KR102627950B1 - System for recommending the Local and using the same - Google Patents

Abstract

Disclosed is a region recommendation system that recommends a specific matching region to the user using environmental colors and a region recommendation method using the same.
The regional recommendation method is a method of recommending a specific region through a regional recommendation system using environmental colors. Using photos of a specific region, multiple regional environmental colors and multiple regional emotional keywords corresponding to a specific region are pre-assigned to the regional recommendation system. A setting step, a step where the region recommendation system receives at least one of a symbol color and a symbol emotion keyword from the terminal, and a step where the region recommendation system determines a specific region corresponding to the input information and recommends the determined specific region to the terminal. Includes.

Description

Local recommendation system and local recommendation method using the same {System for recommending the Local and using the same}

The present invention relates to a local recommendation system and a local recommendation method using the same. More specifically, it relates to a local recommendation system that recommends a specific area to a user and a local recommendation method using the same.

Generally, when people planning a trip want to travel to a specific area, they read books introducing that specific area or get advice from someone who has already experienced that specific area. In this way, people can collect the information needed to travel to a specific area they want to go through various methods, and it is common to make a plan based on this.

However, despite collecting information and making plans for the specific area you want to go to in your own way, there are frequent cases where you are not satisfied because you are unable to properly experience the characteristics of that specific area. Accordingly, even though people planning a trip need more specific and practical help, they have no one to ask for help from, so they end up wasting money and time.

To solve this problem, many local recommendation application systems have been provided recently. However, these local recommendation application systems are generally operated without sufficiently reflecting users' opinions, so there is a problem in that they do not reflect the user's emotions or tastes.

KR 10-2011-0125435 A

The present invention is intended to solve the above problems and provides a region recommendation system that recommends a specific region matching using environmental colors to the user and a region recommendation method using the same.

In addition, the present invention provides a region recommendation system that recommends a specific region matched using emotional keywords to the user, and a region recommendation method using the same.

The region recommendation method according to embodiments of the present invention to solve the above problem is a region recommendation method that recommends a specific region through a region recommendation system using environmental colors, and uses a photo of a specific region to recommend the region to the region recommendation system. Pre-setting regional environmental colors and regional emotional keywords corresponding to the specific region; The local recommendation system receiving at least one of a preference color and a preference emotion keyword from the terminal; and determining a specific area corresponding to the input information by the area recommendation system, and recommending the determined specific area to the terminal.

The step of pre-setting local environmental colors and local emotional keywords includes: receiving photos of a specific area by the local recommendation system; Extracting local environmental colors from the photo based on a database for deriving color keywords pre-stored in the local recommendation system; Deriving regional emotional keywords corresponding to the regional environmental colors based on a color keyword derivation database pre-stored in the regional recommendation system; And a step of matching and storing the specific region, the extracted regional environmental colors, and the derived regional emotional keywords.

Extracting local environmental colors from the photo includes analyzing raw colors of each of a plurality of pixels constituting the photo; Based on the standard environmental colors stored in the color keyword derivation database, merging a plurality of the original colors into local environmental colors, and listing the plurality of local environmental colors according to the number of the original colors included at the time of merging; And extracting a plurality of local environmental colors that match an environmental color combination group consisting of a combination of standard environmental colors pre-stored in the color keyword derivation database from among the plurality of local environmental colors listed.

The step of analyzing the raw color of each of the plurality of pixels constituting the photo involves calculating the RGB average value and the HSV average value of the raw color based on RGB (Red-Green-Blue) and HSV (Hue-Saturation-Value). A step of merging the plurality of raw colors into local environmental colors includes merging the plurality of raw colors into standard environmental colors having RGB values and HSV values approximate to the RGB average value and HSV average value of the raw colors. It includes a step of merging to create local environmental colors.

The environmental color combination group is a combination of standard environmental colors, and the step of extracting a plurality of local environmental colors that match the environmental color combination group includes selecting each of the standard environmental colors constituting the environmental color combination group. A step of extracting some local environmental colors, wherein the step of deriving the local emotional keywords corresponding to the plurality of local environmental colors includes extracting the local emotional keywords stored in the color keyword derivation database. It includes extracting standard emotional keywords matching some of the local environmental colors and storing them as local emotional keywords.

After extracting some of the local environmental colors, adding one local environmental color among the plurality of local environmental colors to the partial local environmental colors; and combining the added local environmental colors with some of the local environmental colors to additionally extract matching standard emotional keywords and additionally store them as local emotional keywords.

The color sensibility keyword database is based on at least one of the Munsell color system and the Kobayashi color image scale.

The step of receiving at least one of the preference color and the preference emotion keyword includes: receiving a plurality of the preference colors from the terminal user; and the step of recommending the specific area to the terminal includes regional environmental color Selecting specific regions that match a combination of a plurality of input symbol colors based on the selected regions; and sequentially listing the selected specific regions according to a matching ratio between the plurality of input symbol colors and the regional environmental colors, and transmitting the listed specific regions to the terminal to list them.

The step of receiving at least one of the preference color and the preference sensibility keyword includes receiving a plurality of the preference sensibility keywords from the terminal user, and the step of recommending the specific area to the terminal includes regional sensibility. Based on keywords, selecting specific regions that match a combination of the plurality of input preference and emotional keywords; And sequentially listing the selected specific regions according to the matching ratio of the plurality of input preference emotional keywords and the regional emotional keywords, and transmitting the listed specific regions to the terminal to list them up.

The step of receiving at least one of the preference colors and the preference emotion keywords includes receiving all of the plurality of preference colors and the plurality of preference emotion keywords from the terminal user, and assigning the specific area to the terminal. The recommendation step is to select specific regions that match the combination of a plurality of symbol colors input based on local environmental colors, and specific regions that match the combination of the plurality of symbol emotion keywords input based on regional emotional keywords. selecting them; And sequentially listing the specific regions according to the matching ratio of the plurality of input symbol colors and the regional environmental colors and the matching ratio of the plurality of input symbol emotional keywords and the regional emotional keywords, and transmitting to the terminal Includes a listing step.

The step of transmitting to the terminal and listing it is, when the user selects a specific area among the specific areas listed in the terminal, local environmental colors, emotional keywords, and photos matched to the specific area. It further includes a step of displaying information.

Before receiving at least one of the preference color and the preference emotion keyword, providing the terminal with a list of local environmental colors whose environmental colors do not overlap with each other; and providing a list of the local emotional keywords to the terminal.

The step of receiving at least one of the preference color and the preference emotion keyword includes receiving one of a photo of the user and a photo of the area from the terminal user, and selecting a specific area corresponding to the inputted information. The determining step includes analyzing the raw color of each of a plurality of pixels constituting the user's photo and the local photo; merging the plurality of raw colors into a plurality of standard environmental colors based on the color keyword derivation database; Extracting a plurality of standard emotional keywords corresponding to each of the plurality of standard environmental colors based on the color keyword derivation database; and determining a specific area using the plurality of merged standard environmental colors and the plurality of standard emotional keywords.

The step of pre-setting the local environmental colors and local emotional keywords includes: the local recommendation system pre-storing the local environmental colors and the emotional keywords corresponding to a photo of a specific area input from a network communication network; And a step of the regional recommendation system using an artificial intelligence-based deep neural network to learn in advance the regional environmental color and the emotional keywords corresponding to photos taken of a specific region, wherein the artificial intelligence collects data. It includes deep learning that clusters or classifies, and the deep neural network includes a convolutional neural network that extracts features of data through an overlap process and an integration process and learns patterns of features.

