Electronic device and content recommendation method thereof

Abstract

An electronic device is disclosed. Instructions stored in a memory of the present electronic device, when executed individually or collectively by at least one processor, may cause the electronic device to: obtain interaction data between a first user and a second user on the basis of an interaction performed by the first user of the electronic device with the second user by using the electronic device; obtain a plurality of keywords on the basis of the interaction data; obtain a knowledge graph for the second user on the basis of the plurality of keywords; identify content of interest of the second user on the basis of the knowledge graph; and display the content of interest on a display.

Description

Electronic devices and their content recommendation methods

[0001] The present disclosure relates to an electronic device for recommending content to be shared with an interaction partner and a content recommendation method thereof.

[0002] Users can interact with each other using various electronic devices, such as smartphones and tablets. For example, users can chat with each other and share various content using communication applications installed on their electronic devices.

[0003] An electronic device according to one embodiment may include a display, a memory storing instructions, and at least one processor including a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain interaction data between a first user and a second user based on an interaction performed by a first user of the electronic device with a second user using the electronic device, obtain a plurality of keywords based on the interaction data, obtain a knowledge graph for the second user based on the plurality of keywords, identify content of interest of the second user based on the knowledge graph, and display the content of interest on the display.

[0004] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify priorities of the plurality of keywords included in the knowledge graph, identify keywords of interest of the second user among the plurality of keywords based on the priorities, and identify content of interest corresponding to the keywords of interest.

[0005] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify a score of each keyword based on the number of each keyword extracted from the interaction data, and to apply a weight to the score of each of the plurality of keywords based on at least one of a user who transmitted the interaction data from which the keyword was extracted, a type of an application that generated the interaction data from which the keyword was extracted, whether the user visited a place corresponding to the keyword, and a time point of sharing the interaction data from which the keyword was extracted, and to identify a priority of the plurality of keywords based on the plurality of scores to which the weight was applied.

[0006] The above instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to apply different weights to the score of the keyword depending on whether the user who transmitted the interaction data from which the keyword was extracted is the first user or the second user.

[0007] The above instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to apply different weights to the score of the keyword depending on the type of application that generated the interaction data from which the keyword was extracted.

[0008] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to apply different weights to the score of the keyword depending on whether one of the first user and the second user has visited a location corresponding to the keyword.

[0009] The above instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to apply different weights to the score of a keyword depending on the time point of sharing of the interaction data from which the keyword was extracted.

[0010] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display content of interest for the second user on the display while providing a user interface for interaction with the second user.

[0011] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, on the display, a user interface recommending a second user related to the content based on a knowledge graph for a plurality of second users when the content is selected.

[0012] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify a common interest keyword of a plurality of second users included in a group based on a knowledge graph of the plurality of second users, and to display a user interface on the display for adding a second user having the common interest keyword as an interest keyword to the group.

[0013] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify common interest keywords of the plurality of second users based on knowledge graphs of each of the plurality of second users included in the group, and to display common interest content for the plurality of second users on the display based on the common keywords of the plurality of second users.

[0014] A method for recommending content in an electronic device according to one embodiment may include an operation of obtaining interaction data between a first user and a second user based on an interaction performed by a first user of the electronic device with a second user using the electronic device, an operation of obtaining a plurality of keywords based on the interaction data, an operation of obtaining a knowledge graph for the second user based on the plurality of keywords, an operation of identifying content of interest of the second user based on the knowledge graph, and an operation of displaying the content of interest.

[0015] A non-transitory computer-readable medium storing computer instructions that, when executed by at least one processor of an electronic device according to one embodiment, cause the electronic device to perform an operation, the operation may include an operation of obtaining interaction data between a first user and a second user based on an interaction performed by a first user of the electronic device with a second user using the electronic device, an operation of obtaining a plurality of keywords based on the interaction data, an operation of obtaining a knowledge graph for the second user based on the plurality of keywords, an operation of identifying content of interest of the second user based on the knowledge graph, and an operation of displaying the content of interest.

[0016] FIGS. 1A and 1B illustrate an example of a block diagram of an electronic device according to one embodiment.

[0017] FIG. 2 is a drawing for explaining the operation of an electronic device according to one embodiment.

[0018] FIG. 3 is a diagram illustrating an example of an operation of an electronic device acquiring a keyword according to one embodiment.

[0019] FIG. 4 illustrates an example of a knowledge graph for a second user generated by an electronic device according to one embodiment.

[0020] FIG. 5 illustrates an example of a knowledge graph for a second user generated by an electronic device according to one embodiment.

[0021] FIGS. 6A and 6B illustrate an example of an operation of an electronic device recommending content of interest to a second user according to one embodiment.

[0022] FIG. 7 illustrates an example of an operation in which an electronic device recommends content of interest to a second user according to one embodiment.

[0023] FIG. 8 illustrates an example of an operation in which an electronic device recommends a second user corresponding to a group according to one embodiment.

[0024] FIG. 9 illustrates an example of an operation in which an electronic device recommends common interest content corresponding to a group according to one embodiment.

