KR102128043B1 - Platform system for recommendating personalized living athletics - Google Patents

Abstract

According to one embodiment of the present invention, a platform system for recommending personalized sports for all comprises: a user terminal providing personal data including user information, body information, and interest information; and an information provision server collecting the personal data, crawling a plurality of pieces of public data from a linked server, and providing a personalized and customized game of sports for all and information on facilities for sports for all based on a region to the user terminal through a machine learning and recommendation algorithm previously set based on the personal data and the public data.

Description

Personalized life sports recommendation platform system{PLATFORM SYSTEM FOR RECOMMENDATING PERSONALIZED LIVING ATHLETICS}

The present invention collects and analyzes personal data of various aspects such as an individual's age, occupation, gender, region, economic conditions and physical condition, and interests and preferences, and recommends personalized and optimal sports and regional-based living sports facilities It is about a personalized life sports recommendation platform system that can be done.

Modern people are reducing the need for exercise and physical education for various purposes such as maintaining and promoting health, using leisure, hobbies, and careers, but it is difficult to secure the continuity of exercise by selecting items that do not fit their living environment and personal characteristics.

Some personalized exercise design and sports recommendation services exist, but they are limited to using limited data based on body or some biometric data.

Accordingly, there is a need to develop a platform that provides an optimal recommendation service considering various aspects of personal lifestyle.

Registered Patent Publication No. 10-1677749 (Name of invention: Recommended service method considering personal preferences and recommended service server therefor)

The problem to be solved by the present invention is to provide a personalized life sports recommendation platform system that can solve the conventional problems.

The personalized life sports recommendation platform system according to an embodiment of the present invention for solving the above problems includes a user terminal that provides personal data including user information, body information, and interest information; And collecting personal data, crawling a plurality of public data from a linked server, and personalizing customized personalized physical education events and local-based living sports facilities through preset machine learning and recommendation algorithms based on the personal data and public data. And an information providing server providing information to the user terminal.

The information providing server includes a first information collection unit that collects public data, sports facility information, and sports information of the latest trend through data crawling; A second information collecting unit that collects and stores user information, body information, interest information, sports trends, and facility information; An information processing unit that identifies or de-identifies data collected or stored by the first information collection unit and the second information collection unit using a preset data modeling method; An information mapping unit mapping user information to data collected or stored by the first information collection unit and the second information collection unit; An information analysis recommendation unit that analyzes and extracts personalized personalized personalized sports items and region-based living sports facility information through preset machine learning and recommendation algorithms based on the mapped data; An information providing unit that visualizes and provides the personalized, sports-specific or regionalized information of the analyzed and extracted information; And a control unit controlling the operation of each component constituting the information providing server.

The first information collection unit analyzes after crawling and storing each information from the public data providing website, the facility information providing website for each industry, and the physical education and national fitness data providing website.

The first information collection unit collects data through crawling of SNS and portal sites by keyword of the sports facility's name, address, latitude and longitude, event, equipment name, and program.

The user information includes body information (height, weight, waist circumference, body mass index, vision, hearing), health information (heart, blood vessels, kidneys, diabetes, blood pressure, liver, smoking, drinking), life information (age, gender, occupation , Annual income, place of work, average working hours), exercise motivation information (appearance, health, illness, social relationship, business, fun, career), and experience information (life sports, subscription facility name, duration, reason for discontinuation).

The information analysis recommendation unit collects user's body and biometric information through a preset machine learning algorithm, calculates similarity between users, and forms NN (Nearest Neighborhood) to predict preferences for sports, sports, and facilities. Also, user or facility information corresponding to similar groups is also recommended.

Although the preferred embodiments of the present invention have been described above, those skilled in the art can variously modify and change the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. Will be able to understand.

Accordingly, according to the personalized life sports recommendation platform system according to an embodiment of the present invention, personal data of various aspects such as age, occupation, gender, region, economic condition and physical condition, and interests and preferences of an individual are collected. By analyzing it, we can recommend personalized and customized optimal sports and regional-based living sports facilities.

