KR102687695B1 - Server and method for managing platform integrated interface - Google Patents

Abstract

One aspect of the present invention provides a platform integrated interface management server. The platform integrated interface management server may include at least one processor and a memory storing instructions for instructing the at least one processor to perform at least one step. The at least one step may include: receiving user device information and service information through the user terminal; generating a user profile vector based on the received device information or service information; and configuring an interface by mapping the weighted user profile vector with an interface parameter for interface configuration according to the type of the user terminal.

Description

Platform integration interface management server and method {SERVER AND METHOD FOR MANAGING PLATFORM INTEGRATED INTERFACE}

The present invention relates to a platform integrated interface management server and method, and more specifically, to provide integrated management of the interface of a service platform running on various devices, to provide interface management interconnection of the service platform according to the user's device, and to provide platform integration. It relates to a platform integrated interface management server and method that provides optimized services.

With recent technological advancements, digital devices such as smartphones, tablets, and personal computers have naturally permeated our daily lives, and these various devices simplify human life and provide various services and applications for easy access to convenient services. .

The user interface (UI), or interface that mediates interactions between users and services and applications, is known to be a key element in determining user experience (UX). However, users have diverse needs and preferences depending on gender, age, region, and level of education.

In existing technologies, user interfaces are generally designed based on average or assumed user characteristics, which brings convenience to design, but has the problem of not being able to address the unique needs of individual users. As a result, the general usage pattern is that the user must adapt to the user interface provided, rather than the user interface adapting to the user, which leads to reduced user satisfaction, decreased efficiency, and increased cognitive load.

To provide more personalized interfaces, some systems are being explored using machine learning algorithms to adjust specific interface parameters based on user interaction history. However, these systems focus on relatively superficial functions and do not reflect the patterns that occur when users use devices or services, and there is a problem in that they do not respond sensitively to changes in the user's usage pattern. .

Accordingly, there is a need for research on a platform integrated interface management method to provide an interface suitable for users on various devices by configuring the user interface through user interaction.

Domestic registered patent No. 10-2549129

The purpose of the present invention to solve the above problems is to provide a platform integrated interface management server and method.

One aspect of the present invention for achieving the above object provides a platform integrated interface management server.

The platform integrated interface management server may include at least one processor and a memory that stores instructions that instruct the at least one processor to perform at least one step.

At least one step includes receiving user device information and service information through a user terminal, generating a user profile vector based on the received device information or service information, and converting the weighted user profile vector to the user terminal. Depending on the type, it may include a step of configuring the interface by mapping it with interface parameters for configuring the interface.

In addition, by analyzing service information, functional interaction intensity (FII) is calculated from the ratio of the number of user interactions with a specific function to the total usage time, and the total number of pages or screens viewed by the user relative to the total usage time of the service. Calculate interface navigation speed (INS) from the ratio, content consumption rate (CCR) from the amount of content consumed during a predetermined period of time, and user interaction latency (CCR) from the average time it takes a user to interact with a notification or respond to an event. Calculate the time (UIL), calculate the input style parameter (ISP) from the total number of characters entered by the user divided by the total input time, and calculate the service dependence index ( Calculate the SDI), calculate the multitasking index (MI) from the average number of services used simultaneously compared to the number of services used by the user, and calculate the multitasking index (MI) from the ratio of the number of errors that occurred and were resolved in the total service usage time of the user. It may further include calculating an error interaction rate (EIR) and analyzing the received service information.

At this time, the step of analyzing service information is to calculate user interaction efficiency (UIE) by dividing functional interaction intensity (FII) by interface navigation speed (INS), and calculating user interaction efficiency (UIE) by dividing content consumption rate (CCR) by interaction waiting time (UIL). ) and the input style parameter (ISP) to calculate the service participation level (SEL), and the service dependency index (SDI) and the multitasking index (MI) are multiplied by the error interaction rate (EIR). The step of calculating dependency and multitasking index (SDMI) may be further included.

