KR102440963B1 - Electronic apparatus, method for controlling thereof, and non-transitory computer readable recording medium - Google Patents

Abstract

In the electronic device of the present disclosure, when a preset command for content is input through an input unit for receiving a user command, a memory, a display for displaying content, and the input unit, the electronic device analyzes the stored content to obtain context information of the content, and a processor that stores context information together with information about the context information in a memory, and controls a display to provide content corresponding to the sensed context when a context corresponding to the context information is detected. At least a part of the control method of the electronic device of the present disclosure may use a rule-based model or an artificial intelligence model learned according to at least one of a machine learning, a neural network, or a deep learning algorithm. For example, the artificial intelligence model may provide context information that is a result determined by using content as an input value to the electronic device.

Description

ELECTRONIC APPARATUS, METHOD FOR CONTROLLING THEREOF, AND NON-TRANSITORY COMPUTER READABLE RECORDING MEDIUM

The present disclosure relates to an electronic device, a method for controlling the same, and a non-transitory computer-readable recording medium, and more particularly, to an electronic device that detects a context and provides content corresponding to the sensed context from among pre-stored content, and a method for controlling the same and to a non-transitory computer-readable recording medium.

In addition, the present disclosure relates to an artificial intelligence (AI) system for simulating functions such as cognition and judgment of a human brain by using a machine learning algorithm and an application thereof.

Recently, artificial intelligence systems that implement human-level intelligence have been used in various fields.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike the existing rule-based smart system, the machine learns, judges, and becomes smarter by itself. As artificial intelligence systems are used, the recognition rate improves and users can understand user preferences more accurately, and the existing rule-based smart systems are gradually being replaced by deep learning-based artificial intelligence systems.

Artificial intelligence technology consists of machine learning (deep learning) and elemental technologies using machine learning.

Machine learning is an algorithm technology that classifies/learns characteristics of input data by itself, and element technology is a technology that uses machine learning algorithms such as deep learning, such as language understanding, visual understanding, reasoning/prediction, knowledge expression, motion control, etc. It consists of technical fields of

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology for recognizing and applying/processing human language/text, and includes natural language processing, machine translation, dialogue system, question and answer, and speech recognition/synthesis. Visual understanding is a technology for recognizing and processing objects like human vision, and includes object recognition, object tracking, image search, human recognition, scene understanding, spatial understanding, image improvement, and the like. Inferential prediction is a technology for logically reasoning and predicting by judging information, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data generation/classification) and knowledge management (data utilization). Motion control is a technology for controlling autonomous driving of a vehicle and movement of a robot, and includes motion control (navigation, collision, driving), manipulation control (action control), and the like.

Meanwhile, in recent years, due to the development of communication technology, it is possible to access numerous contents using an electronic device. In particular, the user may store, scrap, or share the contents in order to reuse some of the numerous contents later.

However, even if the contents are stored, as time passes, the user forgets the stored contents, and thus the usefulness of the stored contents is reduced. In particular, when content is needed, there is a problem in that the user cannot remember the content, which causes inconvenience to the user.

The present disclosure is to solve the above-described problem, and stores the context information of the content together with the information on the content through artificial intelligence technology, and provides the content corresponding to the sensed context when the context corresponding to the context information is detected. It relates to an electronic device, a method for controlling the same, and a non-transitory computer-readable recording medium.

According to an embodiment of the present disclosure for achieving the above object, a method of controlling an electronic device includes: when a preset command for content is input, analyzing the stored content to obtain context information of the content; storing the context information together with the information on the content; and providing content corresponding to the sensed context when a context corresponding to the context information is detected.

In addition, according to an embodiment of the present disclosure for achieving the above object, an electronic device includes an input unit for receiving a user command; Memory; a display for displaying content; and when a preset command for the content is input through the input unit, the stored content is analyzed to obtain context information of the content, and the context information is stored in the memory together with the information on the content, and a processor controlling the display to provide content corresponding to the sensed context when a context corresponding to the context information is detected.

In addition, in a non-transitory computer-readable recording medium storing a program for executing a control method of an electronic device according to an embodiment of the present disclosure for achieving the above object, the control method of the electronic device includes: obtaining context information of the content by analyzing the stored content when a preset command is input; storing the context information together with the information on the content; and providing content corresponding to the sensed context when a context corresponding to the context information is detected.

According to the embodiment of the present disclosure as described above, the electronic device provides pre-stored content corresponding to the sensed context, so that the user can check the scrapped or stored content in a necessary situation without a separate operation.

1 is a block diagram schematically illustrating a configuration of an electronic device according to an embodiment of the present disclosure;
2 is a block diagram illustrating the configuration of an electronic device in detail according to an embodiment of the present disclosure;
3 is a block diagram illustrating a configuration for providing a context-aware service, according to an embodiment of the present disclosure;
4A to 6B are diagrams for explaining an embodiment of providing content corresponding to a context by recognizing a context, according to various embodiments of the present disclosure;
7 is a flowchart illustrating a method of controlling an electronic device according to an embodiment of the present disclosure;
8 is a diagram illustrating a system for providing a context-aware service according to another embodiment of the present disclosure;
9 is a sequence diagram for explaining a control method of a system for providing a context-aware service, according to an embodiment of the present disclosure;
10 is a block diagram illustrating a configuration of a processor according to an embodiment of the present disclosure;
11A is a block diagram illustrating a configuration of a data learning unit according to an embodiment of the present disclosure;
11B is a block diagram illustrating a configuration of a data recognition unit according to an embodiment of the present disclosure.

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In describing the present disclosure, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present disclosure, the detailed description thereof will be omitted. And the terms to be described later are terms defined in consideration of functions in the present disclosure, which may vary according to a user, an operator, or a custom. Therefore, the definition should be made based on the content throughout this specification.

Terms including an ordinal number, such as first, second, etc., may be used to describe various elements, but the elements are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related items or any one of a plurality of related items.

The terms used herein are used to describe the embodiments, and are not intended to limit and/or limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as include or have are intended to designate that a feature, number, operation, component, part, or combination thereof described in the specification exists, and includes one or more other features or number, operation, configuration It should be understood that the possibility of the presence or addition of elements, parts or combinations thereof is not precluded in advance.

In an embodiment, a 'module' or 'unit' performs at least one function or operation, and may be implemented as hardware or software, or a combination of hardware or software. In addition, a plurality of 'modules' or a plurality of 'units' may be integrated into at least one module and implemented by at least one processor, except for 'modules' or 'units' that need to be implemented with specific hardware.

