KR101690052B1 - Context-aware personalized dynamic interface system applying sliding window model in mobile environment - Google Patents

Abstract

The present invention relates to a context-aware personalized dynamic interface providing system using a sliding window model in a mobile environment. More particularly, the present invention relates to a system and method for providing a context- The present invention relates to a context-aware personalized dynamic interface providing system using a sliding window model in a mobile environment to provide a list of applications best suited to a place and a time when a user executes a mobile.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a context-aware personalized dynamic interface providing system,

The present invention relates to a context-aware personalized dynamic interface providing system using a sliding window model in a mobile environment. More particularly, the present invention relates to a system and method for providing a context- The present invention relates to a context-aware personalized dynamic interface providing system using a sliding window model in a mobile environment to provide a list of applications best suited to a place and a time when a user executes a mobile.

With the popularity of smartphones, many applications that can be used in smartphones have been developed and used.

As a result, the number of applications installed on the smartphone is increasing, complicating the interface of the smartphone and inconveniencing the user to manage the interface.

Unlike desktop environments, smartphones have limited-size displays, which means that if you have a lot of applications installed, users will have to manually rearrange or rearrange their interfaces.

Customized information service (personalization service) is a service that provides information that the customer wants or needs, saves time and cost for finding it, and dynamically provides information according to customer preference so that it can be easily accessed.

In order to improve the performance of personalized services and provide users with better quality of personalized services, they are moving toward combining technologies of various fields.

Among them, researches are actively carried out to improve the accuracy of recommendation by using information of sensors as high performance sensors are spreading.

Especially, the application of context - based service has been studied as the technique of recognizing the user 's context by processing the low level data generated by the sensor has been developed.

Therefore, a system that provides a dynamic interface using the application usage pattern and context awareness information of the user is needed.

Such a system can provide the user with a list of desired applications in real time.

The existing dynamic interface providing system analyzed application of users' usage patterns over time or recognized the situation using sensor information and provided a list of applications.

However, since existing technologies provide a list of applications through a time-sensitive situation, the user always has to provide the same list of applications at any place.

In addition, when an application limited to the sensor information is provided, it is necessary to recognize the situation through unreliable data because it is necessary to recognize the situation with inaccurate sensor information.

It is difficult to provide a list of suitable applications because it is difficult to accurately identify the situation.

Therefore, analyzing the application usage pattern in a state where the user's situation is recognized requires a system for providing a highly personalized dynamic interface.

Korean Patent Publication No. 10-2013-0089333

SUMMARY OF THE INVENTION Accordingly, the present invention has been made keeping in mind the above problems occurring in the prior art, and it is a primary object of the present invention to provide a personalized dynamic interface having a high degree of satisfaction by analyzing an application usage pattern in a state where a user's situation is recognized .

In other words, by analyzing the location and time of the user, the user is aware of the situation and provides a list of necessary applications. When the user executes the mobile, the list of the application best suited to the place and time .

According to an aspect of the present invention, there is provided a context-aware personalized dynamic interface providing system using a sliding window model in a mobile environment,

A location auto-recognition unit for automatically recognizing the location of the user by referring to the location information;

And a context-aware dynamic interface unit for analyzing an application usage pattern for a place recognized by the place automatic recognition unit using a sliding window model and providing a personalized dynamic interface suitable for the place.

The context-aware personalized dynamic interface providing system using the sliding window model in the mobile environment according to the present invention has the above-described configuration and operation. The system analyzes the user's location and time to recognize the user's situation, Provide a list of applications, but when the user runs the mobile, it will provide a list of applications that are best suited to the place and time, considering the circumstances.

FIG. 1 is an overall configuration diagram of a context-aware personalized dynamic interface providing system applying a sliding window model in a mobile environment according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a movement path of a context-aware personalized dynamic interface providing system applying a sliding window model in a mobile environment according to an exemplary embodiment of the present invention. FIG. 3 is an application usage graph, FIG. 5 is an exemplary view showing an address value error according to Lat and Lon, FIG. 6 is an exemplary view illustrating a Poi tiling technique, and FIG. 7 is an exemplary diagram illustrating processed log data FIG. 8 is a diagram illustrating an example of a sliding window model, FIG. 9 is a formula for obtaining an execution probability of an application, FIG. 10 is a diagram illustrating an interface generated in a state of being arranged in a lock screen form Fig.

The following merely illustrates the principles of the invention. Therefore, those skilled in the art will be able to devise various apparatuses which, although not explicitly described or illustrated herein, embody the principles of the invention and are included in the concept and scope of the invention.

