion level may be calculated by assigning a higher weight to order information, statistical information, and review information compared to store-specific noise level information. Also, if there are many reviews for the store and each review information contains many keywords that can be used to calculate the congestion level, the review information may be assigned a higher weight compared to store-specific noise level information, order information, and statistical information.

[0071] According to the above description, the store recommendation device (100) can calculate the store-specific congestion level by considering store-specific noise level information, thereby obtaining the store-specific congestion level in near real-time and providing it to the user terminal (200), and can improve the accuracy of the calculated congestion level compared to considering only store-specific noise level information by calculating the store-specific congestion level by further considering order information, statistical information and review information depending on the situation.

[0072] According to one embodiment of the present invention, a store recommendation device (100) may select at least one recommended store that satisfies a preferred congestion level received from a user terminal (200) based on a calculated store-specific congestion level. However, it is not limited thereto, and the store recommendation device (100) may further consider store-specific congestion level, review information, and main user information to select at least one recommended store that satisfies preferred store information including preferred congestion level, preferred mood information, and condition information.

[0073] Specifically, the store recommendation device (100) may derive keywords regarding the purpose of the store visit, the number of customers, the atmosphere, the size of the store space, and the number of tables included in the review information, determine whether the store satisfies the preferred mood information and condition information received from the user terminal (200), and determine whether to select the store as a recommended store.

[0074] Additionally, the store recommendation device (100) may further receive main user information, including age, gender, occupation, and purpose of use, from the user terminal (300) and the store terminal (400), identify the age, gender, occupation, and purpose of use of the main users who primarily use the store, and predict the mood or characteristics of the store by taking these into consideration. The store recommendation device (100) may determine whether the store satisfies the preferred mood information and condition information received from the user terminal (200) based on the predicted mood or characteristics of the store, and determine whether to select the store as a recommended store. At this time, the characteristics correspond to the condition information of the preferred store information and may include, but are not limited to, dessert restaurants, coffee restaurants, brunch sales, no-kids zones, yes-kids zones, pet-friendly, or pet-prohibited.

[0075] According to the above description, the store recommendation device (100) can provide the store's congestion level to the user in near real-time by calculating the congestion level of the cafe based on the noise level of the cafe measured through a user terminal using the cafe, thereby supporting the user in searching for and visiting a store suitable for the purpose of visiting the store and preferred tastes.

[0076] According to one embodiment of the present invention, a store recommendation device (100) can transmit information about at least one selected recommended store to a user terminal (200).

[0077] FIG. 4 is a diagram illustrating an exemplary map display interface that displays a metaverse-based user-customized store map and an information provision interface that allows user input for the selection of a store displayed on the user-customized store map and displays information about the store based on the user input.

[0078] Referring to FIG. 4, the store recommendation device (100) may provide information about the recommended store to the user terminal (200) by providing it to a metaverse-based user-customized store map that includes a list of stores for at least one selected recommended store.

[0079] Additionally, the store recommendation device (100) may be capable of providing the user terminal (200) not only a list of recommended stores but also a list of stores visited by the user and preferred stores stored in the user terminal (200), in addition to a list of recommended stores. In other words, the store recommendation device (100) may generate a user-customized store map that displays a list of at least one of at least one recommended store, a store visited by the user, and a preferred store, and output the generated user-customized store map through the user terminal (200). Here, the user-customized store map may be generated in the form of a metaverse-based map that is virtually simulated based on the actual environmental information of each store included in the store list.

[0080] Specifically, the store recommendation device (100) determines that a store where sound data measurement was performed through the user terminal (200), a store where the user wrote a review after visiting, or a store where the user has a history of placing an order through a series of order and payment processes linked with the store recommendation device (100) is a visited store, and can display a list of such visited stores on a user-customized store map.

[0081] Additionally, as illustrated in FIG. 4(a), the store recommendation device (100) can receive storage inputs for each of a plurality of stores from a user terminal (200), determine the store corresponding to the received storage input as the user's preferred store, and display a list of stores for such preferred stores on a user-customized store map.