In addition, in the step of configuring the interface, the larger the calculated user interaction efficiency multiplied by the predetermined conversion coefficient, the narrower the layout interval is set, and the smaller the calculated user interaction efficiency multiplied by the predetermined conversion coefficient, the smaller the layout. In the step of setting the gap wider, the larger the calculated service participation level multiplied by the predetermined conversion coefficient, the smaller the interface text size is set. The smaller the calculated service participation level multiplied by the predetermined conversion coefficient is, the smaller the interface text size is. It may further include setting the notification frequency to a large value and dividing the calculated service dependency and multitasking index (SDMI) by the average notification frequency generated by the service used by the user during a predetermined period of time.

Additionally, the step of generating an integrated user profile by combining the received device information and service information may be further included.

When using the platform integrated interface management server and method according to the present invention as described above, the use completion rate of administrative services can be increased through accurate support for various administrative services, and user satisfaction can be increased through administrative service support for complex procedures. there is.

The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. will be.

The above-described and other aspects, features and benefits of certain preferred embodiments of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings.
Figure 1 is an exemplary diagram showing the operating environment of a platform integrated interface management server according to an embodiment of the present invention.
Figure 2 is an exemplary diagram showing an example of a platform integrated interface management server.
Figure 3 is an exemplary diagram showing another example of a platform integrated interface management server.
Figure 4 is an example diagram for explaining an example of configuring an interface.
5 is a hardware configuration diagram for the platform integrated interface management server according to FIG. 1.
It should be noted that throughout the drawings, like reference numerals are used to illustrate identical or similar elements, features and structures.

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

In describing the embodiments, description of technical content that is well known in the technical field to which the present invention belongs and that is not directly related to the present invention will be omitted. This is to convey the gist of the present invention more clearly without obscuring it by omitting unnecessary explanation.

For the same reason, some components are exaggerated, omitted, or schematically shown in the accompanying drawings. Additionally, the size of each component does not entirely reflect its actual size. In each drawing, identical or corresponding components are assigned the same reference numbers.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide common knowledge in the technical field to which the present invention pertains. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

At this time, it will be understood that each block of the processing flow diagrams and combinations of the flow diagram diagrams can be performed by computer program instructions. These computer program instructions can be mounted on a processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, so that the instructions performed through the processor of the computer or other programmable data processing equipment are described in the flow chart block(s). It creates the means to perform functions. These computer program instructions may also be stored in computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing equipment to implement a function in a particular manner, so that the computer-usable or computer-readable memory The instructions stored in may also produce manufactured items containing instruction means that perform the functions described in the flow diagram block(s). Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a process that is executed by the computer, thereby generating a process that is executed by the computer or other programmable data processing equipment. Instructions that perform processing equipment may also provide steps for executing the functions described in the flow diagram block(s).

Additionally, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). Additionally, it should be noted that in some alternative execution examples, it is possible for the functions mentioned in the blocks to occur out of order. For example, it is possible for two blocks shown in succession to be performed substantially at the same time, or it is possible for the blocks to be performed in reverse order depending on the corresponding function.

At this time, the term '~unit' used in this embodiment refers to software or hardware components such as FPGA (field-programmable gate array) or ASIC (Application Specific Integrated Circuit), and '~unit' refers to what role perform them. However, '~part' is not limited to software or hardware. The '~ part' may be configured to reside in an addressable storage medium and may be configured to reproduce on one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. In addition, the components and 'parts' may be implemented to regenerate one or more CPUs within the device or secure multimedia card.

In explaining the embodiments of the present invention in detail, the main focus will be on examples of specific systems, but the main point claimed in this specification is that the scope disclosed in this specification is applicable to other communication systems and services with similar technical background. It can be applied within a range that does not significantly deviate, and this can be done at the discretion of a person with skilled technical knowledge in the relevant technical field.

Figure 1 is an exemplary diagram showing the operating environment of a platform integrated interface management server according to an embodiment of the present invention.

Referring to FIG. 1, the platform integrated interface management server 100 (hereinafter referred to as 'server 100') may receive user device information and service information through the user terminal 10. For example, when a user uses the user terminal 10, the server 100 may receive user device information including the usage pattern of the user terminal through a wired or wireless network.

Additionally, the server 100 may receive service information including the attributes of the service used by the user through the user terminal 10 and the service usage aspect.

At this time, the user terminal 10 is a communication capable desktop computer, laptop computer, laptop, smart phone, tablet PC, mobile phone, Smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, It may be a digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant), etc.