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings. 1 is a schematic block diagram illustrating a configuration of an electronic device 100 according to an embodiment of the present disclosure. As shown in FIG. 1 , the electronic device 100 may provide a context-aware service for providing pre-stored content by recognizing a context alone. When the electronic device 100 alone provides a context-aware service, various electronic devices such as smart phones, tablet PCs, notebook PCs, desktop PCs, wearable devices such as smart watches, electronic picture frames, humanoid robots, audio devices, smart TVs, etc. It can be implemented as a device. As another example, as shown in FIG. 8 , the electronic device 100 may provide a context recognition service to the user by interworking with the server 200 .

As shown in FIG. 1 , the electronic device 100 includes an input unit 110 , a display 120 , a memory 160 , and a processor 130 .

The input unit 110 receives a user command. In particular, the input unit 110 may receive a preset command (eg, a scrap command, a save command, a share command, etc.) for currently provided content (eg, web page content, video content, etc.). In this case, the input unit 110 may be implemented as a touch panel.

The display 120 provides content. Also, when a context corresponding to the pre-stored context information is detected, the display 120 may provide a message for guiding the content corresponding to the sensed stored context.

The memory 160 stores various programs and data for controlling the electronic device 100 . In particular, the memory 160 may match and store content information and context information. Also, the memory 160 may store a pre-trained data recognition model for keyword acquisition.

The processor 130 controls the overall operation of the electronic device 100 using various programs and data stored in the memory 160 . In particular, when a preset command for content is input through the input unit 110 , the processor 130 analyzes the stored content to obtain context information of the content, and stores the context information together with the content information into the memory 160 . can be stored in And, when a context corresponding to the stored context information is detected, the processor 130 may control the display 120 to provide content corresponding to the sensed context.

Specifically, the input unit 110 may receive a preset command for the currently provided content. For example, the input unit 110 may receive a share, save, and scrap command for a currently provided web page.

Then, the processor 130 may obtain a keyword for the content to which a preset command is input by using the learned data recognition model, and may obtain context information based on the extracted keyword. In this case, the processor 130 may obtain context information corresponding to the keyword using the pre-learned data recognition model, but this is only an exemplary embodiment, and context information corresponding to the keyword is obtained using a pre-stored matching table. can be obtained

In addition, the processor 130 may tag the obtained context information to information about the content (eg, address information of the content, storage location information, etc.) and store it in the memory 160 .

After the content information and the context information are matched and stored, the processor 130 may detect a context corresponding to the stored context information.

Specifically, the processor 130 may detect a context corresponding to the stored context information from a sensing value obtained from a sensor provided in the electronic device 100 . For example, the processor 130 may obtain the user's location information from the GPS sensor provided in the electronic device 100 and detect the user's context based on the user's location information. Alternatively, the processor 130 may obtain context-related information from an external device connected to the electronic device 100 and detect a context corresponding to the stored context information based on the obtained information. For example, the processor 130 may obtain information about a store from an external device provided in the store, and detect a user's context based on the obtained information. Alternatively, the processor 130 may detect a context corresponding to the context information based on the schedule information stored in the electronic device 100 .

In addition, the processor 130 may determine the current context based on information about the previously sensed context stored in the memory 160 . For example, the processor 130 may detect the context of the user by estimating the destination of the current user based on the movement path of the user detected in the past.

When a context corresponding to the stored context information is detected, the processor 130 may control the display 120 to provide a message for guiding the context detection. In this case, the message includes information on the currently sensed context and the detected context. It may include at least one of information about the content corresponding to the context and an icon for inquiring whether to provide the content.

When a user command (eg, a user command for content confirmation, etc.) is input through the message, the processor 130 may control the display 120 to provide content corresponding to the sensed context.

2 is a block diagram for explaining in detail the configuration of the electronic device 100 according to an embodiment of the present disclosure. Referring to FIG. 2 , the electronic device 100 includes an input unit 110 , a display 120 , a processor 130 , an audio output unit 140 , a communication unit 150 , a memory 160 , and a sensing unit 170 . may include In addition to the components shown in the embodiment of FIG. 2 , the electronic device 100 may include various components such as an image receiving unit (not shown), an image processing unit (not shown), and a power supply unit (not shown). Also, of course, the electronic device 100 is not limited to being implemented including all the configurations shown in FIG. 2 . For example, when the electronic device 100 is implemented as a server, it goes without saying that the display 120 , the audio output unit 140 , and the sensing unit 170 may not be provided.

The input unit 110 may receive a user command. In particular, the input unit 110 may receive a preset command (eg, a scrap command, a save command, a share command, etc.) for the currently provided content.

Meanwhile, the input unit 110 may be implemented as a touch panel to receive a user touch command. In addition, when the input unit 110 is implemented as a touch panel, the touch panel and the display 120 may be combined with each other to form a touch screen forming a mutual layer structure. The touch screen may detect a touch input position, an area, a pressure of the touch input, and the like.

In addition, the input unit 110 may receive user commands in various forms. For example, the input unit 110 may be implemented as a mouse, a keyboard, a voice input device, a motion input device, or the like to receive a user command.

The display 120 may display various guides, image contents, information, UI, etc. provided by the electronic device 100 . The display 120 is implemented as a liquid crystal display (LCD), an organic light emitting diode (OLED) or a plasma display panel (PDP), etc., Various screens that can be provided can be displayed.

The display 120 may provide various types of content. For example, the display 120 may provide various contents such as web page contents and video contents. Also, the display 120 may provide a message for guiding content corresponding to the context.

The audio output unit 140 may output audio. For example, the voice output unit 140 may output a notification sound or a voice message as well as various audio data. The electronic device 100 according to an embodiment of the present invention may include the voice output unit 140 as one of the output units for providing an interactive context sensing function. By outputting the natural language-processed voice message through the voice output unit 140 , the electronic device 100 may provide a user experience as if conversing with the electronic device 100 to the user. The audio output unit 140 may be embedded in the electronic device 100 or implemented in the form of an output port such as a jack.

The communication unit 150 communicates with an external device. For example, the external device may be implemented as another electronic device, a server, a cloud storage, a network, or the like. The communication unit 150 may receive various data for determining a context from an external device. The communication unit 150 may receive a data recognition model for obtaining keywords and obtaining context information from an external device.