[0082] According to one embodiment of the present invention, the store recommendation device (100) may provide an item selection icon for displaying a list of stores for recommended stores, visited stores, and preferred stores, and may display only the list of stores corresponding to at least one of the item selection icons from the user terminal (200) on a user-customized store map. At this time, the items in the store list are not limited to recommended stores, visited stores, and preferred stores, and may include additional items directly set by the user.

[0083] Specifically, the store recommendation device (100) may receive additional storage inputs regarding the item name of an item desired by the user and the store included in the item from the user terminal (200), and generate additional store lists for additional item stores based on the received item name and additional storage inputs regarding the store, and display them on a user-customized store map.

[0084] For example, when a user wants to create and display a list of stores for 'dessert restaurants', the store recommendation device (100) receives an item name 'dessert restaurants' and additional storage inputs for specific stores selected by the user from the user terminal (200), and can create a list of stores for the 'dessert restaurants' item that includes the stores for which additional storage inputs were received. Additionally, the store recommendation device (100) can provide the user with an item selection icon for the newly created 'dessert restaurants' item by placing it alongside item selection icons for each item for recommended stores, visited stores, and preferred stores, and outputting this to the user terminal (200), thereby allowing the user to easily select the desired item and display it on a user-customized store map.

[0085] Additionally, the store recommendation device (100) may set display forms that include at least one of color, shape, and size differently for multiple stores included in a store list based on importance. At this time, the importance may be set according to different criteria for each item in the store list.

[0086] For example, when the displayed item is a recommended store, the store recommendation device (100) may set the importance based on popularity or recommendation order, and when the displayed item is a visited store, the store recommendation device (100) may set the importance based on the number of visits by the user, and when the displayed item is a preferred store or an additional item store created separately, the store recommendation device (100) may determine the importance based on preferences set by the user, etc. However, it is not limited thereto, and the store recommendation device (100) may provide various criteria to the user terminal (200), such as popularity order, high acidity, low acidity, low price order, many reviews order, distance order, recommendation order, etc., and determine the importance of stores within each item based on different or the same criteria for each item according to the user settings for the provided criteria.

[0087] Additionally, the store recommendation device (100) can display a list of stores for multiple items together on a user-customized store map. In this case, by displaying the multiple stores included in the store list in different ways according to each item, the user can be provided with the ability to easily check which item the store belongs to. For example, the store recommendation device (100) may display recommended stores as white location points, visited stores as green circles, and preferred stores as yellow stars, but is not limited thereto.

[0088] Additionally, referring to FIG. 4(a), the store recommendation device (100) can generate a metaverse-based virtual object movable on a user-customized store map based on user information received by a user terminal (200). At this time, the user information may include the user's age, gender, occupation, primary purpose of use of the store, etc., and may further include preferred congestion level, preferred mood information, and condition information included in the preferred store information.

[0089] According to one embodiment of the present invention, the appearance of a virtual object may be set based on the user's store consumption pattern and user settings. The store recommendation device (100) may analyze the user's store consumption pattern by considering the user's store visit history, preferred store information, and the item name of an additional item created to be displayed on a user-customized store map, and set the appearance of a virtual object corresponding to the user based on the analyzed store consumption pattern.

[0090] Additionally, the store recommendation device (100) may set the basic appearance of a virtual object based on the analyzed user's store consumption pattern, but may also modify the appearance of the virtual object from the basic appearance by further considering user settings. Specifically, user settings may refer to settings regarding the selection of information to be reflected in the appearance of the virtual object among user information, such as the user's age, gender, occupation, primary purpose of use of the store, preferred level of congestion, preferred mood information, and condition information. For example, if the user sets the appearance of the virtual object to reflect only gender, primary purpose of use of the store, and preferred mood information, the store recommendation device (100) may change the appearance of the virtual object by reflecting the user's gender, primary purpose of use of the store, and preferred mood information in the basic appearance of the virtual object according to the user's store consumption pattern. However, it is not limited thereto.

