System and method for recommending galleries based on user similarity in a virtual exhibition environment

Abstract

The present invention relates to a technology for recommending galleries based on similar usage patterns in a virtual exhibition environment. A method for recommending galleries based on user similarity in a virtual exhibition environment according to one embodiment may include the steps of: matching a user with points for each gallery used by the user and recording and maintaining them in a database; analyzing the user's gallery usage pattern to calculate points for each gallery; parsing similar users from the database who have gallery points similar to the points for each gallery calculated according to the analyzed gallery usage pattern and points for each gallery that are similar to a reference value or higher; extracting gallery points for the parsed similar users from the database; calculating an expected favorability for each gallery using the extracted gallery points; and recommending galleries based on the calculated expected favorability.

Description

Technology Field

[0001] The present invention relates to a technology for recommending galleries based on similar usage patterns in a virtual exhibition environment, and more specifically, to a technology that provides a method for efficiently operating the entire exhibition service by exposing the exhibition hall that the user is most likely to be interested in when exposing a list of exhibition halls in a virtual exhibition service to the user. Background Technology

[0002] A virtual exhibition environment is a space that provides an experience similar to exhibiting exhibits or artworks in the real world, in a virtual or digital environment. This can be implemented using various platforms such as virtual reality (VR), augmented reality (AR), and web-based 3D environments.

[0003] Virtual exhibition environments generally model a 3D space to allow users to freely explore exhibits.

[0004] Users can click on or interact with exhibits in the virtual environment, obtain additional information, or zoom in on exhibits to view them in detail.

[0005] Various forms of exhibits, such as paintings, photographs, sculptures, and videos, can be provided in a virtual environment.

[0006] Anyone can visit the virtual exhibition and view the exhibits via the Internet, regardless of their physical location.

[0007] It is possible to provide a customized experience by recommending virtual exhibits or offering navigation paths based on the user's interests or specific topics.

[0008] Such virtual exhibition environments can be utilized in various fields, such as education, cultural experiences, and art appreciation.

[0009] Multiple users can simultaneously explore or share virtual exhibitions, view exhibits and share opinions as a group, and freely adjust lighting, textures, and effects within the virtual exhibition environment to create more vivid visual effects. Prior art literature

[0010] Korean Published Patent No. 2023-0077940 "Metaverse Gallery Platform Service" Korean Registered Patent No. 2585298 "System for Providing a Gallery Platform Based on Virtual Reality (VR) Technology" Korean Registered Patent No. 1931807 "Big Data Analysis-Based Art Exhibition / Artwork Recommendation App Service System" The problem to be solved

[0011] The present invention aims to enable the entire exhibition service to be operated efficiently by displaying the exhibition hall that the user is most likely to be interested in when displaying the list of exhibition halls in a virtual exhibition service. means of solving the problem

[0012] A gallery recommendation method based on user similarity in a virtual exhibition hall according to one embodiment may include the steps of: matching a user with gallery-specific points used by the user and recording and maintaining them in a database; analyzing the user's gallery usage pattern to calculate gallery-specific points; parsing similar users from the database who have gallery-specific points similar to the gallery-specific points calculated according to the analyzed gallery usage pattern and points similar to a reference value or higher; extracting gallery-specific points for the parsed similar users from the database; calculating an expected favorability for each gallery using the extracted gallery-specific points; and recommending a gallery based on the calculated expected favorability.

[0013] A gallery recommendation method based on user similarity in a virtual exhibition hall according to one embodiment may further include the steps of analyzing a user's gallery usage pattern, calculating gallery-specific points for each user based on the analyzed usage pattern, and matching the user with the calculated gallery-specific points and recording them in the database.

[0014] The step of calculating gallery-specific points for each user based on the analyzed usage pattern according to one embodiment may include the step of selecting at least one factor that determines the gallery-specific points of the user, and the step of converting the selected at least one factor into a numerical value by reflecting a weight.