To this end, the communication unit 150 may include various communication modules such as a short-range wireless communication module (not shown) and a wireless communication module (not shown). Here, the short-range wireless communication module is a module for performing communication with an external device located in a short distance according to a short-range wireless communication method such as Bluetooth or Zigbee. In addition, the wireless communication module is a module for performing communication by being connected to an external network according to a wireless communication protocol such as WiFi, WiFi direct, IEEE, and the like. In addition, the wireless communication module performs communication by accessing the mobile communication network according to various mobile communication standards such as 3G (3rd Generation), 3GPP (3rd Generation Partnership Project), LTE (Long Term Evoloution), and LTE-A (LTE Advanced). It may further include a mobile communication module.

The memory 160 may store various modules, software, and data for driving the electronic device 100 . For example, the memory 160 may store a data recognition model for acquiring a keyword of content and a data recognition model for acquiring context information matching the keyword. In addition, a model for natural language generation (NLG) may be stored in the memory 160 .

The memory 160 may store programs and data for configuring various screens to be displayed on the display 120 . In addition, the memory 160 may store programs, applications, and data for performing a specific service.

The memory 160 is a storage medium in which various programs necessary for operating the electronic device 100 are stored, and may be implemented in the form of a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or the like. For example, the memory 160 may include a ROM for storing a program for performing an operation of the electronic device 100 and a RAM for temporarily storing data according to an operation of the electronic device 100 .

Meanwhile, the memory 160 may store a plurality of modules for obtaining and storing context information corresponding to the content, and detecting a context corresponding to the stored context information to provide the content. Specifically, as shown in FIG. 3 , the memory 160 includes a content acquisition module 310 , a keyword acquisition module 320 , a context information acquisition module 330 , a database 340 , a context detection module 350 , It may include a content providing module 360 .

The content acquisition module 310 may acquire content received from a server, an external device, or pre-stored content. In this case, the obtained content may be web page content, but this is only an example, and may be various types of content such as video content, photo content, and audio content.

The keyword acquisition module 320 may acquire a keyword for the content. In this case, the keyword acquisition module 320 may acquire a keyword of the content after analyzing the content using the previously-learned data recognition model. Alternatively, the keyword acquisition module 320 may acquire the keyword through semantic analysis of text included in the content.

The context information acquisition module 330 may acquire context information corresponding to the detected keyword. In this case, the context information acquisition module 330 may acquire context information corresponding to the detected keyword using a pre-stored keyword-context information matching table, and may obtain context information corresponding to the detected keyword using the pre-learned data recognition model. Context information can be obtained.

Meanwhile, the data recognition model used by the keyword acquisition module 320 and the context information acquisition module 330 will be described in more detail later with reference to FIGS. 9 to 10B . Also, according to another embodiment of the present invention, context information corresponding to content may be acquired using one data recognition model.

The database 340 may match and store information on content and information on context. In particular, the database 340 may store context information by tagging address information on the content.

The context sensing module 350 may detect the user's context using sensing data acquired from the sensing unit 170 , data transmitted from an external device, or pre-stored schedule data. In addition, the context sensing module 350 may detect a context corresponding to the pre-stored context information by determining whether the sensed context matches the pre-stored context information.

The content providing module 360 may provide content corresponding to the sensed context. In particular, the content providing module 360 may provide a message guiding the detection of a context before providing the content, and may provide the content when a user command is input through the message.

Referring back to FIG. 2 , the sensing unit 170 may acquire sensing data for detecting a context through various sensors. In particular, the sensing unit 170 may obtain data on the user's location from a GPS sensor, and may obtain data on the user's movement from a motion sensor (eg, an acceleration sensor, a gyro sensor, etc.).

In addition, the sensing unit 170 may include various sensors (eg, a temperature sensor, an illuminance sensor, a humidity sensor, etc.) for detecting the surrounding conditions of the electronic device 100 .

The processor 130 may control the above-described configurations of the electronic device 100 . For example, the processor 130 obtains context information corresponding to the content by using a plurality of software modules stored in the memory 160 , matches and stores the obtained content information with the context information, and stores the stored context information It is possible to detect a context corresponding to , and provide content corresponding to the sensed context.

Meanwhile, the processor 130 may be implemented as a single CPU to perform a keyword acquisition operation, a context information acquisition operation, a context detection operation, and the like, or may be implemented with a plurality of processors and IP performing specific functions. The processor 130 may acquire keywords based on deep learning such as a deep neural network (DNN).

In addition, the processor 130 may use big data and history data for each user for keyword acquisition and context information acquisition. Through this, the processor 130 may personalize the data recognition model while using the data recognition model for acquiring keywords and context information learned from big data.

Hereinafter, the present invention will be described in detail with reference to FIGS. 4A to 6B .

According to an embodiment of the present invention, the content acquisition module 310 may acquire the content and provide the acquired content through the display 120 . For example, the content acquisition module 310 may acquire web page content called “Pangyo jackpot restaurant xxx grilled duck” and provide it through the display 120 as shown in FIG. 4A .

When a preset user command (eg, a scrap command, a save command, a share command, etc.) is detected while providing content, the keyword acquisition module 320 may acquire a keyword for the acquired content. Specifically, the keyword acquisition module 320 may acquire a keyword for the content acquired through the pre-learned data recognition model. In this case, the data recognition model may be a learning model for extracting keywords from text and images included in a document. Alternatively, the keyword acquisition module 320 may acquire a keyword for the content through semantic analysis of the text included in the content. For example, the keyword acquisition module 320 uses a pre-learned data recognition model or semantic analysis from the web page content of "Pangyo jackpot restaurant xxx grilled duck", "Pangyo", "duck meat", "restaurant", "meal You can extract keywords such as ".

The context information acquisition module 330 may acquire context information corresponding to the acquired keyword. In this case, the context information obtaining module 330 may obtain context information corresponding to the obtained keyword through a pre-learned data recognition model or a pre-stored keyword-context information matching table.

For example, the context information obtaining module 330 may use context information corresponding to keywords such as "Pangyo", "duck", "restaurant", "meal", etc., "visit Pangyo", "meal in Pangyo", "duck meat". Meals", "restaurant search", etc. can be obtained.

In addition, the database 340 may match and store the information on the content with the context information obtained by the context information obtaining module 330 . In particular, the database 340 may store content information (eg, address information) and context matching information as follows.

Information about the content context information http//: www.matzip.com/origogi "Visit Pangyo", "Meal in Pangyo", "Meal with duck meat", "Search for restaurants"

After the information on the content and the context information are matched and stored in the database 340 , the context detection module 350 may detect a context corresponding to the stored context information.

