Method for providing recommendation menu item and electronic device

Abstract

Provided is a method for providing a recommendation menu item by an electronic device. The method may include the steps of: obtaining context information related to the use of a service currently being used in the electronic device; generating feature data representing a usage pattern for a predefined time, on the basis of the context information; obtaining one or more recommendation items by using a recommendation item inference model which receives the feature data as an input; and providing a recommendation menu item including the one or more recommendation items.

Description

Method and electronic device for providing a recommended menu

[0001] The present disclosure relates to a method, an electronic device, and a server for providing a user with recommendations based on the context in which the electronic device is used.

[0002] Electronic devices provide users with a variety of services through various applications and sources. Furthermore, users can utilize various settings to adjust the device's settings or perform functions.

[0003] However, as the functionality offered by electronic devices increases, the number of settings is also increasing, with each setting being further categorized by function. Consequently, applying settings optimized for the current state of the electronic device requires multiple menu navigations, and the sheer number of settings makes finding the optimal setting difficult.

[0004] According to one aspect of the present disclosure, a method for providing a recommendation menu on an electronic device is provided. The method may include generating data representing a usage pattern over a predetermined period of time based on contextual information related to the use of a service currently being used on the electronic device. The method may include obtaining one or more recommendation items using an inference model that receives the data as input. The method may include providing a recommendation menu comprising the one or more recommendation items. The inference model may be a multi-label model trained using recall as a performance evaluation metric.

[0005] According to one aspect of the present disclosure, an electronic device providing a recommendation menu is provided. The electronic device may include a display unit; a communication interface; a memory storing one or more instructions; and one or more processors executing the one or more instructions stored in the memory. The one or more processors may, by executing the one or more instructions, generate data representing a usage pattern for a predetermined period of time based on contextual information related to the use of a service currently being used on the electronic device. The one or more processors may, by executing the one or more instructions, obtain one or more recommendation items using an inference model that receives the data as input. The one or more processors may, by executing the one or more instructions, control the display unit to provide a recommendation menu composed of the one or more recommendation items. The inference model may be a multi-label model trained using recall as a performance evaluation index.

[0006] According to one aspect of the present disclosure, a computer-readable recording medium having recorded thereon a program for causing an electronic device to execute any one of the aforementioned and hereinafter described methods for providing a recommendation menu may be provided.

[0007] FIG. 1 is a diagram schematically illustrating an operation of an electronic device providing a recommendation according to one embodiment of the present disclosure.

[0008] FIG. 2 is a flowchart illustrating an operation of an electronic device providing a recommendation menu according to one embodiment of the present disclosure.

[0009] FIG. 3 is a diagram illustrating a recommended item inference model according to one embodiment of the present disclosure.

[0010] FIG. 4 is a diagram for explaining an operation of an electronic device according to one embodiment of the present disclosure to infer menu recommendation items.

[0011] FIG. 5A is a diagram illustrating statistical data for training a recommendation item inference model according to one embodiment of the present disclosure.

[0012] FIG. 5b is a diagram illustrating training data for training a recommended item inference model according to one embodiment of the present disclosure.

[0013] FIG. 6A is a drawing for explaining menu items of an electronic device according to one embodiment of the present disclosure.

[0014] FIG. 6b is a diagram illustrating an example of a recommendation menu generated by an electronic device according to one embodiment of the present disclosure.

[0015] FIG. 7 is a diagram for explaining an operation of an electronic device executing a recommendation function according to one embodiment of the present disclosure.

[0016] FIG. 8 is a diagram for explaining an operation of an electronic device providing a recommendation menu according to one embodiment of the present disclosure.

[0017] FIG. 9 is a diagram illustrating an operation of an electronic device interacting with a server according to one embodiment of the present disclosure.

[0018] FIG. 10 is a block diagram illustrating a configuration of an electronic device according to one embodiment of the present disclosure.

[0019] FIG. 11 is a block diagram illustrating a configuration of an electronic device according to one embodiment of the present disclosure.

[0020] FIG. 12 is a block diagram illustrating the configuration of a server according to one embodiment of the present disclosure.

[0021] Hereinafter, terms used in this specification will be briefly described, and the present disclosure will be described in detail. In this disclosure, the expression “at least one of a, b, or c” can refer to “a,” “b,” “c,” “a and b,” “a and c,” “b and c,” “all of a, b, and c,” or variations thereof.

[0022] The terms used in this disclosure are selected from widely used, common terms, taking into account the functions of the disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, in which case their meanings will be described in detail in the relevant description. Therefore, the terms used in this disclosure should not be defined simply as names, but rather based on the meanings of the terms and the overall content of the disclosure.

[0023] Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art described herein. Furthermore, terms containing ordinal numbers, such as "first" or "second," used herein may be used to describe various components, but such components should not be limited by such terms. Such terms are used solely to distinguish one component from another.

[0024] When a part of the specification is said to "include" a component, unless otherwise specifically stated, this does not exclude other components but rather implies the inclusion of other components. Furthermore, terms such as "part" and "module" used in the specification refer to a unit that processes at least one function or operation, which may be implemented in hardware, software, or a combination of hardware and software.

[0025] Below, with reference to the attached drawings, embodiments of the present disclosure are described in detail so that those skilled in the art can easily practice the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, portions irrelevant to the description have been omitted for clarity of explanation, and similar reference numerals have been used throughout the specification to designate similar parts.

[0026] The present disclosure will be described below with reference to the attached drawings.

[0027] FIG. 1 is a diagram schematically illustrating an operation of an electronic device providing a recommendation according to one embodiment of the present disclosure.

[0028] In one embodiment, the electronic device (2000) may include a display or various types of devices that can be connected to a display. For example, the electronic device (2000) may include a TV, a smart monitor, a tablet PC, a laptop PC, a digital signage, a large display, a 360-degree projector, etc. that include a display. Alternatively, the electronic device (2000) may include, but is not limited to, a set-top box, a desktop PC, etc. that can be connected to a display.

[0029] Referring to FIG. 1, an electronic device (2000) can provide a recommendation (100) to a user.

[0030] The electronic device (2000) may provide a user with recommended items based on the usage context of the electronic device (2000). There may be one or more recommended items. For example, the electronic device (2000) may provide a recommendation (100) for changing the screen display mode of the electronic device (2000) to movie mode based on the OTT service (110) being used on the electronic device (2000).

[0031] In one embodiment, the electronic device (2000) may utilize a recommendation item inference model, which is an artificial intelligence model. The electronic device (2000) may obtain contextual information related to the use of the electronic device (2000) and analyze the usage pattern of the electronic device (2000) using the contextual information. The recommendation item inference model may infer one or more recommended items based on the usage pattern of the electronic device (2000).