[0015] The step of converting the selected at least one factor into a numerical value reflecting a prior assigned importance according to one embodiment may include the step of converting the selected at least one factor into a numerical value between 0 and 1 reflecting the prior assigned importance.

[0016] The step of selecting at least one factor determining a user's points per gallery according to one embodiment may include selecting at least one factor from among the time spent visiting the gallery, time spent viewing individual works, distance traveled within the map, number of works viewed, total number of works, number of works liked, number of revisits, and number of works using the zoom function.

[0017] The step of converting the selected at least one factor into a numerical value by reflecting weights according to one embodiment may include the step of reflecting weights differentially based on importance assigned in advance for each of the selected at least one factor.

[0018] The step of converting at least one selected factor into a numerical value by reflecting weights according to one embodiment may include the step of additionally applying excess weights to the simple sum of weights assigned to each factor when at least two factors defined as a pair in advance are selected.

[0019] In the database according to one embodiment, the step of parsing similar users having gallery-specific points similar to the analyzed gallery-specific points and a reference value or higher is:

[0020] The method may include the step of identifying a group formed by a clustering method in an n-dimensional space based on factors based on the user's gallery usage, and the step of selecting at least one similar user among the users in the group whose distance in the n-dimensional space is within a standard.

[0021] The step of selecting at least one similar user among the users in the group according to one embodiment, whose distance in an n-dimensional space is within a standard range, may include the step of calculating the distance between the user and the similar user in the n-dimensional space, the step of normalizing the calculated distance, and the step of selecting the similar user based on the normalized distance.

[0022] A system for recommending galleries in a virtual exhibition hall according to one embodiment may include a database that records a user and the user's gallery-specific points by matching them; a usage pattern analysis unit that calculates gallery-specific points by analyzing the user's gallery usage pattern; a similar user parsing unit that parses similar users from the database who have gallery-specific points similar to the gallery-specific points calculated from the analyzed gallery usage pattern and points equal to or greater than a reference value; a usage pattern extraction unit that extracts gallery-specific points for the parsed similar users from the database; an expected favorability calculation unit that calculates an expected favorability for each gallery using the extracted gallery-specific points; and a gallery recommendation processing unit that recommends galleries based on the calculated expected favorability.

[0023] The usage pattern extraction unit according to one embodiment can select at least one factor that determines the points per gallery of the user, and convert the selected at least one factor into a numerical value by reflecting a weight.

[0024] The usage pattern extraction unit according to one embodiment can convert at least one selected factor into a value between 0 and 1 by reflecting the importance assigned in advance.

[0025] The usage pattern extraction unit according to one embodiment can select at least one factor from among the time spent visiting the gallery, time spent viewing individual works, distance traveled within the map, number of works viewed, total number of works, number of works liked, number of revisits, and number of works using the zoom function in order to select at least one factor.

[0026] The usage pattern extraction unit according to one embodiment may reflect weights differentially based on prior importance for each of the selected at least one factor in order to convert the selected at least one factor into a numerical value by reflecting weights for the selected at least one factor.

[0027] In order to convert the selected at least one factor into a numerical value by reflecting weights for the selected at least one factor, when at least two factors defined as a pair in advance are selected, an excess weight may be additionally applied to the simple sum of the weights assigned to each factor.

[0028] The similar user parsing unit according to one embodiment identifies a group formed by a clustering method in an n-dimensional space based on factors based on the user's gallery usage, and can select at least one similar user among the users in the group whose distance in the n-dimensional space is within a reference range.

