KR20140147168A - Apparatus and method for modeling a personalized lifestyle - Google Patents

Abstract

The present invention relates to an apparatus and a method for modeling a personalized lifestyle. A method for modeling a personalized lifestyle according to the present invention includes the steps of: collecting life logs; extracting individual behavior sequences from the collected life logs; analyzing individual tendencies by using the collected life logs; and generating personalized life habit models according to each tendency by connecting behavior sequences of users having similar tendencies to each other.

Description

[0001] APPARATUS AND METHOD FOR FORMING A PERSONALIZED LIFESTYLE [0002]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a technology for managing lifestyles, collecting big data of an individual's life log, performing a semantic-based analysis using the collected big data, extracting an action sequence according to personalized lifestyle, The present invention relates to a technique for generating a personalized lifestyle model by modeling an extracted behavior sequence so as to infer an action to be taken.

In Korea, especially lifestyle - related diseases are increasing rapidly, but similar cases of metabolic diseases, which can not be explained only by westernization of diet, aging, and increase of obesity population, are emerging from infants and cleaners. As a result, the medical cost of the National Health Insurance has been continuously increasing due to the fact that it can not be solved by the medical drug treatment and it is developed as a chronic disease. Lifestyle medicine has become important as a solution to this problem, but it is difficult to apply lifestyle medicine due to problems such as traditional documentary method, continuous treatment effect, systematic management of patients and difficulty of real effect.

Currently, various IT products and care services (such as child protection and growth care, care for the elderly, mental healing care of the general public, and financial forecasting management in a rapidly changing economic environment) , Psychology, physiology, emotion, etc.) are difficult to understand, express and quantify, there is a fundamental limitation in application and advancement.

In particular, there is a lack of consideration of the factors that determine 'I' represented by lifestyle, and it faces the difficulty of tools or methods that characteristically express human beings with complex and diverse characteristics.

To overcome this problem, various studies using Lifelog data have been conducted worldwide. However, the problem of lack of innovative devices for life log collection and semantic analysis of vast amount of data is still not resolved.

As an example of the conventional life care service technology, Korean Unexamined Patent Publication No. 2004-45459, "Life Care Service Providing System" has been proposed. In the prior art, life care service technology is disclosed in which life log information required for checking a user's health state is collected, life log information is analyzed, and lifecare information used for managing lifestyle of a user is provided

However, in the prior art, the life log information is analyzed and a lifestyle setting process is first required in order to manage a lifestyle of a user, and a rule corresponding to a specific situation has to be set in advance. The rules set forth in the prior art do not consider individual differences but can not be changed appropriately according to the times, and do not mention a specific description of how to set rules. Also, prior art does not consider human diversity in analyzing life logs.

Therefore, it is possible to collect big data of an individual's life log and perform semantic-based analysis using the same to extract a general action sequence, an action sequence according to personalized lifestyle, model the extracted action sequence, It is necessary to infer the behaviors that will occur afterwards and to manage the health of the users by inducing the inferred behaviors in a desirable direction.

Korean Public Patent No. 2012-0045459 (public date 2012.05.09)

SUMMARY OF THE INVENTION It is an object of the present invention to provide an apparatus and method for personalized lifestyle modeling.

Specifically, the present invention collects life logs, extracts individual action sequences from the collected life logs, analyzes the individual propensity using the collected life logs, and correlates the behavior sequences of users having similar propensity, The lifestyle modeling method comprising the steps of: generating a lifestyle model;

According to an aspect of the present invention, there is provided a personalized lifestyle modeling device comprising: a log collection unit for collecting life logs; An action sequence acquiring unit for extracting an individual action sequence from the collected life log; A tendency analysis unit for analyzing individual tendencies using the collected life logs; And a lifestyle model generating unit for generating a lifestyle model that is personalized according to the tendencies by connecting action sequences of users having similar tendencies.