[0032] In one embodiment, the electronic device (2000) may transmit and receive data necessary to provide recommendations (100) to the user with the server (3000). For example, the electronic device (2000) may transmit contextual information (e.g., usage history information, etc.) of the electronic device to the server (3000). The server (3000) may analyze usage patterns of the electronic device (2000) and other electronic devices to generate statistical data. The server (3000) may deploy a trained recommendation item inference model using the statistical data.

[0033] In one embodiment, the electronic device (2000) may receive a trained recommendation item inference model from the server (3000) and infer one or more recommendation items. In one embodiment, the electronic device (2000) may also transmit contextual information to the server (3000) and receive one or more inferred recommendation items from the server (3000).

[0034] In one embodiment, the recommendation (100) may be provided in various forms. For example, the electronic device (2000) may provide a recommendation menu including one or more recommendation items. For example, the electronic device (2000) may provide a single recommendation item. Furthermore, for example, the recommendation (100) may be provided in a form in which the electronic device (2000) automatically executes settings or functions corresponding to the recommendation item.

[0035] The specific operations by which the electronic device (2000) provides recommendations to the user will be described in more detail through the drawings and descriptions thereof described below.

[0036] FIG. 2 is a flowchart illustrating an operation of an electronic device providing a recommendation menu according to one embodiment of the present disclosure.

[0037] In operation S210, the electronic device (2000) can obtain contextual information related to the use of a service currently being used in the electronic device (2000).

[0038] In one embodiment, contextual information related to use of the service may include at least one of service category analysis information, setting history information, and usage history information.

[0039] In one embodiment, the electronic device (2000) can identify the service currently being used on the electronic device (2000). Depending on the viewing environment of the electronic device (2000), the functions and menus used on the electronic device may vary. In other words, usage patterns vary depending on which service is being used on the electronic device (2000), and customized recommendations provided to the user of the electronic device (2000) may also vary depending on the category of the service. Accordingly, the electronic device (2000) can obtain service category analysis information including the category of the service currently being used. In one embodiment, the service category may be one that is pre-classified and defined, such as applications, sources, and content. The service category may include, but is not limited to, video, games, sports, music, applications, HDMI 1, and HDMI 2, for example. The service category analysis information may include, but is not limited to, the category of the service currently being used, the applications and sources included in the category, the number of times the category is used, and the like.

[0040] The setting history information may refer to a history related to setting items applied to the electronic device (2000). In one embodiment, information related to various setting items of the electronic device (2000), such as picture settings, sound settings, mode settings, and other settings, may be included in the setting history information. The setting history information may include, for example, information such as the name of the setting item, an identification value, a set value, the number of times it has been set, and the set time, but is not limited thereto.

[0041] The usage history information may refer to the usage history of applications executed on the electronic device (2000) and the history related to external sources connected to and used by the electronic device (2000). The applications executed on the electronic device (2000) may include applications for providing various services. In one embodiment, the applications may include OTT service applications, game applications, video applications, music applications, etc. The application usage history information may include, but is not limited to, information such as the name of the application, identification information, service category, number of executions, and execution time. The external sources connected to and used by the electronic device (2000) may include various devices connected to and used by the electronic device (2000). In one embodiment, the sources may include a set-top box, a desktop PC, a laptop PC, a game console, a home theater, a sound bar, etc. The history related to the external source may include, but is not limited to, information such as the type of the external source, the number of connections, and the connection time.

[0042] In operation S220, the electronic device (2000) may generate feature data representing a usage pattern over a predefined period of time based on contextual information. The feature data may also be simply referred to as data.

[0043] In one embodiment, the electronic device (2000) may analyze usage history information, setting history information, service categories in use, etc. to analyze usage patterns. In addition, the electronic device (2000) may further utilize various information (e.g., location information, time information, weather information, etc.) that can be utilized to analyze usage patterns.

[0044] A usage pattern may refer to a usage behavior of the electronic device (2000) at the time when a menu item (e.g., executing a function, changing a setting, etc.) of the electronic device (2000) is used. For example, when a user uses the electronic device (2000) during the daytime, the user may use a function to adjust the screen brightness among the menu items of the electronic device (2000) due to sunlight. Or, when using the electronic device (2000) by connecting an external source such as a game console, the user may use a function to adjust the screen resolution and frame rate among the menu items of the electronic device (2000). If the above-mentioned example is digitized, the usage pattern may be data such as, for example, the frequency of use of a menu item, the time period of use, the time taken to use a menu item, the service category being used, the application being used, the source being used, the usage method, preferred settings, preferred themes, etc. In addition, the usage pattern may include information about the time when a menu item of the electronic device (2000) was used and which menu item was used.

[0045] In one embodiment, usage patterns can be organized in a time series format. The electronic device (2000) can store various contextual information acquired as the electronic device (2000) is used, and organize the usage patterns acquired based on the contextual information into time series data. The electronic device (2000) can select data for a period (e.g., 5 minutes, 10 minutes, etc.) that influences the use of menu items of the electronic device (2000) from among the time series data of usage patterns. The electronic device (2000) can segment the selected data into data for a predefined period of time (e.g., 1 minute, 1 minute 30 seconds, etc.). The electronic device (2000) can aggregate the segmented data to create feature data representing the usage patterns for the predefined period of time. The feature data can be used as input data for a recommendation item inference model.

[0046] In operation S230, the electronic device (2000) may obtain one or more recommended items using a recommended item inference model that receives feature data as input. The recommended item inference model may also be simply referred to as an inference model.

[0047] In one embodiment, the recommended item inference model may be a multi-label model trained using recall as a performance evaluation metric. The goal of the recommended item inference model is to output menu items inferred as likely to be used by the user among various menu items. Accordingly, it is important that the training data of the recommended item inference model reflect the actual menu item selection history and actual feature usage history. Recall represents the proportion of actual positive data that the model correctly predicts and is defined as follows:

[0048]

[0049] Here, a true positive (TP) represents a correct inference result in which the model predicts a class, and a false negative (FN) represents an incorrect inference result in which the model fails to predict a class. The recommended item inference model of the present disclosure can be trained to minimize the model's false negative (FN) inference by applying recall as a performance evaluation metric. In other words, the recommended item inference model can be a multi-label model trained to minimize false negatives (FN), which indicate that it fails to properly recommend a desired item, rather than false positives (FP), which indicate that it incorrectly recommends a menu item that the user has not used.

[0050] The electronic device (2000) can obtain one or more recommended items (e.g., menu items) output from a recommended item inference model and identify the priority of the recommended items.

[0051] In operation S240, the electronic device (2000) may provide a recommendation menu consisting of one or more recommendation items.

[0052] In one embodiment, if the electronic device (2000) includes a display, the electronic device (2000) may display a recommendation menu on the screen. Based on a user input selecting the recommendation menu displayed on the screen, the electronic device (2000) may execute a function corresponding to a recommendation item of the recommendation menu.

[0053] In one embodiment, the electronic device (2000) may transmit recommendation menu information to another device. For example, the electronic device (2000) may transmit recommendation menu information to another device including a display, thereby causing the recommendation menu to be displayed on the other device.

