KR102252464B1 - Method for determining status information of user that it is using mobile device based on combination of multiple type data and system thereof - Google Patents

Abstract

Disclosed, in an embodiment of the present invention, is a method of determining state information of a user using a mobile device based on a combination of two or more pieces of data. The method comprises: a data collection step of collecting first data collected from a sensor of a user's terminal, second data about the user's daily pattern, third data about the user's stopping area, and fourth data about demographics in a predetermined range around the user; a condition comparison step of generating a plurality of combinations using at least two or more of the collected first data to fourth data as elements, and comparing the generated combinations with a predetermined condition; a first information calculation step of calculating the user's first state information based on the comparison result; a second information calculation step of inputting the collected first data to fourth data into a machine learning model, verifying the calculated first state information, and calculating the second state information based on the verification result; and a final state determination step of determining the final state of the user based on the first state information and the second state information. In accordance with the present invention, a service app that is optimized to a user's current state can be provided to the user.

Description

{Method for determining status information of user that it is using mobile device based on combination of multiple type data and system thereof}

The present invention relates to a method and a system for determining user status information, and more specifically, by collecting and combining various types of data on a user, and the user's status using a communicable mobile device through the result. It relates to a method and a system for accurately and effectively determining information.

With the development of information and communication technology, users of multifunctional intelligent multifunction devices equipped with various sensors are increasing. In particular, as a representative multifunctional intelligent multifunction device, a smart phone has a feature of providing extremely high portability to the user while having a built-in sensor for providing not only a call function, which was an essential function in the prior art, but also various convenient functions to the user. In addition, the quality and quantity of user-related information collected by the sensor of the smartphone or stored in the smartphone through the active input of the user has been greatly increased compared to the past.

In accordance with the above social changes, various methodologies are being sought to provide various conveniences to users based on information stored in mobile devices that can collect user information, such as smartphones or laptop computers. Due to the limitations of the applied network system and the limitations of the logic for analyzing the collected information, it is difficult to accurately grasp the individual states of various users who use mobile terminals.

Korean Patent Registration No. 10-2160650 (Registration Announcement on September 28, 2020)

The technical problem to be solved by the present invention is to provide a state information determination method capable of accurately determining a user's state by combining multiple data collected in a mobile terminal and a system for implementing the method.

A method according to an embodiment of the present invention for solving the above technical problem is a method of determining status information of a user using a mobile terminal by a combination of two or more types of data. A data collection step of collecting first data, second data on the user's daily life pattern, third data on the user's waypoints, and fourth data on demographic statistics in a certain range around the user; A data classification step of generating a plurality of combinations including at least two or more of the collected first data to fourth data as elements; A first information calculation step of comparing the generated combination with a preset condition and calculating first state information of the user based on the comparison result; A second information calculation step of verifying the calculated first state information by inputting the collected first to fourth data into a machine learning model, and calculating second state information based on the verification result; And a final state determination step of determining a final state of the user based on the first state information and the second state information.

In the above method, the first data includes an acceleration sensor, an acoustic sensor, an infrared sensor, a gyro sensor, a proximity sensor, an RGB sensor, an illuminance sensor, a motion sensor, a hall sensor, a temperature and humidity sensor, and a geomagnetic sensor provided in the user's terminal. It may be data collected from at least two or more of them.

In the method, the second data may be data on the user's residence, work place, wake up time, and sleep time collected through an application installed in the terminal.

In the above method, the third data may be point of interest (POI) data collected by a location information system provided in the terminal.

In the above method, the fourth data may be data on an average value of the number of populations in the specified location when the location of the user is specified by a location information system provided in the user's terminal.

The method may further include a service information output step of searching a database for a service app corresponding to the determined final state, and outputting the searched result through an output unit of the terminal.

In the method, in the first information calculating step, it is determined whether the generated combinations match with a pre-stored heuristic rule, and only combinations that match the heuristic rule are extracted. It can be processed into the first state information.

A system according to another embodiment of the present invention for solving the above technical problem is a system that determines status information of a user using a mobile terminal by combining two or more types of data, and is collected from a sensor of the user's terminal. A data collection unit that collects first data, second data on the user's daily life pattern, third data on the user's waypoints, and fourth data on demographic statistics in a certain range around the user; A data classification unit for generating a plurality of combinations of at least two or more of the collected first data to fourth data as elements; A first information calculator configured to compare the generated combination with a preset condition and calculate first state information of the user based on the comparison result; A second information calculator configured to input the collected first to fourth data into a machine learning model to verify the calculated first state information, and to calculate second state information based on the verification result; And a user state analysis unit determining a final state of the user based on the first state information and the second state information.

