KR102532534B1 - System for providing medical marketing information using artificial intelligence analysis and personal health management, and a method thereof - Google Patents

Abstract

The present invention relates to a system and method for providing medical marketing information using artificial intelligence analysis and personal health management, and more particularly, to a user terminal installed with a health management application and a wearable device to measure and monitor health indicators to improve personal health. After analyzing health risk factors, building a database for medical information, providing answers to questions related to medical information from users, artificial intelligence according to the health risk factors of the individual and the contents of the Q&A with the user Through analysis, expected disease candidates are extracted, a list of medical institutions and medical staff that can treat the extracted disease candidates are recommended, and questions and answers from users living or located in the area are collected from social network services (SNS). Medical treatment using artificial intelligence analysis and personal health management that can maximize marketing effects by providing customized medical information for each individual and region by analyzing the information to be analyzed and controlling the output of related medical information through an offline advertisement output unit or user terminal A marketing information providing system and method are provided.

Description

Medical marketing information providing system and method using artificial intelligence analysis and personal health management

The present invention relates to a system and method for providing medical marketing information using artificial intelligence analysis and personal health management, and more particularly, to a user terminal installed with a health management application and a wearable device to measure and monitor health indicators to improve personal health. After analyzing health risk factors, building a database for medical information, providing answers to questions related to medical information from users, artificial intelligence according to the health risk factors of the individual and the contents of the Q&A with the user Through analysis, expected disease candidates are extracted, a list of medical institutions and medical staff that can treat the extracted disease candidates are recommended, and questions and answers from users living or located in the area are collected from social network services (SNS). Medical treatment using artificial intelligence analysis and personal health management that can maximize marketing effects by providing customized medical information for each individual and region by analyzing the information to be analyzed and controlling the output of related medical information through an offline advertisement output unit or user terminal It relates to a marketing information providing system and method.

Among the components that determine the quality of life, health is the most important, and recently, there is a growing desire for good health care and disease prevention beyond the treatment of diseases. In particular, as the average lifespan of people increases, the desire and demand for health are explosively increasing. Therefore, the demand for the supply of medical services that can meet this is also growing.

Although medical service is a very important field inseparable from modern life, medical consumers do not know proper information about medical service providers (hospitals, clinics), and most of that information comes from non-experts around them. Corresponds to uncertain information that has been handed down.

And, in order to receive treatment at a medical institution, it is common for a patient who has visited a medical institution to apply directly at a reception counter, and in some cases, make a reservation by making an inquiry by phone or the Internet.

At this time, it is not easy for the patient to accurately judge his or her disease and go to the right hospital or clinic. In particular, it is more difficult to select a good doctor suitable for the patient and make a medical appointment.

Therefore, a doctor is selected using information disclosed on the Internet, advertisements of hospitals and clinics posted on TV, the Internet, etc., or information about hospitals and clinics, doctors, etc. is obtained through professional advice from relatives or friends.

Meanwhile, with the recent development of the Internet, various online services have been provided, and many attempts have been made to combine medical services with online services. For example, many sites providing medical-related services have been created on the Internet, and not only large medical institutions but also individual clinics have built their own websites to provide medical information or consult through bulletin boards and e-mails.

However, it is a situation where the level of simple information provision is not greatly exceeded, and it is difficult for the patient himself to obtain the information he really needs in the flood of information. In addition, it is difficult to properly conduct online medical consultation according to the patient's disease, and it is practically very difficult to select and reserve a doctor according to the symptoms of the disease.

On the other hand, with the recent development of Internet technology through wired and wireless networks, advertisements using Internet media are in the limelight from advertisers and users rather than advertisements using voice or video media such as existing radio or television advertisements.

Advertisements using these Internet media can be provided not only to a user's personal desktop or laptop computer, but also to a portable mobile device. In the early days, advertisements through Internet media were simply showing the corresponding advertisement page, but with the recent emergence of systems and programs that provide social network services (SNS), offline (off-line) Viral marketing methods similar to

Viral marketing is a marketing technique that allows Internet users to voluntarily promote a company or company's products through disseminated media such as e-mail, messenger, or blog, and spreads like a computer virus. Because of this, it is called viral marketing, and in a wide range, it is also used together with word of mouth marketing.

Specifically, viral marketing is different from existing advertisements that are unilaterally delivered to consumers in that it is an advertisement that is transmitted word-of-mouth through consumers without direct promotion by the company. It has a marketing method that naturally arouses a topic on the Internet while conveying the content of the advertisement to each other through embedding.

In addition, since such viral marketing costs much less than conventional media advertisements using films such as television and movies, the frequency of use is rapidly spreading in the current advertising market. For example, such viral marketing can be performed through social network services (SNS) such as Facebook, Twitter, KakaoStory, blog, Instagram, Naver Band, etc., or KakaoTalk, Line It is becoming more active in the Internet community through instant messenger services (IMS) used on the Internet, such as (Line).

On the other hand, in some advertisements using viral marketing, an incentive approach (reward or reward method) is used to reward those who inform product information, but it is difficult to clearly distinguish loyal users from abusing users. Therefore, there is a problem in that users with high actual loyalty avoid using the service.

Here, Abusing refers to anything that causes damage to the viral marketing service provider, soju and other users of the viral marketing service system by interfering with the service operation of the viral marketing service system in an abnormal way in using the service of the viral marketing service provider. refers to the actions of

On the other hand, as a prior art for solving the above problems, Korean Patent Registration No. 10-1538278 has "system and method for providing viral marketing service".

On the other hand, as one of the prior art related to the mobile advertisement system, Korea Patent Registration No. 10-1350735 'Mobile advertisement system using a terminal and its advertisement method' discloses detailed information about a product or store for which a mobile advertisement service is desired, and The present invention relates to a technique of performing advertisement for a product or a store by using evaluation results for each item according to predetermined evaluation items for use of the store.

However, Korean Patent Registration No. 10-1350735 is a technology that focuses on enabling consumers to view advertisements they want by classifying advertisement target products in detail according to the characteristics of the goods for which advertisements are desired. The problem of insufficient effectiveness remains.

Meanwhile, retargeting advertisements provide advertisements based on user behavior. For example, an advertisement related to a product the user has viewed on a website or content searched for by the user on a portal site is provided to the user.

However, the retargeting advertisement has a limitation in that it can provide only a limited customized advertisement by exposing a product already purchased by a user as an advertisement or repeatedly exposing a specific product.

On the other hand, SNS users check each other's safety or share activity details through feeds such as their activity information or information they want to share on SNS, and sometimes share feeds containing useful information with other SNS users.