[0054] In one embodiment, the electronic device (2000) can automatically execute a function corresponding to a recommended menu item. For example, the electronic device (2000) can execute an application, change an operating mode, or change a setting.

[0055] FIG. 3 is a diagram illustrating a recommended item inference model according to one embodiment of the present disclosure.

[0056] In this disclosure, unless otherwise specified, the terms "model" and "inference model" refer to a recommended item inference model (300). The recommended item inference model (300) may be an artificial intelligence model trained to input feature data (310) and output one or more recommended menu items (320). The recommended item inference model (300) may be a multi-label model that infers one or more menu items, and the inference operation of the recommended item inference model (300) may be performed after training is completed.

[0057] The electronic device (2000) can preprocess data collected from the electronic device (2000) to create feature data (310). The electronic device (2000) can obtain contextual information including service category analysis information, usage history information, and setting history information while the electronic device (2000) is operating, and can analyze the user's usage pattern of the electronic device (2000).

[0058] In one embodiment, the generated feature data (310) may represent a usage pattern over a predefined period of time. For example, the feature data (310) may include feature elements representing a usage pattern over a previous predetermined period of time (e.g., the previous 5 minutes). Feature elements included in the feature data (310) may include, but are not limited to, for example, the number of uses by service category, the number of uses by application, the number of uses by source, the number of uses by menu item, the number of power on / offs, the type of HDMI-connected equipment, the number of occurrences of light levels, etc.

[0059] The recommended item inference model (300) may be implemented using a deep neural network architecture and algorithm of artificial intelligence for performing a multi-label classification task. In one embodiment, the recommended item inference model (300) may be implemented using a deep neural network model including one or more multi-layer perceptrons (MLPs) composed of hidden layers including weights, but is not limited thereto.

[0060] In one embodiment, the recommendation item inference model (300) may include an input layer (embedding layer), a hidden layer, and an output layer.

[0061] The input layer can process feature data (310), which is input data. For example, the input layer can convert input data into a vector representation to generate an embedding for neural network operations.

[0062] A hidden layer may include one or more fully connected layers containing weights. A fully connected layer connects all nodes between the input and output, performs operations that apply weights and activation functions, and passes the results of these operations to the next layer.

[0063] The output layer can output inference results for each class. For example, the output layer can output probability values ​​for each recommended item.

[0064] The recommendation item inference model (300) recommends optimized menu items to the user. Unlike general prediction, the key to this is to provide the user with menu items in a short path. For example, if multiple manipulation actions are required for the user to select a specific menu item, it is important to provide the specific menu item directly without requiring the user to perform navigation actions (e.g., moving the cursor, turning pages, etc.) to reach the specific menu item. Therefore, instead of applying the performance evaluation index of Precision (TP / (TP+FP) that increases the hit rate of prediction, the electronic device (2000) can train the recommendation item inference model (300) by applying the performance evaluation index of Recall (TP / (TP+FN) that increases the accuracy of inferring well from the trained data.

[0065] In one embodiment, the electronic device (2000) may use the Back-Propagation for Multi-Label Learning (BP-MLL) loss function, which can be used as a loss function for improving recall, during the training process of the recommended item inference model (300). However, the loss function is not limited to the BP-MLL loss function.

[0066] In one embodiment, the electronic device (2000) may adjust various parameter values ​​to minimize and optimize the value of a loss function during the training process of the recommended item inference model (300). Parameters for optimization may include, for example, an optimizer, an initializer, etc. Examples of optimizers may include, but are not limited to, Adaptive Moment Estimation (Adam), Root Mean Square Propagation (RMSprop), Stochastic Gradient Descent (SGD), and Adaptive Gradient Algorithm (Adagrad).

[0067] In one embodiment, the electronic device (2000) may apply hyperparameters (e.g., learning rate, etc.) optimized to improve recall when training the recommended item inference model (300).

[0068] In one embodiment, the recommended item inference model (300) may have been trained on the electronic device (2000).

[0069] In one embodiment, the recommended item inference model (300) may have been trained on a server (3000). The electronic device (2000) may receive the trained recommended item inference model (300) from the server (3000).

[0070] In one embodiment, the recommended item inference model (300) may be trained and operated on the server (3000). The electronic device (2000) may transmit input data to the server (3000) and receive output data (e.g., recommended item inference results) from the server (3000).

[0071] FIG. 4 is a diagram for explaining an operation of an electronic device according to one embodiment of the present disclosure to infer menu recommendation items.

[0072] In one embodiment, the electronic device (2000) may include a usage history collection module (410), a setting history collection module (420), a service category analysis module (430), a usage pattern analysis module (440), and a recommendation item generation module (450). Each module may be composed of a series of codes and a combination of data for implementing a specific function, and may be stored in the memory of the electronic device (2000). Each module may process operations corresponding to a portion of the tasks for the electronic device (2000) to provide a recommendation menu. Each module may interact with each other by transmitting data. The processor of the electronic device (2000) may process tasks corresponding to the functions of each module by executing instructions of the code constituting the modules. The functions of each module are described below.

[0073] The usage history collection module (410) can collect the usage history of applications executed on the electronic device (2000) and the history related to external sources connected to and used by the electronic device (2000). The usage history collection module (410) can manage the collected usage history information. The usage history collection module (410) can transmit the collected usage history information to the usage pattern analysis module (440).

[0074] The configuration history collection module (420) can collect history related to applied configuration items. The configuration history collection module (420) can manage the collected configuration history information and transmit it to the usage pattern analysis module (440).

[0075] The service category analysis module (430) can collect analysis information related to a service category. For example, the electronic device (2000) can identify the service category currently being used on the electronic device (2000) and obtain information on the service category currently being used. For example, the electronic device (2000) can collect information such as applications and sources included in the category, the number of times the category is used, etc. The service category analysis module (430) can manage the collected service category analysis information and transmit it to the usage pattern analysis module (440).

[0076] The usage pattern analysis module (440) can analyze the usage pattern of the electronic device (2000) by using usage history information, setting history information, and service category analysis information. The usage pattern may refer to the usage behavior of the electronic device (2000) at the time when the menu items of the electronic device (2000) are used. For example, when a user uses the electronic device (2000) at night, the user will use the function of adjusting the screen mode of the electronic device (2000) to night mode. The electronic device (2000) can generate data including the frequency of use of the menu item, the time period of use, the time taken to use the menu item, the service category being used, the application being used, the source being used, etc. as the usage pattern for the menu item 'night mode'.

[0077] In one embodiment, the electronic device (2000) may generate feature data representing a usage pattern over a predefined period of time using the usage pattern analysis module (440). For example, the electronic device (2000) may generate feature data including feature elements representing a usage pattern over a previous predetermined period of time (e.g., the previous predetermined period, the previous 1 minute, the previous 5 minutes). The feature data may be used as input data for a recommendation item inference model.