A region recommendation system according to an embodiment of the present invention to solve the above problem is a region recommendation system that recommends a specific region using environmental colors, and includes a receiver for receiving preference colors and preference emotion keywords from a terminal; a database module for deriving color keywords in which a plurality of standard environmental colors and standard emotional keywords corresponding to the plurality of standard environmental colors are pre-stored; It is connected to the color keyword derivation database module, and uses a photo of a specific area or a pre-stored photo of a specific area to match the specific area with at least one of the combination of the standard environmental colors and the standard emotional keywords. Setting module for extracting environmental colors and local emotional keywords; A regional information database module that stores information matching the specific region and the regional environmental colors and information matching the specific region and the regional emotional keywords; a processing module connected to the local information database module and the receiver, respectively, and configured to recommend a specific area matching a plurality of symbol colors and a plurality of symbol emotion keywords input from the terminal; and a transmitter for transmitting the matched specific area to the terminal.

The setting module includes a color analyzer that analyzes the raw color of each of the plurality of pixels constituting the photo of the specific area; a color classifier for producing a plurality of local environmental colors by merging the plurality of analyzed raw colors based on the standard environmental colors; and a keyword classifier that extracts regional emotional keywords corresponding to the regional environmental colors.

The processing module includes: an input unit for receiving at least one of the plurality of symbol colors and the plurality of symbol emotion keywords from the receiver; a judge that determines specific areas matching a plurality of symbol colors and specific areas matching the preference sensibility keyword, based on the local information database module; and an output unit connected to the determiner and configured to transmit the plurality of specific areas determined by the determiner to the transmitter.

The processing module further includes an extractor for extracting in advance a list of regional environmental colors or regional emotional keywords that do not overlap each other, based on the regional information database module, before receiving information through the input device. do.

When receiving either a user's photo or a local photo from the terminal, the processing module analyzes the raw color of each of the plurality of pixels constituting the user's photo and the local photo, and outputs the plurality of raw colors. Merge a plurality of standard environmental colors, extract a plurality of standard emotional keywords matching the plurality of merged standard environmental colors, and combine the plurality of standard emotional keywords into a plurality of symbol colors. It further includes a auxiliary processor that transmits the keyword to the decision unit.

According to the present invention, a specific area matching the environmental color can be recommended to the user using environmental color. Accordingly, the user can intuitively determine the specific area (e.g., tourist destination) desired according to the user's emotional state.

Additionally, using the user's emotional keyword, a specific area that matches the emotional keyword can be recommended to the user. Accordingly, the user can intuitively determine an appropriate specific area according to his emotional state.

In addition, by providing environmental colors and emotional keywords for a specific area in advance, an environment can be provided to the user to easily select environmental colors and emotional keywords even if there are no environmental colors and emotional keywords that the user has thought of in advance.

Figure 1 is an overall schematic diagram showing a local recommendation system and a terminal user according to an embodiment of the present invention.
Figure 2 is a block diagram showing the detailed configuration of a local recommendation system according to an embodiment of the present invention.
Figures 3A to 3G are diagrams showing how the regional recommendation system sets regional environmental colors and regional emotional keywords for a specific region for a photo and receives preference colors and preference emotional keywords from the user.
Figure 4 is a diagram showing a local recommendation system learning information using artificial intelligence.
Figure 5 is a flow chart showing a region recommendation method according to embodiments of the present invention.
Figure 6 is a flow chart showing the process of matching and storing local environmental colors and local emotional keywords for a specific area through photos taken of a specific area.
Figure 7 is a flowchart showing the process of recommending a specific area corresponding to information entered by the user to the user according to the first embodiment of the present invention.
Figure 8 is a diagram illustrating recommending a specific area corresponding to information entered by the user to the user according to the first embodiment of the present invention.
Figure 9 is a flowchart showing the process of recommending a specific area corresponding to information entered by the user to the user according to the second embodiment of the present invention.
Figure 10 is a diagram illustrating recommending a specific area corresponding to information entered by the user to the user according to a second embodiment of the present invention.
Figure 11 is a flowchart showing the process of recommending a specific area corresponding to information entered by the user to the user according to the third embodiment of the present invention.
Figure 12 is a diagram illustrating recommending a specific area corresponding to information entered by the user to the user according to the third embodiment of the present invention.
Figure 13 is a diagram showing a modified version of recommending a specific area corresponding to information entered by the user to the user according to the third embodiment of the present invention.

The embodiments described herein may be modified in various ways. Specific embodiments may be depicted in the drawings and described in detail in the detailed description. However, the specific embodiments disclosed in the attached drawings are only intended to facilitate understanding of the various embodiments. Accordingly, the technical idea is not limited to the specific embodiments disclosed in the attached drawings, and should be understood to include all equivalents or substitutes included in the spirit and technical scope of the invention.

Terms containing ordinal numbers, such as first, second, etc., may be used to describe various components, but these components are not limited by the above-mentioned terms. The above-mentioned terms are used only for the purpose of distinguishing one component from another.

In this specification, terms such as “comprise” or “have” are intended to indicate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof. When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

Meanwhile, a “module” or “unit” for a component used in this specification performs at least one function or operation. And, the “module” or “unit” may perform a function or operation by hardware, software, or a combination of hardware and software. Additionally, a plurality of “modules” or a plurality of “units” excluding a “module” or “unit” that must be performed on specific hardware or performed on at least one processor may be integrated into at least one module. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In addition, when describing the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description thereof is abbreviated or omitted.

Hereinafter, various embodiments will be described in more detail with reference to the attached drawings.

The region recommendation system according to an embodiment of the present invention relates to a system that recommends to a user a specific region that matches using environmental colors and emotional keywords. More specifically, the local recommendation system stores information about a specific area (e.g., a tourist destination or travel destination) in advance as local environmental colors and local emotional keywords using standard environmental colors and standard emotional keywords, and uses It is about a system that recommends (i.e. provides) specific areas matched with preference colors or preference emotion keywords to users.

Figure 1 is an overall schematic diagram showing a local recommendation system and a terminal user according to an embodiment of the present invention, Figure 2 is a block diagram showing the detailed configuration of a local recommendation system according to an embodiment of the present invention, and Figures 3A to 3A Figure 3g is a diagram showing how the local recommendation system sets local environmental colors and local emotional keywords for a specific area for a photo and receives preference colors and preference emotional keywords from the user.

Below, the local recommendation system 100 will be described in detail with reference to FIGS. 1 to 3G.

The region recommendation system 100 according to an embodiment of the present invention is a system that recommends a specific region using environmental colors, and includes a receiver for receiving preference colors (Cu) and preference emotion keywords (Wu) from the terminal 11. (111), a database module 120 for deriving color keywords in which a plurality of standard environmental colors (Cs) and standard emotional keywords (Ws) corresponding to the plurality of standard environmental colors (Cs) are pre-stored, a database module for deriving color keywords ( 120) and using a photo (P) of a specific area or a pre-stored photo (P) of a specific area, a specific area can be selected with standard environmental colors (Cs) (i.e., environmental color combination group (Cc) described later) and standard. Setting module 130 for extracting regional environmental colors (Cr) and regional emotional keywords (Wr) by matching with at least one of emotional keywords (Ws), information matching a specific region and regional environmental colors (Cr) and a regional information database module 140 in which information matched with a specific region and regional emotional keywords (Wr) is stored, each connected to the regional information database module 140 and the receiver 111 and a plurality of inputs from the terminal 11. It may include a processing module 150 for recommending a specific area matching the symbol color (Cu) and a plurality of symbol emotional keywords (Wu), and a transmitter 112 for transmitting the matched specific area to the terminal 11. there is.