As the number of SNS users increases, various marketing methods using social networks are appearing. In order to increase the efficiency of such marketing, it is necessary to collect and analyze accurate information about social network activities by account along with account information of social network users.

Korean Registered Patent [10-1538278] (registration date: 2015. 07. 14) Korean Registered Patent [10-1763895] (registration date: 2017. 07. 26) Korean Registered Patent [10-1350735] (registration date: 2014. 01. 07)

Therefore, the present invention has been made to solve the above problems, and an object of the present invention is to measure and monitor health indicators using a user terminal and a wearable device installed with a health management application to determine individual health risk factors. After analyzing and constructing a database of medical information, it provides answers to questions related to medical information from users, and through artificial intelligence analysis according to the individual's health risk factors and the contents of the Q&A with the user, predicts It extracts a disease candidate group, recommends a list of medical institutions and medical staff that can treat the extracted disease candidate group, and analyzes the Q&A contents of users living or located in the area and information collected from social network services (SNS) Medical marketing information providing system using artificial intelligence analysis and personal health management that can maximize marketing effect by providing personalized and regionally customized medical information by controlling related medical information to be output through an offline advertisement output unit or user terminal, and to provide that way.

Objects of the embodiments of the present invention are not limited to the above-mentioned purposes, and other objects not mentioned above will be clearly understood by those skilled in the art from the description below. .

A system for providing medical marketing information using artificial intelligence analysis and personal health management according to an embodiment of the present invention for achieving the above object is a wearable device worn on a user's body to measure the user's biosignal (170); The signals received from the wearable device are monitored, analyzed, and learned in real time to analyze the user's health risk factors, establish a database of medical information, and then, according to the health risk factors and Q&A with the user Through analysis, related medical information is recommended, and medical information determined by analyzing Q&A contents of users living or located in the area and information collected from social network services (SNS) is sent to an offline advertisement output unit or user terminal. a medical marketing information providing server 100 for providing customized medical advertisements for each individual and for each region by controlling the display to be output through; And a health management application is installed, processing the signal transmitted from the wearable device to detect the user's biometric data, and the user's health analysis result, query answer, and customized medical information from the medical marketing information providing server. and a user terminal 150 for receiving.

The medical marketing information providing server 100 includes a transceiver 101 for receiving biometric data and questions transmitted from the user terminal and transmitting an alarm, result or answer according to health analysis to the user terminal; a processing unit 103 for pre-processing received data and processing data to be transmitted; a database management unit 104 that stores bio-signal information, record information, medical information, learning model, analysis algorithm, and question and answer data; an analysis unit 105 for analyzing the transmitted biometric data and questions to extract health risk factors and disease candidates and to recommend corresponding medical information; an application support unit 106 installed in the user terminal to support the health management application capable of monitoring the user's vital signs and receiving answers to medical-related queries; a medical information provision unit 107 for generating and providing customized medical information to users living or located in the corresponding region; and a compensating unit 108 for calculating the contribution to the customized medical information of the corresponding user and rewarding (compensating) according to the contribution.

The processing unit 103 includes a biometric data collection unit 301 for collecting biometric data received through the user terminal; a biometric data monitoring unit 302 for monitoring the collected biometric data; a keyword extraction unit 303 for extracting a keyword from a query through the user terminal; a query analyzer 304 for interpreting a user's question based on the extracted keywords; a database search unit 305 for searching answers to the user's questions based on a question and answer database; and an answer output unit 306 for outputting an answer to the searched user's question.

The analysis unit 105 includes a risk factor analysis unit 307 for analyzing health risk factors by analyzing the biometric data received from the biometric data monitoring unit 302; a disease candidate group extraction unit 308 for extracting a disease candidate group of the user based on the user's question and the health risk factors; and a medical information recommendation unit 309 for searching for and recommending medical information related to the extracted disease candidates.

The medical information providing unit 107 includes an SNS data collection unit 401 for collecting SNS data for each user; an analysis data set determining unit 402 for determining a data set of a user (user terminal) to be analyzed; an entropy calculator 403 for calculating entropy; a collection data analysis unit 404 for determining customized medical information by analyzing the data of the analysis data set determined by the analysis data set determination unit 402 among the data collected by the SNS data collection unit 401; and a medical information output unit 405 for providing the determined customized medical information to an offline advertisement output unit 160 or a user terminal 150 located in a corresponding region.

The analysis data set determination unit 402 determines, as an analysis data set, uniformly disposed user terminal sets having the largest or smallest entropy values in the modified information entropy calculated for each arrangement of the user terminal sets. characterized by determining

(여기서, S(ns)는 정보 엔트로피, k_B는 임의의 상수이고, 주어진 ns에 대해 고유 연결 형태가 총 Ng개 관측되고, pi(ns)는 각 값의 확률 (i는 1 부터 Ng 까지의 정수)이다.) 및 <수학식 8>

(여기서, Sc(ns)는 상기 수정된 정보 엔트로피, S(ns)는 정보 엔트로피, k_B는 임의의 상수)을 이용하여 상기 수정된 정보 엔트로피를 계산하는 것을 특징으로 한다.The entropy calculation unit 403, <Equation 7>

(Where S(ns) is information entropy, k _B is an arbitrary constant, a total of Ng unique connection types are observed for a given ns, and pi(ns) is the probability of each value (i is a number from 1 to Ng integer)) and <Equation 8>

(Here, Sc(ns) is the corrected information entropy, S(ns) is the information entropy, and k _B is an arbitrary constant) to calculate the corrected information entropy.

In addition, a method for providing medical marketing information using artificial intelligence analysis and personal health management according to an embodiment of the present invention for achieving the above object is, in the medical marketing information providing server 100, the user terminal 150 Biometric data transfer step of receiving the biometric data measured by the wearable device 170 through (S910); In the medical marketing information providing server 100, monitoring the received biometric data to analyze health risk factors, and informing the user terminal 150 when health risk factors occur (S920); a database construction step (S930) of constructing a question and answer database related to medical information in the medical marketing information providing server 100; In the medical marketing information providing server 100, a question answering step (S940) of searching for medical information related queries through the user terminal 150 based on the question and answer database and providing answers; In the medical marketing information providing server 100, a personalized medical information recommendation step (S950) of recommending personalized medical information to a corresponding user through artificial intelligence analysis according to the user's health risk factors and questions and answers; In the medical marketing information providing server 100, a customized medical information determination step (S960) of determining customized medical information by analyzing Q&A contents of users living or located in the corresponding region and data collected from social network services; providing the determined customized medical information to the offline advertisement output unit 160 or user terminals located in the corresponding region (S970); and a compensation step (S980) of calculating the contribution of the customized medical information of the corresponding user terminal and compensating according to the contribution.