Furthermore, all of the conditional terms and embodiments listed herein are, in principle, only intended for the purpose of enabling understanding of the concepts of the present invention, and are not to be construed as limited to such specifically recited embodiments and conditions do.

Hereinafter, a context-aware personalized dynamic interface providing system using a sliding window model in a mobile environment according to the present invention will be described in detail with reference to embodiments.

FIG. 1 is an overall configuration diagram of a context-aware personalized dynamic interface providing system applying a sliding window model in a mobile environment according to an embodiment of the present invention.

As shown in FIG. 1, the personalized dynamic interface providing system of the present invention mainly comprises:

A location auto-recognition unit 100 for automatically recognizing a user's location by referring to the location information, an application usage pattern for a location recognized by the location auto-recognition unit using a sliding window model, And a context-aware dynamic interface providing unit 200 for providing a personalized dynamic interface.

That is, every time the smartphone is used, the GPS information is collected according to the user's time, and the user's travel path pattern is analyzed using the collected information to recognize the situation information such as the user's home, company, and outdoor, To provide a personalized dynamic interface that analyzes application usage patterns and provides a list of appropriate applications.

In order to provide customized services to the users, it is necessary to find individual preferences and demands.

Recently, there are many cases where context information of a user is utilized by referring to customized information providing services.

Since smartphones are always around, it is best to collect the situation data that users are in, and because the situation is always changing dynamically, the data is constantly generated, and when the data is collected and analyzed, the user's situation can be inferred.

Variables that need to be considered in order to recognize the situation are location, time, distance, user's situation, network status, and so on.

The most common information that can be used in a mobile environment is location and time, so it is used for context awareness.

Currently, it is common to provide an interface through a folder on a mobile, and a folder must be randomly generated by a user, set its name, and find a suitable application there.

In the meantime, the place automatic stopping portion 100 of the present invention,

A log processing engine module 110 for processing the raw sensor log data generated by the GPS sensor of the smart phone and the time log and storing the processed raw log data in the log database,

A log database 120 storing data processed by the log processing engine module,

And a situation recognition engine module 130 for recognizing a user's location by analyzing a gyroscope sensor to determine a user's behavior and analyzing a moving path pattern based on the discriminated behavior, do.

More specifically, as a user uses an application (application), raw log data is generated based on data generated from the GPS sensor and the time log on the smartphone.

The generated raw log data is processed in the log processing engine module 110 and stored in the log database 120.

In order to recognize the situation, the gyroscope sensor is analyzed through the context aware engine module 130 to determine the user's behavior.

And the location of the user is recognized by analyzing the moving path pattern based on the discriminated action.

At this time, the context-aware dynamic interface providing unit 200 analyzes the application usage pattern for the place recognized by the place automatic reservation unit using a sliding window model and provides a personalized dynamic interface corresponding to the corresponding place .

For example, when a request is made to a log database based on information about a finally recognized place, a personalized dynamic interface is provided through analysis of the application using pattern of the inquired information.

In other words, a personalized dynamic interface is created by changing the location and time of the user, thereby providing a list of applications.

As shown in FIG. 2, the log processing engine module 110 analyzes a user's route pattern through GPS information, thereby recognizing a location.

That is, the GPS data includes latitude, longitude, and time information. When the GPS data collected in one day are connected in chronological order, the user's travel path can be obtained as shown in FIG.

By analyzing the pattern of this route, users can recognize their location as a house, a company, or an outdoor place.

Even if the latitude and longitude data collected by GPS are in the same position, slight differences may occur, and GPS data can not always be the same.

To solve this problem, GPS data must be converted into a certain range.

Since the address corresponds to a certain range value, the latitude and longitude of the GPS data is converted into the address data, and the address data can receive the certain position data even if a certain error occurs in the GPS data value.

The collected GPS data is slightly different every day, but it has a certain pattern in the week, and if the analysis of the movement pattern of the GPS data is analyzed, the user's position can be recognized as situation information such as home and company.

In order to recognize the above situation, the beginning and end of all the paths are the house. The company is staying in the same place for the longest time, not the place judged as the house, and the application is used a lot. , It is necessary to assume that the situation is.

Based on the above assumptions, in order to determine the place where the user is located, it is time to analyze the usage amount of the application in order to know the beginning and end of the day.

The Interval Time lasts for a long time without application usage.

This time can be determined by comparing the starting and ending points of the Interval Time with the user's sleeping state. This time is determined by measuring the gyroscope's significant change in Y value.