[0029] The similar user parsing unit according to one embodiment calculates the distance between a user and a similar user in an n-dimensional space and normalizes the calculated distance, and selects similar users based on the normalized distance, in order to select at least one similar user among the users in the group whose distance in an n-dimensional space is close within a standard. Effects of the invention

[0030] According to one embodiment, when displaying a list of exhibition halls to a user in a virtual exhibition service, the exhibition hall that the user is most likely to be interested in is displayed so that the entire exhibition service can be operated efficiently. Brief explanation of the drawing

[0031] Figure 1 is a diagram illustrating a system that recommends a gallery based on user similarity in a virtual exhibition environment. FIG. 2 is a drawing illustrating a virtual exhibition environment according to one embodiment. Figure 3a is a diagram illustrating usage pattern information compared to user information recorded in a database. Figure 3b is a diagram illustrating the expected favorability of a gallery by users similar to a specific user and similar users, and similar users. FIGS. 4 to 6 are drawings illustrating various embodiments of recommending a gallery based on calculated expected favorability. Figure 7 is a diagram illustrating a method for recommending a gallery based on user similarity in a virtual exhibition environment. Figure 8 is a diagram illustrating a method for selecting similar users based on normalized distance. Specific details for implementing the invention

[0032] Specific structural or functional descriptions of embodiments according to the concept of the present invention disclosed herein are provided merely for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described herein.

[0033] Embodiments according to the concept of the present invention may be subject to various modifications and may take various forms; therefore, embodiments are illustrated in the drawings and described in detail in this specification. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and includes modifications, equivalents, or substitutions that fall within the spirit and scope of the present invention.

[0034] Terms such as "first" or "second" may be used to describe various components, but said components should not be limited by said terms. For the sole purpose of distinguishing one component from another, for example, without departing from the scope of rights according to the concept of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component.

[0035] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. Conversely, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Expressions describing the relationships between components, such as "between," "exactly between," or "directly adjacent to," should be interpreted in the same way.

[0036] The terms used herein are used merely to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as “comprising” or “having” are intended to specify the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0037] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0039] Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, the scope of the patent application is not limited or restricted by these embodiments. Identical reference numerals in each drawing indicate identical components.

[0040] FIG. 1 is a drawing illustrating a system (100) that recommends a gallery based on user similarity in a virtual exhibition environment.

[0041] A gallery recommendation system (100) according to one embodiment can recommend a gallery to a user based on the user's similarity in a virtual exhibition environment.

[0042] In other words, especially when displaying a list of exhibition halls to users in a virtual exhibition service, the exhibition halls that users are most likely to be interested in are displayed so that the entire exhibition service can be operated efficiently.

[0043] To this end, a gallery recommendation system (100) according to one embodiment may include a database (110), a usage pattern analysis unit (120), a similar user parsing unit (130), a usage pattern extraction unit (140), an expected favorability calculation unit (150), a gallery recommendation processing unit (160), and a control unit (170).

[0044] First, the database (110) can record the points of the user and the user's gallery by matching them.

[0045] Specifically, the database (110) may be composed of tables for storing user information, gallery information, and point records, and each table may be defined with fields and corresponding data types.

[0046] The user information table may include user ID, name, email address, password, etc., and the user ID is automatically generated as a unique identifier and can be recorded so that duplicate values ​​are not allowed.

[0047] The gallery information table may include a gallery ID, owner ID, gallery name, gallery description, etc. for the virtual exhibition, and each gallery can be uniquely identified through the gallery ID.

[0048] Point matching can refer to the process of defining the relationship between a user and a gallery and allocating points accordingly.

[0049] In addition, points per gallery can be interpreted as a value calculated based on the user's usage patterns within that gallery.

[0050] For example, frequently visited galleries may have higher points per gallery compared to galleries that are not frequently visited.

[0051] As another example, activities such as adding new content or leaving comments in the gallery can cause point fluctuations.

[0052] In other words, points can fluctuate depending on user activity, and the user's gallery usage patterns can be reflected in the points per gallery, which are calculated as scalar or vector values.

[0053] The database (110) can record the gallery owner ID and the ID of the gallery by matching them, and

[0054] The database (110) can efficiently search and retrieve the point records of users and galleries.

[0055] In particular, you can view the point history of a specific user or the owner information of a specific gallery.

