KR20200023042A - Method and server for measuring congestion using hashtag - Google Patents

Abstract

The present invention relates to a method and a server for measuring a congestion level by using a hashtag. The method for measuring a congestion level by using a hashtag comprises the following steps of: (a) receiving a keyword related to an event or a place from a user terminal; (b) collecting at least one post including the inputted keyword as a hashtag from a social network service (SNS) server; (c) extracting a person and a background from an image included in the collected post; and (d) measuring a digitized congestion level by using the collected post. According to the present invention, it is possible to measure a congestion level by using a hashtag uploaded to the SNS server to provide the measured congestion level to a user, measure a congestion level by using the number of persons included in an image through image analysis, and improve accuracy and efficiency of congestion level analysis by filtering a post to primarily perform image analysis through a hashtag inputted as a keyword. Also, it is possible to recommend a user for a photographing spot and composition through image analysis.

Description

Method and server for measuring congestion using hashtags {Method and server for measuring congestion using hashtag}

The present invention relates to a method and system for measuring congestion using hashtags and image analysis, and more particularly, extracts a post including a hash tag related to a specific keyword from an SNS server, and analyzes an image included in the extracted post. The present invention relates to a method and system for measuring congestion using hashtags and image analysis for measuring congestion.

In the method of measuring the congestion degree at a specific place, a method of determining the congestion degree of a person using the base station information of the portable terminal possessed by the user is conventionally used. However, such a conventional method has a problem that it is difficult to utilize when the general public wants to grasp the degree of congestion of the destination in real time because the public is not easy to access.

On the other hand, the social network service (SNS) server is uploaded in real time to a large number of people in real time, the recent expansion of smart devices has expanded the social network service (SNS) using a portable terminal such as a smart phone ) As the utilization rate increases, the user uploads a post written in real time using a portable terminal at the time of visit and place to the SNS server. In particular, many tourist sites, attractions, festivals, and high streets are uploaded with images and text along with numerous posts with relevant hashtags. Hashtag is a concept introduced to efficiently classify posts uploaded to a social network service (SNS). The hashtag is a summary or keyword related to the content of the uploaded post, or the upload location and time. Although information is included, there is still a lack of technology for analyzing spatial information using such unstructured data. Therefore, from various information stored in the SNS server, more efficient analysis is performed on how many people visit to which place, how much congestion according to time zone, or what kind of pictures people prefer to take. There is a need for skills that can be provided. In other words, there is a demand for a technology capable of analyzing a degree of congestion of a specific place and time by using information stored in a social network service (SNS) and providing the same to a user.

Republic of Korea Patent Publication No. 10-2008-0016094 (2008.02.21.)

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and an object thereof is to provide a user with a congestion measure by using a hash tag uploaded to a social network service (SNS) server.

In addition, the present invention is to measure the degree of congestion using the number of people included in the image through the image analysis, by increasing the accuracy and efficiency of the congestion analysis by filtering the posts to be subjected to the first image analysis through the keywordized hashtag It is aimed at letting.

In addition, an object of the present invention is to recommend a photographing spot and composition to the user through image analysis.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

According to an embodiment of the present invention, a method for measuring a congestion degree using a hash tag by a congestion measurement server according to an embodiment of the present invention includes: (a) receiving a keyword related to an event or a place from a user terminal; (b) collecting at least one post including a hash tag of the input keyword from an SNS server; (c) extracting people and backgrounds from the images included in the collected posts; (d) measuring the congestion degree digitized using the collected postings.

According to an embodiment, the step (b) may collect the posts uploaded to the SNS server within a certain period of time from which the keyword is input.

According to an embodiment, the step (c) may extract a contour from the image by extracting an outline from the image and comparing the extracted contour with a contour of a pre-stored person.

According to an embodiment, the step (c) may extract and extract the remaining part of the image except for the extracted human area as the background of the image.

According to an embodiment, the congestion degree may be a value obtained by adding weights to the number of people included in the collected post images.

In this case, the weight may be set to be higher as the weight is closer to the average value of the location information of the image included in the one or more posts collected by the location information included in the image.

The weight may be set such that the weight is assigned a higher weight as the number of people included in the image increases.

