KR20210055296A - Method for providing bigdata based matching service connecting individual - Google Patents

Abstract

Provided is a method for providing a matching service for connecting people based on big data, which includes the steps of: receiving user data transmitted for matching from a user terminal; extracting at least one matching terminal having user data and a preset degree of suitability from previously constructed big data; and transmitting the extracted list of at least one matched terminal to the user terminal as a matching list. Therefore, it is possible to find a more accurate ideal type by checking a user's style change and reflecting the change of the ideal type without separate individual updates.

Description

A method of providing a matching service that connects people to people based on big data {METHOD FOR PROVIDING BIGDATA BASED MATCHING SERVICE CONNECTING INDIVIDUAL}

The present invention relates to a method of providing a matching service that connects a person with a person based on big data, and provides a platform for recommending and matching a counterpart by analyzing an individual's style based on big data.

Matching methods that connect people to people include a blind date where an acquaintance directly introduces a person, a marriage information company where an intermediary matches people offline, and registers their profile online and contacts the target of interest among the registered profiles. There are matching blind date applications, online cafes looking for travel companions, and so on.

In the case of blind date and marriage information companies, users who want to match share their opinions on their own preferences and styles to their acquaintances and intermediaries. That is, the user himself/herself converts himself/herself into data. In addition, subjective opinions of acquaintances and intermediaries who introduce the information are added, and the data is converted into only subjective opinions.

In addition, even in the case of a blind date application or an online cafe looking for a travel companion, it can be said that the data is only based on subjective opinions because the user who wants to match creates and shares a profile introducing himself/herself. In other words, in the matching services listed above, since information is given only by subjective opinion of a person, it is difficult to trust the information, and in most cases, it is necessary to make a decision through a meeting. Therefore, those who want to find new people for various purposes (entertainment, marriage, travel companion, etc.) need objective data that can analyze people in addition to the subjective data used previously.

In addition, in the matching services listed above, it is difficult to reflect the changing tendency or style of the introduced person (user) in real time. For example, in the past, if the ideal type has changed to an introverted person but recently changed to an extrovert, you must separately notify your acquaintances and intermediaries of the change of your ideal type, and you must update the profile registered in the blind date application and the cafe looking for travel companions. I was able to announce the change of my ideal type.

For a more accurate ideal matching service, a technology for matching people through objective data analysis is required, and prior art includes Patent No. 10-2028752,'A method of providing a couple matching service using key shares and compatibility'. However, the above technology is limited to matching content using only quantitative data such as date of birth information, age, education, etc., such as family name and compatibility, and qualitative data such as user's disposition and personality are used together to search for people who are close to the ideal type. There was a limit to providing. In addition, there was a limit to checking and reflecting the change of the user's ideal type.

In one embodiment of the present invention, in order to grasp a person's personality, disposition, lifestyle, etc., analysis of interests and emotions through social media and web pages, analysis of terminal use and contact style through reality mining, and social Big data-based people and people who can find the ideal type more accurately and reliably by constructing big data with objective data such as analyzing the preferred social networking style through the media's personal network, and categorizing people close to the ideal type as objective big data. It is to provide a method of providing a matching service that connects.

In addition, one embodiment of the present invention is, among the big data analysis techniques, data such as analysis of interests through social media and web pages that can be automatically updated according to the passage of time, sentiment analysis, and terminal usage and contact style analysis through reality mining. The purpose is to provide a method of providing a matching service that connects people and people based on big data that can reflect changes in ideal types without separate individual updates (profile modification, acquaintance requests, etc.) by checking the user's style change through analysis.

However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention includes the steps of receiving user data transmitted for matching from a user terminal, at least having user data and a preset degree of suitability from pre-built big data. And extracting one terminal to be matched, and transmitting the extracted list of at least one terminal to be matched to the user terminal as a matching list.

According to any one of the above-described problem solving means of the present invention, in order to grasp a person's personality, inclination, lifestyle, etc., an interest analysis and emotion analysis through social media and web pages, and a terminal through reality mining Big data can be built with objective data such as analysis of usage and contact style, and analysis of preferred social networking style through social media's personal network. Accordingly, by categorizing and organizing users' personalities, dispositions, lifestyles, etc. into big data, a more suitable for various purposes (love, marriage, travel companion, etc.) and tastes (personality, travel style, age, eating habits, etc.) of users. You will be able to find the exact ideal type.

In addition, according to any one of the problem solving means of the present invention, among the big data analysis techniques, interest analysis through social media and web pages that can be automatically updated according to the passage of time, emotion analysis, terminal use and contact style through reality mining By checking the user's style change through data analysis such as analysis, it is possible to find a more accurate ideal type by reflecting the change of the ideal type without separate individual updates (profile modification, acquaintance request, etc.).

1 is a diagram illustrating a system for providing a matching service for connecting people based on big data according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a matching service providing server included in the system of FIG. 1.
3 is a view for explaining an embodiment in which a matching service for connecting people based on big data according to an embodiment of the present invention is implemented.
FIG. 4 is a diagram illustrating a process of transmitting and receiving data between components included in the system for providing a matching service for connecting a person to a person based on big data of FIG. 1 according to an embodiment of the present invention.
5 is a flowchart illustrating a method of providing a matching service for connecting people based on big data according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" with another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, and one or more other features, not excluding other components, unless specifically stated to the contrary. It is to be understood that it does not preclude the presence or addition of any number, step, action, component, part, or combination thereof.

The terms "about", "substantially", and the like, as used throughout the specification, are used in or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and are used to provide an understanding of the present invention. To assist, accurate or absolute numerical values are used to prevent unreasonable use of the stated disclosure by unscrupulous infringers. As used throughout the specification of the present invention, the term "step (to)" or "step of" does not mean "step for".

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized by using two or more hardware, or two or more units may be realized by one piece of hardware.

In the present specification, some of the operations or functions described as being performed by a terminal, device, or device may be performed instead in a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, device, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the unique number of the terminal or the identification information of the individual, which is the identification information of the terminal. Can be interpreted as.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a system for providing a matching service for connecting people based on big data according to an embodiment of the present invention. Referring to FIG. 1, a matching service providing system 1 for connecting a person to a person based on big data includes at least one user terminal 100, a matching service providing server 300, and at least one matched terminal 400. , And at least one travel agency server 500. However, the system 1 for providing a matching service that connects people based on big data in FIG. 1 is only an embodiment of the present invention, and thus the present invention is not limitedly interpreted through FIG. 1.

In this case, each component of FIG. 1 is generally connected through a network 200. For example, as shown in FIG. 1, at least one user terminal 100 may be connected to the matching service providing server 300 through the network 200. In addition, the matching service providing server 300 may be connected to at least one user terminal 100, at least one matched terminal 400, and at least one travel agency server 500 through the network 200. In addition, at least one terminal to be matched 400 may be connected to the matching service providing server 300 through the network 200. In addition, the at least one travel agency server 500 may be connected to at least one user terminal 100, a matching service providing server 300, and at least one matched terminal 400 through the network 200.

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, and Long Term (LTE). Evolution) network, 5GPP (5th Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network) , Personal Area Network (PAN), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, Digital Multimedia Broadcasting (DMB) network, and the like, but are not limited thereto.

In the following, the term'at least one' is defined as a term including the singular number and the plural number, and even if the term'at least one' does not exist, each component may exist in the singular or plural, and may mean the singular or plural. It will be self-evident. In addition, it will be possible to change according to the embodiment that each component is provided in the singular or plural.