[0056] The database (110) according to the present invention can manage access rights to ensure the safety of information. In particular, it can restrict access to sensitive information and prevent unauthorized access to data through user authentication and authorization.

[0057] The usage pattern analysis unit (120) can analyze the user's gallery usage pattern and calculate points per gallery.

[0058] The usage pattern analysis unit (120) can collect data to record the user's activities in the virtual exhibition hall.

[0059] An activity can correspond to at least one factor.

[0060] For example, at least one factor may include at least one of the following: time spent visiting the gallery, time spent viewing individual works, distance traveled within the map, number of works viewed, total number of works, number of works liked, number of revisits, and number of works using the zoom function.

[0061] The usage pattern analysis unit (120) can select at least one factor that determines the user's gallery points in order to calculate gallery points for each user based on the analyzed usage pattern. Additionally, the usage pattern analysis unit (120) can convert the selected at least one factor into a numerical value by reflecting a weight.

[0062] In this process, the usage pattern analysis unit (120) can convert at least one selected factor into a value between 0 and 1 by reflecting the importance assigned in advance.

[0063] The usage pattern analysis unit (120) can calculate points per gallery by selecting at least one factor from among the time spent visiting the gallery, time spent viewing individual artworks, distance traveled within the map, number of artworks viewed, total number of artworks, number of artworks liked, number of revisits, and number of artworks that used the zoom function.

[0064] The usage pattern analysis unit (120) can reflect weights for each of the selected at least one factor and convert them into numerical values ​​based on the importance assigned in advance in order to reflect weights for at least one selected factor.

[0065] For example, a higher weight may be given to the time spent revisiting the gallery compared to the time spent visiting the gallery after a visit, and a higher weight may be given to the distance traveled near the artwork rather than the distance traveled within the map.

[0066] The usage pattern analysis unit (120) converts at least one selected factor into a numerical value by reflecting weights, and when at least two factors defined as a pair in advance are selected, it may additionally apply excess weights to the simple sum of the weights assigned to each factor.

[0067] For example, if 'revisit time' and 'number of liked works' are pre-set as a pair, an additional excess weight can be applied to the number of liked works on the revisit compared to the number of liked works on the first visit.

[0068] The similar user parsing unit (130) can parse similar users in the database (110) who have gallery-specific points similar to the gallery-specific points calculated from the analyzed gallery usage pattern and points similar to the reference value.

[0069] The similar user parsing unit (130) must be able to retrieve necessary information by linking with the database (110). The similar user parsing unit (130) can parse similar users based on the gallery usage pattern analysis results received from the database (110).

[0070] The similar user parsing unit (130) can identify users who have points similar to or greater than a reference value by comparing points per gallery.

[0071] For example, the similar user parsing unit (130) can identify users whose gallery points are above a threshold as similar users.

[0072] Additionally, the similar user parsing unit (130) may identify users who have gallery points within a certain range as similar users, and may also identify users whose gallery points are below a threshold as similar users.

[0073] For example, the similar user parsing unit (130) can parse similar users in the database (110) who have gallery points similar to the analyzed gallery points and a reference value.

[0074] To this end, the similar user parsing unit (130) identifies a group formed by a clustering method in an n-dimensional space based on factors based on the user's gallery usage, and can select at least one similar user among the users in the group whose distance in the n-dimensional space is within a standard.

[0075] Additionally, the similar user parsing unit (130) can select at least one similar user among the users in the group whose distance in n-dimensional space is within a standard, calculate the distance between the user and the similar user in n-dimensional space using [Equation 1], and normalize the calculated distance using [Equation 2]. Additionally, the similar user parsing unit (130) can select similar users based on the normalized distance.

[0077] [Mathematical Formula 1]

[0078]

[0079] In [Mathematical Formula 1], the dimension number n f = is the number of factors, and how similar a similar user is to a user who wants to receive a recommendation is determined by the distance (D) in n-dimensional space.