In this case, the context detection module 350 may detect a context from sensing data obtained from the sensing unit 170 . For example, when it is determined that the location information of the electronic device 100 is “Pangyo” from the sensing data sensed by the GPS sensor, the context detection module 350 may detect that the current context is “Visit Pangyo”. .

Also, the context detection module 350 may detect a context from data obtained from an external device. For example, when it is determined that the location information of the electronic device 100 is “Pangyo” using data acquired from an AP installed in a subway station, the context detection module 350 determines that the current context is “Visit Pangyo”. can detect

Also, the context detection module 350 may detect a context from schedule information input by a user. For example, when schedule information such as "meal appointment with A in Pangyo on January XX, 2017" is input, the context detection module 350 may detect a context of "meal in Pangyo".

As another example, when the user inputs the text "restaurant" into the search box of the web page to search for it, the context detection module 350 may detect the context "restaurant search".

The content providing module 360 may control the display 120 to provide content corresponding to the sensed context. For example, when a context such as "visit Pangyo", "meal in Pangyo", or "restaurant search" is detected by the context detection module 350, the content providing module 360 corresponds to the detected context "Pangyo jackpot" The display 120 may be controlled to provide a web page content titled "Restaurant xxx grilled duck".

At this time, the content providing module 360 displays a message 410 inquiring whether to provide the content, as shown in FIG. 4b before providing the web page content called "Pangyo jackpot restaurant xxx grilled duck". can control In this case, the message 410 may include information on content corresponding to the sensed context and an icon for confirming whether the content is provided. When a user command for providing content is input through a message, the content providing module 360 may control the display 120 to provide web page content corresponding to the sensed context as shown in FIG. 4A .

According to another embodiment of the present invention, the content acquisition module 310 may acquire video content called “image helpful for insomnia” and provide it through the display 120 as shown in FIG. 5A .

If a user command for scraping the content is detected while providing the video content “video to help insomnia”, the keyword acquisition module 320 may acquire a keyword for the acquired video content. For example, the keyword acquisition module 320 extracts keywords such as “insomnia”, “sleep induction”, “video”, etc. from the video content called “video to help insomnia” through a pre-learned data recognition model or image analysis. can do.

The context information acquisition module 330 uses a pre-learned data recognition model or a pre-stored keyword-context information matching table to provide context information corresponding to keywords such as "insomnia", "sleep induction", "video", etc. ", etc., can be obtained.

In addition, the database 340 may store content information (eg, address information) and context matching information as follows.

Information about the content context information http//: www.dongyoungsang.com/dontsleep "Insomnia"

After the information on the content and the context information are matched and stored in the database 340 , the context detection module 350 may detect a context corresponding to the stored context information.

In this case, when it is confirmed that the user continues to use the electronic device 100 after a preset time (eg, 2:00 AM), the context detection module 350 detects the “sleep state” as the current context. can

Alternatively, when it is determined through the motion sensor 100 that the user continues to move after a preset time, the context detection module 350 may detect a “sleep state” as the current context.

The content providing module 360 may control the display 120 to provide content corresponding to the sensed context. For example, when a context such as "sleep state" is detected by the context detection module 350, the content providing module 360 provides a video content called "image helpful for insomnia" corresponding to the sensed context. The display 120 may be controlled.

At this time, the content providing module 360 controls the display 120 to provide a message 510 inquiring whether to provide the content as shown in FIG. 5B before providing the video content called “video to help insomnia”. can do. In this case, the message 510 includes information on the detected context (eg, "I can't sleep"), and information on the content corresponding to the detected context (eg, "image helpful for ambiguity"). ) and an icon for checking whether content is provided (eg, an icon for Yes and an icon for No). When a user command for providing content is input through a message, the content providing module 360 may control the display 120 to provide video content corresponding to the sensed context again, as shown in FIG. 5A .

In another embodiment of the present invention, the content acquisition module 310 may obtain web page content called "a method of removing rust using tomato ketchup" and provide it through the display 120, as shown in FIG. 6A . have.

If a user command for scraping the content is detected while providing the web page content "Method of removing rust using tomato ketchup", the keyword acquisition module 320 may acquire a keyword for the acquired video content. For example, the keyword acquisition module 320 is a keyword such as "tomato ketchup", "rust removal", etc. from the web page content called "method of removing rust using tomato ketchup" through a pre-learned data recognition model or image analysis. can be extracted.

The context information acquisition module 330 uses a pre-learned data recognition model or a pre-stored keyword-context information matching table to "purchase tomato ketchup", "Visit the mart", "Remove rust", "Access to shopping site", etc. can be obtained.

In addition, the database 340 may store content information (eg, address information) and context matching information as follows.

Information about the content context information http//: www.tiptip.kr/tomato-nok "Buy Tomato Ketchup", "Visit the Mart", "Remove Rust"

After the information on the content and the context information are matched and stored in the database 340 , the context detection module 350 may detect a context corresponding to the stored context information.

In this case, the context detection module 350 may detect a context from sensing data obtained from the sensing unit 170 . For example, when it is determined that the location information of the electronic device 100 is “mart” from the sensing data detected by the GPS sensor, the context detection module 350 may detect that the current context is “visit the mart” .

Also, the context detection module 350 may detect a context from data obtained from an external device. For example, when it is determined that the location information of the electronic device 100 is a “mart” using data acquired from an AP installed in a mart, the context detection module 350 detects that the current context is “visit a mart” can do.

Also, the context detection module 350 may detect a context from schedule information input by a user. For example, when schedule information "visit a mart on January XX, 2017" is input, the context detection module 350 may detect a context "visit to a mart".

As another example, when a user accesses a grocery shopping site, the context sensing module 350 may detect a context of “access to a shopping site”.

As another example, the memory 160 may store information about a context sensed in the past. For example, the memory 160 may pre-store route information for “visiting a mart”. In addition, the context detection module 350 may determine the current context based on information about the context detected in the past. For example, when the current moving path of the electronic device 100 matches the path for visiting the mart, the context sensing module 350 may detect “visit the mart” as the current context.

The content providing module 360 may control the display 120 to provide content corresponding to the sensed context. For example, when a context such as "visit a mart" or "access to a shopping site" is detected by the context detection module 350, the content providing module 360 is "melted using tomato ketchup" corresponding to the sensed context. The display 120 may be controlled to provide a web page content titled "How to Remove".

