KR102144102B1 - Apparatus and method of arranging furniture - Google Patents

Abstract

Disclosed are a method for arranging furniture and an apparatus thereof. The method for generating furniture arrangement based on artificial intelligence comprises the steps of: obtaining structural information on a subject space in which furniture is to be arranged; generating a minimal furniture arrangement allocating diagram, an experimental furniture arrangement allocating diagram, and a classic furniture arrangement allocating diagram of the subject space; referring to databased spatial objects in which the structural information on the databased spatial object satisfies the structural information on the subject space and a first predefined significance degree, among the databased spatial objects; selecting, from the referred spatial objects, the referred spatial objects in which the furniture arrangement minimalism, the furniture arrangement experimentation, and the furniture arrangement classicism of the referred spatial object satisfy the minimal furniture arrangement allocating diagram, the experimental furniture arrangement allocating diagram, the classic furniture arrangement allocating diagram of the subject space and a second predefined significance degree; and outputting each furniture arrangement for the subject space on the basis of each of the selected spatial objects. The furniture arrangement minimalism, the furniture arrangement experimentation, and the furniture arrangement classicism of the databased spatial objects are generated based on the inference of artificial intelligence. According to the present invention, it is possible to provide a method capable of digitizing and expressing an abstract and artistic concept, the furniture arrangement minimalism, the furniture arrangement experimentation, and the furniture arrangement classicism.

Description

Furniture arrangement method and apparatus {APPARATUS AND METHOD OF ARRANGING FURNITURE}

The following examples relate to a technique for finding a furniture arrangement method optimized for a target space.

As a background technology related to the embodiments, Korean Patent Publication No. KR 10-1485738 B1 discloses a method of providing a furniture arrangement service and a method of using a furniture arrangement service. Specifically, the prior literature is (a) receiving a setting for a virtual residential space and a furniture arrangement area in which furniture is arranged in the residential space, (b) selecting the first furniture and the furniture arrangement area Receiving a selection for a specific location in which the first furniture is to be placed, (c) calculating the size of the remaining space existing after placing the first furniture in the furniture placement area, and (d) the calculation Disclosed is a method of providing a furniture placement service comprising the step of recommending a second furniture having a size that can be placed in the remaining space.

Through this, the prior literature recommends other furniture suitable for the remaining space existing after the furniture is arranged, but by using the user's preference information and other users' furniture arrangement information, it is possible to arrange furniture that the user has not thought of.

In addition, Korean Patent Application Publication No. KR 10-2018-0098868 A discloses a furniture selection and furniture arrangement simulation method online. Specifically, prior literature is (A) the server, supplier information input from the furniture supplier, the type of furniture, specifications and external design system; (B) a spatial information storage step of storing, by the server, spatial information including the size of an interior subject to furniture arrangement received from a user terminal, and spatial plan view information of the interior space in a spatial DB; (C) When the server displays the user's spatial plan view on the user terminal and receives a selection signal for a specific furniture through inquiry of the furniture DB from the user terminal, the furniture plan view of the specific furniture is the same as the spatial plan view. A furniture selection step of converting into storage and displaying it on the user terminal; (D) an arrangement step in which the user arranges the furniture plan view on the spatial plan view at the user terminal; And (E) storing the arrangement information in the arrangement DB when the server receives the arrangement completion signal from the user terminal, and discloses an online furniture selection and furniture arrangement simulation method based on virtual reality. .

However, prior literatures do not disclose a method of numerically expressing abstract and artistic concepts such as furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity. In addition, prior literatures do not disclose a method for creating a furniture arrangement plan by considering the concepts of furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity at the stage of planning furniture arrangement in a space. Does not. Furthermore, prior literatures do not disclose a method of seeking whether a space subject to furniture arrangement would be appropriate if it had any minimalist furniture arrangement allocation, experimental furniture arrangement allocation, and classical furniture arrangement allocation.

Accordingly, there is a need for implementation of a technology that can express abstract and artistic concepts such as furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity in numerical form. In addition, in the stage of planning the furniture arrangement, implementation of a technology capable of generating a furniture arrangement plan is required in consideration of the concepts of furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity. Furthermore, there is a need for implementation of a technique to find out whether a space that is the object of furniture arrangement will be appropriate if it has a minimalist furniture arrangement allocation, an experimental furniture arrangement allocation, and a classical furniture arrangement allocation.

Korean patent publication KR 10-1485738 B1 Korean Patent Application Publication KR 10-2018-0098868 A Korean patent publication KR 10-0765379 B1 Korean Patent Application Publication KR 10-2016-0033495 A

The examples are intended to provide a method of numerically expressing abstract and artistic concepts such as furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity.

The embodiments are intended to provide a method for generating a furniture arrangement plan by considering the concepts of furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity at the stage of planning furniture arrangement.

The embodiments are intended to provide a method of setting whether a space to be subjected to furniture arrangement is appropriate if it has a minimalist furniture arrangement allocation, an experimental furniture arrangement allocation, and a classical furniture arrangement allocation diagram.

Further, the embodiments are intended to provide a method and apparatus for arranging furniture for solving the problems mentioned in the background art and the problems of the relevant technical field revealed in the present specification.

According to an embodiment, a method of generating a furniture arrangement based on artificial intelligence includes: obtaining structural information of a subject space in which the furniture is to be arranged; Generating a minimalism furniture layout allocation diagram, an experimental furniture arrangement allocation diagram, and a classical furniture arrangement allocation diagram of the target space; Referring to the databaseized spatial objects, among the databased spatial objects, in which the structure information of the databased spatial object satisfies the structure information of the target space and a predefined first degree of significance; Among the referenced spatial objects, the furniture arrangement minimalism of the referenced space object, the furniture arrangement empiricality, and the furniture arrangement classicity are the furniture minimalism furniture arrangement allocation degree of the target space, experimental. Selecting the referenced spatial objects satisfying a furniture arrangement allocation diagram and a classical furniture arrangement allocation diagram and a second predefined degree of significance; And outputting each furniture arrangement for the target space based on each of the selected spatial objects, wherein furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicalness of the databaseized space objects It may be generated based on the inference of the artificial intelligence.

According to an embodiment, the minimalism of furniture arrangement of the databaseized spatial object is, the power consumption per number of households in the space corresponding to the databased spatial object, a first average-a space corresponding to the databased spatial object The lower the average power consumption per household number of the spaces in the first range defined by from -, the higher it may be.

According to an embodiment, the furniture arrangement experimentation of the databased spatial object includes a mention that the furniture arrangement follows the trend of art after minimalism in reviews collected for the space corresponding to the databased spatial object. As the number of identified reviews increases, the classicalness of the furniture arrangement of the databased spatial object is mentioned in the reviews collected on the space corresponding to the databased spatial object, that the furniture arrangement follows the pre-minimalism art trend. The more reviews that are determined to contain, the greater the number.

According to an embodiment, the generating of the minimalist furniture layout allocation diagram, the experimental furniture arrangement allocation diagram, and the classical furniture arrangement allocation diagram of the target space may include, from power supplied to the target space, power generated by fossil energy. And obtaining a ratio of power generated by the renewable energy. Generating a minimalistic furniture arrangement allocation map of the target space based on a ratio of power generated by fossil energy; Second average-the average of the power consumption per number of households in the second predefined range including the target space-and the third average-the number of households in the third predefined range including the second range Comparing an average of power consumption per unit; If the second average is high, generating an experimental furniture arrangement allocation diagram of the target space based on a ratio of power generated by the renewable energy; If the third average is high, based on a ratio of the power generated by the renewable energy, generating a classical furniture arrangement allocation diagram of the target space.

A furniture arrangement generation apparatus including artificial intelligence according to an embodiment acquires structural information of a subject space in which furniture is to be placed, and a minimalism furniture arrangement allocation diagram of the target space, and an experimental furniture The database in which an arrangement allocation diagram and a classical furniture arrangement allocation diagram are generated, and among databaseized spatial objects, the structural information of the databased spatial object satisfies the structural information of the target space and a predefined first degree of significance Among the referenced spatial objects, furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicalness of the referenced space objects are the furniture of the target space. The referenced spatial objects that satisfies the minimalistic furniture layout allocation diagram, the experimental furniture allocation allocation diagram, and the classical furniture arrangement allocation diagram and a predefined second degree of significance are selected, and based on each selected spatial object, the object It includes a processor that outputs each furniture arrangement for a space, and furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity of the databaseized spatial objects may be generated based on the inference of the artificial intelligence.