[0081] [Mathematical Formula 2]

[0082]

[0084] f in [Mathematical Equation 2] D represents the normalization reference value (arbitrary setting), and f such that the maximum value of the normalization distance becomes 1. D You must set it.

[0085] Importance (u N ) = can be calculated as similarity or log similarity, and among these, log similarity is 1 / DN, which can be interpreted as having higher importance as the distance is closer.

[0086] According to one embodiment, users with a similarity level greater than a certain standard can be sorted in order of importance, and users with high importance can be considered as similar users.

[0087] The usage pattern extraction unit (140) can extract gallery-specific points for parsed similar users from the database (110).

[0089] According to one embodiment, the usage pattern extraction unit (140) can extract points per gallery by using at least one of [Equation 3] or [Equation 4] below.

[0090] Specifically, the individual points (P) of a user per gallery can be calculated through [Equation 3], and the points (G) of the i-th user per gallery can be calculated through [Equation 4].

[0091] For reference, the i-th user can be interpreted as the user who is the party receiving the similarity recommendation.

[0093] [Mathematical Formula 3]

[0094]

[0095] In [Equation 3], g is the gallery, i is the customer, and w n is the nth weight (weight value is set arbitrarily), f n corresponds to the nth factor.

[0097] [Mathematical Formula 4]

[0098]

[0100] In [Equation 4], i is the customer, u n represents the similarity of the nth similar user.

[0101] User i's expected favorability toward Gallery n (G n , i) can be calculated using the weighted average of the similarity points of gallery usage points of similar users.

[0102] If a similar user has never used nGallery, that user can be excluded.

[0103] Also, expected favorability (G n You can create a recommended gallery list by sorting in descending order of , i).

[0104] By using the points extracted per gallery in this way, it is possible to predict which galleries users will be attracted to.

[0105] For example, a gallery that users identified as similar users have a lot of interest in is more likely to be of interest to the user as well.

[0106] To this end, the expected favorability calculation unit (150) can calculate the expected favorability for each gallery using the extracted gallery-specific points.

[0107] The gallery recommendation processing unit (160) can recommend a gallery based on the calculated expected favorability.

[0108] The control unit (170) can be interpreted as a Central Processing Unit (CPU) and can perform various operations and process data within the system.

[0109] In particular, the control unit (170) can read instructions from memory and interpret and execute the instructions, and can also perform arithmetic operations such as addition, subtraction, multiplication, and division.

[0110] Additionally, the control unit (170) can handle data storage and retrieval, and can also perform the function of reading data from memory and storing the result of performing operations back into memory.

[0111] Additionally, the control unit (170) can manage the execution flow of the program, and in particular, can control the flow of the program using commands such as conditional statements (if-else) or loop statements (for, while). Additionally, the control unit (170) may have a small, fast memory device called a register placed inside, and this register may be used to temporarily store data or perform operations.

[0112] The control unit (170) can handle external events or exception situations and take appropriate measures, and can quickly access data and instructions by using a cache memory that is faster than the main memory.

[0113] In addition, the control unit (170) can use a system bus to communicate with memory or input / output devices and can provide various power management functions to minimize power consumption.

[0114] FIG. 2 is a drawing illustrating a virtual exhibition environment according to one embodiment.

[0115] The virtual exhibition hall (200) may include an exhibition hall that is virtually implemented via the web or mobile and works (210, 220) displayed in the exhibition hall.

[0116] Usage patterns that occur while a user views artworks (210, 220) displayed in a virtual exhibition hall are categorized by gallery and can be quantified as gallery points. Additionally, these quantified gallery points can be matched and stored for each user.

[0117] Users with similar gallery points saved in this way can be grouped into similar user groups.

[0118] FIG. 3a is a diagram illustrating usage pattern information compared to user information recorded in the database (110).

[0119] As shown in reference numeral 310, the database (110) can record user information and usage pattern information corresponding to the user information by matching them with each other.