According to an embodiment, the step (d) may measure congestion according to time series using the collected postings.

According to an embodiment, the congestion measurement method using a hash tag according to the present invention may further include (e) recommending a location and composition for photographing to a user using a background extracted from the image. .

According to an embodiment, the step (e) may include extracting a background from one or more images included in one or more posts, comparing the extracted backgrounds, and comparing the extracted backgrounds with one or more backgrounds having a similarity or more than a preset number. Location information included in any of the images may be recommended as a shooting spot.

On the other hand, a congestion measurement server according to an embodiment of the present invention for performing the congestion measurement method using the hash tag, the keyword input unit for receiving a keyword for the event or place to measure the congestion degree from the user terminal; A post collecting unit configured to collect at least one post including a hash tag of the input keyword from an SNS server; An image analyzer extracting a person and a background from the images included in the collected posts; A congestion measurement unit for measuring the congestion degree digitized by using the collected postings; And a display unit displaying the congestion degree measured by the congestion measure unit to the user.

According to one embodiment, the congestion measurement server according to the present invention further includes a shooting spot recommender for recommending a location and composition for taking a picture to the user by using the extracted background; wherein the shooting spot recommender, one or more If the background is extracted from each of the one or more images included in the article, and the extracted backgrounds are compared with each other, the location information included in any image among the one or more images may be recommended as a photographing spot.

According to the present invention, congestion may be measured and provided to a user by using a hash tag uploaded to a social network service (SNS) server.

In addition, the present invention is to measure the degree of congestion using the number of people included in the image through the image analysis, by increasing the accuracy and efficiency of the congestion analysis by filtering the posts to be subjected to the first image analysis through the keywordized hashtag You can.

In addition, the present invention can recommend a photographing spot and composition to the user through image analysis.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a view showing a congestion measurement system using a hash tag including a congestion measurement server according to the present invention.
2 is a diagram schematically showing the configuration of a congestion measurement server according to an embodiment of the present invention.
3 is a flowchart illustrating a method of measuring a congestion degree using a hash tag by a congestion measurement server according to an embodiment of the present invention.
Figure 4 (a) is a diagram showing the contour extracted from the image analysis unit according to the present invention.
4 (b) is a view showing a background extracted from the image analysis unit according to the present invention.
5 is a diagram illustrating a photographing position and a composition recommendation method using a background extracted from an image according to an embodiment of the present invention.
6 is a flowchart illustrating a method in which a congestion measurement server measures a congestion degree using a hash tag and recommends a photographing position and composition to a user according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention, and methods for achieving them will be apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. It is provided to fully convey the scope of the invention to those skilled in the art, and the present invention is defined only by the scope of the claims. Like reference numerals refer to like elements throughout.

Unless otherwise defined, all terms used in the present specification (including technical and scientific terms) may be used as meanings that can be commonly understood by those skilled in the art. In addition, terms that are defined in a commonly used dictionary are not ideally or excessively interpreted unless they are specifically defined clearly. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase.

In the drawings, parts irrelevant to the description are omitted to clearly describe the present invention, and like reference numerals designate like elements throughout the specification. In addition, when a part "contains" a certain component, this means that it may further include other components, not to exclude other components unless otherwise stated. In addition, the "unit" described in the specification means one unit or block that performs a specific function.

1 is a view showing a congestion measurement system using a hash tag including a congestion measurement server according to the present invention.

Referring to FIG. 1, the congestion degree measurement server 100 using a hash tag according to the present invention is connected to a user terminal 200 and an SNS server 300 through a network, and a post uploaded to an SNS server 300 is provided. The degree of congestion may be measured based on the information and provided to the user terminal 200. The user terminal 200 may be a wired terminal, for example, a PC, or a wireless terminal, for example, a mobile phone, a smartphone, a tablet, a notebook. The user terminal 200 is a congestion measurement server or SNS through a network using a browser for internet access such as a wireless application protocol, which is an internet access protocol, and a Microsoft Internet Explorer (MIE) based on HTML using an HTTP protocol. The server 300 may be connected. The SNS server 300 may be a server operated and managed by an SNS service provider to provide a social network service (SNS).