In the system, the first data includes an acceleration sensor, an acoustic sensor, an infrared sensor, a gyro sensor, a proximity sensor, an RGB sensor, an illuminance sensor, a motion sensor, a hall sensor, a temperature and humidity sensor, and a geomagnetic sensor provided in the user's terminal. It may be data collected from at least two or more of them.

In the system, the second data may be data on the user's residence, work place, wake up time, and sleep time collected through an application installed in the terminal.

In the system, the third data may be point of interest (POI) data collected by a location information system provided in the terminal.

In the system, the fourth data may be data on an average value of the number of populations at the specified location when the location of the user is specified by a location information system provided in the user's terminal.

The system may further include a service information output unit that searches for a service app corresponding to the determined final state in a database, and outputs the searched result through an output unit of the terminal.

In the system, the first information calculation unit determines whether the generated combinations match with a pre-stored heuristic rule, extracts only combinations matching the heuristic rule, and determines It includes a heuristic rule processing unit that processes one state information.

An embodiment of the present invention discloses a computer-readable recording medium storing a program for executing the method.

In addition to the above-described embodiments, if it is interpreted to include all the technical configurations of the present invention according to a reasonable interpretation, it may be included in the scope of the present invention.

According to the present invention, by accurately analyzing the state of a user using a mobile terminal, it is possible to recommend a service app optimized to the user's current state to the user.

In addition, according to the present invention, by estimating and providing a user's individual state, it is possible to develop various automated services that will change operations according to the state of individuals in the future and provide customized services.

1 is a schematic diagram conceptually showing a process in which the method according to the present invention is implemented.
2 is a diagram schematically showing a block diagram of an example of a system according to the present invention.
3 is a diagram schematically showing another embodiment of a system for providing a conditional service.
4 is a diagram schematically showing a flow diagram of an example of a method according to the present invention.

As for terms used in the embodiments, general terms that are currently widely used as possible are selected while taking functions of the present invention into consideration, but this may vary according to the intention or precedent of a technician working in the field, the emergence of new technologies, and the like. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning of the terms will be described in detail in the description of the corresponding invention. Therefore, the terms used in the present invention should be defined based on the meaning of the term and the overall contents of the present invention, not a simple name of the term.

When a part of the specification is said to "include" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary. In addition, terms such as "... unit" and "... module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the drawings.

1 is a schematic diagram conceptually showing a process in which the method according to the present invention is implemented.

Hereinafter, a method for implementing the present invention is a method for providing a state tailored service, and a system for implementing the method according to the present invention will be abbreviated as a state tailored service providing system 100, respectively.

First, the state tailored service providing system 100 collects various types of data in order to accurately determine the state of the user (S1). The data collected in step S1 may include basic user information, terminal sensor data, POI data, and floating population data. For convenience, user basic information, terminal sensor data, POI data, and floating population data may be referred to as first data to fourth data, respectively, regardless of the order.

User basic information refers to data on a user's daily life pattern collected through an application installed in the user's mobile terminal. For example, the user basic information may include the user's residence (address), work place (address), the user's wake up time, and sleep time. The basic user information may be automatically collected through the execution time or the number of executions of the application installed in the mobile terminal, or may be collected aperiodically in the mobile terminal in a manner that the user inputs through an input device.

Terminal sensor data refers to data collected from various sensors included in the user's mobile terminal. Terminal sensor data includes not only the data collected by the sensor linked to the application installed on the user's mobile terminal, but also the data collected by the sensor that is activated alone without being linked with the application installed on the user's mobile terminal. Includes. For example, acceleration sensor, acoustic sensor (MIC), infrared sensor, gyro sensor, proximity sensor, RGB sensor, illuminance sensor, motion sensor, Hall effect sensor, temperature and humidity sensor and geomagnetism provided in the user's mobile terminal All data collected from at least two or more of the geomagnetic sensors may be included in the terminal sensor data.

The terminal sensor data may include a wide range of sensors included in a smart watch operated in conjunction with a mobile terminal in addition to sensors provided in a mobile terminal possessed by a user. For example, the user's heart rate and the user's heart rate by a smart device (smart watch) used with a mobile terminal for the purpose of providing a series of data to a healthcare application installed in the mobile terminal If the pulse rate, the user's blood pressure, the user's blood oxygen saturation, and the like are measured, the above data may also be included in the terminal sensor data in the present invention.

Point Of Interest (POI) data refers to data on a user's waypoint. A user may visit a specific place periodically or aperiodically in addition to a place where he/she frequently visits and stays for a long time, such as a place of residence and work, and in the present invention, a specific place that the user visits other than the place of residence and work is referred to as a stopover place. do. For example, in the present invention, POI data may be data on the locations of restaurants, schools, government offices, tourist information centers, gas stations, bus stops, subway stations, and convenience stores. POI data may be collected by a location information system installed in a mobile terminal, and the location information system may include a Global Positioning System (GPS), Beidou, GLONASS, Galileo, QZSS, and the like.