According to an embodiment of the present invention, through analysis of personal body/biometric information from data through crawling of public data and private data such as public data portals, Korea Sports Development Institute, National Physical Fitness 100, life sports information portals, etc., through machine learning. It can provide a more effective and sustainable platform for living sports and facilities recommendation.

1 is a block diagram of a personalized life sports recommendation platform system according to an embodiment of the present invention.
2 is a block diagram showing the configuration of the information providing server shown in FIG. 1.
3 is a view showing the overall operation of the information providing server shown in FIG.
FIG. 4 is a view showing a data source and a collection process of the information providing server shown in FIG. 1.
5 is a diagram showing a user-based recommendation process by the information providing server shown in FIG. 1.
FIG. 6A is a screen showing an example of a user analysis service by the information providing server shown in FIG. 1.
FIG. 6B is a screen showing an example of a service for recommending living sports by the information providing server shown in FIG. 1.
7 is a screen illustrating an example of a user evaluation and review screen displayed on a user terminal for a personalized life sports recommendation platform system according to an embodiment of the present invention.
8 is a diagram illustrating an example computing environment in which one or more embodiments disclosed herein can be implemented.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains may easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with other elements in between. . Also, when a part is said to "include" a certain component, it means that the component may further include other components, not exclude other components, unless specifically stated otherwise. However, it should be understood that the existence or addition possibilities of numbers, steps, actions, components, parts or combinations thereof are not excluded in advance.

The terms "about", "substantially", and the like used throughout the specification are used in or at a value close to that value when manufacturing and material tolerances specific to the stated meaning are given, and the understanding of the invention To help, accurate or absolute figures are used to prevent unconscionable abusers from unduly using the disclosed disclosure. The term "~(step)" or "step of" as used in the entire specification of the present invention 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 by using both. Further, one unit may be realized by using two or more hardware, and two or more units may be realized by one hardware.

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

In this specification, some of the operations or functions described as mapping or matching with the terminal means that the terminal's identification number or personal identification information, which is the identification data of the terminal, is mapped or matched. Can be interpreted as

1 is a block diagram of a personalized life sports recommendation platform system according to an embodiment of the present invention, FIG. 2 is a block diagram showing the configuration of the information providing server shown in FIG. 1, and FIG. 3 is shown in FIG. FIG. 4 is a view showing the overall operation of the information providing server, and FIG. 4 is a view showing a data source and a collection process of the information providing server shown in FIG. 1, and FIG. 5 is a user-based recommendation process by the information providing server shown in FIG. 1 FIG. 6A is a screen showing an example of a user analysis service by the information providing server shown in FIG. 1, and FIG. 6B is an example of a service for recommending life sports by the information providing server shown in FIG. 1 7 is a screen showing an example of a user evaluation and review screen displayed on a user terminal for a personalized life sports recommendation platform system according to an embodiment of the present invention, and FIG. 8 is one or more implementations disclosed herein. A diagram illustrating an example computing environment in which an example can be implemented.

As shown in FIG. 1, the personalized life sports recommendation platform system according to an embodiment of the present invention includes personal data (Personal) of various aspects such as an individual's age, occupation, gender, region, economic conditions and physical conditions, and interests and preferences. Data) is a machine learning-based intelligent life sports knowledge information platform system that collects and analyzes and recommends personalized and optimal personalized items and regional-based life sports facilities, and includes a user terminal 100 and an information providing server. Here, the user terminal 100 and the information providing server 200 may be interconnected through a wired/wireless network.

Through this, the personalized life sports recommendation platform system according to an embodiment of the present invention analyzes personal body/biometric information from data through crawling of public data and private data, thereby more effective and sustainable life sports through machine learning and Facilities will be recommended.

The user terminal 100 is a user who has or uses the user terminal 100 (or a customer) through the input module (for example, a touch screen, a microphone, etc.), requests for searching for physical education and facilities, user information, and body information , Receives interest information, transmits a request for a request to search for a physical education and facility corresponding to a request for searching for physical education and facilities to the information providing server 200, and outputs information on a physical education and facility provided by the information providing server 200 It can be provided to the user through a module (eg, a display).