2 is a diagram schematically showing the configuration of a congestion measurement server according to an embodiment of the present invention.

2, the congestion measurement server 100 according to an embodiment of the present invention includes a keyword input unit 110 for receiving a keyword for the event or place to measure the congestion degree from the user terminal; A post collecting unit 120 collecting at least one post including a hash tag of the input keyword from an SNS server; An image analyzer 130 extracting a person and a background from the images included in the collected posts; A congestion measurement unit 140 for measuring the congestion degree digitized by using the number of collected posts and the number of persons included in the image; Shooting spot recommending unit 150 for recommending the location and composition for the user to take a picture using the extracted background; And a display unit 160 displaying the congestion degree measured by the congestion measure unit to the user.

The keyword input unit 110 may receive a keyword for an event or a place for measuring a congestion degree from a user terminal. The keyword for the event or place may be, for example, a place name, a festival name, a name of a tourist attraction or a shop, and the like, but is not necessarily limited thereto and may be any word desired by a user. However, in order for a user to be provided with accurate information, it may be desirable to input a keyword that can specify a place where a congestion degree is to be measured. The keyword input to the keyword input unit 110 may not necessarily be one, and one or more keywords necessary for specifying a place may be input.

The post collecting unit 120 may collect at least one post including a keyword input through the keyword input unit 110 as a hash tag from an SNS server. When the user inputs a plurality of keywords, the post collecting unit may collect a post including all of the plurality of keywords input by the user according to the user's selection, or the post including at least one of the plurality of keywords input by the user. You can also collect In addition, the post collecting unit 120 may collect posts uploaded within a predetermined period from a point in time at which a keyword is input or may upload posts uploaded for a predetermined period of time specified by a user. As described above, the present invention filters the analysis target by using a hash tag and analyzes the image included in the extracted post before the image analysis step through the article collection unit 120, thereby increasing the accuracy of congestion measurement. In particular, efficiency can be maximized by drastically reducing the data load for image analysis.

The image analyzing unit 130 may obtain an image from the posting collected by the posting collecting unit 120, and may specify and extract a person and a background included in the obtained image. The image analyzer 130 extracts an outline from the acquired image, extracts a person from the image by comparing the extracted outline with a contour of a pre-stored person, or extracts a feature point from the acquired image, A person may be extracted from an image by comparing the extracted feature point with a feature point of a pre-stored person. However, the method of extracting a person from the acquired image is not limited thereto, and the image analyzer 130 may extract a person from the image using various image analysis techniques. Meanwhile, the image analyzer 130 may specify and extract the remaining part of the acquired image except for the human region extracted through the aforementioned method as the background of the image.

The congestion measuring unit 140 may measure the numerical congestion degree using the number of posts collected by the post collecting unit 120 or the number of people included in the image analyzed by the image analyzing unit 130. According to an embodiment, the congestion measurer 140 measures congestion based on the number of people included in the collected post images, and applies weights to the number of people included in the collected post images. The combined value can be measured and provided as congestion information.

The photographing spot recommending unit 150 may recommend a location and composition for photographing to the user by using the background included in the image extracted by the image analyzing unit 130. According to an embodiment of the present disclosure, the shooting spot recommender 150 extracts a background from one or more images included in one or more posts, and compares the extracted backgrounds, and compares the extracted background with any one of the one or more images. Location information included in the image may be recommended as a shooting spot.

The display unit 160 may display the congestion degree or the recommended photographing spot generated by the congestion measuring unit 140 and the photographing spot recommending unit 150 on the display of the user terminal.

Hereinafter, a method of measuring congestion and a photographing spot recommendation method according to an embodiment of the present invention will be described with reference to FIGS. 3 to 6.

3 is a flowchart illustrating a method of measuring a congestion degree using a hash tag by a congestion measurement server according to an embodiment of the present invention.

Referring to FIG. 3, the congestion measurement server 100 measures a congestion degree using a hash tag according to an embodiment of the present invention, the method comprising: (a) receiving a keyword related to an event or a place from a user terminal; (b) collecting at least one post including a hash tag of the input keyword from an SNS server; (c) extracting people and backgrounds from the images included in the collected posts; (d) measuring the degree of congestion using the collected posts and images included in the posts.