Floating population data refers to data on demographic statistics within a certain range of users' surroundings. Specifically, when the user's location is specified by the location information system provided in the user's terminal, it may be data on an average value of the number of populations at the specified location. For example, if the current location of the user is a cafe located at a specific address, and the average number of the population visiting the cafe at that time is 10, the collected floating population data is 10. The floating population data may vary each time depending on the time when the user's location is identified and the region in which the user is located. In addition, according to the settings of an application installed in the mobile terminal, population data for a certain area may be collected with the user as the center of the current location.

In the present invention, when the floating population data is measured, POI data may be utilized. For example, when using a location information system such as GPS, the resolution of the area (place) where the user is located can be assumed to be a minimum unit of 25m to 50m, and the floating population data is a pico cell, 50m * 50m) can be treated as the number of population in all POI data included.

In step S1, when the above-described types of data are collected, the collected data may be variously combined and processed according to a heuristic rule (S2) or processed by a machine learning processor (S3). The state tailored service providing system 100 stores heuristic rules and feedback data in a database in order to effectively perform steps S2 and S3. Based on the processing results in steps S2 and S3, the state tailored service providing system 100 accurately determines the user's individual state information (S4), and according to the user's state information determined in step S4, the current user The most necessary service can be provided through a mobile terminal.

2 is a diagram schematically showing a block diagram of an example of a system according to the present invention.

Referring to FIG. 2, it can be seen that the conditional service providing system 100 includes a data receiving unit 110, a database 130, a data processing unit 150, and a data output unit 170.

The mobile terminal 10 shown together with the state tailored service providing system 100 according to an embodiment of the present invention includes a display unit for displaying a screen 11 and an input device for receiving data from a user. Means electronic devices. The input device provided in the mobile terminal 10 may be at least one of a keyboard, a mouse, a trackball, a microphone, a mechanical button, and a touch panel.

2, the mobile terminal 10 is shown in the form of a smartphone, but the mobile terminal 10 when the present invention is implemented is not limited to a smartphone, and a tablet personal computer (Tablet PC), a netbook, and It can include all of the same portable terminal.

The state tailored service providing system 100 may correspond to at least one or more processors, or may include at least one or more processors. Accordingly, the state tailored service providing system 100 may be driven in a form included in another hardware device such as a microprocessor or a general-purpose computer system. In other words, the state tailored service providing system 100 may be mounted on the mobile terminal 10 as it is, or connected to the mobile terminal 10 via a wired or wireless network to control the contents displayed on the screen 11 of the terminal 10. It can also be implemented in a form.

The conditional service providing system 100 shown in FIG. 2 highlights only components for emphasizing only the features of the embodiment of the present invention. Therefore, it is understood by those of ordinary skill in the art that other general-purpose components may be further included in addition to the components shown in FIG. 2 when the embodiment shown in FIG. 2 is different from the embodiment shown in FIG. 2. I will be able to.

The system 100 for providing a status tailoring service according to an embodiment of the present invention may control contents displayed on the screen 11 of the mobile terminal 10. More specifically, the state tailored service providing system 100 can control the content displayed on the screen 11 of the mobile terminal 10 to be displayed differently according to the user's input, and Various types of data may be collected according to various sensors, and the operation of the mobile terminal 10 may be controlled to accurately determine the user's state information.

Hereinafter, the state tailored service providing system 100 shown in FIG. 2 is regarded as an example of the system described in FIG. 1, and descriptions overlapping with those described in FIG. 1 will be omitted.

The data receiving unit 110 receives first to fourth data through an application installed in the mobile terminal 10 or various sensors provided. Data received by the data receiving unit 110 is stored in the database 130.

The database 130 may further include a cache memory in addition to the non-volatile memory, and data frequently called by the data processing unit 150 to be described later are stored in the cache memory, It can be operated to improve the overall data processing speed.

The data processing unit 150 receives the first to fourth data stored in the database 130, classifies the data based on the type, length, and shape of each data, and separates the classified data as individual components. To create a combination. The combinations generated by the data processing unit 150 may be compared with a heuristic rule stored in the database 130 and processed into first state information, or processed by a machine learning model to be processed into second state information. A specific example of the result processed by the data processing unit 150 will be described later with reference to FIG. 3.

The data processing unit 150 obtains the user's final state information by synthesizing and analyzing the first state information and the second state information. For example, by analyzing the user's final state information acquired by the data processing unit 150, "the state that the user is playing screen golf with his company colleagues indoors" or "the state that the user is having a meal with his spouse in a restaurant" Information such as "may be obtained, and the data output unit 170 may control the corresponding information to be output on the screen 11 of the mobile terminal 10. After the user visually confirms the information output to the mobile terminal 10, the user can make a simple input to the effect that the confirmed information is true, and after receiving the corresponding input, the user's It is possible to search for an application that can provide the most appropriate service in consideration of the current state information and induce a user to execute the searched application.