The user terminal 100 is a telephone terminal, a terminal, a mobile station (MS), a mobile subscriber station (MSS), a subscriber station (SS), an advanced mobile station (AMS), a wireless terminal (WT), a machine (MTC) -Type Communication) device, M2M (Machine-to-Machine) device, D2D device (Device-to-Device) device.

However, this is only an example, of course, and the user terminal 100 in the present invention should be interpreted as a concept including all devices that are currently developed and commercialized in addition to the above-described examples or capable of data transmission to be developed in the future.

When the user terminal 100 is implemented as a smartphone, the user's location information is acquired through a GPS positioning system, a WiFi positioning system, a cellular positioning system, or a beacon positioning system embedded in the smartphone, The user's activity information can be obtained through the gyro module embedded in the smartphone. The acquired user's location information and/or activity information may be used to recommend life sports and facility information from the information providing server 200. Alternatively, when the user terminal 100 is implemented as a desktop, the user terminal 100 is interlocked with a device worn by the user (eg, a smart phone, a pedometer, etc.), and the user's location information and/or activity Information can be obtained.

In addition, the user terminal 100 includes an interface unit that serves as a passage with an external device connected to the user terminal 100. The interface unit receives data and/or information from an external device or receives power and delivers it to components inside the user terminal 100, transmits data and/or information inside the user terminal 100 to an external device, or internally Can supply power.

The interface unit connects devices equipped with, for example, a wired/wireless headset port, a charging port, a wired/wireless data port, a memory card port, a universal serial bus (USB) port, and an identification module. Port, an audio input/output (I/O) port, and a video input/output (I/O) port.

In other words, the user terminal 100 means an apparatus capable of transmitting and receiving communication signals including user information, body information, interest information, life sports, and facility information in one embodiment of the present invention.

At this time, the user terminal 100 may be pre-installed with one or more applications (Application), in particular, applications that provide services for displaying physical education and facility information, or application programs related to the above services (Application Program) Interface: API), embedded software, or an application including a software development kit (SDK) may be pre-installed for the implementation of the present invention.

The user terminal 100 is a data or signal that the user terminal 100 includes user information, body information, interest information, life sports, and facility information in the information providing server 200 by itself or through the installed one or more applications. You can send or receive.

The user information includes the user's body information, health information, life information, exercise motivation information, and experience information.

Here, the body information may include at least one of kidney information, weight information, waist circumference information, body mass index information, vision information, and hearing information, and health information includes heart rate information, blood vessel information, kidney information, and diabetes information. , Blood pressure information, soy information, smoking information, and alcohol information.

Further, the living information may include at least one of age information, gender information, job information, annual income information, work place information, and average working time information, and exercise motivation information includes appearance information, health information, disease information, and social relationship information. , May include at least one of business information, fun information, and career information, and experience information may include at least one of information on sporting events, name of subscription facility, duration information, and reason for discontinuation.

The information providing server 200 may analyze the big data (personal data and public data) associated with the user and provide the user terminal 100 with life sports items and facility information suitable for the user.

More specifically, the information providing server 200 collects personal data, crawls a plurality of public data from a linked server, and personalizes personalized life through preset machine learning and recommendation algorithms based on personal data and public data. The user terminal 100 provides information on sports events and local-based living sports facilities.

The information providing server 200 calculates the characteristics and preferences of the user based on user information (eg, location information) and personal data that are pre-stored or provided from the user terminal 100, and the characteristics and preferences of the user It is possible to determine, as recommendation information, information on living sports and local-based living sports facilities that are matched with. In addition, the information providing server 200 may provide information on a local physical education facility along with information on a physical education event.

Further, the information providing server 200 may separately store personal data and public data received from the user terminal 100 or an associated server in an internal or external memory.

The information providing server 200 may be implemented as a server or program that analyzes a user's characteristics or preferences based on user information (eg, user's location information, etc.).