[0025] FIG. 10 illustrates an example of an operation in which an electronic device recommends a second user related to content according to one embodiment.

[0026] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0027] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this disclosure are not limited to the aforementioned devices.

[0028] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0029] Throughout this specification, singular expressions include plural expressions unless the context clearly dictates otherwise. When a part of this specification refers to "including" a component, this does not exclude other components, but rather implies the inclusion of other components, unless otherwise specifically stated.

[0030] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0031] FIGS. 1A and 1B illustrate an example block diagram of an electronic device according to one embodiment. The components, their relationships, and their functions illustrated in FIGS. 1A and 1B are exemplary only and do not limit the implementations described or claimed herein.

[0032] Referring to FIG. 1A, the electronic device (100) may include at least one processor (110) (hereinafter, referred to as processor (110)), at least one memory (120) (hereinafter, referred to as memory (120)), and a display (130).

[0033] The processor (110) can control the overall operations of the electronic device (100). For example, the processor (110) is operatively connected to the memory (120) and the display (130) to control the operations of the electronic device (100). In addition, the processor (110) can control the operations of the electronic device (100) according to the present disclosure by executing one or more instructions stored in the memory (120). The processor (110) can be composed of one or more processors.

[0034] The processor (110) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing operations. The processor (110) may include at least one electrical circuit and may individually or collectively perform distributed processing of instructions (or programs, data) stored in the memory (120). The processor (110) may include a processor assembly including one or more processing circuits. The processor (110) may include any processing circuit operative to control the performance and operations of one or more components (e.g., memory (120), display (130), communication circuit (e.g., communication circuit (140) of FIG. 1B)) of the electronic device (100). For example, the processor (110) (e.g., application processor (AP)) may be implemented as a system on chip (SoC) (e.g., one chip or chipset). For example, the processor (110) may be implemented as multiple cores (or at least one core circuit), multiple chips, or multiple chipsets. For example, the processor (110) may include one or more processing circuits. For example, the processor (110) may include one or more processing circuits configured to individually and / or collectively perform various functions of the present disclosure. As a non-limiting example, at least a portion of the processor (110) may be implemented as a system on chip (SoC) of the electronic device (100). At least another portion of the processor (110) may be included in the first chip of the electronic device (100) and may be included in a second chip of another electronic device (100).

[0035] For example, the processor (110) may include a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), an image signal processor (ISP), a display controller, a memory controller, a storage controller, a communication processor (CP), and / or a sensor interface. These components of the processor (110) are merely exemplary. For example, the processor (110) may further include other components. For example, some components of the processor (110) may be omitted from the processor (110). For example, some components of the processor (110) may be included as separate components of the electronic device (100) outside the processor (110). For example, some components of the processor (110) (e.g., a memory controller) may be included within other components (e.g., at least a portion of the memory (120), an interface (e.g., available for connecting to at least one component of the electronic device (100), the display (130)).

[0036] The processor (110) may cause other components of the electronic device (100) to perform various operations by executing instructions stored in the memory (120). The CPU (or central processing circuit) may be configured to control components of the processor (110) based on the execution of instructions stored in the memory (120) (e.g., volatile memory and / or non-volatile memory). The GPU (or graphics processing circuit) may be configured to perform parallel operations (e.g., rendering). The NPU (or neural processing circuit, or AI (artificial intelligence) chip) may be configured to perform operations for an artificial intelligence model (e.g., convolution computation). The ISP (or image signal processing circuit) may be configured to process a raw image acquired through an image sensor into a format suitable for components within the electronic device (100) or components of the processor (110). A display controller (or display control circuit, or display processing unit (DPU)) may be configured to process an image acquired from a CPU, GPU, ISP, or memory (120) (e.g., volatile memory) into a format suitable for the display (130). A memory controller (or memory control circuit) may be configured to control reading data from volatile memory and writing data to volatile memory. A storage controller (or storage control circuit) may be configured to control reading data from non-volatile memory and writing data to non-volatile memory. A CP (communication processing circuit) may be configured to process data acquired from a component of the processor (110) into a format suitable for transmitting to another electronic device via a communication circuit, or to process data acquired from another electronic device via a communication circuit into a format suitable for processing by a component of the processor (110).For example, the communication circuit may include one or more communication circuits. The sensor interface (or sensing data processing circuit, sensor hub) may be configured to process data about the state of the electronic device (100) and / or the state of the surroundings of the electronic device (100), obtained through the sensor, into a format suitable for components of the processor (110).

[0037] For example, the processor (110) may perform a method according to an embodiment of the present disclosure by executing one or more instructions stored in the memory (120).

[0038] When a method according to an embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by a single processor or by a plurality of processors. 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 artificial intelligence-specific processor).

[0039] The processor (110) may be implemented as a single core processor including one core, or may be implemented as one or more multicore processors including a plurality of cores (e.g., homogeneous multicores or heterogeneous multicores). When the processor (110) is implemented as a multicore processor, each of the plurality of cores included in the multicore processor may include an internal processor memory, such as a cache memory or an on-chip memory, and a common cache shared by the plurality of cores may be included in the multicore processor. In addition, each of the plurality of cores (or some of the plurality of cores) included in the multicore processor may independently read and execute a program instruction for implementing a method according to an embodiment of the present disclosure, or all (or some) of the plurality of cores may be linked to read and execute a program instruction for implementing a method according to an embodiment of the present disclosure.