In addition, the local recommendation system 100 uses an artificial intelligence-based deep neural network to determine the local environment color (Cr) and region corresponding to the photo (P) taken of a specific area received from the user's (10) terminal (11). It may further include a learning module 160 for learning emotional keywords (Wr). Meanwhile, the case where the receiver 111 and the transmitter 112 of the local recommendation system 110 according to an embodiment of the present invention are included in the transmission and reception module 110 will be described as an example.

Meanwhile, as described above, environmental color and emotional keywords may each refer to different elements. In the following, the elements referred to by each environmental color and emotional keyword are explained in more detail to help understand what the environmental color and emotional keyword refer to.

Standard environmental color (Cs) is abbreviated as Color-standard and may be a color defined by the Munsell color system and Kobayashi color image scale.

Environmental color combination group (Cc) is an abbreviation for color-combination, and is a group of colors defined by the Kobayashi color image scale. For example, a group of environmental colors in which three standard environmental colors (Cc) are grouped into one set. It can be.

Raw color (Ch) is an abbreviation for color-hypermetropic, and is the unique color of a pixel in a photo. It can be a color quantified by RGB (Red-Green-Blue) and HSV (Hue-Saturation-Value). .

Regional environmental color (Cr) is abbreviated as Color-region, and may be a color that is a combination of multiple raw colors (Ch) that make up the pixels of a photo. In addition, the local environmental colors (Cr) are based on the bundle of environmental colors belonging to the environmental color combination group (Cc), and the top A bundle of regional environmental colors (Cr), which may be a combination of environmental colors representing a specific region. Referring to FIGS. 3C and 3F, the local environmental colors (Cr) may refer to a bundle of 'kokoda', 'modular green', and 'koru' representing a specific region, and the local environmental colors (Cr) may represent the local environment. It can mean 'kokoda', 'modular green' or 'koru', which are single environmental colors that make up the colors (Cr).

The symbol color (Cu) is abbreviated as Color-user, and may be a color that the user 10 personally prefers among colors defined in the Mooncell color space and Kobayashi color image scale.

The standard emotional keyword (Wr) is abbreviated as Word-standard and may be an adjective word (i.e. keyword) defined by the Kobayashi color image scale.

The regional emotional keyword (Wr) is abbreviated as Word-region and is an adjective word included in the standard emotional keyword (Ws), and may be an adjective word representing a specific region.

The symbolic emotional keyword (Wu) is abbreviated as Word-user, is an adjective word included in the standard emotional keyword (Ws), and may be an adjective word that the user 10 personally prefers.

Meanwhile, the information (hereinafter referred to as data) processed by the local recommendation system 100 may include local environmental color (Cr) and local emotional keywords (Wr) for a specific area (e.g., tourist attraction, travel destination, etc.). . In addition, the data may include photos taken of a specific area.

Additionally, the terminal 11 of the user 10 through which the local recommendation system 100 according to an embodiment of the present invention transmits and receives data may include a smartphone device or a computer device. In the following, a case where the local recommendation system 100 transmits and receives data with the terminal 11 of the user 10 in a network environment will be described as an example.

The transmission/reception module 110 may receive data from the terminal 11 of the user 10 and transmit data to the terminal 11 of the user 10. The transmitting and receiving module 110 may be electromagnetically connected to a setting module 130 and a processing module 150, which will be described later. Additionally, the transmission/reception module 110 may include a receiver 111 and a transmitter 112.

The receiver 111 may be connected to the terminals 11 of a plurality of users 10 in a network environment. Additionally, the receiver 111 may be electromagnetically connected to the setting module 130 and the processing module 150. The receiver 111 may receive photo data taken of a specific area from a plurality of users 10. The receiver 111 may transmit the received photo data for a specific area to the setting module 130.

Additionally, the receiver 111 may receive a photo (P) of a specific area. The receiver 111 may transmit the received photo P to the setting module 130. Additionally, the receiver 111 may receive data regarding the user's 10 preference color (Cu) and data regarding the user's 10 preference emotional keyword (Wu). The receiver 111 may transmit the received data about the symbol color (Cu) and data about the symbol emotion keyword (Wu) to the processing module 150.

The transmitter 112 may be connected to the terminals 11 of a plurality of users 10 in a network environment. Additionally, the transmitter 112 may be electromagnetically connected to the processing module 150. The transmitter 112 can transmit information about a specific area to the terminals 11 of a plurality of users 10 based on the information processed by the processing module 150. For example, the transmitter 112 transmits data about the place name of a specific area, or a photograph (P) taken in addition to the place name of a specific area, local environmental colors (Cr) of a specific area, and local sensibility of a specific area. Data about the keyword (Wr) can be transmitted together.

The database module 120 for deriving color keywords is electromagnetically connected to the setting module 130 and the processing module 150 and can transmit data to each other. The color keyword derivation database module 120 may store in advance a plurality of standard environmental colors (Cs) and a plurality of standard image keywords (Ws) corresponding to the plurality of standard environmental colors (Cs).

Referring to FIG. 3D, a plurality of standard environmental colors (Cs) based on the Munsell color system may be stored in the color keyword derivation database module 120. For example, standard environmental colors (Cs) may include 'red', 'orange', 'kokoda', 'modular green', 'koru', etc.

In addition, referring to Figure 3e, the database module 120 for deriving color keywords contains an environmental color combination group (Cc) in which three standard environmental colors (Cs) are combined based on the Kobayashi color image scale. It can be saved. For example, the environmental color combination group (Cc) may include environmental colors such as 'kokoda', 'modular green', and 'koru', as shown in Figure 3f.

Additionally, referring to FIG. 3F, the color keyword derivation database module 120 may store a standard emotional keyword (Ws) matching the environmental color combination group (Cc). For example, standard emotional keywords (Ws) are 'natural' and 'red', and 'orange' and 'purple', which match the environmental colors 'kokoda', 'modular green', and 'koru'. This may include ‘busy’ matched with environmental colors. However, the color space and color image scale used by the database module 120 for deriving color keywords are not limited to this and may vary.

Meanwhile, the database module 120 for deriving color keywords of the local recommendation system 100 according to an embodiment of the present invention may be the same as the database for deriving color keywords described in the local recommendation method described later. That is, the database module 120 for deriving color keywords and the database for deriving color keywords have the same structure and configuration, and only the terms are expressed differently.

The setting module 130 may be electromagnetically connected to the transmission/reception module 110 and the color keyword derivation database module 120, respectively. The setting module 130 matches a photo (P) of a specific area input from the terminal 11 or a pre-stored photo (P) of a specific area with the standard environmental color (Cs) and the standard emotional keyword (Ws), respectively, Environmental colors (Cr) and local emotional keywords (Cr) can be created, and the produced local environmental colors (Cr) and local emotional keywords (Cr) can be stored in the local information database module 140, which will be described later.

Here, the setting module 130 can match and store at least one of regional environmental colors (Cr) and regional emotional keywords (Wr) based on a specific region. In the following, an example will be described where the setting module 130 stores a photo (P), local environmental colors (Cr), and local emotional keywords (Wr) as one set based on a specific area. . The setting module 130 may include a color analyzer 131, a color classifier 132, and a keyword classifier 133.