At this time, the life log may include at least one of Private Data, Public Data, Personal Data, Anonymous Data, Connected Data, and Sensor Data One can be included.

At this time, the action sequence acquiring unit may extract a behavior pattern repeated more than a predetermined number of times by the individual action sequence using the data mining technique in the collected life log.

At this time, the propensity analyzing unit may analyze the individual propensity by analyzing the activity information in the individual social network included in the collected life log.

At this time, the lifestyle model generation unit analyzes the similarities among the behavior sequences of users having similar tendencies, connects the action sequences having high similarity in a tree form, and generates a personalized lifestyle model of the ontology type for each of the tendencies .

A personalized lifestyle modeling method according to an exemplary embodiment of the present invention includes: collecting a life log; Extracting an individual action sequence from the collected life logs; Analyzing individual tendencies using the collected life logs; And generating a personalized lifestyle model by connecting the behavior sequences of the users having similar inclinations to the inclinations.

At this time, the life log may include at least one of Private Data, Public Data, Personal Data, Anonymous Data, Connected Data, and Sensor Data One can be included.

In this case, the step of extracting the individual action sequence may extract a behavior pattern repeated more than a predetermined number of times by the individual action sequence using the data mining technique in the collected life log.

At this time, the step of analyzing the individual tendency may analyze the individual tendency by analyzing the activity information in the individual social network included in the collected life log.

In this case, the step of generating a personalized lifestyle model according to the tendencies may include analyzing the similarities among the behavior sequences of the users having similar tendencies; And generating a personalized lifestyle model on the basis of the tendency by linking the action sequences having a high degree of similarity in a tree form.

The present invention collects lifelogs, extracts individual behavior sequences from the collected life logs, analyzes the individual propensity using the collected life logs, and associates behavior sequences of users with similar propensity, Since the model is created, a user or an expert can generate a personalized lifestyle model using the collected life log without setting an individual action sequence directly, and it can be appropriately changed according to the accumulated data over time So it can evolve over time.

1 is a diagram illustrating a configuration of a lifestyle autonomous care system according to an embodiment of the present invention.
2 is a diagram illustrating a configuration of a reference modeling apparatus for modeling a generalized lifestyle according to an embodiment of the present invention.
3 is a diagram illustrating a personalized modeling apparatus for personalized lifestyle modeling according to an embodiment of the present invention.
4 is a flowchart illustrating a lifestyle management process in the lifestyle autonomic care system according to an exemplary embodiment of the present invention.
5 is a flowchart illustrating a process of generating a reference model in a reference modeling apparatus according to an embodiment of the present invention.
6 is a flowchart illustrating a process of generating a personalized lifestyle model in the personalized modeling apparatus according to an exemplary embodiment of the present invention.
7 is a diagram illustrating an example of a reference model generated according to an embodiment of the present invention.

Other objects and features of the present invention will become apparent from the following description of embodiments with reference to the accompanying drawings.

Preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

However, the present invention is not limited to or limited by the embodiments. Like reference symbols in the drawings denote like elements.

Hereinafter, a lifestyle autonomous care system and method according to an embodiment of the present invention will be described in detail with reference to FIGS. 1 to 7.

1 is a diagram illustrating a configuration of a lifestyle autonomous care system according to an embodiment of the present invention.

Referring to FIG. 1, a lifestyle autonomic care system 100 may include a lifelog collection device 110, a reference modeling device 120, a personalized modeling device 130, and a service device 140.

The life log collecting apparatus 110 includes a private data management server 151, a public data management server 152, a personal computer 153, a smart phone 154, smart glasses 155, The smart clock 157, the bicycle 158, the treadmill 159, the car 160, and the like to collect life logs.

At this time, the life log stores at least one of private data, public data, personal data, anonymous data, connected data, and sensor data. .

Here, the private data can be a schedule, an address book, a credit card usage, a medical record, a shopping history, a call record, a character record, a bank transaction record, a stock transaction record,

Public data includes traffic information, weather information, and various statistical data.