At this time, the content providing module 360 is displayed to provide a message 610 inquiring whether to provide the content, as shown in FIG. 6b before providing the web page content titled "Method of removing rust using tomato ketchup" 120 can be controlled. At this time, in the message 610, information on the detected context (eg, you visited a food store), information on content corresponding to the detected context (eg, using tomato ketchup ...) and an icon (eg, an icon for Yes and an icon for No) for checking whether content is provided. When a user command for providing content is input through a message, the content providing module 360 may control the display 120 to provide video content corresponding to the sensed context again, as shown in FIG. 6A .

7 is a flowchart illustrating a method of controlling an electronic device according to an embodiment of the present disclosure.

First, the electronic device 100 receives a preset command for content (S710). In this case, the preset command may be one of a scrap command, a save command, and a share command, but is not limited thereto.

Then, the electronic device 100 obtains context information of the content by analyzing the content ( S720 ). In this case, the electronic device 100 may obtain a keyword of the content by using the learned data recognition model, and may obtain context information corresponding to the keyword.

Then, the electronic device 100 stores the context information together with the information on the content (S730).

Then, the electronic device 100 detects a context corresponding to the context (S740). In this case, the electronic device 100 may detect a context based on sensing data acquired from the sensing unit 170 , data received from an external device, schedule data, and the like.

Then, the electronic device 100 provides content corresponding to the context (S750). In this case, the electronic device 100 may provide the content after first displaying a message inquiring whether to provide the content, rather than immediately providing the content.

According to the embodiment of the present disclosure as described above, the electronic device 100 provides pre-stored content corresponding to the sensed context, so that the user can check the scrapped or stored content in a necessary situation without a separate operation. there will be

8 is a diagram illustrating a system including the electronic device 100 and the server 200 for generating context information according to another embodiment of the present disclosure. Referring to FIG. 8 , the intelligent assistant system 1000 may include an electronic device 100 and a server 200 .

When a preset user command for content is input, the electronic device 100 transmits the preset user command to the external server 200 . The server 200 may acquire context information of the content based on the learned data recognition model in response to the received user command.

In addition, the server 200 transmits the obtained context information to the external electronic device 100 , and the electronic device 100 may store the content information and the context information transmitted from the server 200 together.

In this way, the electronic device 100 and the server 200 may work together to match and store content information and context information.

That is, the electronic device 100 may detect a context and provide content, and the server 200 may be implemented in the form of obtaining context information of the content. In particular, as shown in FIG. 8 , when the available resources are limited because the electronic device 100 is implemented as a small wearable device such as a smart watch, the process of obtaining the context information of the content is performed in the resource-rich server 200 can be done

9 is a sequence diagram illustrating a control method of a system for providing content by sensing a context, according to an embodiment of the present disclosure.

First, the electronic device 100 provides content (S910). In this case, the content may be web page content or video content, but is not limited thereto.

The electronic device 100 receives a scrap command for content (S920). In this case, the electronic device 100 may receive a save command, a share command, etc. in addition to the scrap command.

The electronic device 100 transmits information about the content to the external server 200 (S930). In this case, the information on the content may be address information of the content, but is not limited thereto.

The server 200 acquires context information of the content based on the information on the content (S940). In this case, the server 200 may extract a keyword of the content based on the information on the content, and obtain context information corresponding to the extracted keyword. In particular, the server 200 may perform keyword extraction and context information acquisition based on the previously learned data recognition model.

The server 200 transmits the obtained context information to the electronic device 100 (S950).

The electronic device 100 stores content information and context information together (S960). In this case, the electronic device 100 may match and store the address information of the content and the context information.

The electronic device 100 detects a context (S970). In this case, the electronic device 100 may detect a context based on sensing data acquired through the sensing unit 170 , data received from an external device, data including schedule information, and the like.

The electronic device 100 provides content corresponding to the context (S980). In this case, the electronic device 100 may provide a content corresponding to the context when a user command is input through the message after first providing a message for guiding the content corresponding to the context.

Meanwhile, in the above-described embodiment, it has been described that the electronic device 100 stores the content information and the context information, but the external server 200 may match the content information and the context information and store them. In this case, the electronic device 100 transmits the sensed context to the external server 200 , the server 200 determines whether there is content information corresponding to the sensed context, and enters the context based on the determination result. Corresponding content information may be transmitted to the external electronic device 100 .

10 is a block diagram of a processor 130 according to some embodiments of the present disclosure. Referring to FIG. 10 , the processor 130 according to some embodiments may include a data learning unit 131 and a data recognition unit 132 .

The data learning unit 131 may be trained so that the data recognition model has a criterion for acquiring a keyword or context. The data learning unit 131 may generate a data recognition model having a determination criterion by applying the learning data to the data recognition model in order to determine a keyword or context.

The processor 130 may acquire a keyword or context corresponding to the content by analyzing the input content according to the learned criteria. The data learning unit 131 may determine which data to use to determine a keyword or context. In addition, the data learning unit 131 acquires data to be used for learning, and applies the acquired data to a data recognition model to be described later (eg, a keyword acquisition model, a context acquisition model, etc.) to obtain keywords or acquire contexts. standards can be learned.

The data recognition unit 132 may determine keyword information or context information corresponding to the content from predetermined data by using the previously learned data recognition model. The data recognition unit 132 may acquire predetermined data (eg, text data included in content) according to a preset criterion by learning, and use the acquired data as an input value to use a data recognition model. In addition, the data recognition unit 132 may obtain a keyword or context by applying the input data to the data recognition model. In addition, the data recognition unit 132 may update the data recognition model based on user feedback on input values and output values. At least one of the data learning unit 131 and the data recognition unit 132 may include one or more It may be manufactured in the form of a hardware chip and mounted on the electronic device 100 . For example, at least one of the data learning unit 131 and the data recognition unit 132 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or a conventional general-purpose processor (eg, It may be manufactured as a part of a CPU or application processor) or a graphics-only processor (eg, GPU) and mounted on the various electronic devices described above. In this case, the dedicated hardware chip for artificial intelligence is a dedicated processor specialized in probability calculation, and has higher parallel processing performance than conventional general-purpose processors, so that it can quickly process computational tasks in the field of artificial intelligence, such as machine learning. In the embodiment of FIG. 10 , the data learning unit 131 and the data recognition unit 132 are both mounted on the electronic device 100 , but they may also be mounted on separate devices. For example, one of the data learning unit 131 and the data recognition unit 132 may be included in the electronic device 100 , and the other may be included in the user terminal 200 . In addition, the data learning unit 131 and the data recognition unit 132 are connected to each other by wire or wirelessly, so that information on the data recognition model built by the data learning unit 131 may be provided to the data recognition unit 132 , , data input to the data recognition unit 132 may be provided to the data learning unit 131 as additional learning data.