In addition, wired and wireless network methods include Bluetooth communication, BLE (Bluetooth Low Energy) communication, Near Field Communication (NFC), WLAN communication, Zigbee communication, Infrared Data Association (IrDA) communication, It may include various communication methods such as WFD (Wi-Fi Direct) communication, UWB (ultra-wideband) communication, Ant+ communication, WIFI communication, and RFID (Radio Frequency Identification) communication, but is not limited thereto.

Here, the user device information includes operating system information related to the functions of the user terminal and the way the user interacts with the user terminal, such as the operating system (e.g. Android, iOS, Windows, macOS, etc.) of the user terminal 10, and the screen of the user terminal. Hardware specifications of your device such as size, resolution, CPU, GPU, RAM, etc., input method including touchscreen, mouse and keyboard, remote control or other input method, browser or application version, type of internet connection (Wi-Fi, Ethernet, 4G) , 5G, etc.) and speed, location information of the user's terminal and 3D movement information of the terminal (e.g. Roll, Pitch, Yaw), user's terminal usage time, battery status, and user's device usage such as accelerometer and gyroscope. It can be included.

Additionally, service information may include time-based usage patterns, including peak usage times for a particular service or application when a user uses a particular app at a specific time of the day, sustained usage time for a particular service or application, and when the user is most likely to use the service or application. Feature-based usage patterns, including frequently used features and interaction sequences; context-based usage patterns, including where users use the Service and what types of services or applications they use most often on different devices; and notifications from services or applications. It may include event-triggered usage patterns, including response patterns and in-app purchase patterns, and interaction-based usage patterns that describe whether users interact with the service, such as social media shares and new content (e.g. reviews, comments, etc.). .

In addition, but not limited to this, more specifically, feature interaction intensity, which refers to the frequency of interaction with a specific feature within a certain period of time, measures the speed at which the user navigates through the service interface, and measures the average time spent per unit screen or per minute. Interface navigation speed, quantified by the average number of pages visited; content consumption rate, which is defined as the speed at which users consume content containing audio, text, or video; and the time it takes users to interact with notifications or respond to events within a service or application. Expressed user interaction latency; for apps involving user input, input style parameters determined by the user's input speed; dependence on the services and applications used by the user; use of a specific service or application compared to the total usage time of the user's terminal; Service dependency index calculated in terms of time, multitasking index expressed as the average number and switching frequency of services or applications used simultaneously through multitasking, and the problem when a user encounters an error message or problem within a service or application and interacts with it The error interaction rate calculated as the time required to solve can be included.

For example, the server 100 analyzes service information to determine functional interaction intensity (FII), interface navigation speed (INS), content consumption rate (CCR), UIL (user interaction waiting time), and input style parameters (ISP). ), Service Dependency Index (SDI), Multitasking Index (MI), and Error Interaction Rate (EIR) can be calculated.

For example, Functional Interaction Intensity (FII) is the ratio of the number of user interactions with a specific function to the total usage time. For a specific function 'f', it is calculated through the following equation in the usage period 't': It can be.

Interface Navigation Speed (INS) is an indicator of the user's navigation speed and can be calculated as the equation below as the ratio of the total number of pages or screens viewed by the user 'v' to the total usage time 't'. there is.

Content Consumption Rate (CCR) can refer to the amount a user consumes content over time, for example, in the case of text content, the total number of words read 'w' is divided into the total read time 't'. The divided value can be calculated as shown in the equation below.

User Interaction Latency (UIL) can refer to the average time it takes a user to interact with a notification or respond to an event. For example, in the case of 'n' events with response times r1, r2, ..., rn, UIL can be calculated as follows:

An input style parameter (ISP) may be a parameter that quantifies the user's input speed. For example, in the case of text input, the total number of characters 'c' entered divided by the total input time 't' can be calculated as shown in the equation below.

The service dependence index (SDI) may be an indicator indicating the user's dependence on a specific service or application. For example, for the user's use time of all services 't' and the use time of specific service 's', SDI can be calculated as shown in the equation below.