The customized medical information determining step (S960) includes a terminal data set selection step (S1010) of randomly selecting a plurality of user terminal sets including a predetermined number of user terminals in the corresponding region; an information entropy calculation step (S1020) of calculating corrected information entropy for the arrangement of each user terminal set selected in the terminal data set selection step (S1010); an analysis data set determination step (S1030) of determining a uniformly distributed set of user terminals having the largest or smallest value of the corrected entropy as an analysis data set; and a content determination step (S1040) of determining the content of the customized medical information by analyzing social network service data and question and answer data for the determined analysis data set.

(여기서, S(ns)는 정보 엔트로피, k_B는 임의의 상수이고, 주어진 ns에 대해 고유 연결 형태가 총 Ng개 관측되고, pi(ns)는 각 값의 확률 (i는 1 부터 Ng 까지의 정수)이다.) 및 <수학식 10>

(여기서, Sc(ns)는 상기 수정된 정보 엔트로피, S(ns)는 정보 엔트로피, k_B는 임의의 상수)을 이용하여 상기 수정된 정보 엔트로피를 계산하는 것을 특징으로 한다.In the information entropy calculation step (S1020), <Equation 9>

(Where S(ns) is information entropy, k _B is an arbitrary constant, a total of Ng unique connection types are observed for a given ns, and pi(ns) is the probability of each value (i is a number from 1 to Ng integer)) and <Equation 10>

(Here, Sc(ns) is the corrected information entropy, S(ns) is the information entropy, and k _B is an arbitrary constant) to calculate the corrected information entropy.

According to a system and method for providing medical marketing information using artificial intelligence analysis and personal health management according to an embodiment of the present invention, health indicators are measured and monitored using a wearable device and a user terminal installed with a health management application, By analyzing health risk factors, it is possible to manage and store detected biometric data, easily monitor it through applications installed on user terminals, and analyze health risk factors and predict disease candidates using previously accumulated data. Therefore, it is possible to effectively manage the user's health.

In addition, according to the medical marketing information providing system and method using artificial intelligence analysis and personal health management according to an embodiment of the present invention, according to the personal health management using artificial intelligence analysis in line with the 4th industrial revolution era By outputting customized medical information, determining an analysis data set using entropy calculated according to the arrangement of user terminals, selecting a user in the corresponding region and analyzing the user's data, customized medical information in the corresponding region ( medical institutions, disease information, medicines, etc.), there is an effect of minimizing the time and cost that consumers have to spend.

In addition, according to the medical marketing information providing system and method using artificial intelligence analysis and personal health management according to an embodiment of the present invention, after providing customized medical information to a user, the contribution of the user's customized medical information is calculated. By rewarding (compensating) by doing so, there is an effect of increasing the effect of advertising.

In addition, according to the medical marketing information providing system and method using artificial intelligence analysis and personal health management according to an embodiment of the present invention, the analysis data set is changed as the arrangement of user terminals is changed, so that as many users as possible are required. There is an effect that can provide customized medical information to be.

In addition, according to the medical marketing information providing system and method using artificial intelligence analysis and personal health management according to an embodiment of the present invention, a patient, a medical consumer, finds a good doctor to cure a disease, makes a reservation, and provides medical service. If you can guide them to receive the service, you can reduce the time and effort of medical consumers, and you can expect marketing effects through service competition as hospitals and clinics. In addition, feedback from medical consumers can be expected by forming a channel between patients who are medical consumers and hospitals with good doctors and providing qualitative medical services.

1 is a configuration diagram of an embodiment of an entire system including a system for providing medical marketing information using artificial intelligence analysis and personal health management to which the present invention is applied.
2 is a configuration diagram of an embodiment of a medical marketing information providing system using artificial intelligence analysis and personal health management according to the present invention.
FIG. 3 is a detailed configuration diagram of an embodiment of the processing unit 103 and analysis unit 105 of FIG. 2 .
4 is a detailed configuration diagram of one embodiment of the medical information providing unit 107 of FIG. 2;
FIG. 5 is a diagram for explaining a method of determining a data set using batch entropy in the analysis data set determining unit 402 of FIG. 4, showing a graph generation result based on Vonoroi fragmentation of a user terminal location.
FIG. 6 is a diagram for explaining a method of determining a data set using batch entropy in the analysis data set determiner 402 of FIG. One embodiment drawing.
7 is a detailed configuration diagram of one embodiment of the compensation unit 108 of FIG. 2;
8 is a detailed configuration diagram of one embodiment of the wearable device 170 of FIG. 2 .
9 is a flowchart of an embodiment of a method for providing medical marketing information using artificial intelligence analysis and personal health management according to the present invention.
10 is a detailed flowchart of the customized medical information determining step (S960) of FIG. 9;
11 is an explanatory diagram of a reward step (S980) in the method of providing medical marketing information using artificial intelligence analysis and personal health management according to the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, or substitutes included in the spirit and scope of the present invention.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be.

On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle.

Terms used in this specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, process, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, processes, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having meanings consistent with the meanings in the context of the related art, and unless explicitly defined in this application, they should not be interpreted in ideal or excessively formal meanings. don't

Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings. Prior to this, the terms or words used in this specification and claims should not be construed as being limited to ordinary or dictionary meanings, and the inventor appropriately uses the concept of terms in order to explain his/her invention in the best way. Based on the principle that it can be defined, it should be interpreted as meaning and concept consistent with the technical spirit of the present invention. In addition, unless there is another definition in the technical terms and scientific terms used, they have meanings commonly understood by those of ordinary skill in the art to which this invention belongs, and the gist of the present invention is described in the following description and accompanying drawings. Descriptions of well-known functions and configurations that may be unnecessarily obscure are omitted. The drawings introduced below are provided as examples to sufficiently convey the spirit of the present invention to those skilled in the art. Accordingly, the present invention may be embodied in other forms without being limited to the drawings presented below. Also, like reference numerals denote like elements throughout the specification. It should be noted that like elements in the drawings are indicated by like numerals wherever possible.

1 is a configuration diagram of an embodiment of an entire system including a system for providing medical marketing information using artificial intelligence analysis and personal health management to which the present invention is applied.

Referring to FIG. 1, the entire system including a medical marketing information providing system using artificial intelligence analysis and personal health management to which the present invention is applied includes a medical marketing information providing server 100 and an advertiser 110 connected through a communication network. , a plurality of user SNSs 120 and 130, generated customized medical information 140, a user terminal 150, a wearable device 170, and an offline advertisement output unit 160.