Personal data can be a bookmark, a search history, a social networking service (SNS) conversation record, a download record, a blog record, and the like.

Anonymous data can be topic information (trend of public opinion), news, real-time keyword ranking, etc., which are discussed in SNS.

Connected data can be records connected to a house or a vehicle. For example, it can detect a room, RFID (personal identification, access record), digital door lock, smart home appliance (usage information) An access point, a car navigation system (navigation path), a black box (video and audio recording), a travel recorder (driving time, driving pattern, etc.).

The sensor data may be data measured through a dedicated device, an environmental sensor, a smart device, a medical device, a personal exercise device, or a personal activity measuring device.

Here, the dedicated device can be a calorie measuring device, a posture measuring device, a clinical thermometer, a stress measuring device, an oral breath measuring device, a drinking measurement device, a moving distance / speed device, Do.

Environmental sensors include temperature measurement sensors, humidity measurement sensors, illumination measurement sensors, CCTV (distance, public transportation, buildings, etc.), carbon dioxide measurement sensors, ozone measurement sensors, carbon monoxide measurement sensors, dust measurement sensors and ultraviolet measurement sensors.

Smart devices include smartphones, head mount displays (such as Google Glass), and smart watches (such as Apple iWatch). The smart device allows you to view the payment history of your app, your favorite apps, It is possible to acquire data such as image, voice, photograph, and favorite music.

The medical instrument may be an electronic balance, a body fat measurement device, a diabetic measurement device, a heart rate measurement device, a blood pressure measurement device, etc., and the measured data may be included in the sensor data.

The personal exercise device may be an exercise device capable of measuring the amount of exercise such as a treadmill, a bicycle, or a sensor submitted to a sneaker, and the amount of exercise measured from the exercise device may be included in the sensor data.

Meanwhile, the life log collection device 110 may be configured as a separate device, but may be included in the reference modeling device 120 or the personalized modeling device 130.

The reference modeling device 120 receives the life logs collected from the life log collection device 110, and generates a reference model using the collected life logs.

At this time, the reference modeling device 120 extracts the action sequence from the collected life log, analyzes the similarity between the extracted action sequences, and generates a reference model by sorting the action sequence using a sequence alignment technique . A more detailed description of the reference modeling device 120 will be described below with reference to FIG.

The personalized modeling device 130 receives the life logs collected from the life log collection device 110, analyzes the individual personalities using the collected life logs, and generates a personalized lifestyle model based on the personalities.

The personalized modeling device 130 extracts a behavior pattern that is repeated more than a predetermined number of times by the individual action sequence using the data mining technique in the collected life log and displays the activity in the individual social network included in the collected life log Analyzing the information, analyzing individual tendencies, and linking behavior sequences of users having similar tendencies, a personalized lifestyle model can be generated according to the tendencies. A more detailed description of the personalized modeling device 130 will be described below with reference to FIG.

The reference model generated by the reference modeling device 120 in the reference modeling device 120 and the personalized lifestyle model generated in the personalized modeling device 130 tend to be more accurate as the life logs accumulate. Thus, the reference model and the personalized lifestyle model evolve over time as it automatically reflects behavioral sequences that may change over time over time.

Meanwhile, the reference model generated by the reference modeling device 120 and the personalized lifestyle model generated by the personalized modeling device 130 in the reference modeling device 120 are merged into one for the service and provided to the service device 140 .

The service device 140 receives the reference model received from the reference modeling device 120 and the user behavior that can be generated based on the user's current information collected using the personalized lifestyle model received from the personalized modeling device 130 And verifies whether the estimated user's behavior has an adverse effect on the user's health.

If the estimated user's behavior has an adverse effect on the user's health, the service device 140 can guide the user to avoid the estimated user's behavior. At this time, the service device 140 can use a direct method or an indirect method as a method for avoiding the estimated user's behavior.