Additionally, the multitasking index (MI) can quantify the average number of services or applications used simultaneously. For example, if a user uses a total of 'm' services and uses 'a' services on average at the same time, MI can be calculated as in the following equation.

Meanwhile, Error Interaction Rate (EIR) can represent the rate at which users discover and resolve errors. For example, for the number of errors 'e' that occurred and were resolved in total usage time 't', EIR can be calculated as follows:

The server 100 may calculate User Interaction Efficiency (UIE), and UIE may mean how efficiently a user interacts with a service or application. At this time, a higher UIE indicates that the user frequently interacts with a specific function and quickly navigates the interface. UIE can be calculated through the ratio of functional interaction strength and interface navigation speed as shown in the equation below.

Additionally, the server 100 may calculate the service engagement level (SEL), which is the user's level of participation in a service or application. SEL is a combination of CCR, UIL, and ISP, calculated as shown in the equation below, and represents the amount of content consumed by the user, response speed to interaction, and input speed.

Additionally, the server 100 can calculate the user's dependency and multitasking habits on a specific service or application using the Service Dependence and Multitasking Index (SDMI). SDMI combines SDI, MI, and EIR to represent the percentage of time a user spends on a specific service or application, the ability to use multiple applications simultaneously, and the error interaction rate, and can be calculated as shown in the equation below.

Meanwhile, the server 100 may create a user profile for the user after the analysis of device information through the user terminal and analysis of service information according to the user's use of the service or application are completed.

For example, the server 100 can collect user device information and service information, extract features from the collected information, normalize it, and analyze it. As an example, the extracted features can be normalized through min-max scaling or normalization.

After the data is normalized, the server 100 can apply a clustering algorithm (DBSCAN, K-Means) to cluster users with similar user terminal usage and service usage patterns. The server 100 may create a profile for each user based on the cluster to which the user belongs and specific actions within the cluster. The created profile can be managed by converting quantitative parameters representing the user's behavior and preferences into vectors.

As an example, each element of the generated vector may consist of one of the specific quantitative parameters measured (e.g., strength of functional interaction or speed of interface navigation). The value of each element of the user vector is a normalized score representing user behavior related to that parameter. For example, a user who frequently interacts with a particular feature may be given a high score for feature interaction intensity.

Additionally, the server 100 may configure a user interface using the generated user profile vector.

For example, the server 100 may use the generated user profile vector as input. At this time, the generated user profile vector may include normalized scores for each user behavior, service, and preference expressed by specific quantitative parameters described above.

Next, the server 100 may generate a user profile vector using detailed information about the terminal or device the user is currently using. This may include device information such as terminal type, operating system, hardware specifications, screen size and resolution, input method, network type and speed, etc.

Additionally, the server 100 may assign scores to user interface elements based on their relevance to user behavior, services, and preferences indicated by the user profile vector.

As an example, the server 100 may consider the function interaction intensity score and, if the user has a high score for interaction with a specific function, assign a high score to the user interface element related to the function. Additionally, the server 100 may use a deep learning model trained to predict the relevance of user interface elements based on the user profile vector and the characteristics of the user interface elements.

Next, the server 100 may arrange the user interface elements that have been given the highest score for the user terminal according to the usage mode of the user terminal. As an example, the server 100 may adjust the deployed user interface to match the interface of the service or application used by the user. For example, server 100 may adjust user interface elements by dynamically rearranging, displaying, hiding, resizing, or restyled.

For example, if a user frequently uses a particular feature, related user interface elements can be moved to a more easily visible location, such as the top or center of the screen, and if a user frequently uses the service in low-light environments, the interface can be automatically darkened. mode can be switched.

Additionally, the server 100 may adjust user interface elements according to the user's service or application usage patterns. For example, the server 100 may adjust between each layout constituting the user interface according to the calculated UIE value. For example, the server 100 may determine the layout interval constituting the user interface according to the equation below.

here is a conversion coefficient that can be determined in advance according to the screen size of various terminals. At this time, Plays a role in converting the size of the UIE value, and depending on the screen size of various terminals (e.g. smartphone, tablet, or PC), the smaller the screen, the larger the value, and the larger the screen, the smaller the value. Through this, when the UIE value is high, the layout spacing becomes smaller and more information can be arranged on the same screen, and when the UIE value is low, the layout spacing is widened and less information can be arranged on the same screen.