Meanwhile, at least one of the data learning unit 131 and the data recognition unit 132 may be implemented as a software module. When at least one of the data learning unit 131 and the data recognition unit 132 is implemented as a software module (or a program module including instructions), the software module is a non-transitory computer readable medium. media) can be saved. At least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by the OS, and the other part may be provided by a predetermined application.

11A is a block diagram of the data learning unit 131 according to some embodiments of the present disclosure. Referring to FIG. 11A , the data learning unit 131 according to an exemplary embodiment includes a data acquiring unit 131-1, a preprocessing unit 131-2, a training data selection unit 131-3, and a model learning unit 131 . -4) and at least one of the model evaluator 131-5 may be optionally further included. The data acquisition unit 131-1 may acquire learning data necessary to acquire a keyword or context. In particular, the data acquisition unit 131-1 may acquire data for acquiring a keyword or context of the content as learning data.

For example, the data acquisition unit 131-1 may receive content including text data or image data from an external server, an external device, or a storage medium.

The preprocessor 131 - 2 may preprocess the acquired data so that the acquired data can be used for keyword acquisition or learning for context acquisition. The pre-processing unit 131-2 may process the acquired data into a preset format so that the model learning unit 131-4, which will be described later, uses the acquired data for learning for keyword acquisition or context acquisition.

For example, when the training data is text data, the preprocessor 131 - 2 may perform preprocessing such as sentence segmentation, part-of-speech tagging, tokenization, stopword removal, and stem extraction on the text data. As another example, when the training data is image data, the preprocessor 131 - 2 may perform decoding, scaling, noise filtering, resolution conversion, etc. on the image data to create an image frame of the same format. Also, the preprocessor 131 - 2 may crop only a specific region included in each of the plurality of input image frames.

The learning data selection unit 131-3 may select data necessary for learning from among the pre-processed data. The selected data may be provided to the model learning unit 131-4. The learning data selection unit 131-3 may select data necessary for learning from among the preprocessed data according to a preset criterion for acquiring a keyword or acquiring a context. In addition, the training data selection unit 131-3 may select data according to a preset criterion by learning by the model learning unit 131-4, which will be described later. For example, the learning data selection unit 131-1 may select only a noun component from the input text data.

The model learning unit 131-4 may learn a criterion regarding how the data recognition model acquires a keyword or context by using the training data.

For example, the model learning unit 131-4 may train the data recognition model through supervised learning using at least a portion of the training data as a criterion for determination. Alternatively, the model learning unit 131-4 may recognize data through unsupervised learning, for example, by learning by itself using learning data without any guidance, and discovering a criterion for judging a situation. model can be trained.

In addition, the model learning unit 131-4 may learn a criterion for which learning data should be used to obtain a keyword or context. As the learning data, data collected or tested by the data learning unit 130 or the manufacturer of the electronic device 100 may be used. The model learning unit 131-4 selects a data recognition model used to acquire keywords or contexts. It can be trained using the training data. In this case, the data recognition model may be a pre-built model. For example, the data recognition model may be a model built in advance by receiving basic training data. As another example, the data recognition model may be a model built in advance using big data. The data recognition model may be constructed in consideration of the field of application of the recognition model, the purpose of learning, or the computer performance of the device. The data recognition model may be, for example, a model based on a neural network.

Data recognition models can be designed to simulate human brain structures on a computer. The data recognition model may include a plurality of network nodes having weights that simulate neurons of a human neural network. A plurality of network nodes may form a connection relationship to each other so as to simulate a synaptic activity in which a neuron sends and receives a signal through a synapse. The data recognition model may include, for example, a neural network model or a deep learning model developed from a neural network model. In a deep learning model, a plurality of network nodes may exchange data according to a convolutional connection relationship while being located at different depths (or layers). For example, a model such as a deep neural network (DNN), a recurrent neural network (RNN), or a bidirectional recurrent deep neural network (BRDNN) may be used as the data recognition model, but is not limited thereto.

According to various embodiments, when there are a plurality of pre-built data recognition models, the model learning unit 131-4 uses a data recognition model to learn a data recognition model that has a high correlation between the input learning data and the basic learning data as a data recognition model. can decide In this case, the basic learning data may be classified for each type of data, and the data recognition model may be previously built for each type of data. For example, the basic training data is pre-classified by various criteria such as the region where the training data is generated, the time when the training data is generated, the size of the training data, the genre of the training data, the creator of the training data, the type of object in the training data, etc. may have been

Also, the model learning unit 131-4 may train the data recognition model using, for example, a learning algorithm including error back-propagation or gradient descent. .

For example, the model learning unit 131-4 may train the data recognition model through supervised learning using the judgment criterion as an input value for learning. Alternatively, the model learning unit 131-4 is, for example, an unsupervised learning that discovers a criterion for acquiring a keyword or a context by learning by itself using learning data necessary for acquiring a keyword or a context without a separate guidance. ), it is possible to train a data recognition model. As another example, the model learning unit 131-4 may train the data recognition model through reinforcement learning using feedback on whether a result of obtaining an alternative keyword or obtaining a context according to learning is correct.

Also, when the data recognition model is learned, the model learning unit 131-4 may store the learned data recognition model. In this case, the model learning unit 131-4 may store the learned data recognition model in the memory 160 of the electronic device 100 .

In this case, the memory 160 in which the learned data recognition model is stored may also store commands or data related to at least one other component of the electronic device 100 together. In addition, the memory 160 may store software and/or programs. For example, a program may include a kernel, middleware, an application programming interface (API) and/or an application program (or "application"), and the like.

Alternatively, the model learning unit 131-4 may store the learned data recognition model in the memory of a server connected to the electronic device 100 through a wired or wireless network.

The data learning unit 130 includes a preprocessing unit 131-2 and a training data selection unit 131-3 to improve the recognition result of the data recognition model or to save resources or time required for generating the data recognition model. may further include.

The pre-processing unit 131-2 may pre-process the data obtained by the data obtaining unit 131-1 to be used for learning for situation determination.

For example, the preprocessor 131 - 2 may process the obtained data into a predefined format so that the model learning unit 131-4 can easily use the data for learning the data recognition model. The preprocessed data may be provided to the model learning unit 131-4 as training data.