The embodiments may provide a method of numerically expressing abstract and artistic concepts such as furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity.

The embodiments may provide a method for generating a furniture arrangement plan by considering the concepts of furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity in the stage of planning furniture arrangement.

The embodiments may provide a method of setting whether a space to be a furniture arrangement is appropriate if it has a minimalist furniture arrangement allocation, an experimental furniture arrangement allocation, and a classical furniture arrangement allocation.

Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other effects that are not mentioned may be clearly understood by those of ordinary skill in the art from the following description.

1 is an exemplary diagram of a configuration of a system according to an embodiment.
2 is a flowchart illustrating an operation of generating a furniture arrangement according to an exemplary embodiment.
3 is a diagram for explaining an operation of generating furniture arrangement minimalism according to an exemplary embodiment.
4 is a diagram for explaining an operation of generating furniture arrangement experimentability and furniture arrangement classical performance according to an exemplary embodiment.
FIG. 5 is a flowchart for explaining an operation of generating a minimalist furniture layout allocation diagram, an experimental furniture arrangement allocation diagram, and a classic furniture arrangement allocation diagram according to an embodiment.
6 is a diagram illustrating learning of an artificial neural network according to an embodiment.
7 is an exemplary diagram of a configuration of an apparatus according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, various changes may be made to the embodiments, and thus the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes to the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed in various forms and implemented. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical idea.

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from other components. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

When a component is referred to as being "connected" to another component, it is to be understood that it may be directly connected or connected to the other component, but other components may exist in the middle.

The terms used in the examples are used for illustrative purposes only and should not be interpreted as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present specification, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof does not preclude in advance.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc., as shown in the figure It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is turned over, a component described as "below" or "beneath" of another component will be placed "above" the other component. I can. Accordingly, the exemplary term “below” may include both directions below and above. Components may be oriented in other directions, and thus spatially relative terms may be interpreted according to orientation.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this application. Does not.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of the reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, if it is determined that a detailed description of related known technologies may unnecessarily obscure the subject matter of the embodiments, the detailed description thereof will be omitted.

1 is an exemplary diagram of a configuration of a system according to an embodiment.

The system according to an embodiment may include a server 100 and a user terminal 110. The server 100 and the user terminal 110 may be connected to a network to exchange data through wired or wireless communication. The system can be used to find furniture arrangements for target spaces (furniture stores, cafes, restaurants, lobbies, galleries, hotels, stores, etc.) for which designers, etc., have requested furniture arrangement consulting from customers, and target spaces directly operated by designers, etc. It can also be used to explore the layout of furniture. For example, the target space may be a vintage furniture store 120. Furniture arranged in the vintage furniture store 120 may include, for example, a vintage sofa 121, a vintage table and a vintage chair 122, a vintage floor stand 123, and the like, and the number and type of furniture are not particularly limited. .

The server 100 may be its own server owned by a person or organization that provides services using the server 100; May be a cloud server; It may be a peer-to-peer (p2p) set of distributed nodes. The server 100 includes arithmetic functions of an ordinary computer; Save/reference function; Input/output function; And it may be configured to perform all or part of the control function. The server 100 may include at least one artificial neural network that performs an inference function. The server 100 may be configured to communicate with the user terminal 110 via wired or wireless.

The server 100 communicates with the user terminal 110 and may perform operations to find a furniture arrangement optimized for the target space. Accordingly, the service provided through the server 100 may be suitable for a designer or a group or a person who professionally performs furniture arrangement.

The user terminal 110 may be a desktop computer, a laptop computer, a tablet, a smartphone, or the like. For example, as shown in FIG. 1, the user terminal 110 may be a desktop computer. The user terminal 110 includes an operation function of an ordinary computer; Save/reference function; Input/output function; And it may be configured to perform all or part of the control function. The user terminal 110 may be configured to communicate with the server 100 by wired or wirelessly.

The user terminal 110 may install an application produced or distributed by a person or organization providing a service using the server 100. The user terminal 110 may transmit information on a target space (furniture store, cafe, restaurant, lobby, gallery, hotel, store, etc.) to which furniture is to be placed to the server 100 through an application, and the server 100 You can acquire furniture arrangement plans in the target space that was calculated and created. For example, the user terminal 110 may transmit information of the vintage furniture store 120 to the server 100 through an application, and obtain furniture arrangement methods of the vintage furniture store 120 calculated and generated by the server 100. I can. Through this, the user of the user terminal 110 can obtain a furniture arrangement for the vintage furniture store 120 operated by the user. Alternatively, the user of the user terminal 110 may present the furniture arrangement of the vintage furniture store 120 to a customer who has requested furniture arrangement consulting. The user of the user terminal 110 may mainly be a designer or the like, but there is no particular restriction on the user's job.

Meanwhile, for convenience of explanation, only one user terminal 110 is illustrated in FIG. 1, but the number of user terminals may vary. As long as the processing capacity of the server 100 allows, there is no particular limitation on the number of user terminals.

Hereinafter, embodiments will be described centering on the operation of the server 100, but the embodiments are not limited by the subject or aspect of communication, and various application examples may be employed. Hereinafter, an embodiment related to an operation of arranging furniture will be described with reference to FIG. 2. Referring to FIG. 3, an embodiment related to an operation of generating furniture arrangement minimalism will be described. Referring to FIG. 4, an embodiment related to an operation of generating furniture placement experimentability and furniture placement classicity is described. With reference to FIG. 5, an embodiment related to an operation of generating a minimalist furniture layout allocation diagram, an experimental furniture arrangement allocation diagram, and a classic furniture arrangement allocation diagram will be described. Referring to FIG. 6, an embodiment related to a learning operation of an artificial neural network will be described.

2 is a flowchart illustrating an operation of generating a furniture arrangement according to an exemplary embodiment.

First, the server 100 may obtain structural information of a subject space in which furniture is to be placed (210 ).

The server 100 may obtain structure information of the target space from the user terminal 110. The target space is a space in which furniture is to be arranged, and may be a furniture store, cafe, restaurant, lobby, gallery, hotel, store, and the like. The structure information of the target space may include standard information, structure information, lighting information, power information, and the like of the target space. The standard information may include a horizontal length, a vertical length, and a height of the target space. The structure information of the target space may include a toilet, a staircase, a window direction, and the number of columns. The lighting information may include the number of lights, the type of each light, a luminous flux of each light, and a color temperature (K) of each light. The power information may include monthly power consumption of the target space, power supplied to the target space, and a ratio of power generated by fossil energy and power generated by renewable energy.

For example, the user of the user terminal 110 of FIG. 1 may plan the furniture arrangement of the vintage furniture store 120 for himself or for his/her customers. In this process, the user terminal 110 may obtain the structure information of the vintage furniture store 120 through the customer's terminal (PC, notebook, smartphone, etc.) or through a user's input. The structure information of the vintage furniture store 120 may include standard information, structure information, lighting information, power information, and the like of the vintage furniture store 120. The user terminal 110 may transmit the input information to the server 100. Through this, the server 100 may obtain structure information of the vintage furniture store 120.

Next, the server 100 may generate a minimalism furniture arrangement allocation diagram, an experimental furniture arrangement allocation diagram, and a classical furniture arrangement allocation diagram of the target space (220).

The minimalistic furniture arrangement allocation degree of the target space may be the proportion of pursuing minimalism aesthetics in arranging furniture in the target space while seeking energy saving through furniture arrangement.

The experimental furniture arrangement allocation map and the classical furniture arrangement allocation diagram of the target space may be a weight to pursue aesthetics other than minimalism aesthetics when arranging furniture in the target space. The target space may have only one value of an experimental furniture layout allocation or a classical furniture allocation allocation. For example, if the experimental furniture arrangement allocation degree of the object space is 30%, the classical furniture arrangement allocation degree of the object space may be 0%; Conversely, if the classical furniture arrangement allocation rate of the target space is 30%, the experimental furniture arrangement allocation rate of the target space may be 0%.

The minimalistic furniture arrangement allocation, the experimental furniture arrangement allocation, and the classical furniture arrangement allocation diagram of the target space may be expressed as a percentage (%) whose sum is 100%.