[0078] The recommended item generation module (450) may include a recommended item inference model. The recommended item generation module (450) may operate the recommended item inference model and manage recommended items. The inference operation of the recommended item inference model may be executed by inference code. The recommended item inference model may receive feature data as input and output one or more recommended items.

[0079] In one embodiment, when a user input is received, the electronic device (2000) may generate feature data representing a usage pattern for a period of time prior to the user input, based on the time at which the user input was received. The electronic device (2000) may input the feature data into a recommendation item inference model to obtain one or more recommended items.

[0080] In one embodiment, user input may be obtained in various ways. User input may include, but is not limited to, touch input on the screen of the electronic device (2000), input via a peripheral device connected via the input / output interface of the electronic device (2000), input received from another device, etc.

[0081] In one embodiment, the user input may be input via another device (e.g., a remote control, a smartphone, etc.). For example, the electronic device (2000) may initiate a series of operations to provide a recommendation menu based on user input via the remote control.

[0082] In one embodiment, the user input may be a voice input. The voice input may be received through a microphone included in the electronic device (2000), or may be received through a microphone included in a remote control or another electronic device (e.g., a smartphone) and transmitted to the electronic device (2000).

[0083] The electronic device (2000) can convert a user's voice input into text using Automatic Speech Recognition (ASR). In addition, the electronic device (2000) can process natural language text using a Natural Language Processing (NLP) model. The electronic device (2000) can initiate a series of operations to provide a recommendation menu in response to various types of natural language voice commands. For example, the electronic device (2000) can provide a recommendation menu in response to a voice command such as "Run the recommendation menu function," and can also provide a recommendation menu related to the settings of application A in response to a voice command such as "Run application A."

[0084] FIG. 5A is a diagram illustrating statistical data for training a recommendation item inference model according to one embodiment of the present disclosure.

[0085] In one embodiment, the electronic device (2000) may train the recommended item inference model prior to performing an inference operation using the recommended item inference model.

[0086] An electronic device (2000) can acquire statistical data (500) regarding the usage patterns and setting histories of multiple other electronic devices. The statistical data (500) may include training data representing the usage patterns of the other electronic devices. In other words, a collection of training data representing the usage patterns of each of the multiple other electronic devices is referred to as statistical data (500). The training data may be, but is not limited to, a feature set array that aggregates multiple features.

[0087] In one embodiment, the statistical data (500) may be training data generated from each of a plurality of other electronic devices and received by the electronic device (2000). In one embodiment, the electronic device (2000) may obtain raw data from the plurality of other electronic devices and analyze usage patterns of the plurality of other electronic devices to generate the statistical data (500). In one embodiment, the electronic device (2000) may also obtain the statistical data (500) from the server (3000). The operation of the other electronic devices or the server (3000) generating the training data may be performed in the same or similar manner as the operation of the electronic device (2000) generating the training data. The operation of the electronic device (2000) generating the training data is further described with reference to FIG. 5B.

[0088] FIG. 5b is a diagram illustrating training data for training a recommended item inference model according to one embodiment of the present disclosure.

[0089] In one embodiment, the electronic device (2000) may generate training data (502) for training a recommended item inference model. Training data (510) included in the training data (502) may be data in the form of one-hot encoding that expresses recommended items (514) actually used for feature data (512) in binary form.

[0090] In one embodiment, feature data (512) represents a usage pattern over a predefined period of time. The electronic device (2000) can organize the usage pattern into time series data. The electronic device (2000) can select data for a period (e.g., 5 minutes, 10 minutes, etc.) that affects the use of menu items of the electronic device (2000) from among the time series data of the usage pattern. The electronic device (2000) can segment the selected data into data for a predefined period of time (e.g., 1 minute, 1 minute 30 seconds, etc.). The electronic device (2000) can aggregate the segmented data to create feature data (512) representing a usage pattern over a predefined period of time. The feature data (512) may be in the form of a set of numerical features, but is not limited thereto.

[0091] In one embodiment, the electronic device (2000) can fine-tune the recommended item inference model using training data (502). The electronic device (2000) can update the recommended item inference model so that it is optimized to suit the preferences of the user of the electronic device (2000) by incorporating the usage patterns of the user of the electronic device (2000) into the recommended item inference model.

[0092] FIG. 6A is a drawing for explaining menu items of an electronic device according to one embodiment of the present disclosure.

[0093] In one embodiment, the menu items (600) of the electronic device (2000) may be configured in a tree structure in which items for applying various settings are classified into upper categories, lower categories, etc.

[0094] For example, when the 'screen mode (610)' item is selected from among the menu items (600), the electronic device (2000) can display submenu items for applying settings such as 'movie screen', 'standard screen', and 'clear screen'. Also, for example, when the 'sound mode (620)' item is selected from among the menu items (600), the electronic device (2000) can display submenu items for applying settings such as 'listen to standard', 'listen clearly', and 'movie sound'.

[0095] In one embodiment, when a user applies a setting or executes a function using menu items (600) of an electronic device (2000), the user must go through multiple manipulation actions to use different items of the menu items (600).

[0096] For example, if a user wants to change the screen mode (610) to 'Clear Screen', the menu items must be selected in the following order: 'Settings' - 'Screen Mode (610)' - 'Clear Screen', and multiple manipulation actions (e.g., moving, selecting, etc.) are required to finally reach the 'Clear Screen' item. Afterwards, if the user wants to change the sound mode (620) to 'Listen to Standard', the user must re-enter the settings menu via the back action or the settings menu button, and the menu items must be selected in the following order: 'Settings' - 'Sound Mode (620)' - 'Listen to Standard'.

[0097] In one embodiment, the electronic device (2000) may use a recommendation item inference model to provide a recommendation menu that is inferred to be appropriate for the context in which the user is currently using the electronic device (2000). Accordingly, the electronic device (2000) may reduce user interaction costs by directly providing specific menu items through the recommendation menu, even without the user performing a navigation action along a predetermined path to reach the specific menu item. The interaction cost may refer to the cost of interaction (e.g., the number of clicks on a remote control) incurred by the user to apply a desired setting or execute a function on the electronic device (2000). The recommendation menu will be further described with reference to FIG. 6B .

[0098] FIG. 6b is a diagram illustrating an example of a recommendation menu generated by an electronic device according to one embodiment of the present disclosure.

[0099] Referring to FIG. 6B, the electronic device (2000) may provide a recommendation menu (630). The recommendation menu (630) may be composed of one or more recommendation items. The one or more recommendation items may be output from a recommendation item inference model.

[0100] In one embodiment, the recommendation menu (630) may display menu items without distinction between upper and lower categories. For example, the recommendation menu (630) may include menu items such as movie screen mode (632), movie sound mode (634), multi-view mode (636), and game mode (638). If a user wishes to use multiple menu items on the electronic device (2000), the user must enter the overall settings menu and select detailed setting items. However, if the user selects a menu item through the recommendation menu (630) provided by the electronic device (2000), multiple setting items can be applied to the electronic device (2000) with a simple operation.