Alternatively, the learning data selection unit 131-3 may selectively select learning data required for learning from among the preprocessed data. The selected training data may be provided to the model learning unit 131-4. The learning data selection unit 131-3 may select learning data necessary for learning from among the preprocessed data according to a preset selection criterion. In addition, the learning data selection unit 131-3 may select the learning data required for learning according to a selection criterion preset by the model learning unit 131-4 learning.

The data learning unit 130 may further include a model evaluation unit 131-5 to improve the recognition result of the data recognition model. The model evaluation unit 131-5 inputs evaluation data to the data recognition model. and, when the determination result output from the evaluation data does not satisfy a predetermined criterion, the model learning unit 131-4 may be trained again. In this case, the evaluation data may be preset data for evaluating the data recognition model.

For example, the model evaluator 131-5 sets a predetermined criterion when the number or ratio of the evaluation data for which the determination result is not accurate among the determination results of the learned data recognition model for the evaluation data exceeds a preset threshold. It can be evaluated as unsatisfactory. For example, when a predetermined criterion is defined as a ratio of 2%, when the learned data recognition model outputs an erroneous judgment result for more than 20 evaluation data out of a total of 1000 evaluation data, the model evaluation unit 131-5 can be evaluated that the trained data recognition model is not suitable.

On the other hand, when there are a plurality of learned data recognition models, the model evaluation unit 131-5 evaluates whether each of the learned data recognition models satisfies a predetermined criterion, and recognizes the model that satisfies the predetermined criterion as final data. can be determined as a model. In this case, when there are a plurality of models satisfying the predetermined criteria, the model evaluator 131 - 5 may determine any one or a predetermined number of models preset in the order of the highest evaluation score as the final data recognition model.

At least one of the data acquisition unit 131-1, the preprocessor 131-2, the training data selection unit 131-3, the model learning unit 131-4, and the model evaluation unit 131-5 described above is , may be implemented as a software module or manufactured in the form of at least one hardware chip and mounted in an electronic device. For example, at least one of the data acquisition unit 131-1, the preprocessor 131-2, the training data selection unit 131-3, the model learning unit 131-4, and the model evaluation unit 131-5 One may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or as part of an existing general-purpose processor (eg, CPU or application processor) or IP for a specific function, It may be mounted on the electronic device 100 .

In addition, the data acquisition unit 131-1, the preprocessor 131-2, the training data selection unit 131-3, the model learning unit 131-4, and the model evaluation unit 131-5 are one electronic device. It may be mounted on the device, or it may be mounted on separate electronic devices, respectively. For example, some of the data acquisition unit 131-1, the preprocessor 131-2, the training data selection unit 131-3, the model learning unit 131-4, and the model evaluation unit 131-5 may be included in the electronic device 100 , and the remaining part may be included in the server 200 .

On the other hand, at least one of the data acquisition unit 131-1, the preprocessor 131-2, the training data selection unit 131-3, the model learning unit 131-4, and the model evaluation unit 131-5 is It can be implemented as a software module. At least one of the data acquisition unit 131-1, the preprocessor 131-2, the training data selection unit 131-3, the model learning unit 131-4, and the model evaluation unit 131-5 is a software module (or, when implemented as a program module including instructions), the software module may be stored in a non-transitory computer-readable recording medium. At least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by the OS, and the other part may be provided by a predetermined application.

11B is a block diagram of the data recognition unit 132 according to some embodiments of the present disclosure. Referring to FIG. 11B , the data recognition unit 132 according to some embodiments may include a data acquisition unit 132-1 and a recognition result providing unit 132-4_. Also, the data recognition unit 132 may selectively further include at least one of a preprocessor 132-2, a data selection unit 132-3, and a model update unit 132-5.

The data acquisition unit 132-1 may acquire data necessary for keyword acquisition or context acquisition, and the preprocessor 132-2 pre-processes the provided data so that the data provided for keyword acquisition or context acquisition can be used. can do. The preprocessor 132-2 may process the acquired data into a preset format so that the recognition result providing unit 132-4, which will be described later, uses the acquired data for keyword acquisition or context acquisition.

The data selection unit 132-3 may select data required for keyword acquisition or context acquisition from among the pre-processed data. The selected data may be provided to the recognition result providing unit 132-4. The data selection unit 132 - 3 may select some or all of the preprocessed data according to a preset criterion for keyword acquisition or context acquisition. In addition, the data selection unit 132-3 may select data according to a preset criterion by learning by the model learning unit 142-4, which will be described later.

The recognition result providing unit 132-4 may determine a keyword or context corresponding to the content by applying the data acquired by the data acquiring unit 132-4 to the data recognition model learned as an input value. Alternatively, the recognition result providing unit 132-4 may provide the recognition result by applying the data preprocessed by the preprocessing unit 132-2 to the data recognition model learned as an input value. Alternatively, the recognition result providing unit 132-4 may provide the recognition result by applying the data selected by the data selection unit 132-3 to the data recognition model as an input value.

Also, the determination result may be determined by a data recognition model. For example, the recognition result providing unit 132 - 4 may obtain a keyword or context corresponding to the content by inputting data included in the content into the data recognition model.

The model updating unit 132 - 5 may update the data recognition model based on the evaluation of the determination result provided by the recognition result providing unit 132 - 4 . For example, the model updating unit 132-5 provides the model learning unit 131-4 with the determination result provided by the recognition result providing unit 132-4, so that the model learning unit 131-4 is You can update the data recognition model.

On the other hand, the data acquisition unit 132-1, the preprocessor 132-2, the data selection unit 132-3, the recognition result providing unit 132-4 and the model update unit 132 in the data recognition unit 132. At least one of -5) may be implemented as a software module or manufactured in the form of at least one hardware chip and mounted in an electronic device. For example, at least one of the data acquisition unit 132-1, the preprocessor 132-2, the data selection unit 132-3, the recognition result providing unit 132-4, and the model update unit 132-5 One may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or as part of an existing general-purpose processor (eg, CPU or application processor) or IP for a specific function, It may be mounted on the electronic device 100 .

In addition, the data acquisition unit 132-1, the preprocessor 132-2, the data selection unit 132-3, the recognition result providing unit 132-4, and the model update unit 132-5 are one electronic device. may be mounted on the , or may be respectively mounted on separate electronic devices. For example, some of the data acquisition unit 132-1, the preprocessor 132-2, the data selection unit 132-3, the recognition result providing unit 132-4, and the model update unit 132-5 may be included in the electronic device 100 , and the remaining part may be included in a server interworking with the electronic reach 100 .

