KR20120033597A - Apparatus and method for recognizing user future context - Google Patents

Apparatus and method for recognizing user future context Download PDF

Info

Publication number
KR20120033597A
KR20120033597A KR1020100095196A KR20100095196A KR20120033597A KR 20120033597 A KR20120033597 A KR 20120033597A KR 1020100095196 A KR1020100095196 A KR 1020100095196A KR 20100095196 A KR20100095196 A KR 20100095196A KR 20120033597 A KR20120033597 A KR 20120033597A
Authority
KR
South Korea
Prior art keywords
user
data
situation
information
context
Prior art date
Application number
KR1020100095196A
Other languages
Korean (ko)
Inventor
이건창
조희련
Original Assignee
성균관대학교산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 성균관대학교산학협력단 filed Critical 성균관대학교산학협력단
Priority to KR1020100095196A priority Critical patent/KR20120033597A/en
Publication of KR20120033597A publication Critical patent/KR20120033597A/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03—Data mining

Abstract

PURPOSE: A user situation prediction apparatus and method thereof are provided to offer customized service information by predicting the situation of a user. CONSTITUTION: A data collection unit(210) receives user feedback data and user situation data from a user terminal(100). A situation prediction model creation unit(220) creates one or more situation prediction models by using data which is patterned. A situation prediction model base(230) stores matched information by matching the created situation prediction model with classification standard information.

Description

Apparatus and method for predicting user situation {APPARATUS AND METHOD FOR RECOGNIZING USER FUTURE CONTEXT}

The present invention relates to a user situation prediction apparatus and method.

Recently, ubiquitous computing has attracted attention. Ubiquitous computing refers to an information and communication environment in which a user can freely access a network regardless of a network or a computer.

Therefore, ubiquitous computing aims to grasp the user's needs in daily life and provide the necessary services to the user. In order to satisfy this goal, research on situational awareness technology that automatically recognizes a user's situation and proposes a service suitable for the recognized situation has been actively conducted.

However, in the ubiquitous environment, since the user's situation changes from time to time, in the existing situation recognition method of recognizing the current situation of the user and suggesting a service suitable for the recognized situation, the proposed service may become meaningless when the user's situation changes. There was this.

Therefore, in order to increase the accuracy of the proposed service, a situation prediction apparatus and method capable of proposing a service considering a future situation of a user are needed.

The present invention is to solve the above-described problem, an embodiment of the present invention using the user context information of the past and the current user context information to predict the user situation of the future point of time, service information suitable for the predicted user context It provides a situation prediction apparatus and method for recommending.

As a technical means for achieving the above technical problem, a user context prediction apparatus according to an aspect of the present invention, the data collection unit for receiving and storing the user context data and user feedback data from the user terminal; Data-mining the plurality of pre-stored user context data and user feedback data for each classification criteria set based on the environment information for each user and the service category information selected by the user, and at least one situation using the data mined data. A situation prediction model generator for learning and generating a prediction model; A situation prediction model base configured to store the generated at least one situation prediction model with information of each classification criterion; Selecting a context prediction model matching a classification criterion according to the received user context data among pre-stored context prediction models, and applying the received user context data to the selected context prediction model to predict a future situation of the user, A situation prediction unit generating prediction result information according to the prediction; And a service recommendation unit which extracts fact data according to the prediction result information from a plurality of pre-stored fact data, generates recommended service information using the extracted fact data, and provides the recommended service information to the user terminal. Is generated through learning the General Bayesian Network.

In addition, a user context prediction method according to another aspect of the present invention includes: receiving user context data from a user terminal; Selecting a context prediction model based on a predetermined classification criterion based on the received user context data among a plurality of pre-stored context prediction models; Applying the user context data to the selected situation prediction model to predict a future situation of a user and generating prediction result information; Extracting fact data according to the prediction result information from a plurality of previously stored fact data; And generating recommended service information based on the extracted fact data, wherein the plurality of situation prediction models are generated through general Bayesian network learning.

According to any one of the above-described problem solving means of the present invention, it is possible to provide service information suitable for the future situation of the user by predicting the user situation in consideration of the change of the user's situation.

Further, according to any one of the problem solving means of the present invention, by selecting the situation prediction model suitable for the current user situation from the plurality of situation prediction model to perform the situation prediction, it is possible to increase the accuracy of the prediction for the user future situation. .

In addition, according to any one of the problem solving means of the present invention, by using the General Bayesian Network (GBN) model that automatically extracts the key variables required for the situation prediction, the user side when the user situation prediction It is efficient because it minimizes the input information to be obtained from.