3 is a diagram schematically showing another embodiment of a system for providing a conditional service.

The state tailored service providing system 200 shown in FIG. 3 is a system in which the function of the state tailored service providing system 200 described in FIGS. 1 and 2 is most expanded, and hereinafter, which has not been described in FIGS. 1 and 2. The function will be described in detail. In addition, modules named with the same name in FIGS. 2 and 3 perform the same function, and the state tailored service providing system 200 of FIG. 3 also obtains the user's final state information according to steps S1 to S4 described in FIG. 1. It is regarded as doing.

Referring to FIG. 3, the system 200 for providing a conditional service shown in FIG. 3 includes a database 210, a data receiving unit 220, a data classification unit 230, a heuristic rule processing unit 240, and a machine learning processing unit 250. ), it can be seen that it includes a user state analysis unit 260 and a service information output unit 270.

The data processing unit 150 described in FIG. 1 may include a data classification unit 230, a heuristic rule processing unit 240, a machine learning processing unit 250, and a user state analysis unit 260, which will be described later. It is assumed that the output unit 170 performs the same function as the service information output unit 270 to be described later. In addition, the heuristic rule processing unit 240 and the machine learning processing unit 250 are modules that process steps S2 and S3 of FIG. 1 and may be referred to as a first information calculation unit and a second information calculation unit.

The database 210 stores various types of data, receives a call from the data receiving unit 220 and the service information output unit 270, and transmits the stored data to the module that sent the call. The data stored in the database 210 includes not only first data, second data, third data, and fourth data, but also a heuristic rule for supporting the function of the heuristic rule processing unit 240, and a machine learning processing unit ( 250) may include logic and parameters of the machine learning model. Here, the first to fourth data are data on the daily patterns of the user who uses the mobile terminal 10, data collected from the sensors of the mobile terminal 10, data on the user's stopover, and a certain range of the user's surroundings. It has already been explained that each means demographic data in

The data receiving unit 220 is connected to the communication module of the mobile terminal 10 to receive various types of data or firstly receive data stored in the database 210. The data transmitted to the data receiving unit 220 is transmitted to the data classifying unit 230 through only basic labeling processing. Depending on the embodiment, the data receiving unit 220 may be implemented by being integrated with the database 210. Hereinafter, a module implemented by being integrated with the database 210 is a data collection unit that is a name distinguished from the data receiving unit 220. It will be called (not shown).

The data classification unit 230 generates a plurality of combinations including at least two or more of the collected first data to fourth data as elements. Specifically, the data classification unit 230 receives the first to fourth data and stores a unique logic for converting the received data into a combination of a certain type.

Data received 1st data-A 2nd data-B 3rd data-C Multiple combinations generated by the data classification unit Combination 1 (A, B) Combination 2 (B, C) Combination 3 (A, C) Combination 4 (A, B, C)

Table 1 is a table briefly showing a plurality of combinations that can be generated after the data classification unit 230 receives each of the first data, the second data, and the third data. Referring to Table 1, the data classifying unit 230 secures a total of three data components by receiving each of the first data, the second data, and the third data. It can be seen that a total of 4 combinations was created, as a combination was created that included at least two.

Data received First data (terminal sensor data)-GPS sensor data 1st data (terminal sensor data)-acceleration sensor data Second data (basic user information)-residential data Multiple combinations generated by the data classification unit Combination 1 (GPS sensor data, acceleration sensor data) Combination 2 (Acceleration sensor data, residential data) Combination 3 (GPS sensor data, residential data) Combination 4 (GPS sensor data, acceleration sensor data, residence data)

Table 2 is a table for specifically explaining Table 1. In Table 2, the data received by the data receiving unit 220 are GPS sensor data, acceleration sensor data, and residential data, and the data classifying unit 230 may generate a total of four combinations from the received data.

Tables 1 and 2 are examples for explaining a plurality of combinations generated by the data classification unit 230, so if a plurality of combinations are generated through the above-described process, different combinations from those described in Tables 1 and 2 It will be apparent to those skilled in the art that it can be produced.