[0091] Referring to FIG. 5 (b) and (c), when the store recommendation device (100) receives a selection input for one of the stores included in the list of stores displayed on the user-customized store map from the user terminal (200), it may output an interface displaying store information and review information for the selected store to the user terminal (200) and provide it to the user. At this time, the store information may include the store name, the representative mood of the store, information on recently measured congestion or noise level, and location information, and the representative mood of the store may be received through the store terminal (400) or may be analyzed and set by the store recommendation device (100) based on review information, but is not limited thereto.

[0092] As described above, the store recommendation device (100) can facilitate the verification and management of a store list for each user by providing a metaverse-based user-customized store map that includes a list of stores such as recommended stores, visited stores, and preferred stores.

[0093] Additionally, referring to FIG. 4, the store recommendation device (100) may further provide a search function for providing information about a specific store, and when it receives the store name of a specific store from a user terminal (200) as search data, it may display the location of the store on a user-customized store map and output store information and review information about the store to provide to the user terminal (200).

[0094] FIG. 5 is a diagram illustrating an exemplary community selection interface in which user input regarding mood information and condition information for selecting a desired community is authorized, and a user information display interface that displays user-specific usage history.

[0095] According to one embodiment of the present invention, a store recommendation device (100) may provide a community that displays at least one of a plurality of stores included in a store list on a user-customized store map to share with other users, and provides a communication function between a plurality of user terminals (200) regarding the shared store map.

[0096] The store recommendation device (100) receives a selection input from a user terminal (200) regarding at least one store that the user wishes to display and share on a user-customized store map, and can display the selected at least one store on the user-customized store map. Additionally, the store recommendation device (100) further receives an input from the user terminal (200) regarding whether to share the user-customized store map in which at least one store is displayed, and if it receives an input regarding sharing, it can upload the user-customized store map in which at least one store is displayed to a community accessible to multiple user terminals (200).

[0097] Additionally, referring to FIG. 5(a), the store recommendation device (100) can provide a search function to the community and receive mood information and condition information regarding a shared store map from a user terminal (200). Based on the received mood information and condition information, the store recommendation device (100) can search for at least one shared map among a plurality of shared maps shared in the community by other users and provide it to the user terminal (200).

[0098] Additionally, referring to FIG. 5(b), the store recommendation device (100) may receive a selection input from the user terminal (200) regarding one of the other users who have shared at least one shared map provided to the user terminal (200), and may provide some user information regarding the selected other user to the user terminal (200).

[0099] The store recommendation device (100) may be provided to enable a user to determine the level of trust in a shared map created by another user through user information about another user. However, the user information about another user may include only at least some of the information about the user according to the information disclosure settings for each other user, but is not limited thereto.

[0100] According to one embodiment of the present invention, the store recommendation device (100) may further provide a 'My Page' interface to the user terminal (200) so that the user can check their preferred store information and record information. The 'My Page' interface may be provided in a layout similar to (b) of FIG. 5, which provides user information of other users as described above, but may include all information about the user of the user terminal (200), unlike the user information of other users. At this time, the record information may include the store visited by the user, review information about reviews written by the user, etc., but is not limited thereto.

[0101] According to one embodiment of the present invention, a store recommendation device (100) can award points to a user terminal (200) that performs at least one of writing a review of a store, measuring sound data at a store, and sharing a cafe map created directly.

[0102] In this regard, the store recommendation device (100) can induce users to write reviews of stores and measure sound data in stores by awarding points, and can improve the accuracy of generating noise levels and calculating congestion levels by store by increasing the amount of information in review information and sound data. Additionally, the store recommendation device (100) can induce users to share cafe maps they have created themselves by awarding points, thereby activating the community and helping users to more easily obtain information about the cafes they want.

[0103] In addition, the store recommendation device (100) can provide events and discount benefits that can be participated in using the provided points.