1 is a block diagram showing the configuration of a situation prediction apparatus according to an embodiment of the present invention.
2 and 3 are diagrams showing an example of a GBN model according to an embodiment of the present invention.
4 is a flowchart illustrating a situation prediction method according to an embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components unless otherwise stated.

1 is a block diagram showing the configuration of a situation prediction apparatus according to an embodiment of the present invention.

2 and 3 are diagrams showing examples of GBN models according to an embodiment of the present invention.

First, as shown in FIG. 1, the situation prediction apparatus 200 according to an embodiment of the present invention includes a data collector 210, a situation prediction model generator 220, a situation prediction model base 230, and a situation prediction. A unit 240, a service recommendation unit 250, and a database 260.

The data collector 210 receives user context data and user feedback data from the user terminal 100, and stores the received user context data and user feedback data in the database 260. In addition, the data collector 210 transmits the user context data to the situation predictor 240.

In this case, the user context data may include user identification information (hereinafter referred to as 'user ID'), user location information, user behavior information, and service category information selected by the user or the user terminal 100. do. For reference, in the database 260 according to an embodiment of the present invention, user environment information for each of a plurality of users or user terminals 100 is pre-stored by matching with a user ID.

The user feedback data includes feedback information that the user selects or inputs to evaluate usefulness and accuracy of recommended service information provided according to the user prediction. Specifically, the user feedback data includes a user ID, service category information selected by the user, provided recommended service information, prediction accuracy (or usability) evaluation information, user location information, and user behavior information.

The situation prediction model generator 220 generates a situation prediction model by learning a situation prediction model based on transaction data stored in the database 260. In addition, the situation prediction model generator 220 stores the generated situation prediction model in the situation prediction model base 230.

In this case, the transaction data includes training data and test data, and the training data and test data include at least one of pre-stored user context data (hereinafter, referred to as 'user history data'), user feedback data, and fact data. From or generated from. For reference, the fact data refers to actual service data included for each service category in which the user wants to receive recommended service information. For example, when the service category is 'food', data such as the name of the type of food that can be recommended to the user and the name of the store selling the food may be included in the fact data.

Meanwhile, the context prediction model generator 220 according to an embodiment of the present invention classifies the entire data set, which is a data set of all users, according to a predetermined classification criterion to classify a plurality of data set groups when the situation prediction model is learned. Then, situation prediction model training is performed based on each data set group. In other words, the situation prediction model generator 220 differently sets a data set group applied to perform situation prediction model learning for each user. For reference, the classification criteria may be set based on environment information for each user.

For example, when a user is a college student and wants to receive specific service information that can be serviced in a corresponding university, a variable such as a department or a grade of the corresponding user may be set based on the variable. In this case, the situation prediction model generator 220 classifies the user history data and transaction data for all students stored in the database 260 according to a predetermined classification criteria (for example, department and grade) and generates a data set group. Based on the situation prediction model training is performed. The situation prediction model generator 220 matches the situation prediction model generated based on the data set group with the information of the classification criteria and stores the situation prediction model in the situation prediction model base 230.

As described above, a plurality of situation prediction models may be generated by learning the situation prediction models based on a data set group in which the entire data set is divided into a plurality of classification criteria. That is, the situation prediction model can be selected by selecting the context prediction model matching the environment information for each user, and thus, the accuracy of the situation prediction can be further increased.

In particular, the situation prediction model generator 220 according to an embodiment of the present invention generates a GBN model as the situation prediction model.

For example, FIG. 2 and FIG. 3 show that the plurality of situation prediction models according to one embodiment of the present invention are GBN models.

Specifically, as shown in FIGS. 2 and 3, the GBN model may be represented by a plurality of nodes and a link connecting each node. In this case, each node represents an attribute for data mining the entire data set, and each link represents a dependency between nodes.

In addition, as shown in FIG. 2, the GBN model is composed of a graph showing probabilistic dependencies between nodes and conditional probabilities for each variable.

That is, the situation prediction model generator 220 performs a process of learning a Bayesian network graph and a process of calculating conditional probabilities of each variable when the GBN model is trained.

In FIGS. 3A and 3B, the situation prediction model generator 220 classifies the same entire data set according to classification criteria and learns and generates a Bayesian network graph for each classified data set group. The GBN model in the form is shown.