Additionally, the server 100 can adjust the size of text displayed in the user interface as shown in the equation below based on SEL.

here is a conversion coefficient that can be determined in advance according to the screen size of various terminals. At this time, Plays a role in converting the size of the SEL value, and depending on the screen size of various terminals (e.g. smartphone, tablet, or PC), the smaller the screen, the larger the value, and the larger the screen, the smaller the value. This allows user interface text to be scaled smaller for high SEL values, providing more dense information on the same screen.

Additionally, the server 100 can adjust the user notification frequency according to SDMI by adjusting the user interface using the equation below.

here, means the average notification frequency generated by the service or application used by the user during a predetermined period of time, and SDMI can be normalized. Through this, the server 100 can generate more notifications for users with high SDMI values, thereby ensuring the user's active use of the service through notifications.

Figure 2 is an exemplary diagram showing an example of a platform integrated interface management server. Referring to FIG. 2, the platform integrated interface management server 200 (hereinafter referred to as 'server 200') includes a device information analysis unit 210, a user profile creation unit 220, and an interface configuration unit 230. It can be included.

The device information analysis unit 210 may receive and analyze usage information of the user terminal. At this time, the user terminal may include various types of user terminals described above with reference to FIG. 1, and the characteristics of the user's device usage pattern may be extracted and normalized, and then a user device profile vector may be generated.

For example, the device information analysis unit 210 may receive device information including device type, operating system, hardware specifications, screen size and resolution, input method, network type and speed, and device usage pattern.

When device information is received, the device information analysis unit 210 may generate feature data based on device information about the user's device use.

As an example, the device information analysis unit 210 may calculate the daily device use time by adding up all session times during the day. For example, if a user has three sessions per day of 30 minutes, 45 minutes, and 60 minutes respectively, the daily screen time can be calculated as 30 + 45 + 60 = 135 minutes.

In addition, the device information analysis unit 210 can determine the time when the user uses the device the most by displaying the start time of all sessions in 24-hour format, and calculates each application or service used by the user on the device as the total device use. You can calculate the application usage rate by dividing by time. For example, if the user's total device usage time is 150 minutes and specific application A is used for 60 minutes, the application A usage ratio may be calculated as 60/150=0.4.

Also, at this time, the device information analysis unit 210 may filter information that is not information about the user's device usage pattern among the device information. For example, the Pearson correlation coefficient algorithm can be used to filter out device information (e.g., device color, device weight, etc.) that is not related to the function of the user device and the user's usage pattern.

Next, the device information analysis unit 210 may perform normalization through min-max normalization or Z-score normalization. As an example, daily device use time can be expressed as 0 minutes up to 1440 minutes (24 hours), and application use rate can be expressed as 0 to 1. This allows us to use min-max normalization to normalize 'device usage time per day' to a range between 0 and 1, as shown in the equation below:

Meanwhile, when information on the device used by the user is analyzed by the device information analysis unit 210, the user profile creation unit 220 can create a user profile.

For example, depending on the type of device information analyzed, if there are five normalized features: daily device usage time, maximum usage time, and application usage percentage of App1, App2, and App3, the initial user profile would be [0.5, 0.6, 0.1 , 0.3, 0.2] can be created in vector form.

At this time, the user profile generator 220 may apply weights to individual features according to the importance of each element constituting the user profile vector. At this time, the importance can be determined in advance by the user, or the weight for each element can be learned based on a specific objective function using a learning algorithm through linear regression or deep learning. For example, a predetermined weight vector [0.2, 0.3, 0.1, 0.2, 0.2] may be applied to each element of the user profile vector, and the weight for the user profile vector may be calculated as 0.37 as the scalar product.

In addition, the user profile creation unit 220 may update the user profile vector by reflecting changes according to changes in the user's device usage pattern, and the importance of each element of the user profile vector may be determined according to the user's device usage pattern. If it has changed, the user profile vector can be updated by correcting the user profile vector and its weight at predetermined intervals (e.g., hourly or daily).

Once the user profile vector is generated, the interface configuration unit 230 may create a user-suitable interface according to the user profile vector.