The at least one user terminal 100 may be a terminal of a user who searches for a counterpart by using a web page, an app page, a program, or an application related to a matching service that connects a person and a person based on big data. In this case, the other party is not limited to the listed ones because it may be various such as a marriage partner, a blind date partner, a travel companion, a walking partner, and an instant meeting. The at least one user terminal 100 may be a terminal that permits and accepts a questionnaire survey or an access right to one's own web traffic and social media to the matching service providing server 300. In addition, the at least one user terminal 100 may be a terminal that is based on big data, but receives a counterpart from the matching service providing server 300 that matches the data collected by the access right allowed by the user. In addition, at least one user terminal 100 is a terminal that grants a proxy right to the matching service providing server 300 for identification when the matching service providing server 300 requests identification from a third trusting institution. I can. In addition, the at least one user terminal 100 may be a terminal that provides not only its own user data, but also information about a desired counterpart in a form such as a keyword. In addition, at least one user terminal 100 provides the matching service providing server 300 with the likelihood of the matched counterpart so that the matching service providing server 300 can relearn the user's ideal type. Can be In addition, the at least one user terminal 100 may be a terminal that selects a questionnaire for checking a travel style and transmits it to the matching service providing server 300. In addition, the at least one user terminal 100 may be a terminal that transmits personal information and an inquiry consent for identification verification to the matching service providing server 300 to receive an identification result from the matching service providing server 300. . In addition, the at least one user terminal 100 may be a terminal that selects any one of at least one keyword or a combination of at least one keyword, and the at least one matched terminal 400 filtered based on this may be a matching service. It may be a terminal receiving from the providing server 300. In addition, at least one user terminal 100 selects a companion of any one terminal to be matched 400, transmits the selection result to the matching service providing server 300, and selected from the matching service providing server 300 When an indication of acceptance of the matched terminal 400 is received, it may be a terminal connected to the travel agency server 500.

Here, the at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) All types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs may be included.

The matching service providing server 300 may be a server that provides a matching service web page, an app page, a program, or an application that connects people and people based on big data. The matching service providing server 300 may be a server that collects user information of at least one user terminal 100 and builds big data. In addition, the matching service providing server 300 classifies at least one user terminal 100 by setting reference data based on the collected big data, but individualizes the information to which the access right is granted by each user terminal 100 Thus, it may be a server that builds individual data. In addition, after matching, the matching service providing server 300 may be a server for sharing a location and a picture of the user terminal 100 with an acquaintance terminal (not shown). In addition, the matching service providing server 300 collects the likelihood from the user terminal 100 and the matched terminal 400 after matching, and imposes a penalty on the object that received a low likelihood as the asymmetry of the likelihood increases. It may be a server that allows information to be relearned. In addition, the matching service providing server 300 can expand the platform to travel service, marriage service, blind date service, opposite sex service, friend search service, and companion search service, using data obtained by relearning big data and matching results. It can be a capable server. In particular, in the case of a travel service, the matching service providing server 300 may be a server that collects travel agency information from at least one travel agency server 500 to register a travel agency, and receives and registers a travel product. In addition, the matching service providing server 300 may be a server that determines whether to subscribe to a member by receiving an identity inquiry result from at least one third trusting institution when receiving a membership subscription request from at least one user terminal 100. And, the matching service providing server 300, if there is no abnormality in the identity check result of the user terminal 100 or if it matches the result transmitted from the user terminal 100, a page for investigating the travel style to the user terminal 100 It may be a server that transmits, stores the result as a response, and classifies the user's travel style into at least one cluster. In addition, the matching service providing server 300 receives any one or at least one combination of at least one keyword from the user terminal 100, and a list of at least one matched terminal 400 filtered by the received keyword It may be a server that transmits to the user terminal 100. In addition, the matching service providing server 300 transmits a companion request event to the matched terminal 400 selected by the user terminal 100, and when an indication of acceptance is received, the matching service providing server 300 transmits it to the user terminal 100 and immediately It may be a server that connects to at least one travel agency server 500 or transmits a keyword and travel style to at least one travel agency server 500 and receives a travel estimate. In addition, the matching service providing server 300 tracks and monitors the location of the user terminal 100 and the matched terminal 400 when a trip starts, and shares the result with an acquaintance terminal (not shown) in real time. It may be a server that synchronizes the photos to the time and location after the trip is over, overlays them on a map, and transmits them to the user terminal 100 and the matched terminal 400.

Here, the matching service providing server 300 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like.

The at least one matched terminal 400 may be a matched user's terminal using a matching service-related web page, an app page, a program, or an application that connects a person to a person based on big data. In the case of a travel service among the various services described above, the terminal to be matched 400 may be a terminal of a companion. At this time, when receiving the companion request event of the user terminal 100 from the matching service providing server 300, the at least one matched terminal 400 transmits an indication of acceptance or rejection to the matching service providing server 300 It may be a terminal to do. In addition, the at least one matched terminal 400 may be a terminal that receives a travel estimate from the travel agency server 500 after transmitting consent, or may be a terminal that performs payment. In addition, the at least one terminal to be matched 400 may be a terminal for tagging and transmitting a location tag to the matching service providing server 300 with a photograph taken when a trip starts, and on a map during or after a trip. It may be a terminal that overlays photos in correspondence with time and location. In addition, the at least one terminal to be matched 400 may be a terminal that transmits satisfaction with the matching result to the matching service providing server 300. At this time, the at least one terminal to be matched 400 is limited to the role of receiving the companion request event from the user terminal 100, but it is obvious that it is a terminal capable of performing an operation or function of the user terminal 100. . Conversely, the user terminal 100 may also perform an operation or function of at least one terminal to be matched 400, but the description is limited to the role of transmitting a companion request event.

Here, the at least one terminal to be matched 400 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one terminal to be matched 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. The at least one terminal to be matched 400 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC). , PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband) Internet) terminal, smart phone (smartphone), smart pad (smartpad), it may include all kinds of handheld (Tablet PC) based wireless communication devices such as.

The at least one travel agency server 500 may use a matching service-related web page, app page, program, or application that connects a person to a person based on big data, and selects a travel style and at least one keyword from the matching service providing server 300. It may be a receiving server. In addition, the at least one travel agency server 500 may be a server that transmits the at least one travel estimate list to the matching service providing server 300 to be transmitted to the user terminal 100 and the matched terminal 400. In addition, the at least one travel agency server 500 may be a server that calculates a fee to the matching service providing server 300 when payment for a travel product is in progress.

Here, the at least one travel agency server 500 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one travel agency server 500 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one travel agency server 500, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) All types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs may be included.

FIG. 2 is a block diagram illustrating a matching service providing server included in the system of FIG. 1, and FIG. 3 is an implementation of a matching service that connects people and people based on big data according to an embodiment of the present invention. It is a figure for explaining an example.

Referring to FIG. 2, the matching service providing server 300 includes a receiving unit 310, a classification unit 320, an extraction unit 330, a filtering unit 340, a transmission unit 350, a sharing unit 360, A calculation unit 370, a relearning unit 380, and a travel management unit 390 may be included.

The matching service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one user terminal 100, at least one matched terminal 400, and at least one In the case of transmitting a matching service application, program, app page, web page, etc. that connects people and people based on big data to the travel agency server 500, at least one user terminal 100 and at least one matched terminal 400 , And at least one travel agency server 500 may install or open a matching service application, a program, an app page, a web page, etc. that connects a person to a person based on big data. In addition, a service program may be driven in at least one user terminal 100, at least one matched terminal 400, and at least one travel agency server 500 by using a script executed in a web browser. Here, the web browser is a program that enables you to use the web (WWW: world wide web) service, which means a program that receives and displays hypertext described in HTML (hyper text mark-up language). For example, Netscape , Explorer, chrome, etc. In addition, the application refers to an application on the terminal, and includes, for example, an app running on a mobile terminal (smart phone).