For example, FIG. 3A illustrates a GBN model trained on the basis of user history data and transaction data of all users, and FIG. 3B illustrates user history data of users belonging to a predetermined classification standard among all users. And a GBN model trained based on transaction data.

The situation prediction model base 230 registers the generated situation prediction models by matching the information of each classification criterion. In addition, the situation prediction model base 230 provides a situation prediction model requested by the situation prediction unit 240.

The context prediction unit 240 selects a context prediction model based on the received current user context data, and applies the current user context data to the selected context prediction model to perform context prediction for the future of the user. In addition, the situation prediction unit 240 transmits the result of the situation prediction to the service recommendation unit 250.

In detail, the context prediction unit 240 confirms the user ID and the service category information from the received user context data, and determines a classification criterion for requesting the context prediction model based on the user ID and the service category information. The situation prediction unit 240 requests the situation prediction model base 230 based on the determined classification criteria. At this time, the situation predictor 240 extracts user environment information for each user ID stored in the database 260 and selects the most suitable classification criteria based on environment information and service category information of the user.

The situation predictor 240 receives a situation prediction model based on the requested classification criteria and is set based on at least one of service category information, user location information, and user behavior information included in the received current user context data. Perform situation prediction based on conditions. At this time, the situation predictor 240 selects a target node based on the condition, and selects a variable having the highest conditional probability value according to the condition information among the selected target nodes as a prediction result.

For example, when the user selects a service category for requesting information of restaurants available in the university, the situation predictor 240 sets a 'place' of a plurality of nodes of the selected GBN model as a target node and receives the received information. Based on the user location information and the restaurant information among the current user context data, a place having the highest conditional probability from the place where the user is currently located can be predicted as a place to be moved in the future.

The service recommender 250 extracts suitable fact data from the fact data stored in the database 260 based on the prediction result received from the situation predictor 240.

In detail, the service recommendation unit 250 extracts fact data corresponding to the received prediction result among pre-stored fact data, and collects valid information from the extracted fact data to generate recommended service information. In addition, the service recommendation unit 250 provides the generated recommended service information to the user terminal 100.

For example, when the user requests the recommendation service information for the service category requesting the information of the restaurant available in the university, the service recommendation unit 250 may provide information about the moving place, which is a prediction result, from the situation prediction unit 240 and the like. Based on the service category information, recommendation service information including fact data such as name data of a restaurant close to the predicted moving place and name data of food sold in the restaurant can be generated.

The database 260 updates and stores the user context data and the user feedback data received for each user, and stores the user identification information and the user environment information by matching them. The database 260 collects or sets transaction data based on user context data, user feedback data, and user history data. The database 260 also stores a number of fact data for recommending services.

The database 260 according to an embodiment of the present invention may store data for each category in a structure classified by category or in a separate storage space for efficient storage of various data.

For example, the database 260 may be divided into a user context database, a user history database, a transaction database, a fact database, a user information database, and the like.

Hereinafter, a situation prediction method according to an embodiment of the present invention will be described in detail with reference to FIG. 4.

4 is a flowchart illustrating a situation prediction method according to an embodiment of the present invention.

First, the received user context data is checked (S410).

In this case, the user context data may be received from the user terminal 100 and may be received by a user's direct input or by automatic transmission of a situation prediction service application installed in the user terminal.

In addition, the user context data includes user identification information, service category information selected by the user, user location information, and user behavior information.

Next, a suitable situation prediction model is selected according to the identified user context data (S420).

In detail, the context prediction model that is determined to be suitable is selected based on at least one of user environment information, service category information, user location information, and user behavior information according to the currently identified user identification information among the plurality of stored situation prediction models. . In this case, the plurality of situation prediction models are generated by learning the situation prediction model for each data set in which the entire data set is divided into predetermined classification criteria.

Then, the situation prediction is performed by applying the currently identified user context data to the selected situation prediction model (S430).

At this time, the situation prediction model according to an embodiment of the present invention is a GBN model. In detail, when a situation prediction is performed, a target node is selected from among a plurality of nodes which are data mining data of the data set group, and the variable having the highest conditional probability with respect to at least one condition among a plurality of variables included in the selected node. Is selected as the prediction result. In this case, the at least one condition may be at least one of user environment information, user location information, user behavior information, and service category information selected by the user.

Then, the fact data suitable for the situation prediction result is extracted (S440).

Specifically, the fact data is previously stored as actual data of service information to be provided to the user. For example, when the situation prediction result is a location variable, fact data corresponding to the service category selected by the user and the location variable that is a prediction result are extracted.

Then, the recommended service information is generated based on the extracted fact data (S450).