The medical marketing information providing server 100 is a wearable device 170 that can access the plurality of user SNSs 120 and 130 through a communication network, can communicate with the advertiser 110, and is connected to the user terminal 150 ), receives and analyzes the measured bio-signal, and transmits information necessary for outputting an advertisement to the user terminal 150 or the offline advertisement output unit 160. The medical marketing information providing server 100 may be included in an operating server of an advertising agency (not shown).

The medical marketing information providing server 100 receives and stores medical information from advertisers (medical institutions, pharmaceutical companies, etc.) or advertiser terminals, and outputs and provides the medical information from the advertisers or advertiser terminals, upon request for medical information. It stores the information necessary to print the .

The medical marketing information providing server 100 provides the generated customized medical information 140 including the medical information to the user terminal 150 of the corresponding user by using the user's questions and answers and the analyzed result of the biometric data, , The corresponding user may receive a reward (compensation) according to the degree of contribution (visiting the corresponding medical institution, promoting to friends) for the received customized medical information.

The user terminal 150 is generally a digital device that includes a function to search for desired information or perform various activities through a communication network, and is a personal computer (e.g., a desktop computer, a laptop computer). Any digital device equipped with a memory unit and a microprocessor, such as a computer, workstation, PDA, web pad, mobile phone, etc., equipped with a microprocessor, can be used as the user terminal 150 according to the present invention. In addition, the user terminal 150 can access a web page that includes the customized medical information 140 generated and output by the medical marketing information providing server 100, and can obtain profits according to the use of the corresponding information. there is.

Meanwhile, the advertiser 110 may be a client requesting an advertisement to the advertising agency through online or offline or a terminal requesting an advertisement through a network (online). Although shown as a client requesting an advertisement in the drawing, it may be an advertiser terminal requesting an advertisement. The advertiser terminal also has properties similar to those of the user terminal 150 .

Meanwhile, the wearable device 170 is worn on the user's body to measure the user's biosignal.

The medical marketing information providing server 100 analyzes the health of the user by monitoring, analyzing, and learning signals transmitted from the wearable device 170 in real time.

The user terminal 150 may output a result of bio-signal monitoring, and may further receive an alarm related to a health risk signal.

2 is a configuration diagram of an embodiment of a medical marketing information providing system using artificial intelligence analysis and personal health management according to the present invention.

As shown in FIG. 2, the medical marketing information providing system using artificial intelligence analysis and personal health management according to the present invention includes a wearable giga 170, a medical marketing information providing server 100, and a user terminal 150. include

The wearable device 170 is worn on the user's body to measure the user's biosignal.

The medical marketing information providing server 100 monitors, analyzes, and learns signals received from the wearable device 170 in real time to analyze the user's health risk factors, builds a database for medical information, and then Through analysis of health risk factors and questions and answers with corresponding users, we recommend related medical information, analyze the contents of questions and answers of users living or located in the area, and information collected from social network services (SNS). The determined medical information is controlled to be output through an offline advertisement output unit or a user terminal, thereby providing customized medical advertisements for each individual and region.

The medical marketing information providing server 100 transmits/receives data required for a medical marketing information providing service to/from the user terminal 150 through a communication network. A health management application for the medical marketing information providing service may be installed in the user terminal 150 .

The user terminal 150 is installed with a health management application, processes the signal transmitted from the wearable device 170 to detect the user's biometric data, and obtains the user's health analysis result and query from the medical marketing information providing server. Receive answers to, and customized medical information.

The user terminal 150 is a digital device having a function to communicate after accessing the medical marketing information providing server 100 through a communication network, and is a personal computer (eg, a desktop computer, a notebook computer, etc.) ), a workstation, a PDA, a web pad, a mobile phone, and the like, any digital device equipped with a memory unit and equipped with a microprocessor and capable of computing can be adopted as the user terminal 150 according to the present invention.

The medical marketing information providing server 100 includes a transceiver 101, a processing unit 103, a database management unit 104, an analysis unit 105, a control unit 102, an application support unit 106, and a medical information providing unit 107. ), and a compensating unit 108 and the like.

The transceiver 101 receives bio data and questions transmitted from the user terminal 150 and transmits an alarm, result or answer according to health analysis to the user terminal 150 .

The processing unit 103 pre-processes received data and processes data to be transmitted.

The database management unit 104 stores bio-signal information, record information, medical information, learning model, algorithm for analysis, and question and answer data.

The analyzer 105 analyzes the received biometric data and questions, extracts health risk factors and disease candidates, and recommends corresponding medical information.

The application support unit 106 is installed in the user terminal 150 to monitor the user's bio-signals and supports the health management application capable of receiving answers to medical-related queries.

The medical information providing unit 107 generates and provides customized medical information to the offline advertisement output unit 106 and user terminals residing or located in a corresponding region.

The compensation unit 108 calculates the contribution of the corresponding user (user terminal) and rewards (compensates) according to the contribution.

The control unit 102 controls data between the transmission/reception unit 101, the processing unit 103, the database management unit 104, the analysis unit 105, the medical information providing unit 107, and the compensating unit 108. Controls the flow and generates control signals necessary to provide medical marketing information service.

The transceiver 101, the control unit 102, the processing unit 103, the database management unit 104, the analysis unit 105, the application support unit 106, the medical information providing unit 107 and the The compensation unit 108 may be program modules, at least some of which communicate with the medical marketing information providing system. These program modules may be included in the medical marketing information providing system in the form of an operating system, application program modules, and other program modules, and may be physically stored on various known storage devices. Also, these program modules may be stored in a remote storage device capable of communicating with the medical marketing information providing system. Meanwhile, these program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types according to the present invention.

Here, the communication network may be configured regardless of its communication mode, such as wired and wireless, and a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN) It can be composed of various communication networks such as Preferably, the communication network referred to in the present invention may be the known World Wide Web (WWW).

In addition, components located in a short distance may communicate through a wireless local area network (LAN) including Wi-Fi, Bluetooth, ZigBee, and the like.

The database manager 104 includes a bio-signal database 104a storing bio-signals, a record database 104b storing records of user's bio-signal evaluation, treatment information of medical institutions, medical staff information, and reviews of medical institutions. A medical information database (104c) storing information, reviews of medical staff, a list of diseases by department, and individual symptoms within the department, health risk factors, disease candidates, medical information analysis, and Q&A with the user terminal 150 Including a learning model data database (104d) that stores learning models necessary for data analysis, an analysis algorithm database (104e) that stores artificial intelligence analysis algorithms, and a question-and-answer database (104f) that stores question-and-answer history. can do.