Subsequently, the heuristic rule processing unit 240 compares the combination generated by the data classification unit 230 with a preset condition, and calculates first state information of the user based on the comparison result. The heuristic rule processing unit 240 receives the heuristic rule from the database 210 or stores the heuristic rule internally in advance, receives the combinations generated by the data classification unit 230 and performs a comparison operation, and performs a comparison operation. It performs a function of processing the result of performing the process into the user's first state information. The heuristic rule required to perform the function of the heuristic rule processing unit 240 may be an example of the above-described preset condition.

state
number Heuristic Rule One Residence & After wake-up time Before bedtime & GPS sensor stop & Acceleration sensor stop 2 8~10 hours after the commencement point & wake-up time & GPS sensor activation & acceleration sensor activation 3 -4~-2 hours before departure from work & 16~20:00 & bedtime & GPS, acceleration sensor activated 4 Residence or work place & GPS sensor stop & acceleration sensor stop & illuminance below average 5 Places other than residential and commuting places & GPS sensor and acceleration sensor active & above average illuminance 6 WIFI signal detection or Bluetooth signal detection & high floating population 7 WIFI signal detection or Bluetooth signal detection & low floating population 8 GPS sensor Vehicle road detection & GPS sensor moving speed over 40km/h & acceleration sensor active 9 GPS sensor bicycle road detection & GPS sensor movement speed 6~25km/h & acceleration sensor active 10 GPS sensor Pedestrian road detection & GPS sensor movement speed less than 5km/h & acceleration sensor active 11 POI restaurant or shopping mall & time 11~13, 17~19 o'clock & GPS sensor stop 12 POI shopping mall/department store/market & WIFI/Bluetooth signal strong & sound sensor signal strong
Above average illuminance & holidays (Saturday/Sunday) & G GPS sensor active & acceleration sensor active 13 POI tennis court/football court & acceleration sensor activated 14 POI Health Club/Swimming Pool & After leaving the office (18~22:00) 15 POI attractions & holidays (Saturday/Sunday) & above average illumination & acceleration sensor active 16 POI Hospital/Pharmacy & WIFI/Bluetooth Signal Strong & Illuminance Below Average & GPS Sensor Active

Table 3 is an example of a heuristic rule referred to by the heuristic rule processing unit 240 to calculate the user's first state information. When interpreting the heuristic rule of status number 1 in Table 3, it is a combination generated by the data classification unit 230, and the user is located in a residential area, and the time when the data is received is after the wake-up time and before the bedtime, and If it is stopped and it is determined that the acceleration sensor is stopped, it means that the combination matches the heuristic rule in state number 1.

As shown in Table 3, the heuristic rule used by the heuristic rule processing unit 240 to calculate the first state information is composed of a rule in which an and condition is expanded in parallel. That is, if any of the conditions connected in parallel is not satisfied, it is determined that the heuristic rule is not matched by the heuristic rule processing unit 240. The heuristic rule processing unit 240 receives a plurality of combinations generated by the data classification unit 230, compares each combination with a heuristic rule to determine whether they match, and extracts only the matching combinations as first state information. Processed.

Status number First status information (text information conversion) One Sleeping condition 2 Work status 3 Leave work 4 Indoor activity 5 Outdoor activity 6 Group activity status 7 Single activity 8 Moving by car 9 Movement status by bicycle 10 Movement status on foot 11 During meal 12 Shopping 13 During outdoor exercise 14 During indoor exercise 15 During travel/tourism 16 Visiting state

Table 4 is a table showing an example of first state information calculated by the heuristic rule processing unit 240. Table 4 should be interpreted in conjunction with Table 3, and when the heuristic rule processing unit 240 finds a combination matching a specific heuristic rule through Table 3, the first state corresponding to the state number by grasping the state number of the combination Information can be calculated.

For example, the heuristic rule processing unit 240 is a combination generated by the data classification unit 230, and the user is located in a residential area, and the time at which the data is received is after waking up and before bedtime, and the GPS sensor is stopped. In addition, if it is determined that the acceleration sensor is stopped, first state information indicating a sleeping state corresponding to state number 1 may be calculated. Since the heuristic rule and the first state information described in Tables 3 and 4 are only examples, the heuristic rule or the first state information included in the system or calculated when the present invention is actually implemented are the items listed in Tables 3 and 4. Not limited.

The heuristic rule processing unit 240 calculates the user's status information based on the collected data by referring to the data shown in Tables 3 and 4, but the information calculated in this process is a process of calculating a combination using data as individual elements. And information obtained only by matching the calculated combinations with a preset heuristic rule, there is a limitation in that it is difficult to completely reflect the user's state.In the present invention, in order to compensate for this limitation, machine learning is used. Second state information is additionally calculated based on the accumulated user data.

The machine learning processing unit 250 inputs the first data to the fourth data received by the data receiving unit 220 into a preset machine learning model to verify the first state information calculated first, and the second state information based on the verification result. Calculate status information. In this process, the machine learning processing unit 250 receives the logic and parameters of the machine learning model for processing the machine learning process from the database 210. The machine learning model that can be applied in the present invention is not limited to one specific model. For example, the machine learning model used by the machine learning processing unit 250 includes at least one of a support vector machine (SVM), a genetic algorithm (GA), and an artificial neural network (ANN). It can be ideal.