The user recognizes an operation of picking up a phone and measures a time when the phone is not used based on the recognized point of time through the context awareness engine module 130. [

Therefore, when the context awareness engine module recognizes the start and end of the day, it can judge the place as home.

On the other hand, after the Interval Time is over, there is usually a long time change of the GPS position and application usage is increasing.

Except for the house, the area in which the person works the longest is usually a company or a school.

You can identify your company by analyzing application usage and where you spend a lot of time during the day.

After the house and the company are recognized, all other places are recognized as outdoor, and the outdoor is assumed to be a place away from home and company.

Meanwhile, the log processing engine module of the present invention performs address value conversion by using a temporal domain value and a poi tiling method in real time when raw log data is generated.

Specifically, user tendencies tend to be repeated with a temporal cycle.

That is, the tendency of the user to change with time changes. For example, the type of application used in the morning differs from that used in the evening, and the frequency of application execution also changes with time.

Therefore, temporal domain values are applied to store the data.

In this case, applying the domain to the accumulated date and time of use of the data makes it easy to derive the application to be applied to the dynamic interface.

The applied domain values are {"morning", "afternoon", "evening", "night"}. Each time information is based on 24 hours a day. "Morning" is 06:00 to 11:00. "Afternoon" City, "evening" is from 17:00 to 20:00, and "night" is from 20:00 to 06:00.

The use date and time is classified according to the time domain, and the usage pattern data of the application used at the relevant time is analyzed to provide a dynamic interface to the user.

Meanwhile, the log processing engine module reduces the number of all data stored in the log database by applying the count information, and the raw log data includes application name, use date and time, latitude and longitude data .

Specifically, when a user uses an application, unprocessed raw log data is generated as shown in FIG. 4, and the generated data has an application name, a date and time of use, a latitude and a path.

At this time, when the raw log data is generated, the log processing engine module stores the temporal domain value and the address conversion process in real time in the log database.

The address value correction is required due to the uncertainty of the GPS data generated in the address conversion process, and the GPS data generated at the same place may be converted to another address value.

As shown in FIG. 5, an error of the address data can be found. Since the user is measured at the same position but is represented by a different address value, it is difficult to accurately recommend the location based recommendation.

In order to solve the above problem, the address value conversion is performed by using the poi tiling method.

As shown in FIG. 6, the map is divided into tiles by giving a correction value +/- 0.001 to the latitude and longitude values based on the log data generated for the first time.

Address value error can be minimized by converting the address value in the form of corrected Lat and Lon values based on the tiled map.

The processed data in the log processing engine module is shown in FIG.

In addition to applying Temporal Domain Values and address translation, the processed data is greatly reduced in the overall number of data by applying count information.

In other words, as the number of stored data increases as the number of stored data increases, optimization of data becomes important because it becomes inapplicable to use in smartphone. Therefore, by measuring the date and time used for each application, The log data is processed and stored in the log database so that it is easy to guess the application usage pattern by time zone.

Meanwhile, the context-aware dynamic interface provider 200 analyzes the application usage pattern for a place recognized by the place automatic reservation section using a sliding window model, and provides a personalized dynamic interface suitable for the corresponding place.

That is, a personalized dynamic interface is created according to the change of the user's place and time, and a list of the applications is provided.

Particularly, the context-aware dynamic interface providing unit 200 is used for recommendation considering only 30 days of data used recently.

That is, the stored data is used for the recommendation considering only the data of 30 days recently used to reflect the application usage pattern to the user recently.

The context aware dynamic interface provider 200 searches the log database for data corresponding to the place and time when the user executes the phone, and provides a list of applications to the user.

Specifically, based on the analyzed data, the application to be provided to the user is determined and used to generate a personalized dynamic interface.

The application usage pattern data accumulated continuously in the log database takes a lot of time to be provided by the user because of the cumulative number of executions over time.

Therefore, the application recommended in the context aware dynamic interface offering should be a new and frequently used application.

To this end, the Fresh-based Recommendation technique is applied.

There are two models of the fresh-based technique.

The Damped Window model calculates the importance by comparing past data with recent data. Sliding Window model is a model that applies only the usage history given in recent period.

Because it is not appropriate to process large data due to the characteristics of mobile devices, Sling Window model considering only recent data is suitable without consideration of data before a certain period in the past.

Therefore, applying the Sliding Window Model in the context-aware dynamic interface interface helps us to predict the recent usage patterns of users who tend to change their usage patterns over time.