In the above embodiment, the database for storing information for the implementation of the present invention is a biological signal database 104a, a record data database 104b, a medical information data database 104c, a learning model data database 104d, and an analysis algorithm database. 104e and the dialogue data database 104f are classified into six databases, but the configuration of the database including these classifications may be changed according to the needs of those skilled in the art.

On the other hand, in the present invention, a database is a concept that includes not only a database in a narrow sense but also a database in a broad sense including data records based on a computer file system. It should be understood that if the data of can be extracted, it can be included in the database according to the present invention.

The medical marketing information providing server 100 according to the present invention classifies and stores medical information by category, and may have a separate medical information database that is periodically updated.

On the other hand, in the question and answer database of the medical marketing information providing server 100 according to the present invention, a keyword dictionary (not shown) storing a plurality of keyword sets for each medical subject, words for evaluating the location and symptoms of symptoms, and A semantic dictionary (not shown) of the corresponding word may be provided.

FIG. 3 is a detailed configuration diagram of an embodiment of the processing unit 103 and analysis unit 105 of FIG. 2 .

As shown in FIG. 3, the processing unit 103 includes a biometric data collection unit 301, a biometric data monitoring unit 302, a keyword extraction unit 303, a query analysis unit 304, a database search unit 305, and an answer output unit 306.

The biometric data collection unit 301 collects biometric data received through the user terminal, and the collected biometric data is stored in a biosignal database.

The biological data monitoring unit 302 monitors the collected biological data.

The keyword extraction unit 303 extracts keywords from a query through the user terminal.

The query analyzer 304 analyzes the user's question based on the extracted keywords.

The database search unit 305 searches for an answer to the user's question based on a question-and-answer database.

The answer output unit 306 outputs an answer to the searched user's question.

Meanwhile, as shown in FIG. 3 , the analysis unit 105 includes a risk factor analysis unit 307 , a disease candidate group extraction unit 308 , and a medical information recommendation unit 309 .

The risk factor analyzer 307 analyzes health risk factors by analyzing biometric data received from the biometric data monitoring unit 302 .

The disease candidate group extraction unit 308 extracts the user's disease candidate group based on the user's question and the health risk factors.

The medical information recommendation unit 309 searches for and recommends medical information, such as information on medical institutions and medicines capable of treating the extracted disease candidate group.

Each of the risk factor analysis unit 307, the disease candidate group extraction unit 308, and the medical information recommending unit 309 uses an artificial intelligence algorithm to provide medical information stored in a database provided in the medical marketing information providing server 100. analysis, extraction and recommendation based on

Based on the user's health analysis results accumulated and stored through the health management application installed in the user terminal 150, health risk factors and the user's disease candidate group may be predicted and displayed.

4 is a detailed configuration diagram of one embodiment of the medical information providing unit 107 of FIG. 2;

The medical information providing unit 107 includes an SNS data collection unit 401, an analysis data set determination unit 402, an entropy calculation unit 403, a collected data analysis unit 404, and a medical information output unit 405. include

The SNS data collection unit 401 collects SNS data for each user.

The analysis data set determining unit 402 determines a data set of a user (user terminal) to be analyzed.

The entropy calculator 403 calculates entropy.

The collected data analysis unit 404 analyzes the data of the analysis data set determined by the analysis data set determination unit 402 among the data collected by the SNS data collection unit 401 according to a big data analysis technique.

Big data refers to data sets that exceed the capabilities of traditional data collection, storage, management, and analysis. Big data can be classified into structured data, semi-structured data, and unstructured data according to the degree of standardization.

Structured data refers to data stored in fixed fields. That is, data that is stored in a certain format. Semi-structured data is data that is not stored in fixed fields, but contains metadata or schema. Examples of semi-structured data include Extensible Mark-up Language (XML) and Hypertext Mark-up Language (HTML). Unstructured data refers to data that is not stored in fixed fields. Examples of unstructured data include text documents, image data, video data, and voice data.

The analysis unit 105 may collect and analyze the big data as described above. Examples of big data analysis techniques include text mining, opinion mining, social network analysis, cluster analysis, neural network analysis, and markov model. However, it is not limited to the exemplified analysis techniques.

Text mining is a technique of extracting and processing useful information from semi-structured text data or unstructured text data based on natural language processing technology. Natural Language Processing (NLP) technology is a technology that enables natural language understanding and natural language generation. Natural language is a term that humans use to communicate, as opposed to artificial language (computer language). Natural language understanding is the process of mechanically analyzing natural language and converting it into a form that computers can understand. Natural language generation refers to enabling computers to output natural language. Natural language processing techniques consist of morphological analysis, syntactic analysis, semantic analysis, and pragmatic analysis.

Reputation analysis is performed on structured text and unstructured text in social media such as blogs, Social Network Services (SNS), Wikis, UCCs, Micro-Blogs, etc. It is a technology that collects and analyzes text to determine the reputation (for example, positive, negative, or neutral) of a product or service.

Social network analysis is a technique of analyzing and extracting the user's influence, interests, and tendencies based on the social network connection structure and connection strength. The types of information that can be utilized when performing social network analysis can be largely classified into follow, reply, share (retweet, in the case of Twitter), etc. Making friends with a specific person online or When you want to see his writings, you follow him, comment or share (retweet), which means an active mutual relationship. By analyzing these relationships, you can evaluate the user's influence or dissemination power, and furthermore, the spread of specific articles. You can track the process, or estimate the future spread of opinions.

Cluster analysis is a technique of finally discovering groups with similar characteristics by merging individuals with similar characteristics.

Hereinafter, a method of calculating entropy and a method of determining an analysis data set will be described with reference to FIGS. 5 and 6 .

5 is a diagram for explaining a method of determining a data set using batch entropy in the analysis data set determining unit 402 of FIG. 4, and is a diagram showing a graph generation result based on Vonoroi fragmentation of a location of a user terminal; FIG. 6 is a diagram for explaining a method of determining a data set using batch entropy in the analysis data set determiner 402 of FIG. It is a drawing of one embodiment.

First, entropy will be explained.

Basically, one of the most effective ways to understand the complexity of data or patterns is to measure their entropy. Since Claude Shannon, the father of information theory, first introduced the concept of information entropy in 1948, the concept of signal entropy has been used in various fields. Information entropy is used for various purposes, such as measuring the amount of information in a signal, which was the original purpose at the time of its creation, as well as data compression/restoration processes, data complexity measurement, and image randomness or transformation checks. It is also used as an inspection indicator of data interpretation or prediction quality through data analysis. The information entropy S presented by Shannon is mathematically the same as the entropy dealt with in statistical physics. (The only difference between the two is the presence or absence of a physical unit.) When the sample space of information is composed of N different values and the ratio (or probability pi,i=1,2,…N) of each value is known, the information Entropy S can be expressed as in Equation 1 below.