In the step (a), the keyword input unit 110 receives a keyword for the event or place to measure the degree of congestion from the user terminal. The keyword for the event or place may be, for example, a place name, a festival name, a tourist attraction or a store name, but is not necessarily limited thereto and may be any word desired by a user. However, in order for a user to be provided with accurate information on the degree of congestion, it may be desirable to input a keyword for specifying a place where the degree of congestion is to be known. The keyword input to the keyword input unit 110 may not necessarily be one, and one or more keywords necessary for specifying a place may be input.

In step (b), the post collecting unit 120 collects at least one post including a keyword input via the keyword input unit 110 as a hash tag from the SNS server. For example, when a user inputs “A” as a keyword, the post collecting unit 120 may collect posts using “A” as a hash tag among posts uploaded to an SNS server. The post collected by the post collecting unit 120 from the SNS server may include one or more images and one or more hashtags, and posts using “A” as a hashtag are collected as a user inputs “A” as a keyword. Can be. When the user inputs a plurality of keywords, the post collecting unit may collect a post including all of the plurality of keywords input by the user according to the user's selection, or the post including at least one of the plurality of keywords input by the user. You can also collect

According to an embodiment of the present disclosure, the post collecting unit 120 may collect only posts uploaded within a predetermined period from a time point at which a keyword is input. In the case of a post that has been uploaded for a certain period of time from the current point of time, there is a possibility that it may be used as an inaccurate data in determining the degree of congestion at the present time. Congestion information can be generated using only uploaded posts.

According to another embodiment, the post collecting unit 120 may collect only posts uploaded for a predetermined period of time specified by the user. It is necessary to generate and provide congestion information for a specific past time point according to the nature of an event or a place where a user wants to grasp the congestion degree. For example, if the user wants to know in advance the congestion degree for a festival that is held once a year, or if he / she wants to know the congestion degree during the weekend for a specific place in advance, the current time point as described above (keyword input) It is more accurate to use posts uploaded during past festivals or past weekends, rather than using posts uploaded for a certain period of time, and may generate congestion information according to the user's intention. Therefore, the post collecting unit 120 according to an embodiment of the present invention may collect only posts uploaded for a predetermined period selected by a user and generate congestion information using the posts. Conditions for the posts collected by the post collecting unit 120 as described above may be changed according to a situation according to a user's selection.

As described above, the present invention performs an image analysis on the image included in the extracted post by filtering the analysis target using the hash tag before the image analyzing step through the post collecting unit 120, thereby increasing the accuracy of the congestion measurement. In particular, efficiency can be maximized by drastically reducing the data load for image analysis.

In the step (c), the image analyzer 130 extracts the person and the background from the images included in the collected posts. The image analyzing unit 130 may obtain an image from the posting collected by the posting collecting unit 120, and may specify and extract a person and a background included in the obtained image.

In the method of extracting a person from an image acquired by the image analyzer 130, the image analyzer 130 according to an embodiment extracts the contour of the acquired image and compares the extracted contour with the contour of the pre-stored person. By this, the person can be identified and extracted from the image. In this case, the image analyzer 130 may extract a contour by defining a point having a color change amount greater than or equal to a reference value in the image as a point on the contour. According to another exemplary embodiment, the image analyzer 130 may extract a person from an image by extracting feature points of the acquired image and comparing the extracted feature points with feature points of a pre-stored person.

Meanwhile, the image analyzer 130 may specify and extract the remaining portion of the acquired image except for the extracted human region as the background of the image.

4 is a diagram illustrating extracting a person and a background of an image by extracting an outline of an image acquired according to an embodiment of the present invention. 4 (a) shows the contour extracted from the image by the image analyzer according to the present invention, and FIG. 4 (b) shows the outline of the background extracted from the image by the image analyzer according to the present invention. As such, the image analyzer 130 extracts a person and a background from the image included in the post, and measures the number of people included in the image from the image or compares the background except the person, as described below. It can provide information about.

In the step (d), the congestion measuring unit 140 measures the digitized congestion degree using the collected article.