Referring to FIG. 2, the receiving unit 310 may receive user data transmitted for matching from the user terminal 100. In this case, the user data may be classified into structured data, semi-structured data, and unstructured data according to the degree of standardization. Structured data is data that has a standard with a fixed type and format, and is a type of data that is entered as a value of a specified format (numeric, date, etc.) in a fixed field or selected as an item, and metadata of various data. Semi-structured data is mostly a text type, and although the field is not fixed, it is a data class that can define the contents included in the text according to the characteristics of the data. Largely, it includes document data containing user opinions and comments added to it. Text data is generally classified as unstructured data, but there are cases where it is classified as semi-structured data or structured data when a choice is given. Unstructured data are items that are difficult to define because of their irregular shape, and generally include text and images. The unstructured data may include various types of moving picture and picture data such as, for example, an image, a picture, or an image. Such unstructured data is also learned as keywords, tags, or meta data, classified and patterned, and when a new classification of unstructured data is required afterwards, the data may be processed into a record format and provided together with related data.

When receiving user data transmitted for matching from the user terminal 100, the receiving unit 310 may provide a page for performing a personality test to the user terminal 100. In addition, when the personality test is performed in the user terminal 100, the receiving unit 310 may map and store the result of the personality test with the user terminal 100. In this case, the at least one pre-stored keyword may include a keyword corresponding to the personality test result. In addition, the receiving unit 310, when receiving user data transmitted for matching from the user terminal 100, receives permission to access the history log of social media from the user terminal 100, and the user terminal 100 When access is granted from, the user terminal 100 may collect interest data through at least one type of social media and web page channel in a background mode. In addition, the receiving unit 310 may extract the collected interest data using text mining, and assign a weight to the content generated by the event in the user terminal 100 to sort and classify the interest data.

When receiving user data transmitted for matching from the user terminal 100, the receiver 310 may receive at least one keyword of a counterpart to be matched from the user terminal 100. This is because some people are looking for people who are similar to the users themselves, but there are people who are looking for people who have a disposition to themselves. This is basic data that allows you to match not only people who are similar to you, but also your ideal type by including information of the other party to be matched by allowing you to select or fill out a questionnaire or additional request in a separate category or in the same category. It can be used as a query, which can then be entered into big data as a query.

The classification unit 320 may analyze the received user data and classify it by extracting a classifier. In this case, the classifier may be selected as one of each classification category. For example, in the personality category, cheerful-depressed, frivolous-calm, humility-arrogant, gentle-cold, honest-left and right/dishonesty, cautious-radical, amorous-nerd, daring-timidity, emotional stability-nervousness, despair-indecisiveness, It can be divided into sacrificial-selfish, compromise-self-righteous, generous-intolerant, etc., but personality cannot be divided dichotomously, so the classifier may not be set as described above. Or, for example, in the category of consumption lifestyle, it can be classified into classifiers such as stall type, follow-up type, self-centered type, fashion leading type, etc., and the stall type focuses on price and external beauty, and uses the sale period or draws attention from others. The group that wants to receive, the follower type does not value individuality, has a passive tendency, and has a lot of different opinions from others, is a group that has little interest in new things, and the self-centered type emphasizes the inner beauty and the price. Groups that value the appearance of the product and use a lot of sales periods or use discount stores, and the trend leader is a group that values their opinions and divides consumption according to the place or atmosphere. Can be, but is not limited to the listed ones. In addition, in addition to the above-described categories, various categories may exist, and various classifiers may be used for each category.

The extraction unit 330 may extract reference data having a predetermined fitness level from pre-built big data based on the classified classifier. At this time, the pre-built big data is a response to at least one kind of survey from at least one user terminal 100 using a matching service including the user terminal 100, a social media or web page activity log, reality mining The data may be learned and constructed as a result of analyzing a combination of one or at least one of a terminal usage style through (Reality Mining) and a social media network. At this time, through the survey, information may be collected so that various aspects such as personality, disposition, lifestyle including dietary life, travel style, and dating style can be analyzed. In addition, personality analysis is not limited to any one type since various types of personality analysis systems have already been established. Interest can be analyzed by analyzing activity contents through social media, web pages or app pages. In this case, at least one type of mining technique included in data mining may be used.

Data mining is classification, which predicts a class of new data by learning a training data set with a known class by searching for an intrinsic relationship between preprocessed data, or clustering, which groups data based on similarity without class information. You can do it. Of course, there may be various other mining methods, and may be mined differently according to the type of big data to be collected and stored or the type of query to be requested later. Web mining, one of the various types, is an application of data mining technology to discover meaningful patterns, profiles, trends, etc. from web resources. All data obtained from the web is analyzed by applying existing data mining technology to the web. Take it. The target data may be server access log data, user registration information, user session, transaction, enterprise resource planning (ERP) data, etc., but is not limited thereto. It may include web structure mining, web content mining, and web usage mining.

Opinion mining, one of the various types, refers to a technology that analyzes users' opinions or ratings in a web document to derive a reputation for a subject. In other words, it is a technology that converts people's subjective opinions into objective information by statistic and quantifying them. It is also called emotional analysis because it analyzes not only people's opinions about an issue or person, but also emotions and attitudes. In addition, since opinion mining is also an analysis target of text, natural language processing methods used in text mining are used, and the main targets of analysis are large-scale web documents such as portal bulletin boards, blogs, and shopping malls. In the opinion mining process, feature extraction is performed to extract vocabulary information by classifying facts and opinions from text, preprocessing to extract meaningful morphemes from sentences of users uploaded to the web, and extracting vocabulary from the text. After judging and classifying what meaning was used, scores are assigned to each user's feelings about the product or service from the preprocessed data to quantify it, and summarize the analyzed information and deliver it to the user efficiently. By summarizing and expressing, finally, the user's reaction, the form of emotion shown to the service, and improvement points are extracted and made into meaningful data.

Reality mining refers to a method of extracting unstructured data from actions that a user uses every day to manipulate machines or motion sensors such as smartphones. The data to be collected in reality mining is communication data such as calls and messaging, and location data extracted by GPS/WIFI. Through this, it aims to mine social behavior and obtain user behavior modeling and life logs. When targeting individuals, individuals use mobile phones, tablets, laptops, cameras, and any device connected to the Internet for a variety of purposes, so they can produce data ranging from GPS locations to frequently asked questions on portal sites such as Google. have. Personal devices can collect a lot of data, but since this is part of an individual's life, in order to collect more data, more data may be obtained using a wearable device including a biometric device. In this case, it will be apparent that other types of data mining that are not mentioned in the above-described configuration are not excluded.

The pre-built big data collects user data of at least one user terminal 100 from at least one user terminal 100 using a matching service including the user terminal 100, and raw data including the collected user data (Raw Data) is stored in parallel and distributed, unstructured data, structured data, and semi-structured data contained in the stored raw data are refined, and pre-processing including classification as metadata is performed. It may be constructed by performing analysis, including data mining, of the preprocessed data, and classifying the preprocessed data based on at least one reference data based on the analyzed data.

Among the big data previously constructed in the present invention, social media or web page activity logs, terminal usage style through reality mining, contact style analysis, social media personal networks, etc. can be used to track changes in the user's ideal type. For example, if the characteristics of an acquaintance's account with active social media exchanges moves from a health and running account to a reading account, it can be seen that the recent user's interest has changed from exercise to reading. Specifically, it is possible to track changes in interest by analyzing YouTube's viewing time, likes, and subscribers, and by analyzing recent interest categories (health, running, beauty, electronic devices, travel), etc. You can also find out through'Like','Following', and'Hashtag' you use.