 In this case, the recommended service information includes valid information corresponding to a preset service information type among the extracted fact data.

Then, the generated recommended service information is provided to the corresponding user terminal 100 (S460).

On the other hand, the above description of the present invention is intended for illustration, and those skilled in the art can understand that the present invention can be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. There will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

And the scope of the present invention is represented by the appended claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts are included in the scope of the present invention. Should be.

100: user terminal 200: situation prediction device
210: data collector 220: situation prediction model generator
230: situation prediction model base 240: situation prediction unit
250: service recommendation unit 260: database

Claims (9)

In the user situation prediction apparatus,
A data collector configured to receive and store user context data and user feedback data from a user terminal;
Data-mining the plurality of pre-stored user context data and user feedback data for each classification criteria set based on the environment information for each user and the service category information selected by the user, and at least one situation using the data mined data. A situation prediction model generator for learning and generating a prediction model;
A situation prediction model base configured to store the generated at least one situation prediction model with information of each classification criterion;
Selecting a context prediction model matching a classification criterion according to the received user context data among pre-stored context prediction models, and applying the received user context data to the selected context prediction model to predict a future situation of the user, A situation prediction unit generating prediction result information according to the prediction; And
A service recommendation unit for extracting fact data according to the prediction result information from a plurality of pre-stored fact data, generating recommended service information using the extracted fact data, and providing the recommended service information to the user's terminal;
And the situation prediction model is generated through general bayesian network learning. The method of claim 1,
The situation prediction unit,
Selecting a target node according to the classification criterion among a plurality of nodes of the selected situation prediction model, and generating, as the prediction result information, a variable having the highest conditional probability according to the classification criterion among a plurality of variables included in the target node; User situation prediction device. The method according to claim 1 or 2,
The classification criteria,
And a user context prediction apparatus set based on at least one of selected service category information, user environment information, user location information, and user behavior information included in the user context data. The method of claim 1,
The situation prediction model generation unit,
The entire data set including the plurality of pre-stored user context data and user feedback data is divided into a plurality of data set groups according to the classification criteria,
A user context prediction apparatus for generating a plurality of context prediction models by performing context prediction model training for each of the plurality of data set groups. In the user situation prediction method,
Receiving user context data from a user terminal;
Selecting a context prediction model based on a predetermined classification criterion based on the received user context data among a plurality of pre-stored context prediction models;
Applying the user context data to the selected situation prediction model to predict a future situation of a user and generating prediction result information;
Extracting fact data according to the prediction result information from a plurality of previously stored fact data; And
Generating recommended service information based on the extracted fact data;
Wherein the plurality of situation prediction models are generated through General Bayesian Network learning. The method of claim 5, wherein
Prior to receiving the user context data,
Receiving and storing user context data and user feedback data from a plurality of users;
Data mining the stored user context data and user feedback data for each preset classification criteria; And
The method may further include generating a situation prediction model for each classification criterion by learning a general Bayesian network of the result data of the data mining.
The classification criteria are set based on the user-specific environment information and the service category information selected by the user. The method according to claim 6,
The data mining step,
And dividing the entire data set including the user context data and the user feedback data of the plurality of users according to the classification criteria into a plurality of data set groups. The method of claim 5, wherein
Generating the prediction result information,
Selecting a target node according to the classification criterion among a plurality of nodes of the selected situation prediction model; And
And generating, as the prediction result information, a variable having the highest conditional probability according to the classification criterion among a plurality of variables included in the target node. The method of claim 5, wherein
The classification criteria,
And a method of predicting user context based on at least one of selected service category information, user environment information, user location information, and user behavior information included in the user context data.
KR1020100095196A 2010-09-30 2010-09-30 Apparatus and method for recognizing user future context KR20120033597A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020100095196A KR20120033597A (en) 2010-09-30 2010-09-30 Apparatus and method for recognizing user future context

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020100095196A KR20120033597A (en) 2010-09-30 2010-09-30 Apparatus and method for recognizing user future context

Publications (1)

Publication Number Publication Date
KR20120033597A true KR20120033597A (en) 2012-04-09

Family

ID=46136332

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020100095196A KR20120033597A (en) 2010-09-30 2010-09-30 Apparatus and method for recognizing user future context

Country Status (1)