For example, for the furniture arrangement of the vintage furniture store 120 requested by the customer, the server 100 calculates a minimalist furniture arrangement allocation diagram, an experimental furniture arrangement allocation diagram, and a classic furniture arrangement allocation diagram of the vintage furniture store 120. Can be generated. For example, the server 100 may generate a minimalist furniture layout allocation rate of the vintage furniture store 120 as 70%, an experimental furniture placement allocation rate of 30%, and a classical furniture placement allocation rate of 0%. In this case, in arranging the furniture in the vintage furniture store 120, the proportion of pursuing energy saving while pursuing a minimalist aesthetic through the arrangement of the furniture may be 70%; The proportion of pursuing the experimental aesthetics of the vintage furniture store 120 through furniture may be 30%.

A detailed operation of generating a minimalist furniture arrangement allocation diagram, an experimental furniture arrangement allocation diagram, and a classic furniture arrangement allocation diagram of the target space will be described later with reference to FIG. 5.

Subsequently, the server 100 may refer to spatial objects that satisfy a first predefined degree of significance among spatial objects that have been databaseized (230 ).

Specifically, the server 100 may refer to databased spatial objects that satisfy the structure information of the target space and a first predefined degree of significance, among the spatial objects that have been databased. have.

In this case, the spatial object may be an object including information on a space (furniture store, cafe, restaurant, lobby, gallery, hotel, store, etc.) in which furniture has been arranged. Space objects are the name of the space, the purpose of the space (furniture store, cafe, restaurant, lobby, gallery, hotel, store, etc.), the location of the space, the size of the space (width, height, height, etc.), and the structure in the space (toilet Presence or absence, presence or absence of stairs, direction of windows, number of columns, etc.), lighting of the space (number of lights, type of each light, luminous flux of each light, color temperature (K) of each light, etc.), power information of the space Information such as (monthly power consumption of a space, etc.), furniture arrangement information, furniture arrangement minimalism in space, furniture arrangement experimentation in space, and furniture arrangement classicity in space may be included. The server 100 may pre-database and store each spatial object corresponding to each space in which furniture is arranged.

The first degree of significance may be a criterion for determining a first comparison value of each databaseized spatial object. The first comparison value may be generated based on the 1-1 comparison value, the 1-2 comparison value, and the 1-3 comparison value. The 1-1 comparison value may be a value obtained by comparing a difference between standard information of a spatial object converted into a database and standard information of a target space. The 1-2th comparison value may be a value obtained by comparing structure information of a spatial object converted into a database with structure information of a target space. The 1-3th comparison value may be a value obtained by comparing lighting information of a spatial object converted into a database and lighting information of a target space.

The server 100 is based on the spatial information and structure information of each of the databased synagogue objects and the structure information of the target space, based on the 1-1 comparison value and the 1-2 comparison value of each databaseized spatial object. , And 1-3th comparison values may be generated. Subsequently, the server 100 is based on the 1-1 comparison value, the 1-2 comparison value, and the 1-3 comparison value of each of the databased spatial objects, You can create comparison values. Subsequently, the server 100 may determine whether the first comparison value of each databaseized spatial object satisfies the first degree of significance. Subsequently, the server 100 may refer to databaseized spatial objects that satisfy the first degree of significance.

Specifically, if the first comparison value is less than 50, for example, the server 100 may determine that the first degree of significance is satisfied. The server 100 may generate a first comparison value based on the 1-1 comparison value, the 1-2 comparison value, and the 1-3 comparison value.

In order to generate the 1-1 comparison value, the server 100 may compare the horizontal length of the target space and calculate what percentage (%) the horizontal length of the standard information of each databaseized spatial object is different. ; Compared with the vertical length of the target space, it is possible to calculate what percentage (%) the vertical length of the standard information of each databased spatial object is different; Compared with the height of the target space, it is possible to calculate what percentage (%) the height of the standard information of each databased spatial object is different. Server 100 is the difference in percent (%) of the horizontal length; Percent difference in vertical length; A 1-1 comparison value may be generated by summing the difference in percent (%) of the height.

In order to generate the 1-2 comparison value, the server 100 compares the existence and number of structures by type of the target space and the existence and number of structures by type of structure information of each databased spatial object, so that the existence and number of structures are determined. As the difference increases, the 1-2 comparison value may be generated by increasing the 1-2 comparison value.

In order to generate the 1-3 comparison value, the server 100 compares the number and features of the lights of the target space and the number and features of the lights of each databaseized spatial object. 3 The 1-3th comparison value may be generated by increasing the comparison value.

For example, the server 100 may refer to the databased spatial objects whose structure information of the databased spatial object satisfies the structure information of the vintage furniture store 120 and a predefined first degree of significance. To this end, the server 100 is based on the structure information of each databaseized gonggak object and the structure information of the vintage furniture store 120, based on the 1-1 comparison value, the 1- 2 comparison values and 1-3 comparison values may be generated.

Specifically, the server 100 compares with the width of 10 m of the vintage furniture store 120, the width of the standard information of the first databased spatial object is 11 m, and can calculate that there is a difference of 10 percent (%). There is; Compared with the 15m length of the vintage furniture store 120, the length of the standard information of the first databased spatial object is 12m, and a difference of 20% (%) can be calculated; Compared with the 3m height of the vintage furniture store 120, the height of the standard information of the first databased spatial object is 3m, and a difference of 0 percent (%) may be calculated. The server 100 is 10, which is a percentage (%) difference of the horizontal length; 20, the difference in percent of the vertical length; A 1-1 comparison value of 30 may be generated by adding 0, which is the difference in percent (%) of the height.

In addition, the server 100 includes a structure for each type of vintage furniture store 120 and the number (toilet: available, stairs: none, window direction: south facing, number of columns: 1) and the first database structured structure by type of spatial object. By comparing the availability and the number (toilet: yes, stairs: none, window direction: south, number of columns: 3), the 1-2th comparison value, for example, 5 may be generated. If there is no toilet in the number and availability of structures for each type of spatial object converted into the first database, the server 100 may generate the 1-2 comparison value, for example, 10 greater than 5; If the number of pillars is 2, the server 100 may generate the 1-2th comparison value, for example, 3, which is less than 5.

In addition, the server 100 includes the number and characteristics of the lights of the vintage furniture store 120 (number of lights: 8, type of each light: [ceiling lamp: 5, floor stand: 2; table stand: 1], Luminous flux of each light: [1579㏐, 1579㏐, 1259㏐, 1259㏐, 1259㏐, 1259㏐, 1259㏐, 1100㏐], color temperature of each light(K): [5000K, 5000K, 4000K, 4000K, 4000K, 4000K, 4000K, 3000K]) and the number and characteristics of lights (number of lights: 10, each type of light: [Ceiling: 7, Floorstand: 2; Tablestand: 2) [1579㏐, 1579㏐, 1259㏐, 1259㏐, 1259㏐, 1259㏐, 1259㏐, 1100㏐, 1100㏐, 1100㏐], each light's color temperature (K): [5000K , 5000K, 4000K, 4000K, 4000K, 4000K, 4000K, 4000K, 3000K, 3000K]) to generate the 1-3th comparison value, for example, 10. If the number of lights is 11 in the number and feature of lights of the first databased spatial object, the server 100 may generate the 1-3 comparison values, for example, 14, which is greater than 10; If the number of lights is 9, the server 100 may generate the 1-3th comparison value, for example, 6, which is less than 10.

The server 100 sums up the 1-1 comparison value 30, the 1-2 comparison value 5, and the 1-3 comparison value 10 of the first databased spatial object, so that the first database is converted. The first comparison value 45 of the spatial object may be generated. The server 100 determines that the first databased spatial object satisfies the first significance level because 45, which is the first comparison value of the first databased spatial object, is less than 50, and the first databased spatial object You can refer to.

On the other hand, the server 100 can determine whether the nth databaseized spatial object satisfies the first significance level, and satisfies the first significance level, using the method described above for the remaining databaseized spatial objects. You can refer to each databased spatial object.

In the following order, the server 100 may select spatial objects that satisfy a second predefined degree of significance among the referenced spatial objects (240).

Specifically, among the referenced spatial objects, the server 100 is based on the minimalism of furniture arrangement, experimentation of furniture arrangement, and classical furniture arrangement of the referenced space objects. Referenced spatial objects that satisfy the diagram and the classical furniture arrangement allocation degree and a predefined second degree of significance may be selected.

Furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicalness of databaseized spatial objects can be generated based on the inference of learned artificial intelligence (artificial neural network). The learning operation of artificial intelligence will be described later with reference to FIG. 6.