[0101] In one embodiment, when the electronic device (2000) provides a recommendation menu (630), it may provide the recommendation menu (630) including menu items that have not been used on the electronic device (2000). Since the recommendation item inference model is trained using statistical data of other electronic devices of multiple other users, the recommendation menu (630) may include menu items that have not been used on the electronic device (2000) but are appropriate for the current usage context.

[0102] In one embodiment, the menu items included in the recommendation menu (630) are not limited to setting items. For example, the electronic device (2000) may include application recommendations, source recommendations, etc. in the recommendation menu (630).

[0103] FIG. 7 is a diagram for explaining an operation of an electronic device executing a recommendation function according to one embodiment of the present disclosure.

[0104] In one embodiment, the electronic device (2000) can execute a function corresponding to a recommended item. The electronic device (2000) can receive user input. The user input may be input by the user to receive a recommended menu from the electronic device (2000). Based on the user input, the electronic device (2000) can initiate a series of operations to provide the recommended menu. In this case, even if the user does not directly input which menu to use into the electronic device (2000), the electronic device (2000) can immediately provide the user with currently required settings and functions.

[0105] In one embodiment, the user input may be input through another device (e.g., a remote control (700), a smartphone, etc.). For example, the electronic device (2000) may initiate operations to provide a recommendation menu based on a user input through the remote control (700). The electronic device (2000) may obtain contextual information related to a service (e.g., an OTT service) currently being used on the electronic device (2000) based on receiving a signal indicating a user input of pressing a specific button from the remote control (700). Based on the contextual information, the electronic device (2000) may generate feature data representing a usage pattern for a time period preceding the user input based on the time when the user input was received. The electronic device (2000) may input the feature data into a recommendation item inference model to obtain one or more recommendation items. Since a detailed description of the above operations has been described in the description of the previous drawings, a repeated description will be omitted.

[0106] In one embodiment, the electronic device (2000) may execute a function corresponding to a recommended item. For example, when a user input via the remote control (700) is identified, the electronic device (2000) may execute a function for changing the screen mode. The electronic device (2000) may change the screen mode to 'movie mode', which is a screen mode suitable for the 'OTT service' currently being used. The electronic device (2000) may display a notification (710) on the screen indicating that the recommended function has been executed. For example, the electronic device (2000) may notify that the screen mode has automatically changed to movie mode in response to a first user input via the remote control (700).

[0107] In one embodiment, the recommendation menu may contain multiple items. If the recommendation menu contains multiple items, the electronic device (2000) may execute a function corresponding to the recommended item with the highest priority. The priority of the recommended item may be determined based on the score of the recommended item class output from the recommendation item inference model.

[0108] In one embodiment, the electronic device (2000) can acquire multiple user inputs and cause multiple functions to be executed. When a first user input is received, the electronic device (2000) can execute a first function included in a recommendation menu, and when a second user input is received, the electronic device (2000) can execute a second function included in the recommendation menu. For example, when a first user input is received via the remote control (700), the electronic device (2000) can change the screen mode to movie mode. Furthermore, when a second user input is received via the remote control (700), the electronic device (2000) can change the sound mode to movie mode.

[0109] In one embodiment, the electronic device (2000) can execute a recommendation function based on a user's voice input. For example, the electronic device (2000) can execute a recommendation function based on a voice command such as "execute the recommendation menu function." For example, the electronic device (2000) can execute a recommendation function related to an OTT service based on a voice command such as "execute the OTT service."

[0110] FIG. 8 is a diagram for explaining an operation of an electronic device providing a recommendation menu according to one embodiment of the present disclosure.

[0111] In one embodiment, the electronic device (2000) may display a recommendation menu on the screen. The recommendation menu may include one or more recommendation items. The recommendation items may include, but are not limited to, setting item recommendations, function recommendations, application recommendations, and source recommendations, for example.

[0112] The electronic device (2000) can display the recommendation menu in various ways. For example, the recommendation menu may be a horizontal menu (810) in which the width of the recommendation menu window is longer than the height of the recommendation menu window. The horizontal menu (810) may be displayed in the lower area of ​​the screen of the electronic device (2000), but is not limited thereto. In addition, the recommendation menu may be a vertical menu (820) in which the height of the recommendation menu window is longer than the width of the recommendation menu window. The vertical menu (820) may be displayed in the side area of ​​the screen of the electronic device (2000), but is not limited thereto.

[0113] In one embodiment, the electronic device (2000) may display a recommendation menu based on user input. For example, the electronic device (2000) may initiate a series of operations to provide a recommendation menu based on the user input received. The electronic device (2000) may display the generated recommendation menu in the form of a horizontal menu (810) or a vertical menu (820).

[0114] In one embodiment, the electronic device (2000) can change the display method of the recommendation menu based on user input.

[0115] FIG. 9 is a diagram illustrating an operation of an electronic device interacting with a server according to one embodiment of the present disclosure.

[0116] In one embodiment, the server (3000) can train a recommendation item inference model (900). The server (3000) can train the recommendation item inference model using statistical data (910) of electronic devices of multiple users. The server (3000) can generate the statistical data (910). The server (2000) can analyze the usage patterns of the multiple electronic devices based on contextual information (usage history information, setting history information, service category analysis information) of the electronic devices. The server (3000) can organize the usage patterns of the multiple electronic devices into time series data, and select data for a period (e.g., 5 minutes, 10 minutes, etc.) that influences the use of menu items from among the time series data of the usage patterns. The server (3000) can segment the selected data into data for a predefined period (e.g., 1 minute, 1 minute 30 seconds, etc.). The server (3000) can aggregate segmented data to create feature data representing usage patterns over a predefined period of time. The server (3000) can generate multiple feature data for multiple electronic devices to create statistical data (910). The server (3000) can use the statistical data (910) to complete training of the recommended item inference model (900) and verify its performance. The server (3000) can deploy the trained recommended item inference model (900) to enable inference operations to be performed on the electronic device.

[0117] The electronic device (2000) can generate feature data (920) representing a usage pattern of the electronic device (2000) for a predetermined period of time, and input the feature data into a recommendation item inference model (900) to obtain one or more recommendation items. The electronic device (2000) can provide a recommendation menu (930) composed of one or more recommendation items. For example, the electronic device (2000) can display the recommendation menu (930) on the screen of the electronic device (2000). Since the operations of the electronic device (2000) generating the recommendation menu have already been described in the description of the previous drawings, a repeated description is omitted for the sake of brevity.

[0118] FIG. 10 is a block diagram illustrating a configuration of an electronic device according to one embodiment of the present disclosure.

[0119] In one embodiment, the electronic device (2000) may include a communication interface (2100), memory (2200), and a processor (2300).