The color analyzer 131 may be electromagnetically connected to the receiver 111 and the local information database module 140, which will be described later. The color analyzer 131 analyzes the raw color (Ch) of each of a plurality of pixels constituting a photo (P) of a specific area input from the terminal 11 of the user 10 or a pre-stored photo (P) of a specific area. can do.

Referring to FIG. 3A, the color analyzer 131 can receive a photo P created as a digital file from the receiver 111. Here, a photo (P) produced as a digital file is made up of a plurality of pixels, and each of the plurality of pixels has a specific raw color (Ch) quantified by RGB and HSV.

Referring to FIG. 3B, the color analyzer 131 can analyze the raw color (Ch) of each of a plurality of pixels. For example, the color analyzer 131 may calculate the RGB average value of the raw color (Ch) and the HSV average value of the raw color (Ch) forming a pixel, based on RGB and HSV.

The color classifier 132 is electromagnetically connected to the color analyzer 131, and based on the database module 120 for deriving color keywords, a plurality of raw colors (Ch) analyzed in the color analyzer 131 are converted into standard environmental colors ( Based on Cs), they can be merged into local environmental colors (Cr).

Referring to FIGS. 3C to 3E, the color classifier 132 divides a plurality of raw colors (Ch) into standard environmental colors (Cs) having RGB and HSV values that approximate the RGB average and HSV average of the raw colors (Ch). can be merged. Accordingly, a plurality of local environmental colors (Cr) can be created by merging different numbers of raw colors (Ch).

The color classifier 132 may list the plurality of local environmental colors (Cr) created in descending order according to the number of merged raw colors (Ch). In the following, a case where the color classifier 132 sequentially lists the top five regional environmental colors (Cr) will be described as an example. Thereafter, the color classifier 132 can produce regional environmental colors (Cr) by sequentially extracting and combining regional environmental colors (Cr) corresponding to the environmental color combination group (Cc) among the listed plurality of regional environmental colors (Cr). there is.

Here, assuming that the regional environmental colors (Cr) are composed of a bundle of, for example, three regional environmental colors (Cr), the top three regional environmental colors (Cr) among the plurality of regional environmental colors (Cr) created are grouped into a specific region. It can be produced with one regional environmental color (Cr) that matches the region. For example, if multiple regional environmental colors (Cr) listed in descending order are 'red', 'orange', 'green', 'blue', and 'purple', the top three regional environmental colors (Cr) A bundle of 'red', 'orange', and 'green' (the matching standard emotional keyword is 'busy') can be produced with local environmental colors (Cr).

Meanwhile, the top three regional environmental colors (Cr) among a plurality of regional environmental colors (Cr) arranged in descending order may not be included in the environmental color combination group (Cc) based on the Kobayashi color image scale. For example, based on the environmental color combination group (Cc), only the top two of the top three regional environmental colors (Cr) among a plurality of regional environmental colors (Cr) are matched, and the third regional environmental color (Cr) is not matched. You can. In this case, the local environmental colors (Cr) matching the environmental color combination group (Cc) can be extracted from a plurality of local environmental colors (Cr) listed in descending order and produced as local environmental colors (Cr).

For example, referring to FIGS. 3C to 3F, five regional environmental colors (Cr), 'kokoda', 'sweet waters', 'modular green', and 'white metal', are shown in a photo (P) taken of a representative area. ', 'koru' can be extracted. In this case, there may be no environmental color combination group (Cc) matching the bundle of 'kokoda', 'sweet waters', and 'modular green', which are the top three regional environmental colors (Cr). Even if you combine 'white metal', which is the next order of 'modular green', there may not be an environmental color combination group (Cc) that matches 'kokoda', 'sweet waters', 'modular green', and 'white metal'. Accordingly, using 'koru', which is the next order of 'white metal', a bundle of 'kokoda', 'modular green', and 'koru' matching the environmental color combination group (Cc) (the matching standard emotional keyword is 'natural') ') can be produced with local environmental colors (Cr).

Meanwhile, the color classifier 132 selects local environmental colors ( Cr) can also be extracted.

Here, the main color of the photo is a color that can convey the overall feeling of the photo, and is a color that occupies the most pixels in the photo. For example, it may be a color that occupies more than 60% to 70% of the entire photo. In addition, the secondary color of a photo is a color that can convey the feeling of change in the photo, and is a color that occupies the second largest number of pixels after the primary color. For example, it may be a color that occupies about 25% to 30%. In addition, the accent color of a photo may be a color scheme that conveys the feeling of change depending on brightness or saturation, and serves as a point that gives an accent to the photo. For example, it may be a color scheme that accounts for less than 5% to 10% of the photo. .

That is, the color classifier 132 selects one local environmental color from the main color of the photo, the secondary color of the photo, and the accent color of the photo, based on the environmental color combination group (Cc) pre-stored in the color keyword derivation database module 120. You can also select (Cr) to create three regional environmental colors (Cr).

The keyword classifier 133 may be electromagnetically connected to the color classifier 132 and the local information database module 140, which will be described later. Referring to FIGS. 3E and 3F, the keyword classifier 133 is based on the color keyword derivation database module 120, and local environment colors (Cr) produced from the color classifier 132 (e.g., three regional environments) A standard emotional keyword (Wr) corresponding to a bundle of colors (Cr) can be extracted. The keyword classifier 133 can produce (i.e., match and store) the extracted standard emotional keywords (Wr) into local emotional keywords (Wr) corresponding to a specific region.

Meanwhile, the keyword classifier 133 extracts local emotional keywords (Wr) matching the local environmental colors (Cr), and then additionally extracts the local emotional keywords (Wr) from among the plurality of local environmental colors (Cr) listed in descending order by the color classifier 132. Local environmental colors (Cr) can be included in existing regional environmental colors (Cr). The keyword classifier 133 combines the additionally included regional environmental colors (Cr) and the existing regional environmental colors (Cr) to additionally extract standard emotional keywords (Ws) matching the environmental color combination group (Cc) to determine the regional environmental colors (Cr). It can also be produced with emotional keywords (Wr). Accordingly, as shown in FIG. 3F, regional environmental colors (Cr) and regional emotional keywords (Wr) extracted from the color classifier 132 may be matched to one photo (P) based on the representative region. . Therefore, the setting module 130 can group a specific area (and a photo (P) taken of a specific area), local environmental colors (Cr), and local emotional keywords (Wr) into one set, which will be described later. It can be stored in the local information database module 140.

The local information database module 140 is electromagnetically connected to the setting module 130 and the processing module 150 and can transmit data to each other. In the local information database module 140, photos (P) taken of a specific area based on a specific area, local environmental colors (Cr), and local emotional keywords (Wr) may be stored in one set. Here, the local information database module 140 may have stored information updated manually by the system administrator. In addition, the local information database module 140 may automatically update information learned from the learning module 160, which will be described later.