In addition, by analyzing accounts of opposite-sex celebrities, popular influencers, and general opposite-sex friends with many interactions among the people whom the user has made friends with through novel media, it is possible to grasp the preferred ideal type or style. Since the interests or ideals identified through the above big data can be automatically updated and stored as user data, changes can be identified without a separate user update.

In the present invention, big data is periodically updated, and the user's ideal type may also be changed according to changes in the user's social media activity, terminal use, and contact style with others.

The filtering unit 340 may extract at least one terminal to be matched 400 that is previously mapped and stored on the extracted reference data. In this case, the filtering does not simply filter by using the score or the degree of matching, but considers the ideal keyword of the matched terminal 400, which is the other party, so that both parties matched can be satisfied. For example, if a woman of type A wants a man of type B, but a man of type B does not want a type of A, only the doctor of type A woman is considered, and the match may be very unsatisfactory for type B men. have. Therefore, it is possible to perform filtering based on other reference data after first considering whether it is closest to the ideal type of both parties. Of course, it does not exclude a method of equally giving weights to each factor.

According to an embodiment of the present invention, the filtering unit 340 may filter a counterpart similar to the user data based on the propensity or personality data included in the user data, and filter to find an ideal counterpart by selecting a preset category. can do. That is, it is possible to directly receive inclination or personality data from the user, or to grasp the user's inclination or personality based on pre-built big data, and filter counterparts having similar personalities and inclinations through this, and provide it to the user. In addition, since the user may change his ideal type, the user may select a preset category and directly select the other person who is the ideal type.

According to an exemplary embodiment of the present invention, when extracting a counterpart similar to the user's personality and disposition, the filtering unit 340 may extract it by reflecting the purpose of the meeting. For example, when the purpose of meeting is divided into marriage, instant meeting, blind date, travel, etc., a person suitable for marriage, a person suitable for an instant meeting, a person suitable for a blind date, and a person suitable for travel may all be determined differently.

The transmission unit 350 may transmit the extracted list of at least one matched terminal 400 to the user terminal 100 as a matching list. In this case, the matching list may transmit the entire matched list, but only the counterparts with a preset number ranked higher may be provided by filtering and sorting based on a factor preferred by the user. Re-filtering may be performed as a person, and quantitative and qualitative analysis are provided together, so that only a person with a preset priority can be selected from among a plurality of matchees. Of course, it is obvious that the application of the results of quantitative or qualitative analysis is not excluded.

The sharing unit 360 transmits the list of at least one matched terminal 400 extracted from the transmission unit 350 to the user terminal 100 as a matching list, and then transmits the list of at least one matched terminal 400 to the user terminal 100 as a matching list. When receiving the transmission of the connection event to the matching terminal 400, the connection event is transmitted to the selected terminal to be matched 400, and when the consent of the terminal to be matched 400 is sent, the matching may be performed. In addition, when the location of the user terminal 100 and the selected matched terminal 400 is the same, the sharing unit 360 tracks and monitors the location of the user terminal 100 and the selected matched terminal 400 as log data. It can be updated in real time. In addition, the sharing unit 360 may overlay log data on a map with at least one acquaintance terminal of the user terminal 100 and the selected terminal 400 to share in real time.

The calculation unit 370 transmits the list of at least one matched terminal 400 extracted from the transmission unit 350 to the user terminal 100 as a matching list, and then transmits the list of the user terminal 100 and the at least one target terminal 400 to the user terminal 100. It is possible to receive mutual favorability between the matching terminals 400. In addition, the calculation unit 370 may calculate a matching compatibility that increases as the symmetry of mutual favorability increases, and gives a penalty so as to correspond to the favorability of an object with a low score as the asymmetry of the preference increases. . In addition, the calculation unit 370 may rearrange the at least one matched terminal 400 in the order of high matching suitability, and re-recommend a list with a high matching suitability to the user terminal 100. In this case, the matching suitability level In the following, an embodiment when the matching service of the present invention is extended to a travel service will be described in detail.

After the step of transmitting the list of at least one matched terminal 400 extracted by the transmission unit 350 to the user terminal 100 as a matching list, the relearning unit 380 When a connection event transmission to one matched terminal 400 is received, a connection event is transmitted to the selected matched terminal 400, and matching may be performed when an approval of the matched terminal 400 is sent. In addition, the relearning unit 380 may receive ratings and reviews for matching from the user terminal 100 and the selected terminal 400 to be matched. In addition, the relearning unit 380 may perform pre-processing by refining the received ratings and reviews, and measure satisfaction with matching using a sentiment analysis algorithm. Then, the relearning unit 380 may relearn a previously constructed matching algorithm based on the measured satisfaction level.

Hereinafter, an embodiment in which the matching service according to an embodiment of the present invention is used in the travel field will be described.

The travel management unit 390 may receive a response to a survey that is previously mapped to the selected travel style and stored by receiving a selection of one or at least one combination of at least one travel style from the user terminal 100. At this time, the pre-mapped and stored survey is a format for selecting any one or at least one combination of a plurality of images for determining the travel style, or any one or at least one combination of a plurality of keywords for determining the travel style. It may be made in the format, but is not limited to the listed ones.

At this time, the travel style may be a questionnaire to determine flight, accommodation, planning, consumption, transportation, meals, inclination, and the like, but is not limited to those listed. Whether the airline prefers direct flights even though it is expensive, whether you want to save money even if you make a stopover, is a good hotel or a guesthouse, etc., the plan is a thorough or unplanned style, and consumption is used by collecting public money. Whether it is better to do it or prefer Dutch Pay, whether to use the bus or subway, taxi, or rental, for meals, go to restaurants or go to any restaurant along the way, inclination quickly and quickly. Whether it is a style to get up early in the morning to digest the schedule, to eat breakfast and go out to work until late in the evening or to dawn, or to spend the travel expenses without lacking or to save and save money, travel photos You can check a variety of factors, such as a style that leaves as much as possible, a style that values travel experience and feeling, a style that is interested in art and culture, or whether you are not interested in artworks or are outsiders.

In addition, you can also identify travel styles by presenting at least one sentence and choosing it or not. For example, if there is a sentence stating that the user wants to allocate about one day for shopping, if the user selects this, the shopping tendency is increased by 1, and if not selected, the shopping tendency is left at the default value of 0. At least one sentence is, it doesn't matter if the food tastes good even if the service is not satisfactory, you don't need to go to the destination you've been to again, it's not bad to go on a trip with a group other than a trip, and the accommodation is 1 degree safe 2 It is also safe, if the security is not good, it is unsuitable for a travel destination, do not drink alcohol in places other than accommodation in a travel destination, I think it is dangerous to go around in the late evening abroad, I want to visit a museum in a travel destination, rather than a downtown area I like the wonderful scenery, travel is also the taste of going to spend money, I want to see more areas by saving the cost of the trip, if the schedule is not correct, it is not bad to go separately, it is not bad to spend time bargaining. It is possible to provide an intuitive interface and a questionnaire to the user rather than presenting an example, such as that the travel plan is completed in advance, so that users can get a high score in terms of convenience.

Of course, the format of the questionnaire survey does not exist only as described above. For example, it is also possible to present an image and select one. For adjectives, since each individual has different associations with words, it is possible to fill the gap between the associated image and the word by intuitively notifying them with images. To be there. For example, in the sentence of making a thorough plan, each person has different standards for the adjective thorough, and the image they think and the actual image are different from each other. In order to reduce such a gap, a keyword tag is attached to each image, and when an image is selected, the attached keyword tag may be included in the propensity keyword of the user terminal 100.