The direct method is a method that allows the user to be able to recognize and avoid possible behaviors by sending possible actions of the user to the user.

The indirect method is an unobtrusive method which instructs the user to do something to avoid the user's behavior in advance. Thus, in the indirect method, the user can be prevented from recognizing the possible actions.

For example, if you have identified a user's personalized lifestyle model, you are in a bad mood, and if you have a behavior sequence that bites meat in a meat home while you are at home, If the user is at work and the current weight of the user is obese, then the user can be encouraged to avoid other eating habits by recommending another route without meat.

In addition, if the user further has an action sequence that improves the mood when the user walks the flower road, the user may be guided to change the mood of the user by providing the user with a route to the exit route via the flower road.

2 is a diagram illustrating a configuration of a reference modeling apparatus for modeling a generalized lifestyle according to an embodiment of the present invention.

2, the reference modeling device 120 includes a control unit 210, a log collection unit 212, a behavior sequence acquisition unit 214, a similarity analysis unit 216, a reference model generation unit 218, 220 and a storage unit 230.

The communication unit 220 is a communication interface device including a receiver and a transmitter, and transmits and receives data by wire or wireless. The communication unit 220 may communicate with the life log collection device 110, the service device 140, and the reference model database 170, and may directly communicate with the devices providing the life log to receive the life log.

The storage unit 230 may store an operating system, an application program, and the like for controlling the overall operation of the reference modeling device 120, and may also store the collected life log and the generated reference model according to the present invention. At this time, the storage unit 230 may be a storage device including a flash memory, a hard disk drive, and the like.

The log collecting unit 212 may collect the life logs or the life logs collected by the life log collecting apparatus 110 through the communication unit 220.

The action sequence acquiring unit 214 extracts the action sequence from the collected life log.

More specifically, the action sequence acquiring unit 214 extracts a behavior sequence having at least one of stimulus mapping, perception, emotion, action, and result in the collected life log using a data mining technique. At this time, an action sequence having stimulation ideation, cognition, emotion, action, and result can be expressed as shown in the example of Table 1 below.

[Table 1]

The action sequence acquiring unit 214 may extract an action sequence from the collected life log, but may also receive an action sequence from a user or an expert (such as a psychologist).

The similarity analyzing unit 216 analyzes the similarity between the action sequences obtained through the action sequence obtaining unit 214. [

In more detail, the similarity analyzer 216 may evaluate the similarity between the extracted behavior sequences using at least one of whether information is generated within a predetermined time and information included in the behavior sequence.

The reference model generation unit 218 generates a reference model by aligning the action sequence using a sequence alignment technique.

More specifically, the reference model generation unit 218 can generate an ontology-type reference model by linking action sequences having high similarity in a tree form, using the similarity of the extracted action sequences.

7 is a diagram illustrating an example of a reference model generated according to an embodiment of the present invention.

FIG. 7 shows an example in which the action sequence of Table 1 is generated as a reference model. Referring to FIG. 7, it can be seen that the reference model is composed of a tree-shaped ontology model.

The sequence alignment technique applied by the reference model generator 218 is a technique that is mainly used for analyzing the similarity of base sequences in the field of bioinformatics. In the present invention, the sequence alignment technique can be modified as shown in Table 2 below.

[Table 2]

The control unit 210 may control the overall operation of the reference modeling device 120. [ The control unit 210 may perform the functions of the log collection unit 212, the action sequence acquisition unit 214, the similarity analysis unit 216, and the reference model generation unit 218. The control unit 210, the log collecting unit 212, the action sequence obtaining unit 214, the similarity analyzing unit 216, and the reference model generating unit 218 are separately described for distinguishing the respective functions. The control unit 210 includes at least one processor configured to perform the functions of the log collection unit 212, the behavior sequence acquisition unit 214, the similarity analysis unit 216, and the reference model generation unit 218 . The control unit 210 may be configured to perform at least one of the functions of the log collecting unit 212, the behavior sequence obtaining unit 214, the similarity analyzing unit 216, and the reference model generating unit 218, Of processors.