Referring to Figure 3g, the processing module 150 is connected to the local information database module 140, the receiver 111, and the transmitter 112, respectively, and selects a specific area corresponding to the information input from the terminal 11 to the terminal ( 11) can be recommended (i.e. provided). Here, the information that the processing module 150 receives from the terminal 11 may be information about the preference color (Cu) containing the personal preference of the user 10 and information about the preference emotion keyword (Wu). The processing module 150 may include an input device 151, a decision device 152, and an output device 153. In addition, the processing module 150 is an extractor that extracts in advance a plurality of standard environmental colors (Cs) that do not overlap with each other or a plurality of standard emotional keywords (Ws) that do not overlap with each other before receiving information through the input device 151. When receiving a photo from (154) and the terminal 11, it may further include an auxiliary processor 155 that analyzes the input photo and converts it into symbol color and symbol emotion keyword.

The input device 151 is electromagnetically connected to the receiver 111 and can receive at least one of a plurality of symbol colors (Cu) and a plurality of symbol emotion keywords (Wu) as input from the receiver 111. Here, the input device 151 can receive a plurality of (at least three) symbol colors (Cu) based on the standard environmental colors (Cs). Additionally, the input device 151 may receive a plurality of symbolic emotional keywords (Wu) based on the standard emotional keyword (Ws).

The judge 152 is electromagnetically connected to the input device 151, and local environmental colors (Cr) that match a plurality of symbol colors (Cu) or a plurality of symbol emotional keywords (Wu) input from the input device 151. and local emotional keywords (Wr) can be determined based on the local information database module 140. That is, the judge 152 searches for local environmental colors (Cr) that match a plurality of symbol colors (Cu) input from the terminal 11, and local emotional keywords (Wr) that match a plurality of symbol emotional keywords (Wu). ) can be found in the local information database module 140 to determine the specific area with the highest matching rate.

For example, the judge 152 may select a specific region that matches at least three input symbol colors (Cu) based on the environmental color combination group (Cc). Thereafter, the judge 152 may select specific regions that match the input preference emotional keywords (Wu) based on the regional emotional keyword (Wr) stored in the regional information database module 140.

Here, the process of determining a specific region through the input symbol color (Cu) by the judge 152 and the process of determining the specific region through the input symbol emotion keyword (Wu) may be carried out simultaneously. Thereafter, the judge 152 may transmit to the output device 153 specific regions matching a plurality of symbol colors (Cu) and specific regions matching the symbol emotion keywords (Wu).

Meanwhile, the judge 152 may sequentially list specific regions with relatively low matching rates, in addition to the specific region with the highest matching rate. Here, the criterion by which the judge 152 sequentially lists specific regions is based on the order in which the matching ratio is relatively high to relatively low (i.e., in descending order). For example, the judge 152 may additionally select specific regions that match at least two of the three or more input symbol colors (Cu). That is, the judge 152 may additionally select specific regions that match a combination of two symbol colors (Cu) that can be selected among the three input symbol colors (Cu).

The output device 153 is connected to the determiner 152 and can output the specific area determined by the determiner 152 to the transmitter 112.

The extractor 154 is connected to the transmitter 112, and before receiving data through the input device 151, based on the local information database module 140, a plurality of local environments in which local environmental colors (Cr) do not overlap with each other are provided. Colors (Cr) and regional emotional keywords (Wr) can be extracted in advance. The extractor 154 may transmit a plurality of regional environmental colors (Cr) and a plurality of regional emotional keywords (Wr) to the user 10 through the transmitter 112. For example, extractor 154 may provide terminal 11 with a list of three local environmental colors (Cr). Additionally, the extractor 154 may provide a list of local emotional keywords (Wr) to the terminal 11. Accordingly, even when the user 10 does not have a specific region in mind in advance, an environment in which the user 10 can easily select regional environmental colors (Cr) and regional emotional keywords (Wr) can be provided by providing choices in advance. .

When receiving a photo from the terminal 11, the auxiliary processor 155 can analyze the input photo and convert it into symbol color (Cu) and symbol emotion keyword (Wu).

More specifically, when the receiver 111 receives one of, for example, a photo of the user 10 or a local photo, from the terminal 11, the receiver 111 may transmit the corresponding data to the auxiliary processor 155. The auxiliary processor 155 analyzes the raw colors (Ch) of each of the plurality of pixels constituting the photo of the user 10 and the local photo, and converts the analyzed raw colors (Ch) into a plurality of standard environmental colors (Cs). can be merged. For example, the auxiliary processor 155 analyzes the raw color (Ch) of each of the plurality of pixels in the same manner as the color analyzer 131 and the color classifier 132 of the setting module 130, and Color (Ch) rules can be merged into multiple standard environmental colors (Cs). Afterwards, the auxiliary processor 155 extracts a plurality of standard emotional keywords (Ws) matching the merged plurality of standard environmental colors (Cs), and converts the plurality of standard environmental colors (Cs) into a plurality of symbol colors (Cu). Setting, a plurality of standard emotional keywords (Ws) can be set as symbolic emotional keywords (Wu) and transmitted to the judge 152.

Figure 4 is a diagram showing a local recommendation system learning information using artificial intelligence.

The learning module 160 is connected to the transmitter 112, the color keyword derivation database module 120, and the local information database module 140, respectively, and is transmitted from the terminal 11 of the plurality of users 10 to the transmitter 112. You can learn information about a specific area in advance using a photo (P) taken of a specific area entered in ). In other words, the learning module 160 automatically creates a specific area (and a photo (P) for a specific area) without the administrator having to separately input local environmental colors (Cr) and local emotional keywords (Wr) for the specific area. , local environmental colors (Cr) and local emotional keywords (Wr) can be learned and stored in the local information database module 140.

More specifically, the learning module 160 uses an artificial intelligence-based deep neural network to learn local environmental colors (Cr) and local emotional keywords (Wr) corresponding to the received photo (P) taken of a specific area. , the learned information can be stored in the local information database module 140. Here, artificial intelligence may include deep learning that clusters or classifies data. Additionally, as shown in FIG. 4, the deep neural network may include a convolutional neural network that extracts features of data and learns patterns of the features through an overlapping process and an integration process. However, the learning module 160 is not limited to this and may be implemented with artificial intelligence using machine learning.

The structure and shape of each component of the local recommendation system 100 described above is not limited to the above description and may vary. In other words, it can change in various ways while performing each function.

Meanwhile, in an embodiment of the present invention, the method of recommending specific regions by receiving environmental colors and emotional keywords from the user is explained along with the region recommendation method.

Figure 5 is a flow chart showing a region recommendation method according to embodiments of the present invention, and Figure 6 shows the process of matching and storing regional environmental colors and regional emotional keywords for a specific region through photos taken of a specific region. Figure 7 is a flow chart showing the process of recommending to the user a specific area corresponding to information entered by the user according to the first embodiment of the present invention, and Figure 8 is the first embodiment of the present invention. According to an example, a diagram showing a specific area corresponding to information entered by the user is recommended to the user, and Figure 9 shows a specific area corresponding to the information entered by the user according to the second embodiment of the present invention. It is a flow chart showing the recommendation process, and Figure 10 is a diagram showing recommending a specific area corresponding to the information entered by the user to the user according to the second embodiment of the present invention, and Figure 11 is a flow chart of the present invention. It is a flow chart showing the process of recommending to the user a specific area corresponding to the information entered by the user according to the third embodiment of the present invention, and Figure 12 is a flow chart showing the process of recommending to the user a specific area corresponding to the information entered by the user according to the third embodiment of the present invention. This is a diagram illustrating a state in which an area is recommended to a user, and Figure 13 is a diagram illustrating a modified state in which a specific region corresponding to information entered by the user is recommended to the user according to the third embodiment of the present invention.