[0120] The communication interface (2100) may include a communication circuit. The communication interface (2100) may use at least one of data communication methods including, for example, wired LAN, wireless LAN, Wi-Fi, Bluetooth, ZigBee, Wi-Fi Direct (WFD), infrared Data Association (IrDA), Bluetooth Low Energy (BLE), Near Field Communication (NFC), Wireless Broadband Internet (Wibro), World Interoperability for Microwave Access (WiMAX), Shared Wireless Access Protocol (SWAP), Wireless Gigabit Alliances (WiGig), and RF communication. The communication interface (2100) may be implemented to include a plurality of modules (for example, a Wi-Fi module, a Bluetooth module, etc.) for implementing the above-described communication methods.

[0121] The communication interface (2100) can transmit and receive data for performing operations of the electronic device (2000) with devices. For example, the electronic device (2000) can transmit and receive data with a server (3000) for providing a recommended menu, and can transmit and receive data with another server (e.g., an OTT service providing server) for providing a service, through the communication interface (2100).

[0122] The memory (2200) may store instructions, data structures, and program codes that can be read by the processor (2300). There may be one or more memories (2200). In the disclosed embodiments, operations performed by the processor (2300) may be implemented by executing instructions or codes of a program stored in the memory (2200).

[0123] The memory (2200) may include non-volatile memory such as read-only memory (ROM) (e.g., programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM)), flash memory (e.g., memory card, solid-state drive (SSD)), and analog recording type (e.g., hard disk drive (HDD), magnetic tape, optical disk), and volatile memory such as random-access memory (RAM) (e.g., dynamic random-access memory (DRAM), static random-access memory (SRAM)).

[0124] The memory (2200) may store data, instructions, and programs that enable the electronic device (2000) to operate to provide a recommendation menu. For example, the memory (2200) may store a usage history collection module (2210), a setting history collection module (2220), a service category analysis module (2230), a usage pattern analysis module (2240), and a recommendation item generation module (2250).

[0125] The processor (2300) can control the overall operations of the electronic device (2000). For example, the processor (2300) can control the overall operations of the electronic device (2000) by executing one or more instructions of a program stored in the memory (2200). There may be one or more processors (2300).

[0126] The processor (2300) may collect and manage usage history information by executing a usage history collection module (2210). The usage history information may include usage history of applications executed on the electronic device (2000) and history related to external sources connected to and used by the electronic device (2000). Since the operations of the electronic device (2000) using the usage history collection module (2210) have been described above, a repeated description thereof will be omitted for brevity.

[0127] The processor (2300) can collect and manage configuration history information by executing the configuration history collection module (2220). The configuration history information may include a history related to configuration items applied to the electronic device (2000). The operations of the electronic device (2000) related to the function of the configuration history collection module (2220) have been described above, and therefore, a repeated description is omitted for the sake of brevity.

[0128] The processor (2300) can execute the service category analysis module (2230) to analyze, collect, and manage the categories of services used in the electronic device (2000). The service category analysis information may include, but is not limited to, the category of the service currently being used, the applications and sources included in the category, the number of times the category is used, etc. The operations of the electronic device (2000) related to the function of the service category analysis module (2230) have been described above, and therefore, a repeated description is omitted for the sake of brevity.

[0129] The processor (2300) can execute the usage pattern analysis module (2240) to analyze and organize usage patterns related to the usage history, setting history, and service categories of the electronic device (2000). The operations of the electronic device (2000) related to the functions of the usage pattern analysis module (2240) have been described above, and therefore, a repeated description will be omitted.

[0130] The processor (2300) may execute the recommendation item generation module (2250) to generate one or more recommendation items that fit the current usage context of the electronic device (2000). The recommendation item generation module (2250) may include a recommendation item inference model and data and codes for operating the recommendation item inference model. Since the operations by which the electronic device (2000) utilizes the recommendation item inference model have been described above, a repeated description is omitted for the sake of brevity.

[0131] Meanwhile, the modules stored in the aforementioned memory (2200) are for convenience of explanation and are not necessarily limited thereto. Other modules may be added to implement the aforementioned embodiments, some of the aforementioned modules may be implemented as a single module, or a single model of the aforementioned modules may be implemented by separating them into multiple modules.

[0132] In one embodiment, the one or more processors (2300) may include at least one of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), an Accelerated Processing Unit (APU), a Many Integrated Core (MIC), a Digital Signal Processor (DSP), and a Neural Processing Unit (NPU). The one or more processors (2300) may be implemented in the form of an integrated system on a chip (SoC) including one or more electronic components. Each of the one or more processors (2300) may also be implemented as separate hardware (H / W).

[0133] When a method according to an embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one processor (2300) or by a plurality of processors (2300). For example, when a first operation, a second operation, and a third operation are performed by a method according to an embodiment, the first operation, the second operation, and the third operation may all be performed by a first processor, or the first operation and the second operation may be performed by a first processor (e.g., a general-purpose processor) and the third operation may be performed by a second processor (e.g., an AI-only processor). Here, an example of the second processor may be an AI-only processor, and the AI-only processor may perform operations for training / inference of an AI model. However, the embodiments of the present disclosure are not limited thereto.

[0134] One or more processors (2300) according to the present disclosure may be implemented as a single-core processor or as a multi-core processor.

[0135] When a method according to one embodiment of the present disclosure includes multiple operations, the multiple operations may be performed by one core or may be performed by multiple cores included in one or more processors (2300).

[0136] Meanwhile, although not illustrated in FIG. 10, the electronic device (2000) may further include additional components to perform the operations described in the aforementioned embodiments. For example, the electronic device (2000) may further include a display, a microphone, an input / output interface, and the like.

[0137] FIG. 11 is a block diagram illustrating a configuration of an electronic device according to one embodiment of the present disclosure.

[0138] In one embodiment, the electronic device (2000) may include a communication interface (2100), a memory (2200), a processor (2300), a display unit (2400), a sensor (2500), a video processing module (2600), an audio processing module (2700), a power module (2800), and an input / output interface (2900).

[0139] The interface (2100), memory (2200), and processor (2300) of FIG. 11 correspond to the communication interface (2100), memory (2200), and processor (2300) of FIG. 10, respectively, and therefore, a repeated description is omitted.

[0140] The display unit (2400) can output a video signal to the screen of the electronic device (2000) under the control of the processor (2300). The display unit (2400) can include a display panel. For example, the electronic device (2000) can output a recommendation menu including one or more recommendation items through the display unit (2400).

[0141] The sensor (2500) can acquire sensor data. The processor (2300) can process the sensor data to acquire information. There may be one or more sensors. The sensors may include, but are not limited to, an IR receiver for detecting remote control signals, a light sensor for detecting ambient light levels, and the like.

[0142] The video processing module (2600) processes video data played by the electronic device (2000). The video processing module (2600) can perform various image processing such as decoding, scaling, noise filtering, frame rate conversion, resolution conversion, rendering, etc. on the video data. The display (2400) can convert video signals, data signals, OSD signals, control signals, etc. processed by the processor (2300) to generate a driving signal and display an image according to the driving signal.