The furniture arrangement minimalism of each databased spatial object is defined in advance from the first average-the space corresponding to each databased spatial object, the amount of power consumption per household number of the space corresponding to each databased spatial object. The lower the average power consumption per household number of the spaces within the first range, the higher may be. A detailed operation of the server 100 inferring the furniture arrangement minimalism of the database-generated spatial object will be described later with reference to FIG. 3.

The furniture arrangement experimentation of each databased spatial object includes a mention that the furniture arrangement follows the trend of art after minimalism in reviews collected by the server 100 for the space corresponding to each databased space object. The more reviews determined to be, the more it can be. The furniture arrangement classicity of each databased spatial object includes a mention that the furniture arrangement follows the pre-minimalism art trend in reviews collected by the server 100 for the space corresponding to each databased space object. The more reviews determined to be, the more it can be. A detailed operation of the server 100 inferring and generating the furniture arrangement experimentability and the furniture arrangement classicity of the spatial object databased will be described later with reference to FIG. 4.

The second degree of significance may be a criterion for determining a second comparison value of each referenced spatial object. The server 100 includes furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classical performance of each referenced spatial object; A second comparison value of each of the referenced spatial objects may be generated based on the minimalist furniture arrangement allocation diagram, the experimental furniture arrangement allocation diagram, and the classical furniture arrangement allocation diagram of the target space. Subsequently, the server 100 may determine whether the second comparison value of each referenced spatial object satisfies the second degree of significance. Subsequently, the server 100 may select the referenced spatial objects that satisfy the second degree of significance.

Specifically, if the second comparison value is less than 5, for example, the server 100 may determine that the second degree of significance is satisfied. In order to generate the second comparison value, the server 100 excludes the aesthetics (experimental or classical) corresponding to the allocation of 0% of the experimental furniture arrangement allocation and the classical furniture arrangement allocation diagram of the target space ( It can be set as 除外美感). Subsequently, the server 100 uses the ratio of the furniture arrangement corresponding to the aesthetics rather than the excluded aesthetics among the furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicity of each referenced spatial object as a percentage (%). Converting; A ratio of furniture arrangement corresponding to aesthetics corresponding to excluded aesthetics is set to 0%; The furniture arrangement minimalism ratio, the furniture arrangement experimentation ratio, and the furniture arrangement classicalness ratio of each referenced spatial object can be calculated. Subsequently, the server 100 may set a difference between the furniture arrangement minimalism ratio of each referenced spatial object and the minimalism furniture arrangement allocation degree of the target space as the second comparison value. If the second comparison value is, for example, less than 5, the server 100 may determine that the second degree of significance is satisfied.

For example, the server 100 may have generated a minimalism furniture allocation allocation of 70%, an experimental furniture allocation allocation of 30%, and a classical furniture allocation allocation of 0% of the vintage furniture store 120. Meanwhile, the furniture arrangement minimalism of the first referenced spatial object may be 330, the furniture arrangement experimentation may be 170, and the furniture arrangement classicity may be 30. The server 100 may set the classicalness, which corresponds to the classical arrangement allocation degree of 0% of the experimental furniture arrangement allocation degree and the classical furniture arrangement allocation degree of the vintage furniture store 120, as an exclusion aesthetic sense (除外美感). . Subsequently, the server 100 converts the ratio of the furniture arrangement minimalism of the first referenced spatial object to the furniture arrangement experimentation (the furniture arrangement corresponding to the aesthetics rather than the exclusion aesthetics) into a percentage (%), 1 Furniture arrangement minimalism ratio of the referenced spatial object 66% [100*(330)/(330+170)=66%] and furniture arrangement empirical ratio 24% [100*(170)/ (330+170)=24%] can be calculated, and the ratio of the furniture arrangement classicity (the furniture arrangement corresponding to the aesthetics corresponding to the excluded aesthetics) can be set to 0%. Subsequently, the server 100 may set 4, which is a difference between the furniture arrangement minimalism ratio of the first referenced spatial object and the minimalism furniture arrangement allocation degree of the vintage furniture store 120, as the second comparison value. Since the second comparison value of the referenced first spatial object is less than 5, the server 100 determines that the referenced first spatial object satisfies the second degree of significance, and may select the referenced first spatial object. .

On the other hand, the server 100 may determine whether the n-th referenced spatial object satisfies the second significance level, using the method described above, for the remaining referenced spatial objects, and each satisfying the second significance level. You can select the referenced spatial object of.

Next, the server 100 may output each furniture arrangement for the target space based on each selected spatial object (250). To this end, the server 100 may extract furniture arrangement information of each selected spatial object. In addition, the server 100 may generate a blueprint model of the target space based on the structure information of the target space, or obtain a blueprint model of the target space through the user terminal 110 or the like. Subsequently, the server 100 may output each furniture arrangement method for the target space by combining the extracted furniture arrangement information with the blueprint model of the target space.

For example, the server 100 may select three spatial objects from among the referenced spatial objects for furniture arrangement of the vintage furniture store 120. The server 100 may extract furniture arrangement information of each selected spatial object. In addition, the server 100 may generate a blueprint model of the vintage furniture store 120 based on the structure information of the vintage furniture store 120, or obtain a blueprint model of the vintage furniture store 120 through the user terminal 110. have. Subsequently, the server 100 may output three furniture arrangement methods for the vintage furniture store 120 by combining each of the extracted furniture arrangement information with the blueprint model of the vintage furniture store 120.

Through the above, the server 100 may perform an operation of generating a furniture arrangement method in consideration of the artistry (minimalism, experimentation, classicalness) and utility of the target space, based on the spatial objects in the database. Through this, the user of the user terminal 110 using the service performed by the server 100 can obtain a furniture arrangement method that can save energy while considering aesthetics. Through this, it is possible to help designers or the like to proceed with the furniture arrangement more easily.

3 is a diagram for explaining an operation of generating furniture arrangement minimalism according to an exemplary embodiment.

Minimalism is an art and cultural trend that pursues simplicity, and seeks to remove unnecessary things and leave only the essence of objects. Therefore, as the number of furniture or the energy consumed per volume of a space is less, it can be seen that the space pursues minimalism in the arrangement and composition of furniture. Focusing on this point, the server 100 may generate furniture arrangement minimalism of database spaces.

Each of the databaseized spatial objects may include numerical data of furniture arrangement minimalism. Here, the minimalism of the furniture arrangement of the databased spatial object is that the amount of power consumption per number of households in the space corresponding to the databased spatial object is the furniture of the spaces within a predefined first range from the space corresponding to the databased spatial object. The lower than the average of the power consumption per number, the higher can be.

For example, the minimalism of the furniture arrangement of the objects of the first floor furniture store in the database-ized building-1 (310) is the power consumption per number of households in the first floor furniture store in the building-1 (310), from the furniture store on the first floor of the building-1 (310). The lower than the average of the power consumption per number of households in the spaces 310, 320, and 330 in the first predefined range 311, the increase may be made.

In FIG. 3, the first predefined range 311 is shown as a circle having a first predefined radius around a spatial object that has been databased, but the predefined first range may be defined differently. For example, the first predefined range may be an administrative region to which a space corresponding to a spatial object converted into a database belongs. For example, if a furniture store on the first floor of Building-1 (310) is located in “Cheongdam-dong, Gangnam-gu, Seoul,” the first predefined range may be “Gangnam-gu” or “Cheongdam-dong”.

In order to obtain the furniture arrangement minimalism of the database-formed spatial object, the server 100 may first obtain power consumption per number of households in the space corresponding to the database-formed spatial object. In addition, spaces within a first predefined range may be referenced from a space corresponding to a spatial object converted into a database. Subsequently, by obtaining the number of households and power consumption of the referenced spaces, an average of power consumption per number of households of the referenced spaces may be obtained. Subsequently, the average of the power consumption per household number of the referenced spaces and the power consumption per household number of the space corresponding to the databased spatial object may be compared.

Based on the basic score, the server 100 determines the power consumption per number of households in the space corresponding to the databased spatial object, per household number in the first predefined range from the space corresponding to the databased spatial object. If it is lower than the average of the power consumption, it is possible to set the furniture arrangement minimalism of the databased spatial object to a higher value than the basic score.

In addition, based on the basic score, the server 100 calculates the amount of power consumption per the number of households in the space corresponding to the databased spatial object, and the households of the spaces within a predefined first range from the space corresponding to the databased spatial object. The higher than the average of the power consumption per number, the lower the furniture arrangement minimalism of the databased spatial object can be set.