In the following, a region recommendation method according to embodiments of the present invention will be described with reference to FIGS. 1 to 13. The region recommendation method according to embodiments of the present invention may be a method of recommending specific regions to the terminal 11 of the user 10 using the region recommendation system 100.

A region recommendation method according to embodiments of the present invention is a method of recommending a region through a region recommendation system 100 using environmental color (C), and a photo (P) of a specific region (e.g., tourist attraction, travel destination, etc.) A step (S110) of pre-setting regional environmental colors (Cr) and regional emotional keywords (Wr) corresponding to a specific region in the regional recommendation system 100 using A step (S120) of receiving at least one of a symbol color (Cu) and a symbol emotion keyword (Wu), and the region recommendation system 100 determines a specific region corresponding to the input information and selects the determined specific region at the terminal 11 ) may include a recommendation step (S130).

In the following, among the embodiments of the present invention, the first to third embodiments will be separately described. At this time, overlapping steps among the first to third embodiments will be omitted and described. Specifically, in the first to third embodiments, the step (S110) of pre-setting the local environmental colors (Cr) and the local emotional keywords (Wr) is the same, and the symbol color (Cu) and the symbolic emotional keyword ( The step (S120) of receiving at least one of Wu) and the step (S130) of determining a specific area and recommending the determined specific area to the terminal 11 may be different from each other.

First, with reference to FIGS. 5 to 8, a region recommendation method according to the first embodiment of the present invention will be described.

The region recommendation method according to the first embodiment of the present invention can preset regional environmental colors (Cr) and regional emotional keywords (Wr) corresponding to a specific region. That is, using a photo (P) of a specific area (e.g., a tourist attraction, travel destination, etc.), local environmental colors (Cr) and local emotional keywords (Wr) corresponding to a specific area are set in advance in the local recommendation system 100. (S110).

More specifically, the receiver 111 may receive photo (P) data taken of a specific area from a plurality of users 10 (S111). Thereafter, the receiver 111 may transmit the received photo P data to the color analyzer 131.

As shown in FIG. 3A, the color analyzer 131 can receive a photo P created as a digital file and composed of a plurality of pixels from the receiver 111.

Afterwards, the color analyzer 131 calculates the RGB (Red-Green-Blue) average value and the HSV (Hue-Saturation-Value) average value of the raw color (Ch) of each of the plurality of pixels constituting the photo (P) to calculate the raw color (Ch) can be analyzed (S112). That is, as shown in FIG. 3B, the color analyzer 131 can calculate the RGB average value of the raw color (Ch) and the HSV average value of the raw color (Ch) forming a pixel based on RGB and HSV. Thereafter, the color analyzer 131 may transmit the analyzed information to the color classifier 132.

Thereafter, the color classifier 132 merges a plurality of raw colors (Ch) analyzed by the color analyzer 131 into local environmental colors (Cr) based on the color keyword derivation database module 120 to produce local environmental colors ( Cr) can be produced (S113). More specifically, as shown in FIGS. 3C to 3E, the color classifier 132 classifies a plurality of standard environmental colors (Cs) with RGB values and HSV values that approximate the RGB average value and HSV average value of the raw color (Ch). Primitive colors (Ch) can be merged. Accordingly, a plurality of local environmental colors (Cr) can be created by merging different numbers of raw colors (Ch).

Thereafter, the color classifier 132 may list a plurality of local environmental colors (Cr) according to the number of raw colors (Ch) included when merging (S114). That is, the color classifier 132 may list the plurality of local environmental colors (Cr) created in descending order according to the number of merged raw colors (Ch). For example, the color classifier 132 may sequentially list the top five regional environmental colors (Cr).

Thereafter, as shown in FIG. 3D, the color classifier 132 can sequentially extract the local environmental color (Cr) corresponding to the environmental color combination group (Cc) from among the plurality of local environmental colors (Cr) listed ( S115). Here, the color classifier 132 can combine the extracted local environmental colors (Cr) to produce local environmental colors (Cr) consisting of three local environmental colors (Cr).

Thereafter, as shown in FIGS. 3E and 3F, the keyword classifier 133 selects local environment colors (Cr) produced from the color classifier 132 based on the color keyword derivation database module 120 (e.g., A standard emotional keyword (Wr) corresponding to a bundle of three regional environmental colors (Cr) can be extracted and stored as a local emotional keyword (Wr) (S116). In other words, the keyword classifier 133 can produce (i.e., match and store) the extracted standard emotional keyword (Wr) as a local emotional keyword (Wr) corresponding to a specific region.

Thereafter, the regional environmental colors (Cr) additionally extracted from among the plurality of regional environmental colors (Cr) listed in descending order by the keyword classifier 133 may be added to the existing regional environmental colors (Cr) (S117).

Afterwards, the keyword classifier 133 combines the additional regional environmental colors (Cr) and the existing regional environmental colors (Cr) to additionally extract standard emotional keywords (Ws) matching the environmental color combination group (Cc). Thus, it can be created and saved as a local emotional keyword (Wr) (S118).

Thereafter, as shown in FIG. 3F, the keyword classifier 133 applies local environmental colors (Cr) and local emotional keywords (Wr) extracted from the color classifier 132 to one photo (P) based on the representative region. ) can be matched and stored in the local information database module 140 (S119).

Afterwards, a plurality of symbol colors (Cu) can be input from the user 10 of the terminal 11 (S121). That is, the input device 151 can receive a plurality of (at least three) symbolic colors (Cu) based on the standard environmental colors (Cs) from the receiver 111.

Afterwards, a specific region matching a combination of a plurality of symbol colors (Cu) inputted based on regional environmental colors (Cr) can be selected (S131). That is, the judge 152 may determine local environmental colors (Cr) that match a plurality of symbol colors (Cu) input from the input device 151 based on the local information database module 140. Specifically, through the judge 152, regional environmental colors (Cr) matching a plurality of symbolic colors (Cu) can be found, and a specific region can be selected through the regional environmental colors (Cr).

Thereafter, as shown in FIG. 8, the judge 152 selects the selected specific regions according to the matching ratio of the plurality of symbol colors (Cu) and the regional environmental colors (Cr) to the specific region with the highest matching ratio. It can be listed sequentially, and the listed specific areas can be sent to the terminal 11 to be listed (S132).

Afterwards, when the user selects a specific area among the listed specific areas, the terminal 11 displays local environmental colors (Cr), regional emotional keywords (Wr), and the specific area matched to the specific area. The taken photo (P) can be displayed (S133). Accordingly, users can easily check information about a specific area.

In the following, a region recommendation method according to a second embodiment of the present invention will be described with reference to FIGS. 5 to 6 and FIGS. 9 to 10.

The region recommendation method according to the second embodiment of the present invention can preset regional environmental colors (Cr) and regional emotional keywords (Wr) corresponding to a specific region. That is, using a photo (P) of a specific area (e.g., a tourist attraction, travel destination, etc.), local environmental colors (Cr) and local emotional keywords (Wr) corresponding to a specific area are set in advance in the local recommendation system 100. (S110). Here, in the region recommendation method according to the second embodiment of the present invention, the step of pre-setting regional environmental colors (Cr) and regional emotional keywords (Wr) is the same as the first embodiment of the present invention, so detailed description is omitted. .

Afterwards, a plurality of symbolic emotional keywords (Wu) can be input from the user 10 of the terminal 11 (S122). That is, the input device 151 can receive a plurality of symbol emotional keywords (Wu) based on the standard emotional keyword (Ws) from the receiver 111.