[0104] FIG. 6 is a diagram illustrating an event information display interface that provides event information and an order information display interface that provides order information and allows user input for order information.

[0105] Referring to FIG. 6(a), the store recommendation device (100) can provide event information for a plurality of stores linked to the store recommendation device (100). The event information may include information about events, discount promotions, etc., that are being conducted independently by each of the plurality of stores, and may include information about events, discount promotions, etc., that can be participated in using provided points.

[0106] For example, the store recommendation device (100) can provide a payment function using points when ordering and paying for a menu at the store, and can provide events such as a random coupon draw that can be participated in using points, and a show-off of a store map that has been set up by the user. In addition, the store recommendation device (100) can provide benefits such as coupons and gifts through the event.

[0107] In this regard, as illustrated in FIG. 6 (b) and (c), the store recommendation device (100) may further provide order and payment functions for a plurality of stores associated with the store recommendation device (100) to the user terminal (200). The store recommendation device (100) receives selection input for at least one store and at least one menu from the user terminal (200), and transmits a payment request for the selected store and selected menu to the user terminal (200), and when the user performs payment for the menu, it may provide the ability to proceed with payment using points provided or coupons provided through an event participated in using points.

[0108] FIG. 7 is a schematic block diagram of a congestion-based store recommendation device according to one embodiment of the present invention.

[0109] Referring to FIG. 7, the store recommendation device (100) may include a receiving unit (110), a congestion calculation unit (120), a recommended store selection unit (130), a map generation unit (140), a transmitting unit (150), and a community providing unit (160).

[0110] According to one embodiment of the present invention, a receiving unit (110) may receive preferred store information including a preferred congestion level from a user terminal (200). At this time, the preferred store information may further include preferred mood information and condition information.

[0111] In addition, the receiving unit (110) can receive order information from the store terminal (400).

[0112] Additionally, the receiving unit (110) may receive sound data measured at the store currently being used by each of the multiple customers among the multiple stores from each of the multiple customer terminals (300) of the multiple customers using the multiple stores.

[0113] According to one embodiment of the present invention, the congestion level calculation unit (120) may generate noise level information for each store based on acoustic data and calculate the congestion level for each store based on the noise level information for each store. Additionally, the congestion level calculation unit (120) may calculate the congestion level for each store by further considering order information.

[0114] According to one embodiment of the present invention, the recommended store selection unit (130) may select at least one recommended store that satisfies the preferred congestion level based on the congestion level of each store. Additionally, the recommended store selection unit (130) may select at least one recommended store by further considering preferred mood information and condition information.

[0115] According to one embodiment of the present invention, the map generation unit (140) can generate a user-customized store map that displays a list of stores for at least one of at least one recommended store, a visited store where a user corresponding to the user terminal (200) has a visit history, and a preferred store already stored in the user terminal (200).

[0116] At this time, the user-customized store map may be generated in the form of a metaverse-based map that is virtually simulated based on the actual environmental information of each store included in the store list, and the map generation unit (140) may generate a metaverse-based virtual object that is movable on the user-customized store map based on user information received by the user terminal (200).

[0117] Additionally, the map generation unit (140) may set different display forms for multiple stores included in the store list, each store including at least one of color, shape, and size based on importance.

[0118] According to one embodiment of the present invention, the transmitting unit (150) may transmit information about at least one selected recommended store to a user terminal (200). Additionally, the transmitting unit (150) may output a user-customized store map generated by the map generating unit (140) through the user terminal (200).

[0119] According to one embodiment of the present invention, the community providing unit (160) may provide a community that displays at least one of a plurality of stores included in a store list on a user-customized store map to share with other users, and provides a communication function between a plurality of user terminals (200) regarding the shared store map.

[0120] Below, based on the details described above, we will briefly examine the operation flow of the present invention.

[0121] FIG. 8 is a flowchart of an operation for a store recommendation method based on congestion according to one embodiment of the present invention.