As shown in FIG. 1, the machine learning processing unit 250 processes the machine learning process by using first to fourth data as input data, but in addition, user feedback data and already calculated first state information are also input data. It can also work by including it in. Since the heuristic rule processing unit 240 determines the user's state information based on the consistency with the preset heuristic rule, the user's behavior pattern is exceptional or the preset heuristic rule is inappropriate, so that the state information of the user with high correlation There may be a situation in which it is impossible to calculate, and the machine learning processing unit 250 may compensate for this situation.

For example, when analyzing the first status information calculated by the data collected at the first time point, it is assumed that the user was in a state of attendance. It is assumed that data similar to the first point of view are collected at the second point of view. In the above situation, the machine learning processing unit 250 not only receives as input data the result of the heuristic rule processing unit 240 determined as the attendance state at the second point of time, but also determines the attendance state at the first point of time, and then actually leaves the office. Since it is a state, history information modified by feedback to the user is also used as input data, machine learning processing is performed, and finally, a result of going to work or leaving work may be outputted as second state information.

As described above, the machine learning processing unit 250 calculates the second state information supplemented with the mechanical determination of the heuristic rule processing unit 240, and the first state information and the second state information in the user state analysis unit 260 to be described later. By synthesizing, the final state of the user is determined. For example, the user state analysis unit 260 may determine the final state of the user as the first state information or the second state information, and adjust based on the first state information, the second state information, and the weight. Accordingly, information different from the first state information and the second state information may be determined as the final state of the user.

As an optional embodiment, the machine learning processing unit 250 may perform machine learning processing using the first state information as training data rather than input data and calculate the second state information. Since there is a model that repeats the process of dividing and verifying data into training data and test data according to machine learning models, if such a model is adopted as a machine learning model, this optional embodiment can be applied.

The service information output unit 270 searches for a service app corresponding to the final state of the user determined by the user state analysis unit 260 in the database 210, and displays the search result on the screen of the mobile terminal 10. By outputting through the output unit as shown in (11), users can experience extremely high convenience by using the service app. In the service information output unit 270, logic for searching for a service app suitable for the user's final state in the database 210 is stored in the form of a script.

For example, the service information output unit 270 provides a service app that allows the user to enjoy a joint game if the user is gathered with several acquaintances, or outputs a map that allows the user to use the bicycle road for a long time while riding a bicycle. The navigation app to be executed can be executed through the mobile terminal 10. In addition, the service information output unit 270 may control to run a service app that provides sleep-induced sound in the mobile terminal 10 of a user who moves for a long time through a train.

Hereinafter, the state tailored service providing system 200 described in FIG. 3 will be described in detail by including the items described in FIGS. 1, 2, and Tables 1 to 4.

The data receiving unit 220 includes the first data collected from the sensor of the user's terminal, the second data on the user's daily pattern, the third data on the user's stopover, and the fourth demographic statistics in a certain range around the user. Receive data. Various types of data received by the data receiving unit 220 are stored and managed in the database 210, and the database 210 and the data receiving unit 220 may be collectively referred to as a data collection unit (not shown).

The data classification unit 230 generates a plurality of combinations using at least two or more of the collected first data to fourth data as elements. Examples of the plurality of combinations generated by the data classification unit 230 have already been described in Tables 1 and 2, and here, in order for the data classification unit 230 to generate a plurality of combinations, the data receiving unit 220 receives The configuration for filtering (classifying) one data will be additionally described.

The mobile terminal 10 used by the user may collect various types of information about the user according to various sensors embedded in the mobile terminal 10 or a unique function of an application installed in the mobile terminal 10. The data receiving unit 220 is interlocked with the hardware configuration of the mobile terminal 10 to receive data periodically or aperiodically. The data classification unit 230 may perform a data classification operation to determine an element constituting the combination before generating a plurality of combinations based on the data received by the data receiving unit 220.

For example, _{at a time t 1} , the data receiving unit 220 has received the first data A, the second data B, the third data C, and the fourth data D, and _{at the time t 2} , the data receiving unit 220 Suppose that A'as the first data, B as the second data, C'as the third data, and D as the fourth data are received. Here, it will be apparent to those skilled in the art that the first data to the fourth data mean the types of data described above.

The data receiving unit 220 _{received the first data to the fourth data not only at the time point t 1} but also at the time point t ₂ , but the values of the second data and the fourth data did not change at all. _{Therefore, when generating a plurality of combinations with data for the time point t 2} , the data classifying unit 230 operates so that only the first data and the third data become elements of the combination. That is, even though the time at which the data was collected has changed over time, data that still does not change is excluded from the elements of the combination, thereby increasing the accuracy and speed of the process of calculating the first state information compared to the heuristic rule. .