As described above, the information providing server 200 may provide/recommend user-specified lifestyle sports information by selecting/determining lifestyle sports by calculating the characteristics and preferences of the user. In addition, the information providing server 200 may provide personalized information to various types of users by providing facility information capable of life sports along with information on sport events.

In one embodiment of the present invention, the information providing server 200 refers to an object capable of transmitting and receiving data through a wireless communication network, and may include an association server, an association server, and/or a client server in the present invention.

In addition, as an example of the information providing server 200 in one embodiment of the present invention, cloud (Cloud) server, IMS (IP Multimedia Subsystem) server, Telephony Application (Telephony Application) server, IM (Instant Messaging) server, MGCF (Media Gateway Control Function) server, MSG (Messaging Gateway) server, may include a CSCF (Call Session Control Function) server, the information providing server 200 is a PC (Personal Computer), notebook computer, tablet PC (Tablet) Personal Computer).

On the other hand, in one embodiment of the present invention, the network means a wireless data communication network for transmitting and receiving data such as text (Text), digital images, digital images between the user terminal 100 and the information providing server 200, the There is no particular limitation on the type.

For example, it may be a wireless communication system that provides a data transmission/reception service through a wireless communication network. Alternatively, an Internet Protocol (IP) network that provides a large data transmission/reception service through an Internet protocol (IP) or each other It may be an All IP network incorporating other IP networks.

In addition, the network includes a mobile communication network including a Wibro (Wireless Broadband) network, a mobile communication network including WCDMA, a High Speed Downlink Packet Access (HSDPA) network, and a Long Term Evolution (LTE) network, LTE advanced (LTE-A). It may be one of a mobile communication network, a satellite communication network, and a Wi-Fi network (Wi-Fi).

In addition, as illustrated in FIG. 3, the information providing server 200 may be provided in a platform form through a collection step, a loading step, a processing step, a search step, an analysis step, and an application step.

The collecting step is a step of collecting sports facility information through the public data API and collecting the latest trend sports information through SNS and portal crawling.

The loading step is a step of storing an individual's emotion, life, body, living body, interest information, sports trend, and facility information, processing large-capacity/real-time data, and storing in the form of a distributed file system.

The processing step is a step of performing natural language processing and structured, semi-structured, and unstructured data modeling, personal information-related non-identification processing, data selection, conversion, integration, and reduction processing.

The search step is a step of mapping customer information, defining interactive data, and performing exploratory ad-hoc analysis.

The analysis step is a step of recommending a daily sports event through a machine learning and recommendation algorithm, and constructing a big data mart to perform statistical analysis and advanced analysis.

The application step is a step of developing visualization engines such as personalized, sports-specific, and regional-specific, and providing analysis information to users through reports and visualizations.

In addition, the information providing server 200, as shown in Figure 4, data from various data sources (for example, public data portal, Korea Sports Development Institute, national fitness 100 analysis / life sports information portal, private data, etc.) You can collect it and use it in the following process.

1) Health examination result analysis, national fitness status analysis, national fitness 100 analysis, national fitness status analysis

2) Feasibility study, analysis of participation in daily sports, analysis of daily sports information, data crawling

3) Weight definition, analysis data and data set, data analysis, recommendation of life sports and facilities, data visualization

Through this, the information providing server 200 has a user perspective (big data and machine learning based personalized recommendation, effective and sustainable living sports and facility use), and a facility/institution point of view (increased utilization of local facilities according to customer attraction, It can be used in stable operation by securing a loyal user).

On the other hand, the information providing server 200 collects health examination information (height/weight/blood pressure/blood sugar, etc.) from public data, that is, public data portal (data.go.kr), or is authorized/permitted by local governments. Various sports facility information is collected from the data development portal for each industry (localdata.kr), or personal exercise program data (blood pressure, physical activity questionnaire, body fat index, body mass index, muscle strength, Muscle endurance, cardiorespiratory endurance, flexibility, agility, wits, coordination, etc.)/College and trend data collected from life sports information portals (life sports news, member organizations, sports events, sports facilities information, sports clubs, school sports facilities) It will be analyzed after loading through open support, competition introduction, lessons, clubs, daily sports, trends, etc./ through purification (excluding missing data) and processing (non-identification processing) of health checkup information data.