[0122] The congestion-based store recommendation method illustrated in FIG. 8 can be performed by the congestion-based store recommendation device (100) described above. Therefore, even if the content described below is omitted, the description of the congestion-based store recommendation device (100) can be equally applied to the description of the congestion-based store recommendation method.

[0123] Referring to FIG. 6, in step S11, the receiver (110) may receive preferred store information including a preferred congestion level from the user terminal (200). At this time, the preferred store information may further include preferred mood information and condition information. Additionally, in step S11, the receiver (110) may further receive order information from the store terminal (400).

[0124] Next, in step S12, the receiving unit (110) may receive sound data measured at the store currently being used by each of the multiple customers among the multiple stores from each of the multiple customer terminals (300) of the multiple customers using the multiple stores.

[0125] Next, in step S13, the congestion calculation unit (120) may generate noise level information for each store based on acoustic data and calculate the congestion level for each store based on the noise level information for each store. Additionally, in step S13, the congestion calculation unit (120) may calculate the congestion level for each store by further considering order information.

[0126] Next, in step S14, the recommended store selection unit (130) may select at least one recommended store that satisfies the preferred congestion level based on the congestion level of each store. Additionally, in step S14, the recommended store selection unit (130) may select at least one recommended store by further considering the preferred mood information and condition information.

[0127] Next, in step S15, the map generation unit (140) can generate a user-customized store map that displays a list of stores for at least one of at least one recommended store, a visited store where the user’s visit history corresponding to the user terminal (200) exists, and a preferred store already stored in the user terminal (200).

[0128] At this time, the user-customized store map may be generated in the form of a metaverse-based map that is virtually simulated based on the actual environmental information of each store included in the store list, and in step S15, the map generation unit (140) may generate a metaverse-based virtual object that is movable on the user-customized store map based on user information received by the user terminal (200).

[0129] Additionally, in step S15, the map generation unit (140) may set different display forms for multiple stores included in the store list, each store including at least one of color, shape, and size based on importance.

[0130] Next, in step S16, the transmitting unit (150) may transmit information about at least one selected recommended store to the user terminal (200). Additionally, in step S16, the transmitting unit (150) may output a user-customized store map generated by the map generating unit (140) through the user terminal (200).

[0131] Next, in step S17, the community providing unit (160) can provide a community that displays at least one of the multiple stores included in the store list on a user-customized store map to share with other users, and provides a communication function between multiple user terminals (200) regarding the shared store map.

[0132] In the description above, steps S11 through S17 may be further divided into additional steps or combined into fewer steps according to an embodiment of the present invention. Additionally, some steps may be omitted as necessary, and the order of the steps may be changed.

[0133] A store recommendation method based on congestion according to one embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa.

[0134] In addition, the aforementioned store recommendation method based on congestion can also be implemented in the form of a computer program or application executed by a computer and stored on a recording medium.

[0135] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical concept or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0136] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and the concept of equivalents thereof should be interpreted as being included within the scope of the present invention. Explanation of the symbols

[0137] 10: Congestion-based store recommendation system 100: Congestion-based store recommendation device 110: Receiver 120: Congestion Calculation Unit 130: Recommended Store Selection Department 140: Map Generation Section 150: Transmitter 160: Community Providers