<Equation 1>

(Here, the sample space of information consists of N different values from 1 to N, and pi is the probability of each value (i is an integer from 1 to N).)

For reference, the base of the logarithm used in Equation 1 may be e, 10, 2, etc., depending on the purpose. For example, since a digital signal is a binary signal, the entropy of a digital signal is usually written as a log base of 2, and through this, the information amount of data can be expressed in units of bits or bytes. Information entropy has the largest value, max(S)=logN, when the sample space is equally distributed according to mathematical definition, that is, when the composition ratio of all information values has the same value (i.e., when pi=1/N). . However, there is a limit to information entropy, which is that there is no consideration of the 'number of cases' in which the data elements constituting information are arranged. For example, consider the two data pairs X1=[121212121212] and X2=[112122211221]. The two pairs of data have the same size and all consist of only 1 and 2 information, and the fraction of each component is equal to 0.5. Considering this, the information entropy of the two data pairs is as shown in Equation 2 below.

<Equation 2>

That is, since the two values have the same value, the complexity difference between the two data cannot be distinguished only by the information entropy. However, anyone can judge that X1 is one-dimensional data with a regular arrangement (i.e., predictable information with certain periodicity), while X2 is one-dimensional data with an irregular arrangement (i.e., information that is almost impossible to predict). can Therefore, if the concept of 'complexity' can be defined, the two pairs of data will be normal if there is a clear difference in this 'complexity'. Therefore, a new mathematical method is needed to distinguish the difference in complexity of signals that cannot be distinguished only by information entropy.

Therefore, in order to quantify the complexity of a pattern that cannot be expressed as a two-dimensional matrix, a batch entropy method for calculating the complexity of a system in which particles are self-assembled (self-assembled structure) is applied.

First of all, the starting point for calculating batch entropy is to identify the positions of individual particles (user terminals) and express their connectivity as a graph. To this end, the coordinates of individual particles are first displayed on a two-dimensional plane, and the optimal non-overlapping area occupied by each particle is calculated based on the coordinates of each particle. This calculation is possible using a method called Voronoi tessellation. Simply put, this method finds a polygon (polytope if 3D)-shaped area surrounded by perpendicular bisectors (bisectors if 3D) of lines connecting each center point. When Voronoi fragmentation is completed, a fragmented graph resembling a honeycomb is created as shown in FIG. 5 .

Now, the next thing to do is to randomly pick a point on the plane where this graph is placed (red point), find the vertices (green points) of the graphs that will be 'shortest neighbors' for a set number (ns), and only use these points. It is to find the unique connection form on the graph that can be made. In order to calculate how often these unique connection types will appear, random points on the plane are tested hundreds or thousands of times to classify the unique connection types (this is called graph isomorphism) and calculate a statistical probability distribution.

For example, FIG. 6 shows the result of calculating the probability of occurrence of different unique connection types for the case where ns=8. Assuming that a total of Ng unique connection types are observed for a given ns, the probability of occurrence of each type pi(ns),i=1,2… Using Ng, their information entropy S(ns) can be calculated as shown in Equation 3 below.

<Equation 3>

Here, k _B is an arbitrary constant, a total of Ng unique connection types are observed for a given ns, and pi(ns) is the probability of each value (i is an integer from 1 to Ng).

Any constant k _B may be Boltzmann's constant, a physical constant that relates the energy at the particle level to the temperature observed at the macroscopic level, and is the ratio of the gas constant to Avogadro's number, and the value is 1.380 6488 × 10 ^{?? 23} J/K.

At this time, since the calculation of S(ns) relies on finding a unique form by randomly picking points in a limited area, the corrected information entropy Sc(ns) to correct the effect of the limited area is calculated by the following <Equation 4> count together

<Equation 4>

(where k _B is an arbitrary constant)

The arbitrary constant can be a positive or negative number, and since only the relative value of entropy for a plurality of user terminal sets needs to be known, the entropy value of the user terminal set having the most uniform arrangement will be the largest value or the smallest value. can

5 and 6, after randomly selecting a plurality of user terminal sets including a predetermined number of user terminals in a corresponding region, the entropy calculation unit 403 calculates < The corrected information entropy is calculated using Equation 3 and Equation 4.

Thereafter, the analysis data set determination unit 402 determines a uniformly distributed set of user terminals having the largest value or the smallest value of the corrected information entropy as the analysis data set, and the collection data analysis unit 404 determines Personalized medical information is determined by analyzing social network service (SNS) data and question and answer data received from the determined analysis data set, and the medical information output unit 405 outputs the determined customized medical information as an offline advertisement located in the corresponding area. It is provided to the unit 160 or the user terminal 150 to be output.

That is, in determining the set of user terminals to be analyzed, the modified information entropy for each set arrangement is calculated to have the largest value or the smallest value (any constant can be positive or negative). So) determines a uniformly distributed set of user terminals as the analysis data set.

7 is a detailed configuration diagram of an embodiment of the compensation unit 108 of FIG. 2 .

As shown in FIG. 7 , the compensation unit 108 includes a contribution calculator 701 and a reward calculator 702 .

The contribution calculation unit 701 calculates a corresponding user's contribution to medical information marketing, and the reward calculator 702 rewards (compensates) the corresponding user according to the contribution to medical information marketing.

8 is a detailed configuration of an embodiment of the wearable device 170 of FIG. 2 .

As shown in FIG. 8 , the wearable device 170 includes a wearable device power supply unit 801 , a wearable device control module 802 , a sensing module 803 , and a wearable device communication module 804 .

The wearable device power supply unit 801 supplies power to the wearable device 170 .

The wearable device control module 202 controls the operation of the wearable device 170 .

The sensing module 803 senses and measures biosignals such as electrocardiogram, heart rate, oxygen saturation, respiratory rate, body temperature, blood pressure, and blood sugar of the user. The sensing module 803 may include at least one or more sensors for sensing biosignals. Also, it is possible for one sensor to detect at least one biosignal.

The wearable device communication module 804 directly transfers the signal measured by the wearable device 170 to the user terminal 150 or the medical marketing information providing server 100 .

Meanwhile, the wearable device 170 includes a wearable device display unit 805 displaying biosignals such as the measured electrocardiogram, heart rate, oxygen saturation, respiratory rate, body temperature, blood pressure, and blood sugar and the user terminal 150 or the A notification unit 806 for outputting a notification signal received from the medical marketing information providing server 100 may be further included.