This selective processing continues even in a situation in which data received by the data receiving unit 220 continues to accumulate, and in order to implement the above data selection processing function of the data classification unit 230, according to an embodiment, the machine learning processing unit ( 250), the logic and parameters of the machine learning model may be used. Each module constituting the state tailored service providing system 200 described in the present invention may process and process data according to a different order from the configuration shown in FIG. 3.

When the data classification unit 230 extracts only meaningful data from the various data of the received mobile terminal 10 and generates a plurality of combinations with the extracted data, the heuristic rule processing unit 240 performs the generated combinations. It compares with the heuristic rule and calculates the first state information based on the result of the comparison, and the machine learning processing unit 250 calculates the second state information by using the first state information and other feedback data.

The user state analysis unit 260 performs a process for calculating reasonable result data (the user's final state) by fusing the first state information and the second state information calculated by the above-described process, and as an optional embodiment, When the final state of the user is determined, the service information output unit 270 searches the database 210 for a service app that can be most helpful to the user and provides it to the user according to a unique logic. If the user who uses the present invention only wants to check the user's own final state and does not want to receive a service app recommendation, the service app recommendation function can be deactivated. The information output unit 270 is omitted, and may function as a system that accurately provides only the user's final state to the user.

4 is a diagram schematically showing a flow diagram of an example of a method according to the present invention.

Since FIG. 4 can be implemented by the system for providing a state tailored service described in FIGS. 1 to 3, descriptions overlapping with those described in FIGS. 1 to 3 will be omitted below, and descriptions of FIGS. 1 to 3 will be described. It will be described with reference.

First, the data receiving unit 220 randomly receives four types of user information data (S410). Random reception in step S410 means that there is no need for restrictions such as that the received data must be periodic or aperiodic. The user information data may include first to fourth data.

Subsequently, the data classification unit 230 receives the received data, classifies and processes it (S430).

The heuristic rule processing unit 240 and the machine learning processing unit 250 determine a detailed state of the user as a result of the data classification unit 230 primarily processing (S450). The state information of the user determined in step S450 may include both the first state information and the second state information, as well as the user state analysis unit 260 analyzed based on the first state information and the second state information. It could be the result.

Finally, the service information output unit 270 identifies the final state of the user through the user state information determined in step S450, and outputs the related service app to the output unit of the user's mobile terminal 10. The user can confirm that he/she is in a working state, a state of work, an exercise state, a visit to the hospital, etc. through the mobile terminal 10, and take the most appropriate action for the corresponding state through the service app output on the mobile terminal 10.

The state tailored service providing system 100 according to the present invention is conceived from the fact that most people have multifunctional intelligent multifunction devices such as smart phones, and that smart phones are devices that accumulate and store various user information, It collects four types of user information data, categorizes and processes the collected information data to accurately and diagnose the user's current state, and provides the most appropriate service app for the user's current state.

The embodiment according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded in a computer-readable medium. In this case, the medium is a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magnetic-optical medium such as a floptical disk, and a ROM. It may include a hardware device specially configured to store and execute program instructions, such as, RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to a person skilled in the computer software field. Examples of the computer program may include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

Specific implementations described in the present invention are examples, and do not limit the scope of the present invention in any way. For brevity of the specification, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection or connection members of the lines between the components shown in the drawings exemplarily represent functional connections and/or physical or circuit connections. It may be referred to as a connection, or circuit connections. In addition, if there is no specific mention such as “essential” or “importantly”, it may not be an essential component for the application of the present invention.

In the specification of the present invention (especially in the claims), the use of the term “above” and a similar reference term may correspond to both the singular and the plural. In addition, when a range is described in the present invention, the invention to which an individual value falling within the range is applied (unless otherwise stated), and each individual value constituting the range is described in the detailed description of the invention. Same as. Finally, unless explicitly stated or contradicted to the order of the steps constituting the method according to the present invention, the steps may be performed in a suitable order. The present invention is not necessarily limited according to the order of description of the steps. The use of all examples or illustrative terms (for example, etc.) in the present invention is merely for describing the present invention in detail, and the scope of the present invention is limited by the above examples or illustrative terms unless limited by the claims. It does not become. In addition, those skilled in the art can recognize that various modifications, combinations, and changes may be configured according to design conditions and factors within the scope of the appended claims or their equivalents.