The travel management unit 390 selects any one or at least one combination of at least one travel destination from the user terminal 100 and collects the user's personal information through at least one third trust agency server (not shown). Can be verified. To go on a trip when two people who don't know each other meet for the first time is like leaving with a lot of risks. Moreover, if the identity of an unknown person elsewhere is not certain, the risk increases exponentially. Therefore, the travel management unit 390 requests confirmation of the user's information from at least one third trusting agency server in order to check whether the information input from the user terminal 100 is accurate, and compares and verifies the result. Also, it is possible to proceed in the form of receiving feedback only whether or not a match is made from a third trusting agency server. For example, if it is stated that there is no criminal record, but in fact, there is a criminal record, information cannot be collected from the matching service providing server 300, which is a private institution, due to the entry into force of the Personal Information Protection Act and the GDPR (General Data Protection Regulation). Therefore, by receiving only the correspondence from the relevant institution, it is possible to check whether the user has entered the correct information and register the user's identity information based only on the matched information, and ignore and not record the inconsistent information. In other words, information that has not been recorded through such a process may be stated as inconsistency in the reason that the information was not recorded so that others can know it. However, since personal information is protected under the Personal Information Protection Act, each institution must use it only for the scope and purpose approved by the individual. Therefore, do not disclose information that is not permitted by each individual.

When at least one of the previously stored keywords is selected, the travel management unit 390 searches for at least one matched terminal 400 filtered based on the keyword, sorts it in a list, and then the user terminal 100 ) Can be provided. At this time, the at least one keyword is outputting the keyword in the form of an icon, and it is also possible to provide only a keyword that is a text or an icon that symbolizes the keyword. In addition, the at least one keyword may include, for example, affinity, travel style, travel destination, travel budget, personality, and the like, but is not limited to those listed. Here, in the case of sorting after simple text analysis only with keywords, since there is a possibility that the data will be quantitatively analyzed and filtered, qualitative analysis by considering the user's priority or weighting based on the previously saved history log of social media. You can also do

For example, a social media site allows users to select Check-in when they arrive in a new area, recording this location information, information about the user's check-in in a specific area, and ratings or advice for that area. In the case of using personal opinions, such as, even if the user does not deliberately leave an opinion on the travel destination or does not receive a survey, the previously stored history log can be used to determine which priorities to consider in the future. Destination recommendation is not only providing simple information on a specific location, but also needs a user's interest in travel, the interests of people with whom he is traveling, or various information about a specific area. Such information can be extracted using a social context recognition technique and applied to a recommendation algorithm, making it possible to recommend personalized travel destinations that are more suitable for users. Therefore, in an embodiment of the present invention, by using social context perception to recommend or weight a travel destination according to a user's personal preference, other people visited a lot, that is, more preferred, even within the recommended travel destination. It can be used to recommend a place or to filter out the companions who respond to it.

To this end, the travel management unit 390 analyzes the social media content generated by the user, and in the case of an individual user, analyzes the influence within each group to extract the interests of the group. It can recommend a travel destination suitable for the user, and can be configured to recommend popular places that have been mentioned a lot to friends within the recommended travel destination. The most important part of the travel destination recommendation system is what social situation can be analyzed to provide personalized services to users. Among various social situations, the user's individual interests and the group's interests are extracted first. At this time, it is possible to construct an interest dictionary having a hierarchical structure by collecting travel destination data from a plurality of tourism information servers for interest analysis, and extracting lower words based on keywords related to travel destinations for each theme based on the data. Text mining techniques can be used to extract user interests, but the present invention is not limited thereto. Through the pre-processing process of the collected user's social media content, noun words that become keywords are extracted using the Hangul morpheme analyzer. After mapping the extracted word and the dictionary of interests, weights for each category may be derived through TF-IDF (Term Frequency-Inverse Document Frequency). For example, if the weight is set to a value between 0 and 1, the category with the maximum value becomes the user's interest. In addition, it is only necessary to consider individual interests to recommend a place for traveling alone, but if two or more members want to go on a trip together, a travel destination recommendation should be made that considers the interests of the group as a whole. The basic method for extracting the interests of a group is to extract the interests of individuals in the group first. After that, it is possible to determine the final group's interests based on the calculation of the influence of the members in the group. The influence of the members in the group means the weight of each member, and the weight can take into account the social situation of the members, and for example, analyze information on time, retweets, mentions, comments, and likes to recognize the social situation. can do. Each weight is reflected in an individual's interest and then standardized to represent a value between 0 and 1, and similar to the method of extracting an individual's interest, the category representing the highest value may be set as the interest of the group including the user. Of course, it will be apparent that it is not limited only to the above-described method, and that various methods can be used.

When receiving a companion event transmission from the user terminal 100 to at least one matched terminal 400, the travel management unit 390 transmits the companion event to the selected matched terminal 400, and the matched terminal 400 ) Can be matched once the approval is sent. In addition, the travel management unit 390 may further induce decision-making by showing the matching degree of the movement trajectory to each other by using the moving trajectory of the user and the companion. For example, a user has a tight plan and lives while moving quickly, but the companion responds to a survey that he is a planner when traveling, but in fact, it is assumed that he is a person who stays in one place for a long time and goes leisurely. In other words, the consequences that occur when the two meet and travel is obvious. Accordingly, in order to increase the accuracy of the questionnaire, assuming that the person does not see it objectively, it is possible to grasp the travel style by conveying the similarity of the movement trajectory, the area of interest, and the degree of correspondence between the two parties.

In addition, in an embodiment of the present invention, a common place of interest between the companion and the user may be provided in consideration of the companion. Since the companion and the user were selected through the above-described process, in the process of extracting the preferences of the user and the companion, the current and past trajectories of each of the user and the companion were extracted, the preferred places of the user and the companion were extracted, and then the user and the companion Create a list of the next visited places from the current place. Then, if the extracted preferred place of the user and the companion exists, the recommended place can be created by considering both the user and the companion's preferred place, which directly or indirectly reflects the preference, and the fitness of the movement trajectory is calculated numerically and graphed. It can be visualized and conveyed. If the common preferences of the user and the companion match, the preferences for each user's location may be combined, or when the common preferences of the user and the companion do not match, the user's location preference and the social media user's location preference may be combined. In order to extract the user's preference for a place, location information obtained by extracting the user's past trajectory information and the place where the user stayed from the past trajectory information is required. In order to recommend a place, the user's trajectory information is used to determine the place to which they have moved, the user's trajectory is used to determine the place to which they have moved in the past, and the time of stay and the time of travel are stored in synchronization, respectively, so that they can stay at any place for several hours. Let's figure out if it's gone and what's the trajectory of movement. Of course, it will be apparent that it is not limited only to the above-described method, and that various methods can be used.

When receiving a companion event transmission from the user terminal 100 to at least one matched terminal 400, the travel management unit 390 transmits the companion event to the selected matched terminal 400, and the matched terminal 400 If the consent of) is sent, after matching, travel destination information and travel style information of the user terminal 100 and the selected terminal 400 to be matched may be transmitted to at least one travel agency server 500. And, the travel management unit 390, when receiving at least one travel product quote that satisfies the travel destination information and travel style information from at least one travel agency server 500, the user terminal 100 and the selected matched terminal 400 ) To transmit at least one travel product estimate, and when selecting any one of the at least one travel product estimate from the user terminal 100 and the selected terminal 400, the selected travel product estimate It is possible to mediate between the provided travel agency server 500, the user terminal 100, and the selected terminal 400 to be matched. At this time, the travel agency server 500 may provide a list of quotations, or the travel agency server ( 500). To this end, keyword tagging and analysis on at least one travel product must be performed, and the tag and analysis result must be mapped and stored in advance with the travel product. Of course, it does not preclude analysis and matching in real time.