9 is a flowchart illustrating an embodiment of a method for providing medical marketing information using artificial intelligence analysis and personal health management according to the present invention.

First, while the user terminal 150 and the wearable device 170 are synchronized and connected to each other, the medical marketing information providing server 100 transmits biometric data measured by the wearable device 170 through the user terminal 150. is delivered (S910).

Thereafter, the medical marketing information providing server 100 analyzes health risk factors by monitoring the transmitted biometric data, and informs the user terminal 150 when health risk factors occur (S920).

In addition, the medical marketing information providing server 100 builds a question and answer database 104c related to medical information (S930).

Thereafter, the medical marketing information providing server 100 searches for medical information-related queries through the user terminal 150 based on the Q&A database 104c and provides answers (S940).

Thereafter, the medical marketing information providing server 100 recommends personalized medical information to the corresponding user through artificial intelligence analysis according to the user's health risk factors and questions and answers (S950).

Then, the medical marketing information providing server 100 determines customized medical information by analyzing Q&A contents of users living or located in the corresponding region and data collected from social network services (S960).

Thereafter, the determined customized medical information is provided to the offline advertisement output unit 160 or user terminals 150 located in the corresponding region (S970).

Thereafter, the medical marketing information providing server 100 obtains profits by providing the customized medical information, calculates the contribution of the customized medical information of the corresponding user terminal, and compensates according to the contribution (S980).

The reward step (S980) will be described in detail with reference to FIG.

10 is a detailed flowchart of the customized medical information determining step (S960) of FIG.

A plurality of user terminal sets including a predetermined number of user terminals in the corresponding region are randomly selected (S1010).

Thereafter, the corrected information entropy is calculated for the arrangement of each user terminal set selected in the terminal data set selection step (S1010) (S1020).

Thereafter, among the plurality of user terminal sets, a uniformly distributed set of user terminals having the largest value or the smallest modified information entropy is determined as an analysis data set (S1030).

Thereafter, with respect to the determined analysis data set, the content of the customized medical information is determined by analyzing social network service data and question and answer data (S1040).

11 is an explanatory diagram of a reward step (S980) in the method of providing medical marketing information using artificial intelligence analysis and personal health management according to the present invention.

Hereinafter, the reward step (S980) will be described in detail.

Before explaining the reward step (S980), the advertising agency can obtain advertising revenue 1110 by various advertising fee calculation methods.

First, an advertising agency having a medical marketing information providing server 100 may sign an advertisement (marketing) contract with an advertiser 110 online or offline.

In the advertising contract stage, the advertising fee according to the output of the customized medical information may not be a per-time price, but a fixed amount of advertising revenue 1 may be set for outputting a preset number of customized medical information for a certain period of time.

Meanwhile, in the advertising contract stage, advertising revenue 2 may be determined according to the number of customized medical information. When the number of outputs of the customized medical information is less than the predetermined number, the advertisement fee per advertisement may be set more expensive than when the number is greater than or equal to the predetermined number.

As an example, as shown in the following <Table 1>, the advertisement fee per piece can be set at 100 won for up to 100 outputs of customized medical information. It can be.

Number of customized medical information outputs unit price per piece advertising revenue up to less than 100 times 100 won Number × 100 won over 100 times 70 won Number × 70 won

On the other hand, advertising revenue 3 determined through an advertiser open competition auction on the web may be set.

For contribution calculation, contribution 1 is calculated by multiplying the number of customized medical information shared by weight 1, contribution 2 is calculated by multiplying the number of shares shared with other types of SNS by weight 2, and contribution is calculated by multiplying the number of views of customized medical information by weight 3 Calculate 3, calculate the contribution 4 by multiplying the number of times the person uses the medical institution (or the number of purchases of the relevant item) and the weight 4, and after sharing, the contribution is calculated by multiplying the number of times the person uses the medical institution (or the number of purchases of the corresponding item) and the weight 5 5 can be calculated.

And, the final customized medical information contribution is calculated using Equation 5 below.

<Equation 5>

Contribution of customized medical information = Contribution 1 + Contribution 2 + Contribution 3 + Contribution 4 + Contribution 5

And, the reward is calculated using Equation 6 below.

<Equation 6>

Reward (compensation) = Personalized medical information contribution x Reward unit price

Although the method for providing medical marketing information using artificial intelligence analysis and personal health management according to an embodiment of the present invention has been described above, a program for implementing the method for providing medical marketing information using artificial intelligence analysis and personal health management is stored. Of course, a program stored in a computer-readable recording medium and a computer-readable recording medium for implementing a method of providing medical marketing information using artificial intelligence analysis and personal health management can be implemented.

That is, those skilled in the art can realize that the above-described method of providing medical marketing information using artificial intelligence analysis and personal health management can be provided by being included in a computer-readable recording medium by tangibly implementing a program of instructions for implementing it. will be easily understandable. In other words, it may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable recording medium. The computer readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and floptical disks. Included are hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, USB memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware device may be configured to act as one or more software modules to perform the operations of the present invention and vice versa.

The present invention is not limited to the above embodiments, and the scope of application is diverse, and various modifications and implementations are possible without departing from the gist of the present invention claimed in the claims.

100: Marketing information provision system 110: Advertisers (medical institutions, pharmaceutical companies)
120: User 1 SNS 130: User m SNS
140: customized medical information 150: user terminal
160: offline advertisement output unit 170: wearable device
101: transmission and reception unit 102: control unit
103: processing unit 104: database management unit
105: analysis unit 106: application support unit
107: medical information provision unit 108: compensation unit
301: Biometric data collection unit 302: Biometric data monitoring unit
303: keyword extraction unit 304: query analysis unit
305: database search unit 306: answer output unit
307: risk factor analysis unit 308: disease candidate group extraction unit
309 Medical information recommendation unit
401: SNS data collection unit 402: Analysis data set determination unit
403: entropy calculation unit 404: collection data analysis unit
405: medical information output unit
701: contribution calculation unit 702: reward calculation unit
801: wearable device power unit 802: wearable device control module
803: detection module 804: wearable device communication module
805: wearable device display unit 805: notification unit
S910: biometric data transfer step
S920: biometric data analysis step
S930: database construction step
S940: Q&A step
S950: Personalized medical information recommendation step
S960: Customized medical information decision step
S970: Customized medical information provision step
S980: Compensation step
S1010: terminal data set selection step
S1020: information entropy calculation step
S1030: analysis data set determination step
S1040: Content determination step

Claims (10)