[0120] Since gallery usage patterns can be quantified, it may be interpreted that each user's information and gallery points have been matched and recorded.

[0121] As shown in reference numeral 310, it can be confirmed that User 1, User 3, User 4, and User 6 have similar gallery usage patterns (gallery usage pattern 1).

[0122] Gallery usage pattern 1 recorded after matching for each user may be the same value for each user, but it may also be a value within the allowable margin of error.

[0123] Figure 3b is a diagram illustrating the expected favorability of a gallery by users similar to a specific user and similar users, and similar users.

[0124] As seen in the table of reference numeral 320, similar users to User 1 are users who have the gallery usage pattern of gallery usage pattern 1.

[0125] That is, since it was confirmed in Fig. 3a that User 1, User 3, User 4, and User 6 have similar gallery usage patterns (Gallery Usage Pattern 1), similar users to User 1 can be determined to be User 3, User 4, and User 6.

[0126] In the table of reference numeral 320, for each of the similar users, User 3, User 4, and User 6, it is possible to check what gallery points they have for each gallery.

[0127] In addition, galleries can be recommended to users based on the gallery points that similar users have for each gallery.

[0128] FIGS. 4 to 6 are drawings illustrating various embodiments of recommending a gallery based on calculated expected favorability.

[0129] Expected favorability can be calculated based on gallery points held by similar users.

[0130] In other words, galleries that similar users are interested in and bookmark, and which have high gallery points, can be recommended to users first.

[0131] FIG. 4 shows an example of sequentially arranging galleries.

[0132] For example, you can list recommended galleries sequentially based on criteria such as time, name, creation date, or remaining time.

[0133] FIG. 5 shows an embodiment in which galleries are listed sequentially and recommended, but specific recommended galleries are displayed with different sizes considering weights.

[0134] In addition, FIG. 6 shows an embodiment in which galleries are listed sequentially and recommended, and specific recommended galleries are displayed with added effects such as color, illumination, brightness, and dimming, taking weights into consideration.

[0135] Figure 7 is a diagram illustrating a method for recommending a gallery based on user similarity in a virtual exhibition environment.

[0136] A gallery recommendation method according to one embodiment can match a user with points for each gallery used by the user and record and maintain them in a database (step 701).

[0137] Next, the gallery recommendation method according to one embodiment analyzes the user's gallery usage pattern to calculate points per gallery (step 702), and in the database, parses similar users who have gallery points similar to the gallery points calculated according to the analyzed gallery usage pattern and a reference value or higher (step 703).

[0138] For example, in order to analyze the usage pattern of a user's gallery in the present invention, points per gallery are calculated for each user based on the analyzed usage pattern, and the user and the calculated points per gallery can be matched and recorded in the database.

[0139] In addition, the gallery recommendation method according to one embodiment can extract gallery-specific points for parsed similar users from a database (step 704), and calculate an expected favorability rating for each gallery using the extracted gallery-specific points (step 705).

[0140] Afterwards, the gallery recommendation method according to one embodiment can recommend a gallery based on the calculated expected favorability (step 706).

[0141] A gallery recommendation method according to one embodiment can calculate gallery-specific points for each user based on analyzed usage patterns and select at least one factor that determines the user's gallery-specific points.

[0142] In addition, the gallery recommendation method according to one embodiment can convert at least one selected factor into a numerical value by reflecting weights.

[0143] A gallery recommendation method according to one embodiment can convert at least one selected factor into a numerical value between 0 and 1 by reflecting the importance assigned in advance to the selected factor.

[0144] In addition, the gallery recommendation method according to one embodiment may select at least one factor from among the time spent visiting a gallery, time spent viewing individual works, distance traveled within a map, number of works viewed, total number of works, number of works liked, number of revisits, and number of works using the zoom function in order to select at least one factor that determines the user's points per gallery.