That is, the usage pattern is analyzed using only the data of the last 30 days without using the old pattern data and analyzing the usage pattern.

It can play a large role in reflecting the change in the user tendency in the application list prediction result by reflecting the change in the user's recent usage pattern with time.

FIG. 8 shows the data of the users divided into {"morning", "afternoon", "evening", "night"} according to Temporal Domain Values in order to apply sliding window model.

We use the last 30 days of data to know the three applications at the current "night" time to predict, and during the last 30 days we analyze the usage pattern of the application used for "night" .

In addition, the context-aware dynamic interface providing unit can obtain the execution probability of the application using the formula shown in FIG.

You can get application usage probabilities by using the number of executions of specific applications and the number of executions of all applications for the current location and temp domain.

The obtained probability sums up the records of the last 30 days to predict the list of the applications with the highest probability to be executed currently.

The context-aware dynamic interface provider displays a list of personalized applications when the location of the user is recognized and the application usage pattern according to the location is analyzed.

The displayed application list is preferably arranged from the left in the order in which the user is most likely to use the current one.

Updates are made according to the location of the move (house, company, outdoor) or change of time ("morning", "afternoon", "evening", "night") and are provided in the form of LockScreen.

The apparatus of the present invention periodically recognizes the user's situation in the background state and generates a personalized dynamic interface based on the perceived information.

As a result, a personalized dynamic interface is provided as the user's location and time change.

In particular, the context aware dynamic interface providing unit generates a dynamic interface according to a change of a user's location and time, and provides the user with three application lists.

FIG. 10 is a diagram illustrating an example of a status of an interface generated in a state of being arranged in the form of a lock screen. In the embodiment, a total of ten recommended applications are displayed and icons corresponding to the respective places are displayed to show where the recognized locations .

The recommended applications are also different if they are in the same time zone.

At this time, although the change rate of the upper application is small, it is possible to see the recommended application change according to the change of the place and time.

While the top-ranked applications show little change, you can see the recommended applications at the bottom according to the characteristics of each time zone and location.

Although the smartphone has a problem that it is inconvenient for the user to manually rearrange the interface with the small display and the inconvenience of searching for the app to execute the desired application, the present invention allows the user to analyze the location- To provide a dynamic interface.

Therefore, it is possible to solve the complexity problem in the passive interface of the current smartphone and the inconvenience of finding and executing the desired app.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It should be understood that various modifications may be made by those skilled in the art without departing from the spirit and scope of the present invention.

100: Place Auto Tear
200: Context-aware dynamic interface offering

Claims (8)

A context-aware personalized dynamic interface providing system,
A location auto-recognition unit 100 for automatically recognizing a location of a user by referring to the location information;
And a context-aware dynamic interface providing unit 200 for analyzing an application usage pattern for a place recognized by the place automatic book keeping unit by using a sliding window model and providing a personalized dynamic interface corresponding to the place and time Respectively,
The place auto hold unit (100)
A log processing engine module 110 for processing the raw sensor log data generated by the GPS sensor of the smart phone and the time log and storing the processed raw log data in the log database,
A log database 120 storing data processed by the log processing engine module,
And a situation recognition engine module 130 for recognizing a user's location by analyzing a gyroscope sensor to determine a user's behavior and analyzing a moving path pattern based on the discriminated behavior, In addition,
The log processing engine module 110,
When raw log data is generated, address value conversion is performed using a temporal domain value and a Poi tiling technique in real time, and count information is applied to reduce the total number of data stored in the log database. A Personalized Dynamic Interface Providing System Based on Situational Cognition Applying Model.

delete delete delete The method according to claim 1,
The raw log data includes:
And the application name, the date and time of use, the latitude and the longitude of the mobile terminal, and a sliding window model in the mobile environment. The method according to claim 1,
The context-aware dynamic interface component 200,
Wherein the personalized dynamic interface is generated according to the change of the user's location and time, and the list of the applications is provided, and the context-aware personalized dynamic interface providing system applying the sliding window model in the mobile environment. The method according to claim 1,
The context-aware dynamic interface component 200,
And provides a list of applications in the form of LockScreen. A context-aware personalized dynamic interface providing system applying a sliding window model in a mobile environment. The method according to claim 1,
The place auto hold unit (100)
Wherein the mobile terminal recognizes at least one of a home, a school, a company, and an outdoor location by analyzing a pattern of a moving route. The system provides a personalized dynamic interface based on a context-aware application using a sliding window model in a mobile environment.

Images