In addition, the information providing server 200 analyzes data through SNS and portal crawls using private data analysis, that is, the name, address, latitude, event, and program of a sports facility as keywords, or the name, address, and address when registering standard information for sports facilities. Data analysis is performed through crawling through SNS and portals (crawling data is subject to text mining such as affiliation analysis and positive/negative) using keywords such as latitude, longitude, and equipment name.

In addition, the information providing server 200 is personal data from the user terminal, that is, body information (height, weight, waist circumference, body mass index, chills, hearing), health information (heart, blood vessels, kidneys, diabetes, blood pressure, liver, Smoking, drinking), life information (age, gender, job, annual income, place of work, average working hours), motivation for exercise (appearance, health, illness, social relationship, business, fun, career), experience information (life sports events, upon enrollment) Description, duration, and reason for interruption) are collected and used for analysis using a web collection tool.

In addition, the information providing server 200 collects and analyzes information on life sports trends, fashion events/programs, issue events/programs, and review information on local facilities on the portal site.

In addition, the information providing server 200 is a living sports item and facility recommendation algorithm, and various machine learning algorithms (user-based recommendation (user body/biometric information collection, similarity calculation between users, formation of Nearest Neighborhood, preference prediction, exercise recommendation) ), Item-Based or User-Based to recommend similar users or similar sports facilities, Contents-Based method to recommend items and facilities with similar characteristics, multiple machine learning Ensemble methods using algorithms, YouTube's latest algorithms that precisely analyze content characteristics, etc. can also be applied.

More specifically, as shown in FIG. 2, the information providing server 200 includes a first information collecting unit 210, a second information collecting unit 220, an information processing unit 230, and an information mapping unit 240. , An information analysis recommendation unit 250, an information providing unit 260, and a control unit 270.

Although not shown, basically, the information providing server 200 further includes a communication unit, receiving user information and personal data from the user terminal 100, and recommending life sports and facility information to the user terminal 100 Transmit, and receive public data from an associated server (not shown). For example, the communication unit may be implemented as a communication module using a wired or wireless communication method.

The first information collecting unit 210 collects public data, sports facility information, and sports information of the latest trend through data crawling.

The first information collection unit 210 analyzes after crawling and storing each information from a public data providing website, a facility information providing website for each industry, and a physical education and national fitness data providing website.

The first information collecting unit 210 collects data through crawling of SNS and portal sites using keywords of sports facilities such as trade name, address, latitude, longitude, event, equipment name, and program.

The first information collecting unit 210 may collect user information and personal data. Here, the user information includes user basic information such as the user's ID, name, gender, age, address, sports trend and facility information, user's location information (eg, user's location information, etc.), user's activity information ( For example, it may include additional user information such as life sports interest information.

The first information collecting unit 210 is the basic public data-related basic data, that is, meta information on public data provided by various public institutions, Open API utilization log, search keyword information, usage log, and final public data selected through search It may include log data including a path log (search path log) to.

In addition, the first information collecting unit 210 may include user information (eg, age, residence area, gender, etc.) as basic data. The basic data received through the first information collecting unit may be used as learning data for machine learning.

In addition, the first information collecting unit 210 may collect log data of each of a plurality of open sites in an Open API manner to increase the accuracy of machine learning. Also, the first information collection unit may collect sports issue information or trend information (issue/trend information) generated by a person in charge of the open site. In addition, the first information collecting unit verifies the hit ratio of the recommendation data (that is, recommendation public data, recommendation related keywords) provided by the linked server and reflects the recommendation hit log back to the recommendation process for calculating the recommendation data It may include.

The second information collecting unit 220 collects and stores user information, body information, interest information, sports trends, and facility information.