Meanwhile, at least one of the data acquisition unit 132-1, the preprocessor 132-2, the data selection unit 132-3, the recognition result providing unit 132-4, and the model update unit 132-5 is It can be implemented as a software module. At least one of the data acquisition unit 132-1, the preprocessor 132-2, the data selection unit 132-3, the recognition result providing unit 132-4, and the model update unit 132-5 is a software module (or, when implemented as a program module including instructions), the software module may be stored in a non-transitory computer-readable recording medium. At least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by the OS, and the other part may be provided by a predetermined application.

The methods described above may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software.

Here, the program command is stored in a computer-readable non-transitory recording medium, read and executed by the computer, thereby implementing an embodiment of the present disclosure.

Here, the non-transitory readable recording medium means a medium that stores data semi-permanently and can be read by a device, and includes a register, a cache, a buffer, etc., and includes a signal and a current. Transmission media such as etc. are not included.

Specifically, the above-described program instructions are stored in a non-transitory readable recording medium such as a CD, DVD, hard disk, Blu-ray disk, USB, internal memory (eg, memory 110), memory card, ROM or RAM, etc. can be

Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The above hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

Also, the method according to the disclosed embodiments may be provided as a computer program product.

The computer program product may include a S/W program, a computer-readable storage medium in which the S/W program is stored, or a product traded between a seller and a buyer.

For example, computer program products are products (eg, downloadable apps) in the form of S/W programs distributed electronically through electronic devices or manufacturers of electronic devices or electronic markets (eg, Google Play Store, App Store). may include For electronic distribution, at least a portion of the S/W program may be stored in a storage medium or may be temporarily generated. In this case, the storage medium may be a server of a manufacturer or an electronic market, or a storage medium of a relay server.

As described above, although the present disclosure has been described with reference to limited embodiments and drawings, the present disclosure is not limited to the above embodiments, and those skilled in the art to which the present disclosure pertains various modifications and variations from these descriptions. This is possible. Therefore, the scope of the present disclosure should not be limited to the described embodiments, but should be defined by the claims described below as well as the claims and equivalents.

100: electronic device 110: input unit
120: display 130: processor
140: audio output unit 150: communication unit
160: memory 170: sensing unit

Claims (19)

A method for controlling an electronic device, comprising:
obtaining a keyword of the content by analyzing an image of the content when a preset command for content is input, and obtaining context information corresponding to the content based on the keyword;
storing the context information together with the information on the content; and
When a context corresponding to the context information is detected, providing content corresponding to the sensed context; includes,
The providing step is
detecting a context corresponding to a user's location based on a sensed value obtained from a sensor provided in the electronic device;
Identifying context information corresponding to the sensed context, and providing pre-stored content corresponding to the identified context information; Control method comprising a. According to claim 1,
Obtaining the context information includes:
obtaining a keyword of the content using a data recognition model learned using an artificial intelligence algorithm;
and generating the context information based on the obtained keyword. According to claim 1,
The information on the content includes address information of the content,
The saving step is
The control method according to claim 1, wherein the context information is tagged and stored in the address information of the content. delete According to claim 1,
The providing step is
acquiring context-related information from an external device connected to the electronic device;
and providing content corresponding to the sensed context when a context corresponding to the context information is detected based on the information. According to claim 1,
The providing step is
detecting a context corresponding to the context information based on schedule information of a user of the electronic device;
A control method comprising a; providing content corresponding to the sensed context. According to claim 1,
The electronic device stores information on a context sensed in the past in a memory,
The providing step is
determining a current context based on information on the context sensed in the past; and
When the determined current context corresponds to the context information, providing content corresponding to the sensed context. According to claim 1,
The providing step is
providing a message for guiding context detection when a context corresponding to the context information is detected;
When a user command is input through the message, providing content corresponding to the sensed context; Control method comprising a. According to claim 1,
The content is web page content,
The predetermined command is a control method, characterized in that the scrap command for the web page content. In an electronic device,
an input unit for receiving user commands;
Memory;
a display for displaying content; and
When a preset command for the content is input through the input unit, an image of the content is analyzed to obtain a keyword of the content, and context information corresponding to the content is obtained based on the keyword, A processor that stores the context information together with information about the context information in the memory, and controls the display to provide content corresponding to the sensed context when a context corresponding to the context information is detected; includes;
The processor is
Based on a sensing value obtained from a sensor provided in the electronic device, a context corresponding to the user's location is detected, context information corresponding to the sensed context is identified, and pre-stored corresponding to the identified context information An electronic device that controls the display to provide content. 11. The method of claim 10,
The processor is
The electronic device of claim 1, wherein the keyword of the content is acquired using a data recognition model learned using an artificial intelligence algorithm, and the context information is acquired based on the acquired keyword. 11. The method of claim 10,
The information on the content includes address information of the content,
The processor is
The electronic device of claim 1, wherein the context information is tagged with the address information of the content and stored in the memory. delete 11. The method of claim 10,
The processor is
acquiring context-related information from an external device connected to the electronic device, and controlling the display to provide content corresponding to the sensed context when a context corresponding to the context information is detected based on the information characterized by an electronic device. 11. The method of claim 10,
The processor is
and detecting a context corresponding to the context information based on the user's schedule information of the electronic device, and controlling the display to provide content corresponding to the sensed context. 11. The method of claim 10,
The memory stores information about contexts sensed in the past,
The processor is
determining a current context based on information on the context sensed in the past, and controlling the display to provide content corresponding to the sensed context when the determined current context corresponds to the context information electronic device. 11. The method of claim 10,
The processor is
When a context corresponding to the context information is detected, the display is controlled to provide a message for guiding the detection of the context, and when a user command is input through the message, the display is configured to provide content corresponding to the sensed context Electronic device, characterized in that for controlling. 11. The method of claim 10,
The content is web page content,
The electronic device of claim 1, wherein the preset command is a scrap command for the web page content. A non-transitory computer-readable recording medium storing a program for executing a control method of an electronic device.
The control method of the electronic device,
obtaining a keyword of the content by analyzing an image of the stored content when a preset command for content is input, and obtaining context information corresponding to the content based on the keyword;
storing the context information together with the information on the content; and
When a context corresponding to the context information is detected, providing content corresponding to the sensed context; includes,
The providing step is
detecting a context corresponding to a user's location based on a sensed value obtained from a sensor provided in the electronic device;
A recording medium comprising a; identifying context information corresponding to the sensed context, and providing pre-stored content corresponding to the identified context information.

Images