According to one embodiment, the congestion measurer 140 may measure the congestion degree based on the number of people included in the collected post images. At this time, the congestion measurement unit 140 may measure the sum value by applying a weight to the number of people included in the images of the plurality of posts collected and provide the information as congestion information. That is, the congestion measuring unit 140 according to an embodiment of the present invention may measure the congestion degree through Equation 1 below.

<Equation 1>

-C: congestion,

n: number of posts collected

: i 번째 게시글의 이미지에 포함된 사람의 수-

: the number of people in the image of the i post

: i 번째 게시글에 부여되는 가중치-

: weight assigned to the i post

: i 번째 게시글의 이미지에 포함된 촬영 위치 정보-

: Shooting location information included in the image of the i post

: i 번째 게시글의 이미지에 포함된 촬영 시간 정보-

: Shooting time information included in images of i th post

)는, 혼잡도 측정의 정확도를 높이기 위한 것으로, 게시글에 포함된 이미지가 실제 사용자가 원하는 장소, 원하는 시간의 혼잡도를 얼마나 반영하고 있는지에 따라 다양한 방법으로 설정될 수 있다. 즉, <수학식 1>에 기재된 바와 같이, 가중치

는 다양한 변수들에 대한 함수일 수 있다.At this time, the weight applied to the number of people included in the image of the collected posts (

) Is to increase the accuracy of the measurement of congestion, and may be set in various ways depending on how much the image included in the post reflects the congestion of a desired place and a desired time. That is, as described in <Equation 1>, the weight

May be a function on various variables.

)는 상기 이미지에 포함된 위치 정보가 수집한 복수의 게시글에 포함된 이미지의 위치 정보의 평균값에서 가까울수록 높은 가중치가 부여되도록 설정될 수 있다. 또는, 상기 가중치(

)는 상기 이미지에 포함된 촬영 위치 정보를 기반으로 인접하여 촬영된 이미지가 많을수록 높은 가중치가 부여되도록 설정될 수 있다. 이는 장소와 관련한 키워드를 해시태그로 입력하여 업로드 한 사용자가 실제로 해당 장소에 있을 가능성이 높은 경우 일수록 혼잡도 분석에 적합함을 수식화한 것으로, 특정 장소와 관련한 키워드를 해시태그로 한 게시글이 많은 위치에서 촬영된 이미지일수록 실제로 해당 장소에서 촬영된 이미지일 가능성이 높은 것으로 판단하고 더 높은 가중치가 적용되도록 할 수 있다. According to one embodiment, the weight (

) May be set to be assigned a higher weight as the position information included in the image is closer to the average value of the position information of the images included in the plurality of posts. Or the weight (

) May be set to be assigned a higher weight as the number of adjacent images photographed based on the photographing position information included in the image. This is a formula that is suitable for congestion analysis when the user who uploaded a keyword related to a place as a hashtag is more likely to be actually in the place.In a case where there are many posts that hash the keyword related to a specific place It may be determined that the photographed image is more likely to be an image actually photographed at the corresponding place, and a higher weight may be applied.

)는 상기 이미지에 포함된 촬영 시간 정보를 기반으로 최근에 촬영된 이미지일수록 높은 가중치가 부여되도록 설정될 수 있다. 이는 최근에 촬영된 이미지일수록 현재 시점에서의 혼잡도를 분석하는 데에 적합함을 수식화한 것이다.According to another embodiment, the weight (

) May be set to have a higher weight for the most recently photographed image based on the photographing time information included in the image. This is a formula that the more recently photographed image is suitable for analyzing the congestion degree at the present time.

)는 상기 이미지에 포함된 사람의 수가 많을수록 높은 가중치가 부여되도록 설정될 수 있다. 수집된 이미지에 따라서는 특정 장소에 존재하는 사람들을 충분히 포함하지 않을 수 있으므로 이미지 내 나타나지 않은 사람들이 반드시 그 장소에 있지 않음을 의미하는 것은 아니고, 따라서 이미지 내 사람 수가 적다는 사실이 반드시 해당 장소가 혼잡하지 않음을 의미하지는 않는다. 반면, 이미지 내에 나타난 사람들은 반드시 해당 장소에 있음을 의미하기 때문에, 이미지 내 포함된 사람의 수가 많은 이미지가 사람의 수가 적은 이미지보다 혼잡도 분석에 있어서 더 적합할 수 있다. 이에 따라, 일 실시예에 따르면 이미지 내 포함된 사람의 수가 적은 게시글보다는 사람의 수가 많은 게시글에 더 높은 가중치가 부여되도록 설정될 수 있다.According to another embodiment, the weight (