The information processing unit 230 identifies or de-identifies data collected or stored by the first information collection unit and the second information collection unit using a preset data modeling method. In addition, prior to calculating the recommendation data, the information processing unit 230 may first record (or load) the basic data in the recommendation data mart (Data Mart, DM) through the recommendation DM process to calculate the recommendation data. .

At this time, the recommended data mart may include a preference DM considering the preference score based on the preference calculation condition for the basic data. In addition, the recommended data mart may include an associated DM considering the associated score based on the keyword-based association for each public data based on the preferred DM. In addition, the recommended data mart may include a trend DM based on a preference DM, considering a score of interest based on keywords and/or public data information described through issue management or trend management. That is, as an example, the recommended data mart may be configured to include at least one of a preferred DM, an associated DM, and a trend DM. Based on this, the generation unit 220 includes a preferred DM, an associated DM, and a trend DM. The basic data 330 may be recorded in the recommended data mart in consideration of the properties of the recommended data mart. Here, in the DM, the public data to which the preference score has been assigned may be recorded by generating aggregated data for each viewpoint (that is, according to the preset preference calculation condition) for giving the preference score, and a more detailed description will be described later. do. In addition, the basic data may be stored in a recommended data mart as a data set.

The information mapping unit 240 maps user information to data collected or stored by the first information collecting unit and the second information collecting unit.

The information analysis recommendation unit 250 analyzes and extracts personalized personalized sports events and region-based living sports facility information through preset machine learning and recommendation algorithms based on data mapped by the information mapping unit 240. do.

The information analysis recommendation unit 250 collects user body and biometric information through a preset machine learning algorithm, calculates similarity between users, and forms a neighborhood of NN to predict preferences for sports and facilities for living. Therefore, each information is recommended, and user or facility information corresponding to each similar group is also recommended.

In addition, the information analysis recommendation unit 250 may calculate a user's preference based on the user information.

In one embodiment, the information analysis recommendation unit 250 may calculate a user's preference based on the preference survey result (or survey result information) and life sports history information.

In one embodiment, the information analysis recommendation unit 250 is applied to a cloud service-based artificial intelligence technology. As an example, Azure Machine Learning is a service that can be conveniently and efficiently utilized through Azure, an MS cloud platform that is a cloud-based data prediction analysis service released by Microsoft. Users can predict future trends and apply them to real problems through the latest analysis system of Azure Machine Learning and high-speed processed data. Specifically, an intuitive and simplified web service construction process, analysis model update support through API (application programming interface, language or message format used for communication between the operating system and application programs), Python and R support, and Terra Realize'big learning' through efficient classification and analysis support of byte-level data. It can be recommended for fashion or events that change frequently.

In addition, BlueMig Platform for a Service (PaaS) cloud technology for developer's convenience, services such as Facebook and Naver typically require B2C services to handle a large number of users, but for detailed adjustment of complex architecture to process big data It was advantageous to run the infrastructure in person, but the point is that mobile app development requires a platform that can be started and managed quickly with a small number of people. Among them, services like IBM's PaaS can be easily developed with simple configuration on the web. Management and construction became possible. Also, like Bluemix, it can be developed through more than 140 open APIs, and Bluemix is a platform suitable for small and large startup projects.

In addition, the search engine searches for data stored in the database based on personal data and public data, and recommends customized products to the user. As a search engine, Splunk Enterprise is a software platform that can search, analyze and visualize Machine-DATA generated from various event sources such as websites, applications, sensors, and devices. In addition, Big Query is Google's solution platform for big data analysis.It can analyze and visualize TB-sized data in a short time using Hadoop, an open source data analysis tool. Data analysis technology is based on Google's search engine, which can instantly search websites around the world.

In addition, Elastic Search is one of the big data search engines and supports RESTFul API (Representative State Transfer, matching http's routing and CRUD (create read update delete)), excellent search function and easy scale It is a powerful distributed system capable of out (increasing processing power by increasing the number of connected servers).