Thereafter, the determiner 152 may select specific regions that match a combination of a plurality of symbolic emotional keywords (Wu) based on the regional information database module 140 (S134). That is, the judge 152 may determine regional emotional keywords (Wr) matching the plurality of symbol emotional keywords (Wu) input from the input device 151 based on the local information database module 140. Specifically, through the judge 152, local emotional keywords (Wr) matching a plurality of emotional keywords (Ws) can be found, and a specific region can be selected through the local emotional keywords (Wr).

Thereafter, as shown in FIG. 10, the judge 152 determines the selected specific regions with the highest matching ratio according to the matching ratio of the plurality of input symbol emotional keywords (Wu) and regional emotional keywords (Wr). The list can be done sequentially starting from the region, and the listed specific regions can be transmitted to the terminal 11 (S135).

Thereafter, in the terminal 11, when the user selects a specific area among the listed specific areas, regional emotional keywords (Wr), regional environmental colors (Cr), and the specific area matched to the specific area are displayed. A photo (P) taken can be displayed (S135). Accordingly, users can easily check information about a specific area.

In the following, a region recommendation method according to a third embodiment of the present invention will be described with reference to FIGS. 5 to 6 and FIGS. 11 to 13.

The region recommendation method according to the third embodiment of the present invention can preset regional environmental colors (Cr) and regional emotional keywords (Wr) corresponding to a specific region. That is, using a photo (P) of a specific area (e.g., a tourist attraction, travel destination, etc.), local environmental colors (Cr) and local emotional keywords (Wr) corresponding to a specific area are set in advance in the local recommendation system 100. (S110). Here, in the region recommendation method according to the third embodiment of the present invention, the step of pre-setting regional environmental colors (Cr) and regional emotional keywords (Wr) is the same as the first embodiment of the present invention, so detailed description is omitted. .

Afterwards, a plurality of symbol colors (Cu) can be input from the user 10 of the terminal 11. At the same time, a plurality of symbolic emotional keywords (Wu) can be input from the user 10 of the terminal 11 (S124). Referring to FIG. 12, the input device 151 receives a plurality of (at least three) symbol colors (Cu) based on the standard environmental color (Cs) from the receiver 111, and inputs a plurality of symbol colors (Cu) based on the standard emotional keyword (Ws). You can input a symbolic emotional keyword (Wu). Thereafter, the judge 152 selects a specific region that matches a combination of a plurality of symbol colors (Cu) input based on the regional environmental colors (Cr) based on the regional information database module 140, and selects a specific region matching the plurality of symbol colors (Cu). You can select specific regions that match a combination of emotional keywords (Wu) (S137).

Meanwhile, referring to FIG. 13, the process of selecting a specific region that matches the combination of a plurality of symbol colors (Cu) input based on regional environmental colors (Cr) and matching the combination of a plurality of symbol emotional keywords (Wu) The process of selecting specific regions may be reversed. In the following, an example will be described where the process of first selecting a specific region that matches a combination of a plurality of symbol colors (Cu) input based on regional environmental colors (Cr) is first performed.

More specifically, the judge 152 may determine local environmental colors (Cr) matching a plurality of symbol colors (Cu) input from the input device 151 based on the local information database module 140. Thereafter, the judge 152 may determine regional emotional keywords (Wr) matching the plurality of symbol emotional keywords (Wu) input from the input device 151 based on the local information database module 140. Afterwards, specific regions can be selected through regional environmental colors (Cr) and regional emotional keywords (Wr).

Thereafter, as shown in FIG. 12, the judge 152 selects the selected specific regions according to the matching ratio of the plurality of symbol colors (Cu) and the regional environmental colors (Cr) to the specific region with the highest matching ratio. The selected specific regions can be listed sequentially starting from the specific region with the highest matching rate according to the matching ratio of the plurality of symbol emotional keywords (Wu) and regional emotional keywords (Wr) entered. Afterwards, the listed specific areas can be sent to the terminal 11 and listed (S138).

Afterwards, when the user selects a specific area among the listed specific areas, the terminal 11 displays local environmental colors (Cr), regional emotional keywords (Wr), and the specific area matched to the specific area. The taken photo (P) can be displayed (S133). Accordingly, users can easily check information about a specific area.

In this way, using environmental colors, a specific area that matches the environmental colors can be recommended to the user. Accordingly, the user can intuitively determine the specific area (e.g., tourist destination) desired according to the user's emotional state. Additionally, using the user's emotional keyword, a specific area that matches the emotional keyword can be recommended to the user. Accordingly, the user can intuitively determine an appropriate specific area according to his emotional state. In addition, by providing environmental colors and emotional keywords for a specific area in advance, an environment can be provided to the user to easily select environmental colors and emotional keywords even if there are no environmental colors and emotional keywords that the user has thought of in advance.

Although embodiments of the present invention have been described in more detail with reference to the accompanying drawings, the present invention is not necessarily limited to these embodiments, and various modifications may be made without departing from the technical spirit of the present invention. . Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. The scope of protection of the present invention should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of the present invention.

100: Local recommendation system 110: Transmission and reception module
120: Database module for deriving color keywords 130: Setting module
140: Local information database module 150: Processing module
160: Learning module 10: User
11: terminal

Claims (19)