A concrete numerical value of furniture arrangement minimalism of each databaseized spatial object can be generated based on the inference of learned artificial intelligence (artificial neural network). The learning operation of artificial intelligence will be described later with reference to FIG. 6.

For example, the server 100 is a building-1 (310) second-floor furniture store that is included in the first predefined range 311 in obtaining the furniture arrangement minimalism of the first-floor furniture store object of the building-1 (310). , The editing shop inside the building-2 (320), and the power consumption per household number of the building-N (330) pension can be obtained. The server 100 may not consider the power consumption per number of households of the building-N+1 340 that is not included in the first predefined range 311.

Table 399 shows the number of households and power consumption of Building-1 (310) 1st floor furniture store, Building-1 (310) 2nd floor furniture store, editing shop inside Building-2 (320), and Building-N (330) pension. Is shown as an example. The power consumption may be, for example, monthly power consumption [kW]. The server 100 based on the table 399, the power consumption per household number of the first floor of the building-1 (310) 33.3; Building-1 (310) The power consumption per household on the second floor is 50; The power consumption per number of households in the editorial shop inside the building-2 (320) is 50; Building-N (330) The power consumption per household number of the pension can be calculated as 40. Then, the server 100 is the power consumption per household number of the second floor furniture store in the building-1 (310); Power consumption per number of households in the editorial shop inside building-2 (320); And building-N (330) It is possible to obtain an average of 46.7 power consumption per household number of pensions.

Server 100 is based on a basic score, for example, 200, the power consumption per household number of the first floor furniture store in Building-1 (310) 33.3, the power consumption per household number of the spaces within the first predefined range 311 Since it is lower than the average of 46.7, it is possible to set the furniture arrangement minimalism of the furniture store object on the first floor of Building-1 (310) to a value higher than the basic score, for example, 330. A concrete numerical value of furniture arrangement minimalism of the furniture store object on the first floor of the building-1 310 may be generated based on the inference of the learned artificial intelligence (artificial neural network) of the server 100.

On the other hand, if the power consumption per household number of the first-floor furniture store in Building-1 (310) is 30, the server 100 has a higher value than the basic score for the minimalism of furniture arrangement of the furniture store object on the first floor of Building-1 (310). , Can be set to 360. If the power consumption per household number of the first-floor furniture store in Building-1 (310) was 50, the server 100 would set the furniture arrangement minimalism of the furniture store object on the first floor of Building-1 (310) to a value lower than the base score, for example, 190. Can be set.

Through the above, the server 100 may obtain the furniture arrangement minimalism of the spatial objects in the database. The high minimalism of furniture arrangement of spatial objects in the database means that the power consumption per number of furniture in the space corresponding to the space object is low, and the space has a high degree of pursuit of energy saving through furniture arrangement, and the space is furniture arrangement. It can be interpreted as the meaning of pursuing a lot of minimalistic aesthetics. Furniture arrangement minimalism of databaseized spatial objects can be utilized to create a furniture arrangement plan suitable for the target space.

4 is a diagram for explaining an operation of generating furniture arrangement experimentability and furniture arrangement classical performance according to an exemplary embodiment.

Each of the databased spatial objects may include numerical data such as furniture placement experimentation and furniture placement classicity. The experimentality of the furniture arrangement of the databased spatial object increases as more reviews were determined to include the mention that the furniture arrangement follows the trend of art after minimalism in the reviews collected on the space corresponding to the databased spatial object. I can. The classicalness of the furniture arrangement of the databased spatial object will increase as more reviews are determined to include the mention that the furniture arrangement follows the pre-minimalist art trend in the reviews collected on the space corresponding to the databased spatial object. I can.

For example, in the reviews collected about the furniture store on the first floor of the building-1 (310), the furniture placement experimentation and the classical furniture placement of the object of the first floor of the building-1 (310) in the database, the furniture placement was after minimalism. The greater the number of reviews determined to include mentions that follow the trend of art or that the arrangement of furniture follows the trend of art before minimalism, the greater the increase may be.

The server 100 may collect reviews on a space corresponding to the databased spatial object in order to obtain the furniture arrangement experimentability and the furniture arrangement classicity of the databased spatial object. Reviews can be collected through social media, blogs, map services, applications that provide spatial information services, and the like. The collection may be performed in a keyword extraction method, a hashtag extraction method, a text mining method, or the like. Subsequently, the server 100 may classify reviews with a reference to the furniture from the collected reviews. The classification may be performed by a keyword extraction method, a hashtag extraction method, a text mining method, or the like. Subsequently, in the classified reviews, the server 100 may determine whether a reference to the furniture includes a reference that the furniture arrangement follows the art trend after minimalism or that the furniture arrangement follows the art trend before minimalism. The determination may be made by a keyword extraction method, a hashtag extraction method, a text mining method, or the like.

In the reviews collected on the space corresponding to the databased spatial object, the server 100 determines that the furniture arrangement follows the trend of art after minimalism, the more reviews (411), the databaseized space The furniture arrangement experimentability of the object may be set to a higher value (412). For example, in the reviews collected on the space corresponding to the spatial object in the database, the server 100 may find that the furniture arrangement is Avant-Garde, Postmodern, Scandinavian The more reviews that are determined to contain the statement that the database is made, the more experimentally the furniture arrangements of the databased spatial objects can be increased.

In addition, the server 100, in the reviews collected on the space corresponding to the spatial object converted into a database, the more reviews determined to include a mention that the furniture arrangement follows the pre-minimalism art trend (421), the database is made. The classical furniture arrangement of the spatial object may be set to a higher value (422). For example, the server 100 mentions that the furniture arrangement is Baroque, Rococo, or Art Nouveau in the reviews collected on the space corresponding to the databased spatial object. The more reviews that are determined to be included, the more classic furniture arrangement of the databased spatial object can be increased.

Specific values of the furniture placement experimentation and furniture placement classicity of each databased spatial object may be generated based on the inference of the learned artificial intelligence (artificial neural network). The learning operation of artificial intelligence will be described later with reference to FIG. 6.

For example, the server 100 is the first floor of the building-1 (310) in the application and web in obtaining the furniture arrangement experimentability and the furniture arrangement classicity of the spatial object corresponding to the first floor of the building-1 (310). You can collect reviews about furniture stores. Subsequently, the server 100 may classify reviews having a reference to the furniture from reviews of the furniture store on the first floor of the building-1 (310). Subsequently, the server 100 may determine, from the classified reviews, reviews with positive comments about the furniture.

In the reviews on the first floor furniture store in Building-1 (310), the server 100 has 17 reviews including a mention that the furniture arrangement follows the art trend after minimalism, and mentions that the furniture arrangement follows the art trend before minimalism. It is determined that there are 3 reviews including, and the furniture arrangement experimentability of the furniture store object on the first floor of the building-1 (310) may be set to 170 and the furniture arrangement classicity to 30. Concrete values of the furniture arrangement experimentability and the furniture arrangement classicity of the first floor furniture store object of the building-1 (310) may be generated based on the inference of the learned artificial intelligence (artificial neural network) of the server 100.

On the other hand, if the reviews on the 1st floor furniture store in Building-1 (310), 22 reviews including a mention that the furniture arrangement follows the art trend after minimalism, and the mention that the furniture arrangement follows the art trend before minimalism. If it is determined that there are two reviews, the server 100 may set the furniture arrangement experimentation of the first floor furniture store object of the building-1 310 to a value higher than 170 and the furniture arrangement classicity to a value lower than 30. have. If the reviews on the 1st floor furniture store of Building-1 (310), 15 reviews including the mention that the furniture arrangement follows the trend of art after minimalism, and the review includes the mention that the furniture arrangement follows the trend of art after minimalism When it is determined that there are 5 cases, the server 100 may set the furniture arrangement experimentation of the first floor furniture store object of the building-1 310 to a value lower than 170 and the furniture arrangement classicity to a value higher than 30.

Through the above, the server 100 may obtain the furniture arrangement experimentation and furniture arrangement classicity of the databaseized spatial objects. The experimentality of furniture arrangement can be interpreted as a numerical value expressing the aesthetics after the trend of minimalism such as avant-garde, postmodern, and Scandinavian of space. The classicity of furniture arrangement can be interpreted as a numerical value representing the aesthetics before the trend of minimalism such as baroque, rococo, and art nouveau of the space. The furniture arrangement experimentation and the furniture arrangement classicalness of the databaseized spatial objects can be utilized to create a furniture arrangement plan suitable for the target space.