Country Link
KR (1) KR20120033597A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101384593B1 (en) * 2012-08-03 2014-04-14 공주대학교 산학협력단 Behavior pattern reasoning based on context awarness
KR101441420B1 (en) * 2012-06-18 2014-09-25 인하대학교 산학협력단 System and method for providing driving guide service and smart car
KR101468379B1 (en) * 2012-06-29 2014-12-02 인텔렉추얼디스커버리 주식회사 Access method for decrypting encryption data
KR20140139263A (en) * 2013-05-27 2014-12-05 삼성디스플레이 주식회사 Flexable display device having guide function of gesture command and method thereof
KR101642487B1 (en) * 2015-06-30 2016-07-25 주식회사 카카오 Method for predicting user's future location and, apparatus and method for providing contents using the same method
KR20170142342A (en) * 2016-06-17 2017-12-28 건국대학교 산학협력단 Method of providing service using context recognition information of peripheral devices of based on a location at a specific place, and apparatus performing the same
KR20180050812A (en) * 2016-11-07 2018-05-16 인하대학교 산학협력단 System and method for tailored intervetion through prediction of inpatient falls
WO2019103199A1 (en) * 2017-11-23 2019-05-31 주식회사 모다 Personalized intelligent system and method for operating same
KR20210060830A (en) * 2019-11-19 2021-05-27 주식회사 피씨엔 Big data intelligent collecting method and device

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101441420B1 (en) * 2012-06-18 2014-09-25 인하대학교 산학협력단 System and method for providing driving guide service and smart car
KR101468379B1 (en) * 2012-06-29 2014-12-02 인텔렉추얼디스커버리 주식회사 Access method for decrypting encryption data
KR101384593B1 (en) * 2012-08-03 2014-04-14 공주대학교 산학협력단 Behavior pattern reasoning based on context awarness
KR20140139263A (en) * 2013-05-27 2014-12-05 삼성디스플레이 주식회사 Flexable display device having guide function of gesture command and method thereof
KR101642487B1 (en) * 2015-06-30 2016-07-25 주식회사 카카오 Method for predicting user's future location and, apparatus and method for providing contents using the same method
KR20170142342A (en) * 2016-06-17 2017-12-28 건국대학교 산학협력단 Method of providing service using context recognition information of peripheral devices of based on a location at a specific place, and apparatus performing the same
KR20180050812A (en) * 2016-11-07 2018-05-16 인하대학교 산학협력단 System and method for tailored intervetion through prediction of inpatient falls
WO2019103199A1 (en) * 2017-11-23 2019-05-31 주식회사 모다 Personalized intelligent system and method for operating same
KR20210060830A (en) * 2019-11-19 2021-05-27 주식회사 피씨엔 Big data intelligent collecting method and device

Similar Documents

Publication Publication Date Title
KR20120033597A (en) Apparatus and method for recognizing user future context
US9934515B1 (en) Content recommendation system using a neural network language model
CN112182412B (en) Method, computing device, and computer storage medium for recommending physical examination items
US20110125700A1 (en) User model processing device
CN108875055B (en) Answer providing method and equipment
KR20190101327A (en) Method and apparatus for assessing price for subscription products
US20100318576A1 (en) Apparatus and method for providing goal predictive interface
US9864951B1 (en) Randomized latent feature learning
US11386463B2 (en) Method and apparatus for labeling data
US9767409B1 (en) Latent feature based tag routing
WO2010010654A1 (en) Usage estimation device
Ricci Recommender systems in tourism
KR20200054356A (en) Deep Learning Based Caching System and Method for Self-Driving Car in Multi-access Edge Computing
US20220014597A1 (en) Computer-implemented system and method for distributed activity detection
CN110969184A (en) Directed trajectory through communication decision trees using iterative artificial intelligence
Salah et al. Fuzzy AHP for learning service selection in context-aware ubiquitous learning systems
Baumann et al. Selecting individual and population models for predicting human mobility
US20200202068A1 (en) Computing apparatus and information input method of the computing apparatus
CN111625680A (en) Method and device for determining search result
Peerzade Web service recommendation using PCC based collaborative filtering
CN107861769B (en) Application cleaning method and device, storage medium and electronic equipment
US20230106590A1 (en) Question-answer expansion
WO2019059755A1 (en) A dynamically networked social platform with a predictive module for services delivery
CN112992367B (en) Smart medical interaction method based on big data and smart medical cloud computing system
JP2023536769A (en) METHOD, APPARATUS AND SYSTEM FOR RECOMMENDING EXPLANATION CONTENT FOR MAXIMIZING EDUCATIONAL EFFECT TO USER

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E902 Notification of reason for refusal
E601 Decision to refuse application