3 is a diagram illustrating a personalized modeling apparatus for personalized lifestyle modeling according to an embodiment of the present invention.

3, the personalized modeling device 130 includes a control unit 310, a log collection unit 312, an action sequence acquisition unit 314, a propensity analysis unit 316, a lifestyle model generation unit 318, A communication unit 320 and a storage unit 330. [

The communication unit 320 is a communication interface device including a receiver and a transmitter, and transmits and receives data by wire or wireless. The communication unit 320 may communicate with the life log collection device 110, the service device 140, and the lifestyle model database 180, and may directly communicate with the devices providing the life log to receive the life log .

The storage unit 330 stores an operating system, an application program, and the like for controlling the overall operation of the personalized modeling device 130, and can also store the collected life log and the generated personalized lifestyle model according to the present invention . At this time, the storage unit 330 may be a storage device including a flash memory, a hard disk drive, and the like.

The log collecting unit 312 may collect the life logs or receive the life logs collected by the life log collecting apparatus 110 through the communication unit 320. [

The action sequence acquisition unit 314 extracts the individual action sequence from the collected life logs. In more detail, the behavior sequence acquiring unit 314 may search for a behavior pattern repeated more than a predetermined number of times for each individual in the collected life log using a data mining technique, and extract the individual behavior sequences.

Meanwhile, the action sequence acquiring unit 314 may extract an action sequence from the collected life log, but may also receive an action sequence from a user or an expert.

The propensity analyzing unit 316 analyzes individual propensity using the collected life log. In more detail, the propensity analyzing unit 316 analyzes the individual propensity by understanding the interests, tastes, eating habits, activities, and the like of each individual from the activity information on the individual social network included in the collected life log. At this time, the activity information on the social network may include the number of connections of the social network, the object to be visited, the number of registered friends, the number of uploaded articles, the number of responses, and the context analysis of the uploaded article.

The behavior sequence acquisition unit 314 and the shaping analysis unit 316 can use the distributed computing technology Hadoop and MapReduce technology to analyze a large-capacity lifelog. That is, the behavior sequence acquisition unit 314 and the shaping analysis unit 316 may store and manage an individual's behavior sequence through the Hadoop system, and distribute analysis techniques through MapReduce.

The lifestyle model generation unit 318 generates lifestyle models that are personalized according to the tendencies by connecting action sequences of users having similar tendencies.

More specifically, the lifestyle model generation unit 318 analyzes the similarities between the behavior sequences of users having similar inclinations, connects the high-similarity action sequences to the tree form, and displays the personalized lifestyle model of the ontology type on the basis of the inclinations Can be generated.

On the other hand, individuals use specific heuristics for their decisions and behaviors, and it is necessary to verify the suitability of personal lifestyle models using this heuristic.

The validation of the personal lifestyle model is based on the heuristic of each individual by using the heuristic of the individual who has already been designed by psychologists and physiologists, and the method of the heuristic of the individual, The suitability of the habit model can be confirmed.

Then, we can grasp the relation between the user's personal lifestyle model and heuristic, judge the suitability of personal lifestyle model based on heuristic (associate with psychology, physiologist) and analyze heuristic to re-adjust personal lifestyle model have.

However, to minimize the intervention of the user or the expert, the heuristic of the individual is estimated through the existing accumulated behavior sequence and the personal lifestyle model, and the behavior sequence of the user having the same or similar heuristic is searched, It is desirable that a method of verifying fitness of a personal lifestyle model by deriving a pattern is desirable.