FIG. 5 is a flowchart for explaining an operation of generating a minimalist furniture layout allocation diagram, an experimental furniture arrangement allocation diagram, and a classic furniture arrangement allocation diagram according to an embodiment.

An operation in which the server 100 generates a minimalist furniture arrangement allocation diagram, an experimental furniture arrangement allocation diagram, and a classical furniture arrangement allocation diagram of a target space may include the following detailed operations.

First, the server 100 may obtain a ratio of power generated by fossil energy and power generated by new renewable energy from the power supplied to the target space (510). Fossil energy may include petroleum energy, coal energy, natural gas energy, and the like. The renewable energy may include solar energy, wind energy, and the like. The server 100 obtains and obtains the location information of the target space from the user terminal 110, information on the power sources supplied to the area including the target space, whether the target space has its own solar power facility, etc. Based on one information, it is possible to obtain a ratio of power generated by fossil energy and power generated by renewable energy from the power supplied to the target space.

For example, the server 100 may obtain a ratio of power generated by fossil energy and power generated by renewable energy from power supplied to the customer's vintage furniture store 120, which is a target space. Specifically, the server 100 includes location information of the vintage furniture store 120, information on power sources supplied to the region including the vintage furniture store 120, whether the vintage furniture store 120 has its own solar power facility, etc. By acquiring, it can be obtained that the ratio of the power generated by fossil energy and the power generated by renewable energy in the power supplied to the customer's vintage furniture store 120 is 7:3.

Next, the server 100 may generate a minimalistic furniture arrangement allocation diagram of the target space based on a ratio of power generated by fossil energy (520).

For example, if the ratio of the power generated by fossil energy in the power supplied to the vintage furniture store 120 is 7, the server 100 generates the minimal furniture arrangement allocation rate of the vintage furniture store 120 as 70%. can do.

Subsequently, the server 100 may compare the second average and the third average (530 ).

The second average may be an average of power consumption per household number of spaces within the second predefined range including the target space. The second predefined range may be a circular shape having a second predefined radius around the target space, or an administrative region to which the target space belongs. For example, if the target space is located in “Cheongdam-dong, Gangnam-gu, Seoul,” the second predefined range may be “Gangnam-gu” or “Cheongdam-dong”.

The third average may be an average of power consumption per household number of spaces within a third predefined range including the second range. The third predefined range may be a circular shape having a third predefined radius (the third radius has a larger value than the second radius) around the target space, or an administrative region encompassing the second predefined range. Can be For example, if the second predefined range is “Gangnam-gu”, the third predefined range may be “Seoul City”; If the second predefined range is “Cheongdam-dong”, the third predefined range may be “Gangnam-gu”.

For example, if the vintage furniture store 120 is located in “Cheongdam-dong, Gangnam-gu, Seoul”, the second predefined range may be “Cheongdam-dong”, and the third predefined range may be “Gangnam-gu”. The server 100 may obtain an average of 50, which is an average of power consumption per household number of spaces in "Cheongdam-dong", as a second average, and a third average, of 40, which is an average of power consumption per household number of spaces in "Gangnam-gu".

In the following order, when the second average is high, the server 100 may generate an experimental furniture arrangement allocation diagram of the target space based on the ratio of power generated by renewable energy (540).

For example, since the second average of 50 of the vintage furniture store 120 is higher than the third average of 40, the server 100 is based on the ratio 3 of power generated by renewable energy, and the server 100 is It is possible to generate an experimental furniture arrangement allocation rate of the furniture store 120 as 30%. In addition, the server 100 may set the classic furniture arrangement allocation degree of the vintage furniture store 120 to 0%.

On the other hand, when the third average is high, the server 100 may generate a classical furniture arrangement allocation diagram of the target space based on a ratio of power generated by renewable energy (550).

For example, unlike the previous example, if the second average of the vintage furniture store 120 is 40 and the third average is 50, since the third average is higher than the second average, the server 100 generates renewable energy. Based on the ratio of the generated power 3, the server 100 may generate 30% of the classic furniture arrangement allocation degree of the vintage furniture store 120. In addition, the server 100 may set the experimental furniture arrangement allocation degree of the vintage furniture store 120 to 0%.

Through the above, the server 100 is based on the ratio of the power generated by fossil energy and the power generated by renewable energy in the power supplied to the target space, the minimalistic furniture arrangement allocation diagram of the target space, experimental The furniture layout allocation map and the classical furniture layout allocation diagram can be obtained. Thereafter, the server 100, among the referenced spatial objects, the furniture arrangement minimalism of the referenced space object, the furniture arrangement experimentation, and the furniture arrangement classicity, the minimalism furniture arrangement allocation degree and the experimental furniture arrangement allocation degree of the target space. , And spatial objects satisfying the classical furniture arrangement allocation degree and the second degree of significance may be selected, and furniture arrangements for the target space may be output based on the selected spatial object.

Through this, the server 100 may pursue the aesthetics of various artistic trends rather than energy efficiency as much as the ratio of the supply of renewable energy to the target space. At this time, since the area where the second average is higher than the third average is an area that uses a lot of electrical effects such as lighting compared to the number of households, it can be interpreted that the experimental furniture arrangement will be preferred over the classical furniture arrangement. 100) can assign an experimental furniture layout allocation chart to the target space located in the corresponding area. In addition, since an area where the third average is higher than the second average is an area that uses less electrical effects such as lighting than the number of households, it can be interpreted that the classical furniture arrangement will be preferred over the experimental furniture arrangement. 100) can assign classic furniture layout allocation to target spaces located in the area. On the other hand, the server 100 can create a furniture arrangement method that emphasizes energy efficiency rather than pursuing the aesthetics of various artistic trends while having minimalistic aesthetics as much as the ratio of fossil energy supplied to the target space.

Through this, new and renewable energy is supplied to the target space, so that even if power is consumed, the aesthetic sense of various artistic trends can be secured in the target space without burdening the environment. At this time, the area where the second average is higher than the third average is an area that uses a lot of electrical effects such as lighting compared to the number of households, so the server 100 gives an experimental furniture arrangement allocation chart to the target space located in the corresponding area. Can do; An area where the third average is higher than the second average is an area that uses less electrical effects, such as lighting, compared to the number of households, so the server 100 can assign a classical furniture layout allocation chart to the target space located in the corresponding area. have. In addition, fossil energy is supplied to the target space, and energy efficiency can be secured while pursuing a minimalist aesthetic rather than pursuing the aesthetics of various artistic trends in the target space, as long as power consumption leads to environmental pollution.

Furthermore, the server 100 may obtain a ratio of the expected power to be generated by the renewable energy and the expected power to be generated by the fossil energy at a first future point in time. At this time, the first future time point may be, for example, 10 years later. The first future point of view may be defined differently according to the redevelopment plan of the area including the target space or the replacement cycle of the commercial area.

Specifically, the server 100 obtains location information of the target space from the user terminal 110, information on future power sources supplied to the region including the target space, and the possibility that the target space will establish its own solar power facility. Thus, based on the obtained information, a ratio of the expected power generated by fossil energy and the expected power generated by new renewable energy from the estimated power supplied to the target space may be obtained.

Subsequently, the server 100 may generate an experimental furniture arrangement allocation diagram and a classical furniture arrangement allocation diagram of the target space at a first future viewpoint based on the ratio of the expected power to be generated by renewable energy at a first future viewpoint. have. In addition, the server 100 may generate a minimalistic furniture arrangement allocation diagram of the target space at the first future time point, based on the ratio of the expected power generated by fossil energy at the first future time point.

Subsequently, among the referenced spatial objects, the server 100 determines the minimalism of furniture arrangement, experimentation of furniture arrangement, and classicalness of furniture arrangement, from the first future viewpoint to the minimalism furniture arrangement allocation degree of the target space and the first future viewpoint. In, the spatial objects of the first future view satisfying the experimental furniture arrangement allocation map of the target space and the classical furniture arrangement allocation degree of the target space and the second significance degree at the first future viewpoint may be selected. Subsequently, the server 100 may output furniture arrangement methods for the target space based on the spatial objects selected through the selection step 240 of FIG. 2 and the spatial objects of a first future viewpoint.

Specifically, the server 100 may select one spatial object selected through the selection step 240 of FIG. 2 and one spatial object at a first future viewpoint.