[0143] The audio processing module (2700) processes audio data played by the electronic device (2000). The audio processing module (2700) can perform various processing operations, such as decoding, amplification, and noise filtering of audio data.

[0144] The power module (2800) supplies power input from an external power source to components within the electronic device (2000) under the control of the processor (2300). In addition, the power module (2800) can supply power output from one or more batteries located within the electronic device (2000) to the internal components under the control of the processor (2300).

[0145] The input / output interface (2900) processes input / output from the outside of the electronic device (2000). The input / output interface (2900) receives video (e.g., moving pictures, etc.), audio (e.g., voice, music, etc.), and additional information (e.g., EPG, etc.). The input / output interface (2900) may include any one of a Universal Serial Bus (USB), a High-Definition Multimedia Interface (HDMI), a Mobile High-Definition Link (MHL), a Display Port (DP), a Thunderbolt, a Video Graphics Array (VGA) port, an RGB port, a D-subminiature (D-SUB), a Digital Visual Interface (DVI), a component jack, a PC port, and an audio jack. That is, the input / output interface (2900) may be implemented to include a plurality of modules (e.g., a USB port, an HDMI port, etc.) for implementing the above-described input / output methods. The electronic device (2000) can be connected to external devices such as a display, camera, microphone, speaker, touch pad, etc. through an input / output interface (2900).

[0146] The user input receiver can process user input. For example, the user input receiver can obtain and process user input and / or voice input from a microphone, touchpad, etc. connected via the input / output interface (2900). For example, the user input receiver can obtain and process user input and / or voice input from a remote controller connected via the communication interface (2100).

[0147] FIG. 12 is a block diagram illustrating the configuration of a server according to one embodiment of the present disclosure.

[0148] In one embodiment, the operations performed by the electronic device (2000) or the electronic device (2000) and the server (3000) through interaction may be performed solely by the server (3000).

[0149] The server (3000) may include a communication interface (3100), memory (3200), and a processor (3300). The server (3000) may be a high-performance computing device, higher than the electronic device (2000), capable of processing complex operations and tasks using large amounts of data, such as training, inference, management, and distribution of a recommendation item inference model.

[0150] The communication interface (3100) can perform data communication with other electronic devices under the control of the processor (3300).

[0151] The communication interface (3100) may include a communication circuit that can perform data communication between the server (3000) and another electronic device (e.g., the electronic device (2000)) using at least one of data communication methods including, for example, wired LAN, wireless LAN, Wi-Fi, Bluetooth, ZigBee, Wi-Fi Direct (WFD), infrared Data Association (IrDA), Bluetooth Low Energy (BLE), Near Field Communication (NFC), Wireless Broadband Internet (Wibro), World Interoperability for Microwave Access (WiMAX), Shared Wireless Access Protocol (SWAP), Wireless Gigabit Alliances (WiGig), and RF communication.

[0152] The communication interface (3100) can transmit and receive data for providing a recommended menu to and from the electronic device (2000) under the control of the processor (3300). For example, the server (3000) can receive contextual information (e.g., usage history information, setting history information, service category information, etc.) from the electronic device (2000) via the communication interface (3100) and can also transmit information regarding the recommended menu to the electronic device (2000).

[0153] The memory (3200) may store instructions, data structures, and program codes that can be read by the processor (3300). Operations performed by the processor (3300) may be implemented by executing instructions or codes of a program stored in the memory (3200).

[0154] The memory (3200) may include a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), and may include a non-volatile memory including at least one of a ROM (Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, and an optical disk, and a volatile memory such as a RAM (Random Access Memory) or a SRAM (Static Random Access Memory).

[0155] The memory (3200) may store one or more instructions and / or programs that cause the server (3000) to operate to generate a recommendation menu. For example, the memory (3200) may store a usage history collection module (3210), a setting history collection module (3220), a service category analysis module (3230), a usage pattern analysis module (3240), and a recommendation item generation module (3250). Since the functions of each module have been described above, a repeated description will be omitted.

[0156] The processor (3300) can control the overall operations of the server (3000). For example, the processor (3300) can control the overall operations of the server (3000) for generating a recommendation menu by executing one or more instructions of a program stored in the memory (3200). There may be one or more processors (3300).

[0157] The processor (3300) may be configured as at least one of, for example, a Central Processing Unit, a microprocessor, a Graphic Processing Unit, Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), an Application Processor, a Neural Processing Unit, or an artificial intelligence processor designed with a hardware structure specialized for processing artificial intelligence models, but is not limited thereto.

[0158] The present disclosure relates to a method and an electronic device for providing recommendations for settings, applications, sources, etc., based on the context in which the electronic device is used. The technical challenges addressed by the present disclosure are not limited to those described above, and other technical challenges not mentioned herein will be readily apparent to those skilled in the art, based on the description herein.

[0159] According to one aspect of the present disclosure, a method for an electronic device to provide a recommendation menu is provided.

[0160] The method may include a step of generating data representing a usage pattern over a predefined period of time based on contextual information related to the use of a service currently being used on the electronic device.

[0161] The method may include a step of obtaining one or more recommended items through an inference model that receives the data as input.

[0162] The method may include a step of providing a recommendation menu comprising one or more of the recommendation items.

[0163] The above inference model may be a multi-label model trained by applying recall as a performance evaluation index.

[0164] The context information may include at least one of a history related to setting items applied to the electronic device, a history of use of an application executed on the electronic device, and a history related to an external source used in connection with the electronic device.

[0165] The step of providing the above recommended menu may include providing the recommended menu including menu items that were not used in the electronic device.

[0166] The step of generating the above data may include a step of generating data corresponding to a usage pattern during a time period prior to receiving the user input, when the user input is received.

[0167] The user input may be received via a remote controller that is in communication with the electronic device and capable of receiving the user input or voice input.

[0168] The step of providing the above recommended menu may include a step of executing a first function included in the recommended menu when a first user input is received.

[0169] The step of providing the above recommended menu may include a step of executing a second function included in the recommended menu when a second user input is received.

[0170] The method may include a step of obtaining statistical data of usage patterns and setting histories of a plurality of different electronic devices.

[0171] The method may include a step of training the inference model using statistical data of usage patterns and setting histories of the plurality of different electronic devices.

[0172] The method may include a step of updating the inference model based on training data that organizes the usage pattern and setting history of the electronic device in a time series format.

[0173] The step of updating the above inference model may include the step of selecting data of a predetermined period from the training data in the form of a time series, and updating the inference model based on the data of the predetermined period.

[0174] The step of providing the above recommended menu may include a step of automatically executing a function corresponding to a recommended item of the above recommended menu.

[0175] According to one aspect of the present disclosure, an electronic device providing a recommendation menu is provided.

[0176] The electronic device may include a display unit; a communication interface; a memory storing one or more instructions; and one or more processors executing the one or more instructions stored in the memory.