Elastic Search is based on the Apache Lucene (a high-performance text search engine library written in Java) that can be executed without any additional configuration in the Java environment, and can input, delete, and search data through the RESTFul API. It provides a library of Java, PHP, Perl, JavaScript, Python, Ruby, etc., and also supports plug-in installation to easily extend the functionality. The search engine according to an embodiment of the present invention uses the NoSQL Elastic Search Engine as a big data searching engine.

The information analysis recommendation unit 250 calculates recommendation scores including preference scores, related scores, and interest scores for public data included in the basic data based on the data mapped by the information mapping unit 240. can do.

In addition, the information analysis recommendation unit 250 may generate a recommendation list (ie, recommendation data list, recommendation keyword association list) based on the calculated recommendation score. Specifically, the information analysis recommendation unit may generate a recommendation data list related to recommended public data by performing a recommendation process. Here, the recommended data list can be expressed differently because it is a recommended public data list.

In addition, the information analysis recommendation unit 250 may generate a recommendation related keyword related recommendation keyword association list by performing a keyword grouping process based on data mapped by the information mapping unit 240. At this time, the information analysis recommendation unit 250 is based on the recommended score including the preferred score, the associated score and the score of interest, and collaborative filtering (Collaborative Filtering, CF) based Pearson correlation (Pearson Correlation) machine learning As a recommendation list, a recommendation data list and/or a recommendation keyword association list can be generated.

The information analysis recommendation unit 250 may calculate a recommendation score including a preference score considering preset preference calculation conditions for personal data and public data included in data mapped by the information mapping unit 240. have. Here, the preset condition for calculating preferences is a classification system (or category) in an open site that provides public data, the number of views of public data (that is, the number of views of the data set), and the number of public data downloads (that is, the data set). Number of downloads), OpenDate of public data, and Grade Average of public data.

6A and 6B, the information providing unit 260 visualizes and analyzes information extracted and analyzed by the information analysis recommendation unit for each individual, sports, or region.

In an embodiment of the present invention, as shown in FIG. 7, a preset question form may be presented to a user, and an answer to the question form may be provided as user information. To this end, a user analysis screen, user average satisfaction by fitness level, recommendation satisfaction, occupancy by star rating, view of user reviews of other facilities, and registration of my review can be provided.

The control unit 270 is a device that controls the operation of each component constituting the information providing server 200, and analyzes big data (personal data and public data) associated with a user, and is suitable for a user's physical education sports and facilities Built-in driving program, machine learning and recommendation algorithm to extract information.

8 is an illustration of an example computing environment in which one or more embodiments disclosed herein can be implemented, an example of a system 1000 including a computing device 1100 configured to implement one or more of the embodiments described above. It shows. For example, computing device 1100 may be a personal computer, server computer, handheld or laptop device, mobile device (mobile phone, PDA, media player, etc.), multiprocessor system, consumer electronics, mini computer, mainframe computer, Distributed computing environments including any of the aforementioned systems or devices, and the like, but is not limited thereto.

Computing device 1100 may include at least one processing unit 1110 and memory 1120. Here, the processing unit 1110 may include, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor, an application specific integrated circuit (ASIC), or field programmable gate arrays (FPGA). And may have multiple cores.

The memory 1120 may be volatile memory (eg, RAM, etc.), non-volatile memory (eg, ROM, flash memory, etc.) or a combination thereof. Further, the computing device 1100 may include additional storage 1130. The storage 1130 includes, but is not limited to, magnetic storage, optical storage, and the like. Computer-readable instructions for implementing one or more embodiments disclosed herein may be stored in the storage 1130, and other computer-readable instructions for implementing an operating system, application programs, and the like may also be stored. Computer readable instructions stored in storage 1130 may be loaded into memory 1120 for execution by processing unit 1110. Further, the computing device 1100 may include an input device(s) 1140 and an output device(s) 1150.