) May be set to be assigned a higher weight as the number of people included in the image increases. Depending on the images collected, this may not necessarily include people who exist in a particular place, which does not necessarily mean that people who do not appear in the image are not necessarily there. It doesn't mean it's not crowded. On the other hand, since people appearing in an image necessarily mean that they are in the place, an image having a large number of people included in the image may be more suitable for congestion analysis than an image having a small number of people. Accordingly, according to an embodiment of the present invention, a post with a large number of people may be set to have a higher weight than a post with a small number of people included in the image.

)는 게시글 수집부(120)가 수집한 게시글의 수가 많을수록 높은 가중치가 부여되도록 설정될 수 있다.According to another embodiment, the weight (

) May be set to be assigned a higher weight as the number of posts collected by the post collecting unit 120 increases.

)는 게시글에 포함된 이미지가 실제 사용자가 원하는 장소의 혼잡도를 얼마나 잘 반영하고 있는지에 따라 다양한 방법으로 설정될 수 있다. 즉, <수학식 1>에는

가 수집한 게시글의 수, i 번째 게시글에 포함된 이미지의 촬영 위치 및 촬영 시간, i 번째 게시글의 이미지에 포함된 사람의 수

의 함수로 기재되어 있으나, 반드시 이에 한정되는 것은 아니고 다양한 요인을 변수로가질 수 있음은 물론이다.The above-described weight setting method is for illustrative purposes only and is not necessarily limited thereto.

) Can be set in a variety of ways, depending on how well the image included in the post reflects the congestion of the actual location. That is, in Equation 1

Number of posts collected by the user, the location and time of the image in the i post, and the number of people in the i post

Although described as a function of, it is not necessarily limited thereto, and various factors may be variables.

The degree of congestion C calculated by the above-described manner may be, for example, an absolute value or a ratio of the number of people that the place can accommodate and the number of people present in the place. Alternatively, the ratio may be a ratio of congestion at the time when the place is most crowded within a predetermined period and congestion at the present time.

In a congestion measurement method using a hash tag according to an embodiment of the present invention, time congestion information for a keyword input by a user may be measured to provide congestion information for each time zone.

The image uploaded to the SNS server may include EXIF (Photographic Image File Format). Exchangeable image file format (EXIF) is a kind of information data stored inside the photo file.The camera manufacturer, camera model, direction of rotation, date and time, color space, focal length, flash, ISO speed, aperture, shutter Information such as speed and satellite location information (GPS) may be included.

The congestion measurement server according to an embodiment of the present invention collects a post including a keyword input by a user as a hash tag, and extracts the image from the photographing information of the image included in the collected post (Exchangeable image file format, EXIF). Obtains the captured time information, and measures the congestion degree in time series based on this, and may provide the same to the user. That is, the user may be provided with information on how crowded the degree of congestion at the point of time when the user wants to visit or the degree of congestion is measured, compared to the degree of congestion at other points in time.

5 is a diagram illustrating a photographing position and a composition recommendation method using a background extracted from an image according to an embodiment of the present invention.

Referring to FIG. 5, the method for measuring congestion using a hash tag according to an embodiment of the present invention may further include (e) recommending a location and composition for photographing to a user using a background extracted from an image. can do. According to an embodiment, the step (e) extracts a background from each of a plurality of images included in the plurality of posts, and compares the extracted backgrounds when the background having a similarity or more than a preset value is a predetermined number or more. The location information included in any of the images may be recommended as a shooting spot.

As described above, the image analysis unit 130 of the present invention may extract a person from the acquired image, and specify and extract the remaining portions except for the extracted human region as the background of the image. Tourist spots or attractions that many people visit may have their favorite shooting spots. Pictures taken at such shooting spots may have similar backgrounds, except for people in the image, taken at similar locations and compositions. . That is, when there are many images with similar backgrounds among the images included in the collected posts, the place where the images are taken may be determined as a shooting spot that people prefer. Accordingly, according to an embodiment of the present invention, the shooting spot recommender 150 extracts a background from one or more images included in one or more posts, and compares the extracted background to set a background having a similarity or more than a preset value. If the number is more than one, the location information included in any one of the one or more images may be recommended as a photographing spot.