The control unit 310 can control the overall operation of the personalized modeling device 130. [ The control unit 310 may perform the functions of the log collection unit 312, the behavior sequence acquisition unit 314, the propensity analysis unit 316, and the lifestyle model generation unit 318. The functions of the control unit 310, the log collection unit 312, the action sequence acquisition unit 314, the propensity analysis unit 316, and the lifestyle model generation unit 318 are separately described to distinguish the functions . Accordingly, the control unit 310 includes at least one processor configured to perform the functions of the log collection unit 312, the behavior sequence acquisition unit 314, the propensity analysis unit 316, and the lifestyle model generation unit 318, . ≪ / RTI > The control unit 310 may be configured to perform at least some of the functions of the log collection unit 312, the behavior sequence acquisition unit 314, the propensity analysis unit 316, and the lifestyle model generation unit 318, And may include one processor.

Hereinafter, a method for managing lifestyle in the lifestyle autonomous care system according to the present invention will be described with reference to the drawings.

4 is a flowchart illustrating a lifestyle management process in the lifestyle autonomic care system according to an exemplary embodiment of the present invention.

Referring to FIG. 4, the lifestyle autonomic care system 100 includes a private data management server 100 for managing private data, public data, personal data, anonymous data, And the sensor data (S410).

Then, the lifestyle autonomic care system 100 generates a reference model using the collected life logs (S412). At this time, the lifestyle autonomic care system 100 extracts a behavior sequence from the collected life logs, analyzes the similarity between the extracted behavior sequences, and aligns the behavior sequence using a sequence alignment technique to obtain a reference model Can be generated. A more detailed description of creating the reference model will be described below with reference to FIG.

Then, the lifestyle autonomic care system 100 analyzes personal tendencies using the collected life logs, and generates a personalized lifestyle model according to inclinations (S414).

At this time, the lifestyle autonomic care system 100 extracts a behavior pattern that repeats more than a predetermined number of times in the collected life log by using a data mining technique, as an individual action sequence, Analyzing individual activity information by analyzing the activity information in the user, and linking the behavior sequences of users having similar tendencies, thereby generating a personalized lifestyle model based on the tendencies. A more detailed description of creating a personalized lifestyle model will be described below with reference to FIG.

In addition, the lifestyle autonomic care system 100 estimates the user behavior that can be generated by reflecting the current information of the user collected in the reference model and the personalized lifestyle model (S416).

Then, the lifestyle autonomic care system 100 checks whether the estimated user's behavior has an adverse effect on the user's health (S418).

If it is determined in operation S418 that the estimated user's behavior has an adverse effect on the user's health, the lifestyle autonomic care system 100 induces the user to avoid the estimated user's behavior in operation S420.

At this time, the lifestyle autonomic care system 100 transmits the user's action, which can be generated to induce the user to avoid the estimated user's behavior, or instructs the user to perform an action, .

5 is a flowchart illustrating a process of generating a reference model in a reference modeling apparatus according to an embodiment of the present invention.

Referring to FIG. 5, the reference modeling device 120 may include private data, public data, personal data, anonymous data, connected data, and sensor data And sensor data (S510).

Then, the reference modeling device 120 extracts the action sequence from the collected life log (S520). At this time, the reference modeling device 120 can extract a behavior sequence having at least one of stimulus ideation, perception, emotion, behavior, and result in the collected life log using a data mining technique.

Then, the reference modeling device 120 analyzes the similarity between the extracted action sequences (S530). At this time, the reference modeling device 120 can evaluate and analyze the similarity between the extracted action sequences by using at least one of whether or not the information is included within a predetermined time and information included in the action sequence.

Then, the reference modeling device 120 generates a reference model by aligning the action sequence using a sequence alignment technique (S540). At this time, the reference modeling device 120 may generate an ontology-type reference model by connecting action sequences having high similarity in a tree form using the similarity of the extracted action sequences.

6 is a flowchart illustrating a process of generating a personalized lifestyle model in the personalized modeling apparatus according to an exemplary embodiment of the present invention.