[0145] A gallery recommendation method according to one embodiment may reflect weights for at least one selected factor and convert them into numerical values, and for each of at least one selected factor, weights may be reflected differentially based on importance assigned in advance.

[0146] In order to convert at least one selected factor into a numerical value by reflecting weights for each selected factor, when at least two factors defined as a pair in advance are selected, an excess weight may be additionally applied to the simple sum of the weights assigned to each factor.

[0147] Figure 8 is a diagram illustrating a method for selecting similar users based on normalized distance.

[0148] In the present invention, in order to select similar users based on normalized distance, groups formed by a clustering method in an n-dimensional space based on factors according to the user's gallery usage can be identified.

[0149] In addition, the distance between a user and similar users in an n-dimensional space can be calculated, and the calculated distance can be normalized. Furthermore, similar users can be selected based on the normalized distance.

[0150] Meanwhile, the gallery recommendation method according to one embodiment can identify groups formed by a clustering method in an n-dimensional space based on factors related to the user's gallery usage in order to parse similar users who have gallery points similar to the analyzed gallery points and a reference value or higher in a database (step 801).

[0151] In addition, the gallery recommendation method according to one embodiment can select at least one similar user among the users in the group whose distance in an n-dimensional space is within a standard.

[0152] To select similar users, a gallery recommendation method according to one embodiment calculates the distance between a user and a similar user in an n-dimensional space (step 802), and can normalize the calculated distance (step 803). Additionally, similar users can be selected based on the normalized distance (step 804).

[0153] Ultimately, by using the present invention, when displaying a list of exhibition halls to a user in a virtual exhibition service, the exhibition hall that the user is most likely to be interested in is displayed, thereby enabling the entire exhibition service to be operated efficiently.

[0155] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0156] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0157] The method according to the embodiment 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 alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, 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 embodiment, and vice versa.