Subsequently, the server 100 may extract a common point from the furniture arrangement of the two spatial objects.

Subsequently, for the difference between the furniture arrangement of the two spatial objects, the server 100 determines the experimental furniture arrangement allocation diagram of the target space or the classical furniture arrangement allocation diagram (a furniture arrangement allocation corresponding to the aesthetics rather than the exclusion aesthetics Selecting a furniture arrangement of the spatial object at a first future point in time with a probability proportional to ); The selection step 240 of FIG. 2 with a probability proportional to the experimental furniture arrangement allocation diagram or the classical furniture arrangement allocation diagram generated through the generation step 220 of FIG. 2 (a furniture arrangement allocation diagram corresponding to aesthetics rather than exclusion) The furniture arrangement of the selected spatial object can be selected through. For example, if the experimental furniture arrangement allocation rate of the target space is 40% and the experimental furniture arrangement allocation rate generated through the generation step 220 of FIG. 2 at the first future point in time is 30%, the furniture arrangement of two spatial objects Regarding the difference, we select the furniture arrangement of the spatial object at the first future point with the probability of 4/7[40/(40+30)=4/7], and 3/7[30/(40+30)=3 The furniture arrangement of the spatial object selected through the selection step 240 of FIG. 2 may be selected with a probability of /7].

Subsequently, the server 100 is based on the extracted common point, the furniture arrangement of the selected spatial object at the first future point of view, and the furniture arrangement of the spatial object selected through the selection step 240 of FIG. You can print the layout plan.

Through this, the server 100 may generate a furniture arrangement method that considers not only the target space at the present time but also the appearance of the target space at a future time. For example, if it is expected that more renewable energy will be supplied to the target space at the first future point in time, the environmental burden of the target space will be less in the future. Even if we focus more on furniture arrangement for aesthetics, it can be furniture arrangement considering the environment. In this way, the server 100 may provide a furniture arrangement plan in consideration of future development.

6 is a diagram illustrating learning of an artificial neural network according to an embodiment.

The artificial neural network may be a configuration included in the server 100 and may be learned through the server 100 or a separate learning device.

The first artificial neural network is the power consumption per number of households in the space (furniture store, cafe, restaurant, lobby, gallery, hotel, store, etc.) corresponding to the spatial object, and the furniture of the spaces within the first predefined range including the space. By receiving the average of the power consumption per number, it is possible to output the furniture arrangement minimalism of the corresponding space object as a numerical value.

The 2-1 artificial neural network may receive reviews including comments on the furniture of the space from among reviews collected on the space corresponding to the spatial object, and output the furniture arrangement experimentation of the spatial object as a numerical value. .

The 2-2 artificial neural network may receive reviews including comments on the furniture in the space from among reviews collected on the space corresponding to the spatial object, and output the furniture arrangement classicity of the spatial object as a numerical value. .

Hereinafter, a process of learning an artificial neural network through a learning device will be described.

First, the learning device may acquire training data and a label (600).

For the first artificial neural network learning, the learning device is the power consumption per number of households in each space (furniture store, cafe, restaurant, lobby, gallery, hotel, store, etc.), and a space within a first predefined range from each space. Data sets consisting of an average of power consumption per household number of children can be obtained as training data.

In addition, for learning of the first artificial neural network, the learning device may obtain a numerical evaluation of expert critics as a label on the degree of minimalism in each space.

For the 2-1 artificial neural network learning, the learning apparatus may acquire a list of reviews including a reference to the furniture of the space from among the reviews collected for each space as training data.

In addition, for learning the 2-1 artificial neural network, the learning device may acquire a numerical evaluation of expert critics as a label on the degree to which the experimentality of each space is implemented.

For the 2-2 artificial neural network learning, the learning apparatus may acquire a list of reviews including a reference to the furniture of the space from among the reviews collected for each space as training data.

In addition, for learning of the 2-2 artificial neural network, the learning device may obtain a numerical evaluation of expert critics as a label on the degree to which the classicalness of each space is implemented.

Now, the learning device may generate an input of an artificial neural network from the training data (610).

The training device may use the training data as an input of the artificial neural network, or may generate an input of the artificial neural network after undergoing a known process of removing unnecessary information from each training data.

Next, the learning device may apply the input to the artificial neural network (620).

The artificial neural network included in the server may be an artificial neural network that is learned according to supervised learning. The artificial neural network may be a convolutional neural network (CNN) or a recurrent neural network (RNN) structure suitable for training through supervised learning.

Subsequently, the learning device may obtain an output from the artificial neural network (630).

The output of the first artificial neural network may be an inference of furniture arrangement minimalism of a spatial object corresponding to a space. Specifically, in the case where the power consumption per number of households in the space is higher than the average of the power consumption per number of households in the spaces within a first predefined range from the corresponding space; When the power consumption per number of households in the space is significantly higher than the average of the power consumption per household number of the spaces within the first range predefined from the space; When the power consumption per number of households in the space is lower than the average of the power consumption per number of households in the spaces within the first predefined range from the space; According to the case where the power consumption per number of households in a space is significantly lower than the average of the power consumption per household number of spaces within the first predefined range from the corresponding space, the pattern of the degree of implementation of minimalism of the space is analyzed, Furniture layout minimalism can be printed in numerical terms. At this time, the first artificial neural network is based on the basic score, the power consumption per number of households in the space corresponding to the spatial object, the power consumption per number of households in the first range defined from the space corresponding to the spatial object. As the value is lower than the average, the furniture arrangement minimalism of the spatial object may be output as a value higher than the basic score. In addition, the first artificial neural network is based on the basic score, the power consumption per number of households in the space corresponding to the spatial object, the power consumption per number of households in the spaces within the first range predefined from the space corresponding to the spatial object. As the value is higher than the average, the furniture arrangement minimalism of the spatial object may be output as a value lower than the basic score.

The output of the 2-1 artificial neural network may be an inference of furniture arrangement experimentability of a spatial object corresponding to a space. Specifically, there are many reviews that have been determined to include mentions that artificial neural networks follow the trend of art after minimalism; Significantly many reviews identified as including mentions of following art trends after minimalism; Few reviews were determined to include mentions of following art trends after minimalism; In some cases where there are no reviews that have been determined to include mentions of following art trends after minimalism, a pattern of the degree of realization of the experimentality of the space can be analyzed and the experimentalness of the furniture arrangement of the spatial object can be output as a numerical value. In this case, the determination of whether the review includes a mention that the furniture arrangement follows the trend of art after minimalism may be determined by a keyword extraction method, a hashtag extraction method, a text minig method, or the like.

The output of the 2-2 artificial neural network may be an inference of classical furniture arrangement of a spatial object corresponding to a space. Specifically, there are many reviews that have been determined to include mentions that artificial neural networks follow the pre-minimal art trend; Significantly many reviews identified as including references to pre-minimalism art trends; Few reviews were determined to include mentions of pre-minimalism art trends; In some cases where there are no reviews that have been determined to include mentions of following art trends before minimalism, the pattern of the degree of experimental realization of the space can be analyzed and the classicalness of the furniture arrangement of the spatial object can be output as a number. At this time, the determination of whether or not the review includes mention that the furniture arrangement follows the pre-minimalism art trend can be determined by a keyword extraction method, a hashtag extraction method, a text minig method, etc.

Thereafter, the learning device may compare the output and the label (640 ). The process of comparing the output of the artificial neural network corresponding to the inference with the label corresponding to the correct answer may be performed by calculating a loss function. As the loss function, a known mean squared error (MSE), cross entropy error (CEE), and the like may be used. However, the present invention is not limited thereto, and loss functions used in various artificial neural network models may be used as long as the deviation, error, or difference between the output of the artificial neural network and the label can be measured.

Next, the learning device may optimize the artificial neural network based on the comparison value (650). By updating the weights of the nodes of the artificial neural network so that the comparison value of the learning device becomes smaller, the output of the artificial neural network corresponding to inference and the label corresponding to the correct answer can be gradually matched. Through this, the artificial neural network It can be optimized to output an inference close to the correct answer. Specifically, the learning apparatus may optimize the artificial neural network by repeating the process of resetting the weight of the artificial neural network so that the loss function corresponding to the comparison value approaches the estimated value of the minimum value. For optimization of artificial neural networks, known backpropagation algorithms, stochastic gradient descent, and the like can be used. However, the present invention is not limited thereto, and weight optimization algorithms used in various neural network models may be used.

The learning device can learn the artificial neural network by repeating this process.