It is a regional recommendation method that recommends a specific region through a regional recommendation system using environmental colors.
Using a photo of a specific area in the local recommendation system, pre-setting local environmental colors and local emotional keywords corresponding to the specific area in the local recommendation system;
The local recommendation system receiving at least one of a preference color and a preference emotion keyword from the terminal; and
A step of the area recommendation system determining a specific area corresponding to the input information and recommending the determined specific area to the terminal,
The step of pre-setting the local environmental colors and local emotional keywords is,
The local recommendation system is,
Receiving photos of a specific area;
Extracting local environmental colors from the photo based on a database for deriving color keywords pre-stored in the local recommendation system;
Deriving regional emotional keywords corresponding to the regional environmental colors based on a color keyword derivation database pre-stored in the regional recommendation system; and
Comprising: matching and storing the specific region and the extracted regional environmental colors and the derived regional emotional keywords;
The step of extracting local environmental colors from the photo is,
analyzing the raw color of each of a plurality of pixels constituting the photo by a color analyzer of the setting module of the local recommendation system;
The color classifier of the setting module merges the plurality of raw colors into local environmental colors based on the standard environmental colors stored in the color keyword derivation database, and merges the plurality of raw colors into regional environmental colors according to the number of raw colors included at the time of merging. Step of listing environmental colors; and
Among the plurality of local environmental colors listed by the color classifier of the setting module, sequentially extract one by one a plurality of local environmental colors that match an environmental color combination group consisting of a combination of standard environmental colors pre-stored in the color keyword derivation database; A region recommendation method comprising: producing the regional environmental colors by combining them. delete delete In claim 1,
The step of analyzing the raw color of each of the plurality of pixels constituting the photo is,
A color analyzer of the setting module calculates the RGB average value and the HSV average value of the raw color based on RGB (Red-Green-Blue) and HSV (Hue-Saturation-Value),
The step of merging the plurality of raw colors into local environmental colors includes:
A color classifier of the setting module produces a local environmental color by merging a plurality of the raw colors into a standard environmental color having RGB and HSV values that approximate the RGB average value and the HSV average value of the raw colors. Regional recommendation including; method. In claim 1,
The environmental color combination group is a combination of standard environmental colors,
In the step of extracting a plurality of local environmental colors that match the environmental color combination group, the color classifier of the setting module extracts some local environmental colors that each match the standard environmental colors constituting the environmental color combination group. Including the step of doing;
In the step of deriving the local emotional keywords corresponding to the plurality of local environmental colors, the keyword classifier of the setting module selects some of the local environmental colors extracted based on standard emotional keywords stored in the color keyword derivation database. A local recommendation method including the step of extracting standard emotional keywords that match the local emotional keywords and storing them as local emotional keywords. In claim 5,
After the step of extracting some of the local environmental colors,
adding one local environmental color among the plurality of local environmental colors listed by the keyword classifier to some of the local environmental colors; and
A region recommendation method comprising: combining the regional environmental colors to which the keyword classifier has been added and some of the regional environmental colors, extracting additional matching standard emotional keywords, and additionally storing them as local emotional keywords. In claim 1,
The database for deriving the color keywords is,
A region recommendation method based on at least one of the Munsell color system and Kobayashi color image scale. In claim 5,
The step of receiving at least one of the preference color and the preference emotion keyword includes receiving a plurality of the preference colors from a user using the terminal,
The step of recommending the specific area to the terminal is,
Selecting specific regions that match a combination of a plurality of input symbol colors based on regional environmental colors; and
A region recommendation method comprising: sequentially listing the selected specific regions according to a matching ratio between the plurality of symbol colors and the regional environment colors, and transmitting the listed specific regions to the terminal to list them up. In claim 6,
The step of receiving at least one of the preference color and the preference emotion keyword includes receiving a plurality of the preference emotion keywords from a user using the terminal,
The step of recommending the specific area to the terminal is,
Based on regional emotional keywords, selecting specific regions that match a combination of a plurality of input symbolic emotional keywords; and
A region recommendation method comprising sequentially listing the selected specific regions according to a matching ratio of the plurality of input preference emotional keywords and the regional emotional keywords, and transmitting the listed specific regions to the terminal to list them up. . In claim 6,
The step of receiving at least one of the preference colors and the preference emotion keywords includes: receiving all of the plurality of preference colors and the plurality of preference emotion keywords from a user using the terminal;
The step of recommending the specific area to the terminal is,
Selecting specific areas that match a combination of a plurality of symbol colors input based on regional environmental colors, and selecting specific areas that match a combination of a plurality of symbol and emotion keywords input based on regional emotional keywords; and
According to the matching ratio of the plurality of input symbol colors and the local environment colors and the matching ratio of the plurality of input symbol emotional keywords and the regional emotional keywords, the specific regions are sequentially listed and transmitted to the terminal to create a list. A local recommendation method including the step of upgrading. The method according to any one of claims 8 to 10,
The step of transmitting to the terminal and listing,
When a user using the terminal selects a specific area among the specific areas listed in the terminal, information on local environmental colors, emotional keywords, and photos matched to the specific area are displayed; Local recommendations including more. In claim 5,
Before receiving at least one of the symbol color and symbol emotion keyword,
providing the terminal with a list of local environmental colors that do not overlap each other; and
A local recommendation method further comprising providing a list of local emotional keywords to the terminal. In claim 6,
The step of receiving at least one of the preference color and the preference emotion keyword includes receiving one of the user's photo and the local photo from the user using the terminal;
The step of determining a specific area corresponding to the input information is,
Analyzing the raw color of each of a plurality of pixels constituting the user's photo and the local photo;
merging the plurality of raw colors into a plurality of standard environmental colors based on the color keyword derivation database;
Extracting a plurality of standard emotional keywords corresponding to each of the plurality of standard environmental colors based on the color keyword derivation database; and
A region recommendation method comprising: determining a specific region using a plurality of merged standard environmental colors and a plurality of standard emotional keywords. In claim 1,
The step of pre-setting the local environmental colors and local emotional keywords is,
Pre-storing, by the local recommendation system, the local environmental color and the emotional keyword corresponding to a photo of a specific area input from a network; and
A step of the regional recommendation system using an artificial intelligence-based deep neural network to learn in advance the regional environmental color and emotional keywords corresponding to photos taken of a specific region,
The artificial intelligence includes deep learning that clusters or classifies data,
The deep neural network is a local recommendation method that includes a convolutional neural network that extracts features of data through an overlapping process and an integration process and learns patterns of features. As a regional recommendation system that recommends a specific region using environmental color,
A receiver for receiving symbol colors and symbol emotion keywords from the terminal;
a database module for deriving color keywords in which a plurality of standard environmental colors and standard emotional keywords corresponding to the plurality of standard environmental colors are pre-stored;
It is connected to the color keyword derivation database module, and uses a photo of a specific area or a pre-stored photo of a specific area to match the specific area with at least one of the combination of the standard environmental colors and the standard emotional keywords. Setting module for extracting environmental colors and local emotional keywords;
A regional information database module that stores information matching the specific region and the regional environmental colors and information matching the specific region and the regional emotional keywords;
a processing module connected to the local information database module and the receiver, respectively, and configured to recommend a specific area matching a plurality of symbol colors and a plurality of symbol emotion keywords input from the terminal; and
Includes a transmitter for transmitting a matched specific area to the terminal,
The setting module receives a photo of a specific area and extracts local environmental colors from the photo based on the color keyword derivation database module,
Based on the color keyword derivation database module, local emotional keywords corresponding to the local environmental colors are derived, and the local environmental colors are matched with the specific area and the extracted local environmental colors and the derived local emotional keywords to determine the local environmental colors. and set the local emotional keywords in advance,
a color analyzer that analyzes the raw color of each of the plurality of pixels constituting the photo of the specific area;
Based on the standard environmental colors stored in the color keyword derivation database module, a plurality of the raw colors are merged into local environmental colors, and the plurality of local environmental colors are listed according to the number of raw colors included at the time of merging, Among the plurality of local environmental colors listed, a plurality of local environmental colors that match an environmental color combination group consisting of a combination of standard environmental colors pre-stored in the color keyword derivation database module are sequentially extracted one by one and combined to obtain the local environmental colors. A local recommendation system that includes a color classifier to produce them. In claim 15,
The setting module is,
A local recommendation system including a keyword classifier that extracts local emotional keywords corresponding to the local environmental colors. In claim 15,
The processing module is,
an input device for receiving at least one of the plurality of symbol colors and the plurality of symbol emotion keywords from the receiver;
a judge that determines specific areas matching a plurality of symbol colors and specific areas matching the preference sensibility keyword, based on the local information database module; and
An output device connected to the determiner and configured to transmit the plurality of specific regions determined by the determiner to the transmitter. In claim 17,
The processing module is,
A local recommendation system further comprising: an extractor for extracting in advance a list of local environmental colors or local emotional keywords whose environmental colors do not overlap with each other, based on the local information database module, before receiving information through the input device. In claim 17,
The processing module is,
When receiving one of a photo of a user using the terminal and a local photo from the terminal, the raw color of each of the plurality of pixels constituting the photo of the user and the local photo is analyzed, and the plurality of raw colors are divided into a plurality of pixels. Merge the standard environmental colors, extract a plurality of standard emotional keywords matching the merged plurality of standard environmental colors, and convert the plurality of standard environmental colors into a plurality of symbol colors. A local recommendation system further comprising: an auxiliary processor that transmits to the judge.

Images