In the medical marketing information providing system using artificial intelligence analysis and personal health management,
a wearable device 170 worn on the user's body to measure the user's biosignal;
The signal received from the wearable device is monitored, analyzed, and learned in real time to analyze the user's health risk factors, establish a database for medical information, and then, according to the health risk factors and Q&A with the user Through analysis, related medical information is recommended, and medical information determined by analyzing Q&A contents of users living or located in the area and information collected from social network services (SNS) is sent to an offline advertisement output unit or user terminal. a medical marketing information providing server 100 for providing customized medical advertisements for each individual and for each region by controlling the display to be output through; and
A health management application is installed, and the user's biometric data is detected by processing the signal transmitted from the wearable device, and the user's health analysis results, answers to inquiries, and customized medical information are received from the medical marketing information providing server. User terminal 150 for
including,
The medical marketing information providing server 100,
a transceiver 101 for receiving biometric data and questions transmitted from the user terminal, and transmitting an alarm, result or answer according to health analysis to the user terminal;
a processing unit 103 for pre-processing received data and processing data to be transmitted;
a database management unit 104 that stores bio-signal information, record information, medical information, learning model, analysis algorithm, and question and answer data;
an analysis unit 105 for analyzing the transmitted biometric data and questions to extract health risk factors and disease candidates and to recommend corresponding medical information;
an application support unit 106 installed in the user terminal to support the health management application capable of monitoring the user's vital signs and receiving answers to medical-related queries;
a medical information provision unit 107 for generating and providing customized medical information to users living or located in the corresponding region; and
Compensation unit 108 for calculating the contribution to the customized medical information of the corresponding user and rewarding (compensating) according to the contribution
It is characterized by including,
The medical information providing unit 107,
SNS data collection unit 401 for collecting SNS data for each user;
an analysis data set determining unit 402 for determining a data set of a user (user terminal) to be analyzed;
an entropy calculator 403 for calculating entropy;
a collection data analysis unit 404 for determining customized medical information by analyzing the data of the analysis data set determined by the analysis data set determination unit 402 among the data collected by the SNS data collection unit 401; and
A medical information output unit 405 for providing the determined customized medical information to an offline advertisement output unit 160 or a user terminal 150 located in a corresponding region
Medical marketing information providing system using artificial intelligence analysis and personal health management, characterized in that it comprises a.
delete According to claim 1,
The processing unit 103,
a biometric data collection unit 301 for collecting biometric data received through the user terminal;
a biometric data monitoring unit 302 for monitoring the collected biometric data;
a keyword extraction unit 303 for extracting a keyword from a query through the user terminal;
a query analyzer 304 for interpreting a user's question based on the extracted keywords;
a database search unit 305 for searching answers to the user's questions based on a question and answer database; and
An answer output unit 306 for outputting an answer to the searched user's question
Medical marketing information providing system using artificial intelligence analysis and personal health management, characterized in that it comprises a.
According to claim 3,
The analysis unit 105,
a risk factor analyzer 307 for analyzing health risk factors by analyzing the biometric data received from the biometric data monitoring unit 302;
a disease candidate group extraction unit 308 for extracting a disease candidate group of the user based on the user's question and the health risk factors; and
Medical information recommendation unit 309 for searching and recommending medical information related to the extracted disease candidate group
Medical marketing information providing system using artificial intelligence analysis and personal health management, characterized in that it comprises a.
delete According to claim 1,
The analysis data set determining unit 402,
In the modified information entropy calculated for the arrangement of each user terminal set, artificial intelligence analysis and personal Medical marketing information provision system using health management.
According to claim 6,
The entropy calculation unit 403,
A medical marketing information providing system using artificial intelligence analysis and personal health management, characterized in that the corrected information entropy is calculated using the following Equation 7 and Equation 8.
<Equation 7>

(Where S(ns) is information entropy, k _B is an arbitrary constant, a total of Ng unique connection types are observed for a given ns, and pi(ns) is the probability of each value (i is a number from 1 to Ng integer).)
<Equation 8>

(Where Sc(ns) is the modified information entropy, S(ns) is information entropy, and k _B is an arbitrary constant)
In the method of providing medical marketing information using artificial intelligence analysis and personal health management in the medical marketing information providing system using artificial intelligence analysis and personal health management of claim 1,
In the medical marketing information providing server 100, a biometric data transmission step of receiving biometric data measured by the wearable device 170 through the user terminal 150 (S910);
In the medical marketing information providing server 100, monitoring the received biometric data to analyze health risk factors, and informing the user terminal 150 when health risk factors occur (S920);
a database construction step (S930) of constructing a question and answer database related to medical information in the medical marketing information providing server 100;
In the medical marketing information providing server 100, a question answering step (S940) of searching for medical information related queries through the user terminal 150 based on the question and answer database and providing answers;
In the medical marketing information providing server 100, a personalized medical information recommendation step (S950) of recommending personalized medical information to a corresponding user through artificial intelligence analysis according to the user's health risk factors and questions and answers;
Customized medical information determination step of determining customized medical information by analyzing Q&A contents of users living or located in the corresponding area and data collected from social network services in the medical information providing unit of the medical marketing information providing server 100 (S960);
In the medical information providing unit of the medical marketing information providing server 100, providing the determined customized medical information to the offline advertisement output unit 160 or user terminals located in the corresponding region (S970). ); and
Compensation step (S980) of calculating the contribution of the customized medical information of the corresponding user terminal in the compensating unit of the medical marketing information providing server 100 and compensating according to the contribution
including,
In the customized medical information determining step (S960),
a terminal data set selection step (S1010) of randomly selecting a plurality of user terminal sets including a preset number of user terminals in the corresponding region;
an information entropy calculation step (S1020) of calculating corrected information entropy for the arrangement of each user terminal set selected in the terminal data set selection step (S1010);
an analysis data set determination step (S1030) of determining a uniformly distributed set of user terminals having the largest or smallest value of the corrected entropy as an analysis data set; and
A content determination step of determining the content of the customized medical information by analyzing social network service data and question and answer data for the determined analysis data set (S1040)
A method for providing medical marketing information using artificial intelligence analysis and personal health management, comprising a.
delete According to claim 8,
In the information entropy calculation step (S1020),
A method of providing medical marketing information using artificial intelligence analysis and personal health management, characterized in that the corrected information entropy is calculated using the following Equation 9 and Equation 10.
<Equation 9>

(Where S(ns) is information entropy, k _B is an arbitrary constant, a total of Ng unique connection types are observed for a given ns, and pi(ns) is the probability of each value (i is a number from 1 to Ng integer).)
<Equation 10>

(Where Sc(ns) is the modified information entropy, S(ns) is information entropy, and k _B is an arbitrary constant)

Images