For example, the interface configuration unit 230 may map a weighted user profile vector to parameters for interface configuration. As an example, assume a user profile vector in which “daily device usage time”, “maximum usage time”, and “application usage ratio of App1, 2, and 3” are weighted as [0.37, 0.42, 0.15, 0.32, 0.28]. You can.

At this time, each element can be converted into a parameter constituting the user interface. For example, daily screen time (0.37) can be interpreted as the user's overall screen time. Higher usage times may mean higher interactivity, and users may prefer more condensed information for faster device usage.

For example, the interface configuration unit 230 may map the interface parameter 'content density' to determine the compression rate of information. At this time, the range of 'content density' may be expressed as a range from 1 to 10, where '1' may mean that the content density is low and 10 may mean that the content density is high. For example, the interface configuration unit 230 can calculate the content density as content density = 1 + 0.37*9 = 4.33 by using a linear mapping function such as content density = 1 + profile[0]*9. . Once the content density is calculated, the interface configuration unit 230 may display information in proportion to the content density within the same screen. At this time, the information may include icons, service pages, images, and text fonts. As the content density increases, the size of the icons, service pages, images, and text fonts are changed to a smaller interface so that more information is provided on the same size screen. can be configured.

In addition, the interface configuration unit 230 determines that the higher the maximum usage time is, the more frequently the user potentially uses the device late in a dark environment, and maps the maximum usage time to the 'color palette' interface parameter. For example, if the user profile vector 'profile[1]' is greater than 0.5, the 'Color Palette' can be set to 'Dark' mode, otherwise it can be 'Light'.

Additionally, by using the app usage ratios (0.15, 0.32, 0.28) of App1, App2, and App3, the interface configuration unit 230 can identify the most frequently used applications and make the applications more easily accessible through the interface. You can configure the interface and create a priority for use of applications on the main screen by creating a 'shortcut rank' parameter. For example, if the usage ratios of applications App2, App3, and App1 are 0.32, 0.28, and 0.15, respectively, 'Shortcut Rank' can create a ranking in descending order as App2 > App3 > App1. Additionally, when arranging application icons according to the 'shortcut rank', the interface configuration unit 230 may arrange the application icons so that the area of a closed curve formed by connecting the centers of the placed application icons is minimized. For example, application icons may have different sizes and shapes, but if applications are arranged according to 'shortcut rank' and the area of the closed curve connecting their centers is minimized, each application icon is densely placed. This can increase user convenience.

In this way, the interface configuration unit 230 can configure the interface by calculating the interface parameters and mapping them to the interface configuration according to the type of user terminal. For example, when a user uses a smartphone, the content density value may be interpreted differently due to the limited screen size compared to a PC. In other words, high 'content density' does not mean displaying more items on a single screen, but rather applying folding menus or tabbed browsing to accommodate more content in an easy-to-navigate manner. Additionally, the 'color palette' parameter can directly determine the color theme of the user interface based on the user's usage time in the user terminal, thereby increasing the convenience of use of the user terminal.

Additionally, 'Shortcut Rank' determines the order of application icons on the home screen or in the smartphone's application drawer, allowing easy access to frequently used apps.

Figure 3 is an exemplary diagram showing another example of a platform integrated interface management server. Referring to FIG. 3, the platform integrated interface management server 300 (hereinafter referred to as 'server 300') includes a device information analysis unit 310, a service information analysis unit 320, and a user profile creation unit 330. and an interface configuration unit 340. At this time, the device information analysis unit 310, the user profile creation unit 330, and the interface configuration unit 340 are the device information analysis unit 210, the user profile creation unit 220, and the interface configuration described above with reference to FIG. 2. Since each may have the same configuration as the unit 230, the following description will focus on configurations that do not overlap.

The service information analysis unit 320 may collect data related to the user's interaction with a service or application running on the user terminal. For example, the service information analysis unit 320 may use an Event-Driven Data Collection (EDDC) algorithm to collect comprehensive data about the user's interaction with services or applications used in the user terminal. EDDC utilizes system hooks to receive events that the user is performing on the terminal.

Specifically, the EDDC algorithm can perform event logging by capturing user interactions such as the user starting or closing an application on the user terminal, navigating within the application, and performing various in-app activities. For example, you can record when a user opens a messaging app, the interactions within the app (reading messages, sending messages, accessing other chats, etc.), and a timestamp when the user exits the app.