When receiving a companion event transmission from the user terminal 100 to at least one matched terminal 400, the travel management unit 390 transmits the companion event to the selected matched terminal 400, and the matched terminal 400 ) Is sent, after matching, if the location of the user terminal 100 and the selected matched terminal 400 is the same as the location of the travel destination, the location of the user terminal 100 and the selected matched terminal 400 is tracked and Monitoring can be updated in real time with log data. According to an embodiment of the present invention, even if the location of the user terminal 100 and the selected matched terminal 400 is not the same as the location of the travel destination, the location tracking and monitoring of the user terminal 100 and the selected matched terminal 400 are logged. Data can be updated in real time. In addition, the travel management unit 390 may overlay log data on a map with at least one acquaintance terminal (not shown) of the user terminal 100 and the selected terminal 400 to share in real time. If you travel with someone you don't know each other, the safety of that person is what your family worries most. If you don't know the background at all, even if you have done a background check on the system, it still cannot be ruled out that your family's heart is unstable. Therefore, by tracking the location of the user and the companion in real time with the acquaintance terminal of the acquaintance including the family and sharing in real time, the situation of the user and the companion can be known. The above embodiment related to location tracking is not limited to travel companions, and may be applied to matching for other purposes such as blind date other than travel and marriage meeting.

In addition, the travel management unit 390, when receiving a companion event transmission from the user terminal 100 to at least one matched terminal 400, transmits the companion event to the selected matched terminal 400, and When the consent of 400 is sent, after matching, the GPS tag is attached to at least one picture taken by the user terminal 100 and the selected terminal 400 in synchronization with time, and the GPS tag is pre-mapped and stored. You can attach an attraction tag. In addition, the travel management unit 390 overlays the attraction tag on the map, synchronizes and overlays at least one photo list and thumbnail mapped to the attraction tag with time, and the user terminal 100 and the selected terminal 400 to be matched. ), you can allow access to share maps. This is a good function when leaving memories as a record after a trip, but it can also be used to know what kind of picture was taken on the map in real time and where it is currently in combination with the travel management unit 390. In this case, even if the user and the companion are not contacted in real time, photos taken anywhere and anytime can be viewed on a map and the time is displayed, so it can be assured. The above photo embodiment is not limited to travel companions, and may be applied to other purposes such as blind date other than travel, marriage meeting, and the like.

The travel management unit 390 receives a selection of one or at least one combination of at least one travel style from the user terminal 100, and before receiving a response to a survey that is previously mapped to the selected travel style and stored, the user When a page for performing a personality test is provided to the terminal 100 and the personality test is performed in the user terminal 100, the result of the personality test may be mapped to the user terminal 100 and stored. In this case, the at least one pre-stored keyword may include a keyword corresponding to the personality test result. Accordingly, not only the travel style but also the personality acts as a filter to select the other person. However, the travel style should be the same or similar, but the personality is a little different. For example, an introvert might fit well with an extrovert, and an activist might fit well with a businessman. In other words, it does not mean that it is not always good to be the same, but it can be configured to select a personality that matches each other through an MBTI test that divides the personality. At this time, MBTI's test is rather long, so it can be tedious and the application is turned off while making a selection.This can be intuitively selected, or if existing test results exist, the user can be maximized by using them. You can set up your application in a way that doesn't bother you. The personality test embodiment is not limited to travel companionship, and may be applied to matching for other purposes such as blind date other than travel, marriage meeting, etc.

The travel management unit 390 receives a selection of one or at least one combination of at least one travel style from the user terminal 100, and before receiving a response to a survey that is previously mapped to the selected travel style and stored, the user The terminal 100 may receive permission to access the history log of social media. In addition, the travel management unit 390, when receiving permission from the user terminal 100, collects interest data through at least one kind of social media and web page channel in the background mode in the user terminal 100, The collected interest data may be extracted using text mining, and the interest data may be sorted by assigning a weight to the content generated by the event in the user terminal 100. In addition, the travel management unit 390 sorts in descending order based on popularity based on the frequency and number of check-in events previously mapped to geographic information included in the interest data, and geographic information sorted in descending order. May be stored to be mapped to the user terminal 100 and set to be included in the recommendation list list.

At this time, the semantic polarity information of the vocabulary is one of the important linguistic resources in the field of opinion mining.For example, the semantic polarity of the vocabulary can be determined using Point-wise Mutual Information (PMI) based on probability theory. I can. Although PMI is relatively simple, good results can be obtained. Through morpheme analysis by collecting articles written by users on social media, it is possible to grasp the user's thoughts on the contents with comments. Words, sentences or phrases that can reveal personality can be extracted and stored in a database, user opinions can be grasped at the sentence or phrase level, and words or keywords representing personality can be mapped and stored. When there is a personality-related keyword stored in the database using a morpheme analyzer, a sentence or phrase is extracted, and meaningful morphemes are extracted from the sentence, and the negative words are deducted and the positive words are given additional points, and the scores of the sentences are summed up. It is possible to grasp the user's perception or propensity for the content. After the personality or disposition is determined in this way, the personality or disposition identified in the background mode is reflected when selecting a keyword afterwards, so that the other person can be filtered. You can match the other person by matching similar personalities or dispositions, or by matching personalities or dispositions that are complementary to each other. At this time, when opinion mining, as a method of constructing linguistic resources, the meaning direction of adjectives is classified and constructed by using the relationship between adjectives and conjunctions, or linguistic resources can be constructed by using thesaurus and antonym information between words. In addition, a study based on statistical probability theory can be used, and a method that combines both can also be used.

When receiving a companion event transmission from the user terminal 100 to at least one matched terminal 400, the travel management unit 390 transmits the companion event to the selected matched terminal 400, and the matched terminal 400 After the match is sent when the consent of) is sent, ratings and reviews for matching may be received from the user terminal 100 and the selected terminal 400 to be matched after the trip ends. In addition, the travel management unit 390 performs pre-processing by refining the received ratings and reviews, and can measure satisfaction for matching using a sentiment analysis algorithm, and build a pre-process based on the measured satisfaction. The matched algorithm can be retrained. At the time of matching, I feel there is no error in the matching algorithm, but when I hear the opinions of the parties after going on a trip, an error may be found. Therefore, it is possible to ask for opinions on each of the users and companions, and to correct errors.

Emotional analysis is an analysis technique that extracts people's subjective attitudes or emotions based on text mining, one of the important fields of big data analysis. The sentiment analysis may be used to extract an emotional word from a review or comment of a previous matching result in order to match an individual with a counterpart. At this time, the emotion level of the extracted emotion word is analyzed using the previously constructed emotional photo, and the user's emotion toward the other party is analyzed and used for the next matching. By analyzing the level of emotion on the emotion word, you can recommend a suitable partner for the user next time by using a collaborative filtering method and a context-based technique together. As a preliminary step for emotional analysis, in the process of processing natural language, you need to go through the process of tagging parts of speech such as nouns, verbs, adjectives, etc. in sentences, and when tagging is completed, you can analyze and grasp the emotions of each part of speech. May include a process. The emotion analysis embodiment is not limited to travel companionship, and may be applied to matching for other purposes, such as a blind date other than travel, marriage meeting, and the like.

The travel management unit 390 selects any one or at least one combination of at least one travel destination from the user terminal 100, collects and verifies the user's personal information through at least one third trust agency server, The user terminal 100 and the at least one matched terminal 400 may receive mutual favorability. For example, A's likelihood of B is 30%, but if A-B is matched in a situation where B's likelihood of A is 100%, A's satisfaction may be relatively lower than that of B. In other words, it starts under the premise that matching satisfaction can be high only when the symmetry of the affinity of A-B is high. The travel management unit 390 may calculate a matching suitability that increases as the symmetry of mutual favorability increases, and the higher the asymmetry of favorability increases, a penalty is given to correspond to the favorability of an object with a low score. The at least one terminal to be matched 400 may be sorted in the highest order of, and a list having a high matching suitability may be recommended to the user terminal 100.