Here, the input device(s) 1140 may include, for example, a keyboard, mouse, pen, voice input device, touch input device, infrared camera, video input device, or any other input device. Further, the output device(s) 1150 may include, for example, one or more displays, speakers, printers, or any other output device. Also, the computing device 1100 may use an input device or output device provided in another computing device as the input device(s) 1140 or the output device(s) 1150. In addition, the computing device 1100 can include a communication connection(s) 1160 that enables the computing device 1100 to communicate with other devices (eg, the computing device 1300 ).

Here, the communication connection(s) 1160 may be a modem, network interface card (NIC), integrated network interface, radio frequency transmitter/receiver, infrared port, USB connection, or other for connecting the computing device 1100 to another computing device. Interface. Further, the communication connection(s) 1160 may include a wired connection or a wireless connection. Each component of the above-described computing device 1100 may be connected by various interconnections such as a bus (eg, peripheral component interconnection (PCI), USB, firmware (IEEE 1394), optical bus structure, etc.) Or may be interconnected by the network 1200. As used herein, terms such as "component", "system", and the like generally refer to a computer-related entity that is hardware, a combination of hardware and software, software, or running software.

The present invention is not limited by the above-described embodiments and the accompanying drawings. For those skilled in the art to which the present invention pertains, it will be apparent that components according to the present invention can be substituted, modified and changed without departing from the technical spirit of the present invention.

100: user terminal 200: information providing server
210: first information collection unit 220: second information collection unit
230: information processing unit 240: information mapping unit
250: Information analysis recommendation unit 260: Information provision unit
270: control unit

Claims (6)

As a recommendation to the user for the optimal daily life sports and regional-based life sports facilities,
A user terminal providing personal data including user information, body information, and interest information; And
Collect personal data, crawl a plurality of public data from a linked server, and personalize customized personalized physical education events and community-based living sports facility information through preset machine learning and recommendation algorithms based on the personal data and public data An information providing server providing a ranking to the user terminal, calculating a user's characteristics and preferences, and providing information on life sports and local sports facilities that match the user's characteristics and preferences;
Personalized life sports recommendation platform system comprising a.
According to claim 1,
The information providing server
A first information collection unit that collects public data, sports facility information, and sports information of the latest trend through data crawling;
A second information collection unit for collecting and distributing user information, body information, interest information, sports trends, and facility information;
An information processing unit that identifies or de-identifies data collected or stored by the first information collection unit and the second information collection unit using a preset data modeling method;
An information mapping unit mapping user information to data collected or stored by the first information collection unit and the second information collection unit;
An information analysis recommendation unit that analyzes and extracts personalized personalized personalized sports items and region-based living sports facility information through preset machine learning and recommendation algorithms based on the mapped data;
An information providing unit that visualizes and provides the personalized, sports-specific or regionalized information of the analyzed and extracted information; And
A personalized life sports recommendation platform system including a control unit controlling operations of the first information collection unit, the second information collection unit, the information processing unit, the information mapping unit, the information analysis recommendation unit, and the information providing unit.
According to claim 2,
The first information collecting unit is a personalized life sports recommendation platform system that analyzes after crawling and storing each information from a public data providing website, a facility information providing website for each industry, and a physical education and national fitness data providing website.
According to claim 2,
The first information collection unit is a personalized life sports recommendation platform system that collects data through crawling of SNS and portal sites by keyword of the sports facility's trade name, address, latitude and longitude, event, equipment name, and program.
According to claim 2,
The user information includes body information (height, weight, waist circumference, body mass index, vision, hearing), health information (heart, blood vessels, kidneys, diabetes, blood pressure, liver, smoking, drinking), life information (age, gender, occupation Individuals including, annual income, work place, average working hours), exercise motivation information (appearance, health, illness, social relations, business, fun, career), and experience information (life sports, subscription facility name, duration, reason for discontinuation) Customized life sports recommendation platform system.
According to claim 2,
The information analysis recommendation unit collects user's body and biometric information through a preset machine learning algorithm, calculates similarity between users, and forms NN (Nearest Neighborhood) to predict preferences for sports, sports, and facilities. Personalized life sports recommendation platform system that recommends and recommends user or facility information corresponding to similar groups.

Images