Through this, the learning apparatus is based on an average of the power consumption per number of households in the space and the power consumption per household number of the spaces within a first range defined from the space; A first artificial neural network that outputs furniture arrangement minimalism of a corresponding spatial object as a numerical value may be trained. The first artificial neural network may be used to generate the furniture arrangement minimalism of the databaseized spatial objects described above with reference to FIGS. 2 and 3. Furniture arrangement minimalism of databaseized spatial objects can be used to create furniture arrangements for the target space.

In addition, the learning device is based on reviews including a reference to the furniture of the space, among the reviews collected for the space corresponding to the spatial object; It is possible to train the 2-1 artificial neural network that outputs the experimentality of the furniture arrangement of the corresponding spatial object as a value. The 2-1 artificial neural network may be used to generate the furniture arrangement experimentability of the databaseized spatial objects described above with reference to FIGS. 2 and 4. The furniture arrangement experimentation of databased spatial objects can be used to create furniture arrangements for the target space.

In addition, the learning device is based on reviews including a reference to the furniture of the space, among the reviews collected for the space corresponding to the spatial object; It is possible to train a 2-2 artificial neural network that outputs the furniture arrangement classicity of the corresponding spatial object as a number. The 2-2 artificial neural network may be used to generate the furniture arrangement classics of the databaseized spatial objects described above with reference to FIGS. 2 and 4. The furniture layout classicity of databased spatial objects can be used to create furniture layouts for the target space.

7 is an exemplary diagram of a configuration of an apparatus according to an embodiment.

The device 701 according to one embodiment includes a processor 702 and a memory 703. The processor 702 may include at least one of the devices described above with reference to FIGS. 1 to 6, or may perform at least one method described above with reference to FIGS. 1 to 6. Specifically, the device 701 may be a server 100, a user terminal 110, or an artificial neural network learning device. A person or organization using the device 701 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 6.

The memory 703 may store information related to the above-described methods or a program in which methods described below are implemented. The memory 703 may be a volatile memory or a nonvolatile memory.

The processor 702 can execute a program and control the device 701. The code of a program executed by the processor 702 may be stored in the memory 703. The device 701 is connected to an external device (eg, a personal computer or a network) through an input/output device (not shown), and may exchange data through wired or wireless communication.

The device 701 may be used to train an artificial neural network or use the learned artificial neural network. The memory 703 may include a learning artificial neural network or a learned artificial neural network. The processor 702 may train or execute an artificial neural network algorithm stored in the memory 703. The device 701 for training the artificial neural network and the device 701 using the learned artificial neural network may be the same or may be separate.

The embodiments 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 devices, methods, and components described in the embodiments are, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, such as one or more general purpose computers or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

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 in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of the program instructions include not only machine language codes such as those produced by a compiler but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

The software may include a computer program, code, instructions, or a combination of one or more of these, configuring the processing unit to behave as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

As described above, although the embodiments have been described by the limited drawings, a person of ordinary skill in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in an order different from the described method, and/or components such as a system, structure, device, circuit, etc. described are combined or combined in a form different from the described method, or other components Alternatively, even if substituted or substituted by an equivalent, an appropriate result can be achieved.

Therefore, other implementations, other embodiments, and claims and equivalents fall within the scope of the following claims.

Claims (5)

In a method of creating a furniture arrangement performed by a server based on artificial intelligence,
Obtaining structural information of a subject space in which furniture is to be placed;
Generating a minimalism furniture layout allocation diagram, an experimental furniture arrangement allocation diagram, and a classical furniture arrangement allocation diagram of the target space;
Referring to the databaseized spatial objects, among the databased spatial objects, in which the structure information of the databased spatial object satisfies the structure information of the target space and a predefined first degree of significance;
Among the referenced spatial objects, the furniture arrangement minimalism of the referenced space object, the furniture arrangement experimentation, and the furniture arrangement classicity are the furniture minimalism furniture arrangement allocation degree of the target space. Selecting the referenced spatial objects satisfying a furniture arrangement allocation diagram and a classical furniture arrangement allocation diagram and a second predefined degree of significance; And
Outputting each furniture arrangement for the target space based on each selected spatial object
Including,
Furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicalness of the databaseized spatial objects are generated based on the inference of the artificial intelligence,
The step of generating a minimalist furniture arrangement allocation map, an experimental furniture arrangement allocation diagram, and a classic furniture arrangement allocation diagram of the target space,
Acquiring a ratio of power generated by fossil energy and power generated by renewable energy from the power supplied to the target space;
Generating a minimalistic furniture arrangement allocation map of the target space based on a ratio of power generated by fossil energy;
Second average-the average of power consumption per number of households in the second predefined range including the target space-and the third average-the number of households in the third predefined range including the second range Comparing an average of power consumption per unit;
If the second average is high, generating an experimental furniture arrangement allocation diagram of the target space based on a ratio of power generated by the renewable energy; And
If the third average is high, generating a classical furniture arrangement allocation diagram of the target space based on a ratio of power generated by the renewable energy
Including,
Based on each of the selected spatial objects, outputting each furniture arrangement for the target space,
Extracting pre-stored furniture arrangement information of each of the selected spatial objects;
Generating a blueprint model of the target space based on the structure information of the target space; And
Combining each of the previously stored furniture arrangement information with a blueprint model of the target space, and outputting each furniture arrangement plan for the target space;
Including
How to arrange furniture.
The method of claim 1,
The furniture arrangement minimalism of the databaseized spatial object,
Power consumption per number of households in a space corresponding to the databased spatial object, a first average-an average of power consumption per household number of spaces within a first predefined range from a space corresponding to the databased spatial object The lower the
Increasing
How to arrange furniture.
The method of claim 1,
The furniture arrangement experimentation of the databased spatial object,
In the reviews collected on the space corresponding to the databaseized spatial object, the more reviews determined to include a mention that the furniture arrangement follows the trend of art after minimalism,
Increase,
The classical furniture arrangement of the databased spatial object is,
In the reviews collected on the space corresponding to the spatial object of the database, the more reviews determined to include a mention that the furniture arrangement follows the pre-minimalism art trend,
Increasing,
How to arrange furniture.
A computer program coupled to hardware and stored on a medium for performing any one of the methods of claims 1 to 3.
In the furniture arrangement device comprising artificial intelligence,
Acquire structural information of the subject space in which the furniture is to be placed,
Generate a minimalism furniture arrangement allocation diagram, an experimental furniture arrangement allocation diagram, and a classical furniture arrangement allocation diagram of the target space,
Among the databased spatial objects, the structure information of the databased spatial object refers to the databased spatial objects satisfying the structure information of the target space and a predefined first degree of significance,
Among the referenced spatial objects, the furniture arrangement minimalism of the referenced space object, the furniture arrangement experimentation, and the furniture arrangement classicity are the furniture minimalism furniture arrangement allocation degree of the target space. Selecting the referenced spatial objects satisfying the furniture arrangement allocation map and the classical furniture arrangement allocation diagram and a predefined second degree of significance,
Processor that outputs each furniture arrangement for the target space based on each selected spatial object
Including,
Furniture arrangement minimalism, furniture arrangement experimentation, and furniture arrangement classicalness of the databaseized spatial objects are generated based on the inference of the artificial intelligence,
The operation of the processor generating a minimalist furniture layout allocation diagram, an experimental furniture arrangement allocation diagram, and a classic furniture arrangement allocation diagram of the target space,
From the power supplied to the target space, obtain a ratio of power generated by fossil energy and power generated by renewable energy,
Based on the ratio of power generated by fossil energy, a minimalistic furniture arrangement allocation map of the target space is generated,
Second average-the average of power consumption per number of households in the second predefined range including the target space-and the third average-the number of households in the third predefined range including the second range Compare the average of each power consumption,
If the second average is high, based on the ratio of the power generated by the renewable energy, to generate an experimental furniture arrangement allocation diagram of the target space,
If the third average is high, based on the ratio of the power generated by the renewable energy, generating a classical furniture arrangement allocation diagram of the target space
Includes actions,
The operation of outputting, by the processor, each arrangement of furniture for the target space, based on each of the selected spatial objects,
Extracting pre-stored furniture arrangement information of each of the selected spatial objects,
Based on the structure information of the target space, a blueprint model of the target space is generated,
Combining each of the previously stored furniture arrangement information with a blueprint model of the target space, and outputting each furniture arrangement plan for the target space.
Including motion
Furniture placement device

Images