To this end, it is necessary to know the one-way profile favorability that the user has with the companion.For example, profile information such as age, occupation, education, and annual salary height, and preferred ideal type information for the same item can be input from the user terminal 100. In addition, it is possible to assign weights to profile items that the user considers important. After expressing the information of all users and companions in this way, the similarity of the distance between the user's ideal type and the other companion's actual profile is calculated. For example, in order to calculate the profile favorability that user A has with his companion B, the Euclidean distance between the user A's ideal type attribute and the actual profile may be calculated. However, before distance calculation, standardization may be performed to have a preset range for each attribute-specific unit, and the distance may be calculated by half-forming the weight set by the user for each attribute. Next, it is possible to calculate the likelihood that the user feels toward the companion, which is the other party, based on the probabilistic similarity of the entire distance distribution. The Euclidean distance represents the difference between the user A's ideal type and the actual companion B's profile, but with this value alone, it is not possible to know where the user's preference for companionship is located in the overall percentile. To this end, it is possible to calculate a relative position occupied by the Euclidean distance in the total distance distribution. It is assumed that the shorter the Euclidean distance, the relatively close the other party's profile to the ideal type of User A and thus has a high profile favorability. In this way, when the cumulative probability of the Euclidean distance is used in the distance distribution, the profile favorability can be calculated, and the mutual matching suitability can be calculated.

For example, you can consider the arithmetic mean of the profile preferences between each other. However, simply applying the arithmetic mean does not give mutual symmetric satisfaction, so if both sides are perfectly symmetric, the matching suitability and the arithmetic mean value are equally given. Differential penalties can be given so that it is close to the preference of the side. For example, suppose A likes B 20%, and B likes A 80%. The difference is a penalty of 60%. If both favorable feelings are completely symmetric, the values may be 1, and the more asymmetry is, the closer to 0. Of course, it will be apparent that the method of matching is not limited to the above-described method and may be various. The embodiment of the matching suitability is not limited to travel companionship, and may be applied to matching for other purposes, such as a blind date other than travel, marriage meeting, and the like.

Hereinafter, an operation process according to the configuration of the matching service providing server of FIG. 2 will be described in detail with reference to FIG. 3 as an example. However, it will be apparent that the embodiment is only one applied to the travel field among various embodiments of the present invention, and is not limited thereto.

Referring to FIG. 3A, (a) when receiving personal information from the user terminal 100, the matching service providing server 300 receives an error in personal information through a third trusting agency, and has been verified for identity. In the case of, register as a member. And, (b) by selecting various, simple and intuitive questions for each category in order to check the travel style, it is possible to cluster users in the travel style. In addition, when a travel destination and a keyword are selected as shown in (a) of FIG. 3B, at least one terminal to be matched 400 is filtered to correspond to the keyword so that the user terminal 100 selects it. At this time, the matching service providing server 300 transmits the companion application event to the matched terminal 400 selected by the user terminal 100, and (b) intermediaries the travel agency server 500 if there is a match between the expressions of intention. do.

As shown in (a) of FIG. 3C, the matching service providing server 300 overlays photos synchronized with time and location on the map in real time, while matching the companion and mediating the trip. It can be shared as, (b) After the trip is over, it is possible to create a travel book using the photos, locations, and maps recorded in the log, or retrain and retrain the matching algorithm through reviews. You can also learn.

Matters that are not described about the method of providing a matching service that connects people and people based on big data in FIGS. 2 and 3 are described above with respect to the method of providing a matching service that connects people and people based on big data through FIG. 1. Since the content is the same as the content or can be easily inferred from the described content, the following description will be omitted.

FIG. 4 is a diagram illustrating a process of transmitting and receiving data between components included in the system for providing a matching service for connecting a person to a person based on big data of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted/received between components will be described with reference to FIG. 4, but the present application is not limitedly interpreted as such an embodiment. It is obvious to those skilled in the art that the process of transmitting and receiving data may be changed.

Referring to FIG. 4, when the matching service providing server 300 receives travel agency registration and product registration from at least one travel agency server 500 (S4100), and receives a membership application from the user terminal 100 (S4200) , If the background check is completed and there is no error or inconsistency by performing the identification (S4300), the user is registered as a member. At this time, in the case of background check, it is also possible to do a background check only for the procedure for obtaining accompany, although all members are registered only if the other person seeks to accompany the other person.

In addition, the matching service providing server 300 analyzes and defines the user's travel style and classifies the user into a plurality of clusters using the result of response to the travel style survey from the user terminal 100 (S4410). And store it (S4500). In addition, when the user terminal 100 selects one or more keywords, the matching service providing server 300 allows the terminal to be matched 400 to be filtered based on this (S4700), and the result is transmitted to the user terminal. It transmits to (100) (S4710) to select a companion (S4720).

On the other hand, the matching service providing server 300 transmits an accompaniment event to the matched terminal 400 (S4730), and when a response of consent is fed back from the matched terminal 400 (S4740), the user terminal 100 and the Matching is transmitted to the matching terminal 400 (S4750), and travel style and keyword information of the user and companion is provided to the travel agency server 500 (S4800), and a travel estimate list is received from the travel agency server 500 (S4810). It is transmitted to the user terminal 100 and the terminal to be matched 400 (S4900).

The matching service providing server 300, when the user terminal 100 and the matched terminal 400 agree to one of the travel estimates from the travel estimate list (S4910), to proceed with the travel contract (S4920). In addition, in the case of a trip with a free tour product rather than a package tour, there are many cases where you do not know what to look for as a point in front of a similar-looking ruins or statue even if you do not find the way well or even if you have found the way. Therefore, it displays each building or attraction point based on AR, and automatically streams content with a guide voice based on GPS coordinates, so that users and companions can experience the trip in depth without getting lost and without a guide. I can.

The order between the above-described steps S4100 to S4920 is only an example and is not limited thereto. That is, the order of the above-described steps (S4100 to S4920) may be mutually changed, and some of the steps may be executed or deleted at the same time.

The matters that are not described about the method of providing a matching service for connecting people based on big data of FIG. 4 are described above with respect to the method of providing a matching service connecting people based on big data through FIGS. 1 to 3. Since the content is the same as the content or can be easily inferred from the described content, the following description will be omitted.

5 is a flowchart illustrating a method of providing a matching service for connecting people based on big data according to an embodiment of the present invention. 5, the matching service providing server receives user data transmitted for matching from a user terminal (S5100).

In addition, the matching service providing server analyzes the received user data and extracts a classifier and classifies it (S5200), and extracts reference data having a preset degree of suitability from pre-built big data based on the classifier (S5300). .

In addition, the matching service providing server extracts at least one matched terminal previously mapped to the extracted reference data and stored (S5400), and transmits the extracted list of at least one matched terminal to the user terminal as a matching list. (S5500).

The matters that are not described about the method of providing a matching service for connecting people and people based on big data of FIG. 5 are described above with respect to the method of providing a matching service for connecting people and people based on big data through FIGS. 1 to 4. Since the content is the same as the content or can be easily inferred from the described content, the following description will be omitted.