Referring to FIG. 6, the personalized modeling device 130 may include private data, public data, personal data, anonymous data, connected data, And a sensor data (S610).

Then, the personalized modeling device 130 extracts the individual action sequence from the collected life log (S620). At this time, the personalized modeling device 130 can extract a behavior pattern that is repeated more than a predetermined number of times by the individual action sequence in the collected life log using the data mining technique.

Then, the personalized modeling device 130 analyzes individual tendencies using the collected life logs (S630). At this time, the personalized modeling device 130 may analyze activity information in individual social networks included in the collected life log, and analyze personal tendencies.

Then, the personalized modeling device 130 links the behavior sequences of users having similar tendencies to generate personalized lifestyle models according to inclinations (S640). At this time, the personalized modeling device 130 analyzes the similarities between the behavior sequences of users having similar tendencies, and connects the action sequences having high similarity in the form of a tree, thereby generating a personalized lifestyle model of the ontology type for each of the inclinations .

The lifestyle autonomic care method according to an embodiment of the present invention may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

As described above, the present invention has been described with reference to particular embodiments, such as specific elements, and specific embodiments and drawings. However, it should be understood that the present invention is not limited to the above- And various modifications and changes may be made thereto by those skilled in the art to which the present invention pertains.

Accordingly, the spirit of the present invention should not be construed as being limited to the embodiments described, and all of the equivalents or equivalents of the claims, as well as the following claims, belong to the scope of the present invention .

Claims (11)

A log collector for collecting life logs;
An action sequence acquiring unit for extracting an individual action sequence from the collected life log;
A tendency analysis unit for analyzing individual tendencies using the collected life logs; And
And a lifestyle model generating unit for generating a lifestyle model that is personalized according to the tendencies by connecting action sequences of users having similar tendencies
A personalized lifestyle modeling device. The method according to claim 1,
The above-
And includes at least one of private data, public data, personal data, anonymous data, connected data, and sensor data.
A personalized lifestyle modeling device. The method according to claim 1,
Wherein the action sequence obtaining unit comprises:
Extracting a behavior pattern repeated by a predetermined number of times or more for each individual using the personalized action sequence using the data mining technique in the collected life log
A personalized lifestyle modeling device. The method according to claim 1,
The propensity analyzing unit,
Analyzing the activity information in the individual social network included in the collected life log and analyzing the individual tendency
A personalized lifestyle modeling device. The method according to claim 1,
Wherein the lifestyle model generation unit comprises:
Analyzing similarities among the behavior sequences of users having similar inclinations, linking the action sequences having high similarities in a tree form, and generating a personalized lifestyle model on the basis of the inclinations
A personalized lifestyle modeling device. Collecting a life log;
Extracting an individual action sequence from the collected life logs;
Analyzing individual tendencies using the collected life logs; And
And associating a behavior sequence of a user having similar tendencies to generate a personalized lifestyle model according to the tendency
A personalized lifestyle modeling method. The method according to claim 6,
The above-
And includes at least one of private data, public data, personal data, anonymous data, connected data, and sensor data.
A personalized lifestyle modeling method. The method according to claim 6,
Wherein the step of extracting the individual action sequence comprises:
Extracting a behavior pattern repeated by a predetermined number of times or more for each individual using the personalized action sequence using the data mining technique in the collected life log
A personalized lifestyle modeling method. The method according to claim 6,
Wherein analyzing the personal preference comprises:
Analyzing the activity information in the individual social network included in the collected life log and analyzing the individual tendency
A personalized lifestyle modeling method. The method according to claim 6,
The step of generating a personalized lifestyle model according to the inclination includes:
Analyzing a similarity between the behavior sequences of the users having similar tendencies; And
Generating a personalized lifestyle model of the ontology type for each inclination by connecting the action sequences having high similarity in a tree form
A personalized lifestyle modeling method. A computer-readable recording medium having recorded thereon a program for executing the method according to any one of claims 6 to 10.

Images