For example, the service information analysis unit 320 can convert the collected data into a structured format that can be quantified. As an example, the service information analysis unit 320 may transform the collected data and parse the event log generated by the EDDC algorithm.

For example, the service information analysis unit 320 analyzes the collected event log of the user's application use to determine at least one item such as 'app use period', 'app use frequency', 'in-app activity type', and 'daily usage amount'. It can be classified by the above user behavior. As an example, 'app usage period' may represent the average time of a user's session for a specific app, and 'daily usage' may represent a user's app usage behavior across multiple times of the day.

After extracting features of the user's behavior, the service information analysis unit 320 can normalize the classified features to a common scale between 0 and 1. Through this, the service information analysis unit 320 can directly compare the values of different features and prevent a single feature from disproportionately affecting the overall analysis due to the numerical scale.

Additionally, the service information analysis unit 320 can perform feature extraction and normalization using a deep learning learning model. For example, the service information analysis unit 320 may use a CNN (Convolutional Neural Network) model to extract features according to the user's application use. In other words, the service information analysis unit 320 can identify features from the user's application usage pattern and correlation using a CNN model trained on the user's past usage data.

Meanwhile, the user profile creation unit 330 may create a user profile by combining the analyzed device information and service information. For example, the user profile creation unit 330 may obtain a vector of [Android 10, 1080x2400, LTE, evening] as a vector for [OS version, resolution, network type, usage time] as analyzed device information. there is. In addition, as the analyzed service information, a vector of [2 hours, 10 times/hour, none, day] can be obtained as a vector for [app use period, app use frequency, in-app activity type, daily usage pattern].

At this time, the user profile creation unit 330 may apply a predetermined weight to the device information vector and the service information vector to integrate the device information and service information to create a user profile. For example, the user profile creation unit 330 may assign weights of [0.4, 0.2, 0.3, 0.1] to [OS version, resolution, network type, usage time]. In other words, the OS version is given the greatest weight because it is related to the compatibility of future applications, resolution is closely related to UI and UX, so it is given a weight of 0.2, and network type is related to connectivity and speed, so it is given a weight of 0.3. And, a weight of 0.1 can be assigned to the usage time according to the user's activity.

Additionally, the user profile creation unit 330 may assign a weight of [0.3, 0.4, 0.1, 0.2] to [app use period, app use frequency, in-app activity type, daily use amount]. In other words, the app usage period represents the total time the user interacts with the service, so it is given a weight of 0.3, the app usage frequency represents how often the user engages with the service, so it is given the largest weight of 0.4, and in-app Since there is no activity, the lowest weight of 0.1 is assigned, and during the day when users are most likely to be active, a weight of 0.2 can be assigned.

Meanwhile, the user profile creation unit 330 may integrate the analyzed device information and service information to create an integrated user profile. For example, the user profile generator 330 may align the vectors by adjusting the user profile vector generated based on the analyzed device information and the user profile vector generated based on service information to the same length. For example, if the length of the user profile vector created based on device information is 5 and the length of the user profile vector created based on service information is 4, the length of the user profile vector created based on device information is adjusted to 4. Vectors can be sorted.

Next, the user profile creation unit 330 generates one vector by merging the user profile vector generated based on the analyzed device information and the user profile vector generated based on the service information, thereby creating one integrated user profile vector. can be created. One integrated user profile vector may include all of the user's device information and service information about service use, such as [[OS version, resolution, network type, usage time], [app usage period, app usage frequency] , in-app activity type, and daily usage]], an integrated user profile vector can be created. Meanwhile, the user profile generator 330 may assign weights to the integrated user profile vector according to its importance, and in this case, the sum of the weights may be set to be 1.

After the integrated user profile is created, the interface configuration unit 340 can configure the interface using the integrated user profile.

Figure 4 is an example diagram for explaining an example of configuring an interface. Referring to FIG. 4, the user interface 400 may be composed of at least one layout 401, 402, 403, and 404, and the layout displays information consisting of text, image, video, voice, and a combination thereof. It can be. Additionally, the layout is not limited to this, and the layout may be a button or input window for performing the function of a service or application.