A method of providing a matching service for connecting a person to a person based on big data according to an embodiment described with reference to FIG. 5 is in the form of a recording medium including instructions executable by a computer such as an application executed by a computer or a program module. It can also be implemented as Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The method for providing a matching service for connecting people based on big data according to an embodiment of the present invention described above includes an application basically installed in a terminal (this may include a program included in a platform or an operating system basically installed in the terminal). Yes), and may be executed by an application (that is, a program) directly installed on the master terminal by a user through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method for providing a matching service for connecting people and people based on big data according to an embodiment of the present invention described above is implemented as an application (i.e., a program) that is basically installed on a terminal or directly installed by a user, and It can be recorded on a computer-readable recording medium, such as.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (17)

In the matching service providing method executed in the matching service providing server,
Receiving user data transmitted for matching from a user terminal;
Extracting at least one matched terminal having a predetermined fitness level with the user data from pre-established big data; And
Transmitting the extracted list of at least one matched terminal to the user terminal as a matching list;
A method of providing a matching service that connects people and people based on big data including a.
The method of claim 1,
Extracting at least one matched terminal having a predetermined fitness level with the user data from the previously established big data,
Analyzing the received user data and extracting and classifying a classifier;
Extracting reference data having a predetermined fitness level from pre-built big data based on the classified classifier; And
Extracting at least one matched terminal previously mapped and stored on the extracted reference data;
The method of providing a matching service that connects people and people based on big data, which is executed by performing.
The method of claim 1,
Extracting at least one matched terminal having a predetermined fitness level with the user data from the previously established big data,
Filtering a counterpart similar to the user data based on the propensity or personality data analyzed through the pre-built big data;
That includes, a method of providing a matching service for connecting people and people based on big data.
The method of claim 1,
Extracting at least one matched terminal having a predetermined fitness level with the user data from the previously established big data,
Filtering to find a partner who is an ideal type by selecting a preset category;
That includes, a method of providing a matching service for connecting people and people based on big data.
The method of claim 1,
The previously built big data,
Response to at least one kind of survey from at least one user terminal using the matching service including the user terminal, a social media or web page activity log, terminal usage style through reality mining, social media A method of providing a matching service for connecting people and people based on big data, which is data that is learned and built as a result of analyzing any one or at least one combination of social networks.
The method of claim 1,
The previously built big data,
Collecting user data of at least one user terminal from at least one user terminal using the matching service including the user terminal;
Storing raw data including the collected user data in parallel and distributed;
Refining unstructured data, structured data, and semi-structured data included in the stored raw data, and performing pre-processing including classification as metadata;
Performing an analysis including data mining on the preprocessed data;
Classifying based on at least one reference data based on the analyzed data;
The method of providing a matching service that connects people and people based on big data.
The method of claim 1,
After the step of transmitting the extracted list of at least one matched terminal to the user terminal as a matching list,
Transmitting a connection event to the selected terminal to be matched when receiving transmission of a connection event from the user terminal to the at least one terminal to be matched, and matching when approval of the terminal to be matched is sent;
Real-time updating of location tracking and monitoring of the user terminal and the selected terminal to be matched with log data after the matching;
Overlaying the log data on a map with at least one acquaintance terminal of the user terminal and the selected terminal to be matched and sharing the log data in real time;
The method of providing a matching service for connecting people and people based on big data that further comprises.
The method of claim 1,
After the step of transmitting the extracted list of at least one matched terminal to the user terminal as a matching list,
Receiving mutual favorability between the user terminal and at least one matched terminal;
Calculating a matching compatibility that increases as the symmetry of the mutual favorability increases, and gives a penalty so as to correspond to the favorability of an object with a low score as the asymmetry of the preference increases;
Rearranging the at least one matched terminal in the order of the highest matching suitability, and re-recommending the list with the high matching suitability to the user terminal;
The method of providing a matching service for connecting people and people based on big data that further comprises.
The method of claim 1,
Receiving user data transmitted for matching from the user terminal,
Providing a page for performing a personality test to the user terminal; And
When the personality test is performed in the user terminal, mapping and storing the result of the personality test with the user terminal;
A method of providing a matching service that connects people and people based on big data including a.
The method of claim 1,
Receiving user data transmitted for matching from the user terminal,
Receiving permission to access a history log of social media from the user terminal;
Collecting interest data through at least one type of social media and web page channel in a background mode in the user terminal when access is granted from the user terminal;
Extracting the collected interest data using text mining, and assigning weights to content generated events in the user terminal to sort and classify interest data;
That includes, a method of providing a matching service for connecting people and people based on big data.
The method of claim 1,
After the step of transmitting the extracted list of at least one matched terminal to the user terminal as a matching list,
Transmitting a connection event to the selected terminal to be matched when receiving transmission of a connection event from the user terminal to the at least one terminal to be matched, and matching when approval of the terminal to be matched is sent;
Receiving ratings and reviews for matching from the user terminal and the selected terminal to be matched;
Performing pre-processing by purifying the received ratings and reviews, and measuring a satisfaction level for matching using a sentiment analysis algorithm;
Retraining a previously constructed matching algorithm based on the measured satisfaction level;
The method of providing a matching service for connecting people and people based on big data that further comprises.
The method of claim 1,
Collecting and verifying the user's personal information through at least one third trust agency server;
The method of providing a matching service for connecting people and people based on big data that further comprises.
The method of claim 1,
After receiving user data transmitted for matching from the user terminal,
Any one or less of at least one travel style from the user terminal
Receiving a response to a survey that is previously mapped to the selected travel style and stored by selecting a combination of FIG. And
When at least one of the at least one pre-stored keyword is selected in the user terminal, searching for at least one matched terminal filtered based on the keyword, sorting it in a list-up, and providing it to the user terminal;
The method of providing a matching service for connecting people and people based on big data that further comprises.
The method of claim 13,
The previously mapped and stored questionnaire survey,
A format for selecting any one or at least one combination of a plurality of images for grasping the travel style, or a format for selecting any one or at least one combination of a plurality of keywords for grasping the travel style. A method of providing a matching service that connects data-driven people to people.
The method of claim 13,
When at least one of the pre-stored at least one keyword is selected in the user terminal, after the step of searching for at least one matched terminal filtered based on the keyword, sorting it in a list-up, and providing it to the user terminal on,
Transmitting a connection event to the selected terminal to be matched when receiving transmission of a connection event from the user terminal to the at least one terminal to be matched, and matching when approval of the terminal to be matched is sent;
Transmitting travel destination information and travel style information of the user terminal and the selected terminal to be matched to at least one travel agency server;
Transmitting at least one travel product quotation to the user terminal and the selected matched terminal when receiving at least one travel product quotation that satisfies the travel destination information and travel style information from the at least one travel agency server;
In the case of selecting any one of the at least one travel product quotation from the user terminal and the selected matched terminal, mediating between the travel agency server providing the selected travel product quotation, the user terminal and the selected matched terminal step;
The method of providing a matching service for connecting people and people based on big data that further comprises.
The method of claim 13,
When at least one of the pre-stored at least one keyword is selected in the user terminal, after the step of searching for at least one matched terminal filtered based on the keyword, sorting it in a list-up, and providing it to the user terminal on,
Transmitting a connection event to the selected terminal to be matched when receiving transmission of a connection event from the user terminal to the at least one terminal to be matched, and matching when approval of the terminal to be matched is sent;
Attaching a GPS tag to at least one picture taken by the user terminal and the selected terminal to be matched in synchronization with time, and attaching a pre-mapped and stored attraction tag to the GPS tag;
Overlaying the attraction tag on a map, and synchronizing and overlaying at least one photo list and thumbnail mapped to the attraction tag with time;
Allowing access to share the map at the user terminal and the selected terminal to be matched;
The method of providing a matching service for connecting people and people based on big data that further comprises.
In the method of providing an application that operates in conjunction with a matching service providing server that executes the matching service providing method,
The application providing method, characterized in that the matching service providing server implements the method according to any one of claims 1 to 17.

Images