10: mobile terminal
100, 200: status information service providing system
110: data receiving unit
130: database
150: data processing unit
170: data output unit
210: database
220: data receiving unit
230: data classification unit
240: heuristic rule processing unit
250: machine learning processing unit
260: user condition analysis unit
270: service information output unit

Claims (15)

As a method of determining the status information of a user using a mobile terminal by a combination of two or more types of data,
First data collected from the sensor of the user's terminal, second data on the user's daily pattern, third data on the user's waypoint, and fourth data on demographic statistics in a certain range around the user, A data collection step of collecting data including all four types of data;
A data classification step of generating a plurality of combinations including at least two or more of the collected first data to fourth data as elements;
A first information calculation step of comparing the generated combination with a preset condition and calculating first state information of the user based on the comparison result;
A second information calculation step of verifying the calculated first state information by inputting the collected first to fourth data into a machine learning model, and calculating second state information based on the verification result; And
A final state determination step of determining a final state of the user based on the first state information and the second state information; including, the state information of the user using the mobile terminal as a combination of two or more pieces of data. How to judge. The method of claim 1,
The first data,
Two, which are data collected from at least two of the acceleration sensor, acoustic sensor, infrared sensor, gyro sensor, proximity sensor, RGB sensor, illuminance sensor, motion sensor, hall sensor, temperature and humidity sensor, and geomagnetic sensor provided in the user's terminal. A method of determining the status information of a user using a mobile terminal based on a combination of more than one type of data. The method of claim 1,
The second data,
A method of determining the status information of a user using a mobile terminal by a combination of two or more data, which is data on the user's residence, work place, wake up time, and sleep time collected through an application installed in the terminal. The method of claim 1,
The third data,
A method of determining status information of a user using a mobile terminal by a combination of two or more pieces of data, which are point of interest (POI) data collected by a location information system provided in the terminal. The method of claim 1,
The fourth data,
When the location of the user is specified by the location information system provided in the user's terminal, the status information of the user using the mobile terminal as a combination of two or more data, which is data on the average value of the number of populations at the specified location How to judge. The method of claim 1,
The above method,
A mobile terminal with a combination of two or more pieces of data, further comprising a service information output step of searching for a service app corresponding to the determined final state in a database and outputting the searched result through an output unit of the terminal How to determine the user's status information using. The method of claim 1,
The first information calculation step,
It is determined whether the plurality of generated combinations coincide with a previously stored heuristic rule,
And a heuristic rule processing step of extracting only combinations consistent with the heuristic rule and processing it into first state information. A method of determining state information of a user using a mobile terminal with a combination of two or more pieces of data. A computer-readable recording medium storing a program for executing the method according to any one of claims 1 to 7. As a system that determines the status information of a user using a mobile terminal by a combination of two or more types of data,
The first data collected from the sensor of the user's terminal, the second data on the daily pattern of the user, the third data on the user's stopover, and the fourth data on the demographic statistics in a certain range around the user. A data collection unit to receive;
A data classification unit that generates a plurality of combinations of at least two or more of the collected first data to fourth data as elements;
A first information calculation unit comparing the generated combination with a preset condition and calculating first state information of the user based on the comparison result;
A second information calculator configured to input the collected first to fourth data into a machine learning model to verify the calculated first state information, and to calculate second state information based on the verification result; And
Based on the first state information and the second state information, a user state analysis unit that determines the final state of the user; including, the state information of the user using the mobile terminal by a combination of two or more data Judging system. The method of claim 9,
The first data,
Two, which are data collected from at least two of the acceleration sensor, acoustic sensor, infrared sensor, gyro sensor, proximity sensor, RGB sensor, illuminance sensor, motion sensor, hall sensor, temperature and humidity sensor, and geomagnetic sensor provided in the user's terminal. A system that determines the status information of a user using a mobile terminal based on a combination of more than one type of data. The method of claim 9,
The second data,
A system for determining the status information of a user using a mobile terminal by a combination of two or more data, which is data on the user's residence, work place, wake up time, and sleep time collected through an application installed in the terminal. The method of claim 9,
The third data,
A system for determining status information of a user using a mobile terminal by a combination of two or more pieces of data, which are point of interest (POI) data collected by a location information system provided in the terminal. The method of claim 9,
The fourth data,
When the location of the user is specified by the location information system provided in the user's terminal, the status information of the user using the mobile terminal as a combination of two or more data, which is data on the average value of the number of populations at the specified location System to judge. The method of claim 9,
The system,
A mobile terminal with a combination of two or more data, further comprising a service information output unit for searching a service app corresponding to the determined final state in the database and outputting the searched result through the output unit of the terminal. A system that determines the user's status information. The method of claim 9,
The first information calculation unit
It is determined whether the plurality of generated combinations coincide with a previously stored heuristic rule,
A system for determining status information of a user using a mobile terminal by combining two or more pieces of data, extracting only combinations that match the heuristic rule and processing them into first status information.

Images