Referring to FIGS. 3 and 4 , the interface configuration unit 340 may configure the layouts 401, 402, 403, and 404 of the user interface 400 based on the generated user profile vector. For example, a layout can be created by changing layout components including size, shape, form, color, and density that make up the layout.

Additionally, the interface configuration unit 340 can adjust the layout by adjusting the layout components in the basic layout created in advance according to device information and service information.

FIG. 5 is a hardware configuration diagram of the platform integrated interface management server according to FIG. 1.

Referring to FIG. 5, the platform integrated interface management server 500 stores at least one processor 510 and instructions instructing the at least one processor 510 to perform at least one step. It may include a memory (memory, 520).

Here, the at least one processor 510 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. You can. Each of the memory 520 and the storage device 560 may be comprised of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory 520 may be comprised of at least one of read only memory (ROM) and random access memory (RAM).

Additionally, the platform integrated interface management server 500 may include a transceiver 530 that performs communication through a wireless network. Additionally, the platform integrated interface management server 500 may further include an input interface device 540, an output interface device 550, a storage device 560, etc. Each component included in the platform integrated interface management server 500 is connected by a bus 570 and can communicate with each other.

Methods according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. Computer-readable media may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on a computer-readable medium may be those specifically designed and configured for the present invention, or may be known and usable by those skilled in the art of computer software.

Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions may include machine language code such as that created by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.

Additionally, the above-described method or device may be implemented by combining all or part of its components or functions, or may be implemented separately.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and field of the present invention as set forth in the following patent claims. You will understand that you can do it.

Claims (5)

As a platform unified interface management server,
at least one processor; and
a memory storing instructions that instruct the at least one processor to perform at least one step;
The at least one step is,
Receiving user device information and service information through a user terminal;
generating a user profile vector based on the received device information or service information;
configuring an interface by mapping a weighted user profile vector with interface parameters for configuring an interface according to the type of the user terminal; and
By analyzing service information, functional interaction intensity (FII) is calculated from the ratio of the number of user interactions with a specific function to the total usage time,
Calculate the interface navigation speed (INS) from the ratio of the total number of pages or screens viewed by the user to the total usage time of the service,
Calculate the content consumption rate (CCR) from the amount of content consumed during a predetermined period of time,
Calculating a user interaction latency (UIL) from the average time it takes for the user to interact with a notification or respond to an event,
Calculating an input style parameter (ISP) from the total number of characters entered by the user divided by the total input time,
Calculating a service dependence index (SDI) from the specific service usage time for all service usage times of the user,
Calculate the multitasking index (MI) from the average number of services used simultaneously compared to the number of services used by the user,
Analyzing the received service information by calculating an error interaction rate (EIR) from a ratio of the number of errors that occurred and were resolved in the user's total service usage time, further comprising:
server.


delete In claim 1,
The step of analyzing the service information is,
calculating user interaction efficiency (UIE) by dividing the functional interaction intensity (FII) by the interface navigation speed (INS);
calculating a service engagement level (SEL) by dividing the content consumption rate (CCR) by the product of the interaction latency (UIL) and the input style parameter (ISP); and
Calculating a service dependence and multitasking index (SDMI) by dividing the product of the service dependence index (SDI) and the multitasking index (MI) by the error interaction rate (EIR),
server.
In claim 3,
The step of configuring the interface is,
Setting the layout spacing to be narrower as the value calculated by multiplying the calculated user interaction efficiency by a predetermined conversion coefficient is larger, and setting the layout spacing wider as the value calculated by multiplying the calculated user interaction efficiency by the predetermined conversion coefficient is smaller. ;
Setting the interface text size to be smaller as the value obtained by multiplying the calculated service participation level by a predetermined conversion coefficient is larger, and setting the interface text size larger as the value obtained by multiplying the calculated service participation level by the predetermined conversion coefficient is smaller. ; and
Setting a notification frequency based on the calculated service dependency and multitasking index (SDMI) divided by the average notification frequency generated by the service used by the user during a predetermined period of time; further comprising,
server.
In claim 1,
Combining the received device information and the service information to create an integrated user profile; further comprising,
server.

Images