[0177] The one or more processors may, by executing the one or more instructions, generate data representing a usage pattern for a predefined period of time based on contextual information related to the use of a service currently being used in the electronic device.

[0178] The one or more processors can obtain one or more recommended items through an inference model that receives the data as input by executing the one or more instructions.

[0179] The one or more processors can control the display unit to provide a recommendation menu composed of the one or more recommendation items by executing the one or more instructions.

[0180] The above inference model may be a multi-label model trained by applying recall as a performance evaluation index.

[0181] The context information may include at least one of a history related to setting items applied to the electronic device, a history of use of an application executed on the electronic device, and a history related to an external source used in connection with the electronic device.

[0182] The one or more processors can control the display unit to provide the recommendation menu, including menu items that have not been used in the electronic device, by executing the one or more instructions.

[0183] The electronic device may include a user input receiving unit.

[0184] The one or more processors may, by executing the one or more instructions, generate data corresponding to a usage pattern during a time period prior to receiving the user input when the user input is received.

[0185] The user input receiving unit may be a remote controller that is connected to the electronic device and can receive user input or voice input.

[0186] The one or more processors can be controlled to perform a first function included in the recommendation menu when a first user input is received through the user input receiving unit by executing the one or more instructions.

[0187] The one or more processors can be controlled to perform a second function included in the recommendation menu when a second user input is received through the user input receiving unit by executing the one or more instructions.

[0188] The one or more processors may include a step of receiving statistical data of usage patterns and setting histories of a plurality of other electronic devices through the communication interface by executing the one or more instructions.

[0189] The one or more processors can be controlled to train the inference model by using statistical data of usage patterns and setting histories of the plurality of other electronic devices by executing the one or more instructions.

[0190] The one or more processors can be controlled to update the inference model based on training data that organizes the usage pattern and setting history of the electronic device in a time series format by executing the one or more instructions.

[0191] The one or more processors can be controlled to select data of a predetermined period from among the training data in the form of a time series by executing the one or more instructions, and to update the inference model based on the data of the predetermined period.

[0192] The one or more processors can automatically execute a function corresponding to a recommended item of the recommended menu by executing the one or more instructions.

[0193] Meanwhile, embodiments of the present disclosure may also be implemented in the form of a recording medium containing computer-executable instructions, such as program modules, executed by a computer. Computer-readable media may be any available media that can be accessed by a computer, and include both volatile and nonvolatile media, removable and non-removable media. Furthermore, computer-readable media may include computer storage media and communication media. Computer storage media include both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Communication media may typically include computer-readable instructions, data structures, or other data in a modulated data signal, such as program modules.

[0194] Additionally, a computer-readable storage medium may be provided in the form of a non-transitory storage medium. Here, the term "non-transitory storage medium" simply means a tangible device that does not contain signals (e.g., electromagnetic waves). This term does not distinguish between cases where data is permanently stored in the storage medium and cases where data is temporarily stored. For example, a "non-transitory storage medium" may include a buffer in which data is temporarily stored.

[0195] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable app) may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0196] The above description of the present disclosure is provided for illustrative purposes only, and those skilled in the art will readily appreciate that modifications to other specific forms can be made without altering the technical spirit or essential features of the present disclosure. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, components described as being single may be implemented in a distributed manner, and similarly, components described as being distributed may be implemented in a combined manner.

[0197] The scope of the present disclosure is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present disclosure.

Claims

1. In a method for an electronic device to provide a recommendation menu, A step of generating data corresponding to a usage pattern for a predefined period of time based on contextual information related to the use of the currently used service; A step of obtaining one or more recommended items through an inference model that receives the above data as input; and Comprising a step of providing a recommendation menu comprising one or more of the above recommendation items, A method, characterized in that the above inference model is a multi-label model trained by applying recall as a performance evaluation index.

2. In paragraph 1, A method according to claim 1, wherein the context information includes at least one of a history related to setting items applied to the electronic device, a usage history of an application executed on the electronic device, and a history related to an external source used while connected to the electronic device.

3. In paragraph 1, The steps for providing the above recommended menu are: A method for providing a recommendation menu including menu items that were not used in the electronic device.

4. In paragraph 1, The steps for generating the above data are: A method comprising the step of generating data corresponding to a usage pattern during a time prior to receiving said user input, when a user input is received.

5. In paragraph 4, The steps for providing the above recommended menu are: a step of executing a first function included in the recommendation menu when a first user input is received; and A method comprising the step of executing a second function included in the recommendation menu when a second user input is received.

6. In paragraph 1, The above method, A step of obtaining statistical data on usage patterns and setting histories of multiple different electronic devices; and A method further comprising the step of training the inference model using statistical data of usage patterns and setting histories of the plurality of other electronic devices.

7. In paragraph 1, The above method, A method further comprising a step of updating the inference model based on training data that organizes the usage pattern and setting history of the electronic device in a time series format.

8. In electronic devices, Display section; communication interface; Memory for storing instructions; and comprising at least one processor, By executing the above instructions by the at least one processor, the electronic device, Based on contextual information related to the use of the currently used service, data corresponding to usage patterns over a predefined period of time are generated, Obtain one or more recommended items through an inference model that receives the above data as input, Controlling the display unit to provide a recommendation menu including one or more of the above recommended items; An electronic device, characterized in that the above inference model is a multi-label model trained by applying recall as a performance evaluation index.

9. In paragraph 8, An electronic device, wherein the context information includes at least one of a history related to setting items applied to the electronic device, a usage history of an application executed on the electronic device, and a history related to an external source used while connected to the electronic device.

10. In paragraph 8, By executing the above instructions by the at least one processor, the electronic device, An electronic device that controls the display unit to provide the recommended menu including menu items that have not been used in the electronic device.

11. In paragraph 8, The electronic device further includes a user input receiving unit, By executing the above instructions by the at least one processor, the electronic device, An electronic device that, when receiving user input, generates data corresponding to usage patterns during a time period prior to receiving said user input.

12. In paragraph 11, By executing the above instructions by the at least one processor, the electronic device, When a first user input is received through the above user input receiving unit, the first function included in the above recommendation menu is controlled to be performed, An electronic device that controls a second function included in the recommendation menu to be performed when a second user input is received through the user input receiving unit.

13. In paragraph 8, By executing the above instructions by the at least one processor, the electronic device, Receive statistical data on usage patterns and setting histories of multiple other electronic devices through the above communication interface, An electronic device that controls the training of the inference model by using statistical data of usage patterns and setting histories of the plurality of other electronic devices.

14. In paragraph 8, By executing the above instructions by the at least one processor, the electronic device, An electronic device that controls the inference model to be updated based on training data that organizes the usage pattern and setting history of the electronic device in a time series format.

15. A computer-readable recording medium having recorded thereon a program for executing the method of any one of clauses 1 to 7 on a computer.

Images