[0158] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0159] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for recommending galleries in a virtual exhibition hall based on user similarity, operated by a gallery recommendation system comprising a database, a usage pattern analysis unit, a similar user parsing unit, a usage pattern extraction unit, an expected favorability calculation unit, and a gallery recommendation processing unit, comprising: a step of matching and recording and maintaining a user and the points for each gallery used by the user in a database; a step of analyzing the user's gallery usage pattern in a usage pattern analysis unit and calculating points for each gallery; a step of parsing similar users in the database who have gallery points similar to the points for each gallery calculated according to the analyzed gallery usage pattern and points for each gallery that are similar to a reference value or higher in a similar user parsing unit; a step of extracting gallery points for the parsed similar users from the database in a usage pattern extraction unit; and a step of calculating an expected favorability for each gallery using the extracted gallery points in an expected favorability calculation unit. A method for recommending galleries based on user similarity in a virtual exhibition hall, comprising: a step of recommending galleries based on the calculated expected favorability in a gallery recommendation processing unit; a step of parsing similar users in a database who have gallery-specific points similar to the analyzed gallery-specific points and gallery-specific points greater than or equal to a reference value, a step of identifying a group formed by a clustering method in an n-dimensional space based on factors according to the user's gallery usage; and a step of selecting at least one similar user among the users in the group whose distance in the n-dimensional space is within a reference. Claim 2 A method for recommending galleries based on user similarity in a virtual exhibition hall, further comprising: a step of analyzing a user’s usage pattern for a gallery; a step of calculating gallery-specific points for each user based on the analyzed usage pattern; and a step of matching the user with the calculated gallery-specific points and recording them in the database. Claim 3 A method for recommending galleries based on user similarity in a virtual exhibition hall, wherein the step of calculating gallery-specific points for each user based on the analyzed usage pattern comprises: a step of selecting at least one factor that determines the user's gallery-specific points; and a step of converting the selected at least one factor into a numerical value by reflecting weights. Claim 4 In paragraph 3, the step of converting at least one selected factor into a numerical value reflecting a prior assigned importance includes the step of converting at least one selected factor into a numerical value between 0 and 1 reflecting the prior assigned importance, in a gallery recommendation method based on user similarity in a virtual exhibition. Claim 5 In paragraph 3, the step of selecting at least one factor determining the user's points per gallery comprises selecting at least one factor from among the time spent visiting the gallery, time spent viewing individual works, distance traveled within the map, number of works viewed, total number of works, number of works liked, number of revisits, and number of works using the zoom function, in a method for recommending galleries based on user similarity in a virtual exhibition. Claim 6 In claim 5, the step of converting at least one selected factor into a numerical value by reflecting a weight includes the step of reflecting a weight differentially based on a pre-assigned importance for each of the at least one selected factor, in a gallery recommendation method based on user similarity in a virtual exhibition. Claim 7 In claim 5, the step of converting at least one selected factor into a numerical value by reflecting weights includes the step of additionally applying excess weights to the simple sum of weights assigned to each factor when at least two factors defined as a pair in advance are selected. A gallery recommendation method based on user similarity in a virtual exhibition hall. Claim 8 delete Claim 9 A method for recommending a gallery based on user similarity in a virtual exhibition hall, wherein, in claim 1, the step of selecting at least one similar user among users within the group whose distance in an n-dimensional space is within a standard includes: a step of calculating the distance between a user and a similar user in an n-dimensional space; a step of normalizing the calculated distance; and a step of selecting a similar user based on the normalized distance. Claim 10 A system for recommending galleries in a virtual exhibition hall comprises: a database that records a user and the user's gallery-specific points by matching them; a usage pattern analysis unit that analyzes the user's gallery usage pattern and calculates gallery-specific points; a similar user parsing unit that parses similar users from the database who have gallery-specific points similar to the gallery-specific points calculated from the analyzed gallery usage pattern and have gallery-specific points equal to or greater than a reference value; a usage pattern extraction unit that extracts gallery-specific points for the parsed similar users from the database; an expected favorability calculation unit that calculates an expected favorability for each gallery using the extracted gallery-specific points; and a gallery recommendation processing unit that recommends galleries based on the calculated expected favorability, wherein the similar user parsing unit identifies a group formed by a clustering method in an n-dimensional space based on factors according to the user's gallery usage, and selects at least one similar user among the users in the group whose distance in the n-dimensional space is within a reference. Claim 11 In claim 10, the above usage pattern extraction unit selects at least one factor determining the user's gallery-specific points and converts the selected at least one factor into a numerical value by reflecting a weight. This is a gallery recommendation system based on user similarity. Claim 12 In claim 11, the above usage pattern extraction unit is a gallery recommendation system based on user similarity that converts at least one selected factor into a value between 0 and 1, reflecting the importance assigned in the above dictionary. Claim 13 A gallery recommendation system based on user similarity according to claim 11, wherein the above-mentioned usage pattern extraction unit selects at least one factor from among the time spent visiting a gallery, time spent viewing individual works, distance traveled within a map, number of works viewed, total number of works, number of works liked, number of revisits, and number of works using the zoom function in order to select at least one factor. Claim 14 A gallery recommendation system based on user similarity according to claim 13, wherein the usage pattern extraction unit is characterized by reflecting weights differentially based on prior importance for each of the selected at least one factor in order to convert them into numerical values ​​by reflecting weights for the selected at least one factor. Claim 15 A gallery recommendation system based on user similarity according to claim 13, wherein the usage pattern extraction unit additionally assigns excess weight to the simple sum of weights assigned to each factor when at least two factors defined in advance as pairs are selected, in order to convert the selected at least one factor into a numerical value by reflecting weights for each selected factor. Claim 16 delete Claim 17 A gallery recommendation system based on user similarity according to claim 10, wherein the similar user parsing unit calculates the distance between a user and a similar user in an n-dimensional space, normalizes the calculated distance, and selects similar users based on the normalized distance in order to select at least one similar user among the users in the group whose distance in an n-dimensional space is within a standard.

Images