Claims

Claim 1 A store recommendation method based on congestion performed by a congestion-based store recommendation device, comprising: receiving preferred store information including preferred congestion from a user terminal; receiving acoustic data measured at a store currently used by each of the plurality of users among the plurality of stores from each of the user terminals of the plurality of users using the plurality of stores; generating store-specific noise level information based on the acoustic data and calculating store-specific congestion based on the store-specific noise level information; selecting at least one recommended store that satisfies the preferred congestion based on the store-specific congestion; and transmitting information about the at least one recommended store to the user terminal, wherein the step of receiving the acoustic data involves determining whether each of the plurality of users is actually in a state of visiting the store based on the location information of each of the user terminals, and allowing the measurement of the acoustic data for each of the user terminals, and continuing the measurement of the acoustic data until a non-conversational section greater than or equal to the minimum section required for generating store-specific noise level information is included in the acoustic data. Claim 2 A store recommendation method according to claim 1, further comprising the step of receiving order information from a store terminal, wherein the step of calculating the congestion level calculates the congestion level for each store by further considering the order information. Claim 3 delete Claim 4 A store recommendation method according to claim 1, wherein the preferred store information further includes preferred mood information and condition information, and the step of selecting at least one recommended store further considers the preferred mood information and the condition information to select the at least one recommended store. Claim 5 A store recommendation method according to claim 1, further comprising the step of generating a user-customized store map that displays a list of at least one of the following: at least one recommended store, a visited store where a user corresponding to the user terminal has a visit history, and a preferred store already stored in the user terminal, wherein the step of transmitting to the user terminal is to output the user-customized store map through the user terminal. Claim 6 In claim 5, the user-customized store map is generated in the form of a metaverse-based map that is virtually simulated based on actual environmental information of each store included in the store list, and the step of generating the user-customized store map includes the step of generating a metaverse-based virtual object movable on the user-customized store map based on user information received by the user terminal, a store recommendation method. Claim 7 In claim 5, the step of generating the user-customized store map is to set different display forms, including at least one of color, shape, and size, for a plurality of stores included in the store list based on importance. Claim 8 A store recommendation method according to claim 5, further comprising the step of displaying at least one of the multiple stores included in the store list on the user-customized store map to share with other users, and providing a community that provides a communication function between multiple user terminals regarding the shared store map. Claim 9 A store recommendation device based on congestion, comprising: a receiving unit that receives preferred store information including preferred congestion from a user terminal and receives acoustic data measured at a store currently used by each of the multiple users among the multiple stores from each of the multiple users' terminals of the multiple users using the multiple stores; a congestion calculation unit that generates store-specific noise level information based on the acoustic data and calculates store-specific congestion based on the store-specific noise level information; a recommended store selection unit that selects at least one recommended store satisfying the preferred congestion based on the store-specific congestion; and a transmitting unit that transmits information about the at least one recommended store to the user terminal, wherein the receiving unit determines whether each of the multiple users is actually in a state of visiting the store based on the location information of each of the user terminals and allows the measurement of the acoustic data for each of the user terminals, and continues the measurement of the acoustic data until a non-conversational section greater than or equal to the minimum section required for generating store-specific noise level information is included in the acoustic data. Claim 10 A store recommendation device according to claim 9, wherein the receiving unit receives order information from a store terminal, and the congestion level calculation unit calculates the congestion level for each store by further considering the order information. Claim 11 delete Claim 12 A store recommendation device according to claim 9, wherein the preferred store information further includes preferred mood information and condition information, and the recommended store selection unit further considers the preferred mood information and the condition information to select at least one recommended store. Claim 13 A store recommendation device according to claim 9, further comprising a map generating unit that generates a user-customized store map for at least one of the following: at least one recommended store, a visited store where a user’s visit history corresponding to the user terminal exists, and a preferred store already stored in the user terminal, wherein the transmitting unit outputs the user-customized store map through the user terminal. Claim 14 In claim 13, the user-customized store map is generated in the form of a metaverse-based map that is virtually simulated based on actual environmental information of each store included in the store list, and the map generation unit generates a metaverse-based virtual object movable on the user-customized store map based on user information received by the user terminal, a store recommendation device. Claim 15 In paragraph 13, the map generating unit sets different display forms including at least one of color, shape, and size according to the plurality of stores based on importance for the plurality of stores included in the store list. Claim 16 A store recommendation device according to claim 13, further comprising a community providing unit that displays at least one of a plurality of stores included in the store list on the user-customized store map to share with other users, and provides a community that provides a communication function between a plurality of user terminals regarding the shared store map.

Images