6 is a flowchart illustrating a method of measuring a congestion degree using a hash tag and recommending a photographing position and composition to a user by a congestion measurement server according to an embodiment of the present invention.

Referring to FIG. 6, when the congestion measurement server 100 according to the present invention receives a keyword related to an event or a place from a user terminal, postings including the received keyword as a hash tag from an SNS server may be collected. Collected posts may include images uploaded together, which may include people and backgrounds. The congestion measurement server 100 may extract a person and a background from the image, measure a congestion using the number of people extracted from the image, and recommend a shooting spot using the extracted background.

The embodiments of the present invention described above are disclosed for the purpose of illustration, and the present invention is not limited thereto. In addition, one of ordinary skill in the art of the present invention will be able to make various modifications and changes within the spirit and scope of the present invention, and such modifications and changes should be considered to be within the scope of the present invention.

100: congestion measurement server
110: keyword input unit 120: post collection unit
130: image analysis unit 140: congestion measuring unit
150: shooting spot recommendation unit 160: display unit
200: user terminal 300: SNS server

Claims (12)

In the congestion measurement server to measure the congestion degree using a hash tag,
(a) receiving a keyword related to an event or a place from a user terminal;
(b) collecting at least one post including a hash tag of the input keyword from an SNS server;
(c) extracting people and backgrounds from the images included in the collected posts;
(D) measuring the congestion degree digitized by using the collected postings; characterized in that it comprises a, a congestion measurement method using a hash tag.
The method of claim 1,
In the step (b), the congestion measurement method using a hash tag, characterized in that the collection of posts uploaded to the SNS server within a certain period from the time the keyword is input.
The method of claim 1,
In the step (c), extracting a contour from the image, and extracting a person from the image by comparing the extracted contour with the contour of the pre-stored person, congestion degree using a hash tag.
The method of claim 3,
In the step (c), the congestion measurement method using a hash tag, characterized in that for extracting the remaining portion of the image except for the extracted human region by specifying as a background of the image.
The method of claim 1,
The congestion degree is a congestion measurement method using a hash tag, characterized in that the sum of the weighted to the number of people included in the image of the collected posts.
The method of claim 5,
The weighting method is a congestion measurement method using a hash tag, characterized in that the weight is set so that the closer the weight is closer to the average value of the location information of the image included in the post collected by the location information included in the image.
The method of claim 5,
The weight is a congestion measurement method using a hash tag, characterized in that the higher the number of people included in the image is set to be given a higher weight.
The method of claim 1,
In the step (d), the congestion measurement method using a hash tag, characterized in that for measuring the congestion degree according to the time series using the collected postings.
The method of claim 1,
(e) recommending a location and composition for taking a picture to the user by using the background extracted from the image. The method of claim 1, further comprising a hash tag.
The method of claim 9,
Step (e) extracts a background from one or more images included in one or more posts, and compares the extracted backgrounds to any one of the one or more images when the similarity level is equal to or greater than a preset number. Congestion measurement method using a hash tag, characterized in that to recommend the included location information as a shooting spot.
A keyword input unit for receiving a keyword for an event or a place for measuring a congestion degree from a user terminal;
A post collecting unit configured to collect at least one post including a hash tag of the input keyword from an SNS server;
An image analyzer extracting a person and a background from the images included in the collected posts;
A congestion measurement unit for measuring the congestion degree digitized by using the collected postings;
And a display unit configured to display a congestion degree measured by the congestion measure unit to a user.
The method of claim 11,
A shooting spot recommender for recommending a location and composition for taking a picture to the user by using the extracted background;
The photographing spot recommender extracts a background from one or more images included in one or more posts, and compares the extracted backgrounds to be included in any one of the one or more images when the background having a similarity or more is a preset number or more. Congestion degree measurement server using a hash tag, characterized in that the recommended location information as a shooting spot.

Images