[0040] 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 core among the plurality of cores included in a multi-core processor, or may be performed by the plurality of cores. 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 core included in the multi-core processor, or the first operation and the second operation may be performed by a first core included in the multi-core processor, and the third operation may be performed by a second core included in the multi-core processor.

[0041] In embodiments of the present disclosure, a processor may mean a system on a chip (SoC) in which one or more processors and other electronic components are integrated, a single-core processor, a multi-core processor, or a core included in a single-core processor or a multi-core processor, wherein the core may be implemented as a CPU, a GPU, an accelerated processing unit (APU), a many integrated core (MIC), a digital signal processor (DSP), an NPU, a hardware accelerator, or a machine learning accelerator, but embodiments of the present disclosure are not limited thereto.

[0042] The memory (120) may include one or more storage media (or one or more storage devices). For example, the memory (120) may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory (e.g., non-volatile memory) such as a hard drive, flash memory, read-only memory (ROM), semi-permanent memory (e.g., volatile memory) such as random access memory (RAM), any other suitable type of storage (or storage assembly), or any combination thereof. The memory (120) may include cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (100). As a non-limiting example, the cache memory may be included within the processor (110). The memory (120) may be fixedly embedded within the electronic device (100) or incorporated into one or more suitable types of components (e.g., a subscriber identity module (SIM) card and / or a secure digital (SD) card) that can be repeatedly inserted into and removed from the electronic device (100).

[0043] For example, the memory (120) may store one or more software applications, such as an operating system (or system) software application, a firmware software application, a driver software application, a plug-in (e.g., add-in, add-on, and / or applet) software application, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (110). For example, the memory (120) may store instructions callable by an application programming interface (API). For example, the memory (120) may store instructions within a library.

[0044] The display (130) can output visual information to the user. The visual information can include visual objects displayed on the display (130). For example, the visual objects can include screens, images, icons, graphical user interface (GUI), and user interface (UI) elements.

[0045] For example, the display (130) may be implemented as a flat panel display (FPD), a curved display, or a flexible display. For example, the display (130) may be implemented as various types of displays, such as a liquid crystal display (LCD) display, an active matrix organic light emitting diodes (AMOLED) display, a light emitting diodes (LED), a micro LED, or a mini LED.

[0046] The display (130) may include a touch-sensitive circuit configured to detect a touch. The touch-sensitive circuit may acquire a user input of touching (or selecting) a visual object displayed on the display (130). For example, the touch-sensitive circuit may detect an input (e.g., a touch input or a hovering input) at a specific location of the display (130) by measuring a change in a signal (e.g., voltage, light intensity, resistance, or charge) at the specific location, and provide information about the detected input to the processor (110).

[0047] Referring to FIG. 1B, the electronic device (100) may include a processor (110), memory (120), a display (130), and a communication circuit (140). However, this configuration is merely exemplary, and it is understood that new configurations may be added or some configurations may be omitted when implementing the present disclosure. Meanwhile, among the configurations illustrated in FIG. 1B, a detailed description of any configurations that overlap with those illustrated in FIG. 1A will be omitted.

[0048] The communication circuit (140) can perform data communication with an external electronic device. For example, the communication circuit (140) can communicate with the external electronic device via a network. The processor (110) can receive data from the external electronic device via the communication circuit (140) and transmit data to the external electronic device via the communication circuit (140).

[0049] The communication circuit (140) may include hardware components for supporting transmission and / or reception of electrical signals between the electronic device (100) and an external electronic device. For example, the communication circuit (140) may support transmission and / or reception of electrical signals based on various types of protocols such as Ethernet, LAN (local area network), WAN (wide area network), Wi-Fi (wireless fidelity), Bluetooth, BLE (bluetooth low energy), ZigBee, LTE (long term evolution), 5G NR (new radio), and / or 6G.

[0050] The components illustrated in FIGS. 1A and 1B are merely exemplary. For example, the electronic device (100) may include other components (e.g., at least one image sensor, at least one sensor, a power management integrated circuit (PMIC), an audio processing circuit, an antenna, a rechargeable battery, and / or an input / output interface). For example, some components may be omitted from the electronic device (100). For example, some components may be integrated into a single component.

[0051] In the following examples, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0052] FIG. 2 is a diagram illustrating the operation of an electronic device according to one embodiment. The processor (110) may perform at least one of the operations of FIG. 2. Instructions stored in the memory (120), when individually or collectively executed by the processor (110), may cause the electronic device (100) to perform the operations of FIG. 2.

[0053] In operation 210, the electronic device (100) can obtain interaction data between a first user and a second user.

[0054] In one embodiment, the first user may be a user of the electronic device (100), and the second user may be a counterpart with whom the first user interacts using a communication application (e.g., a message application, a messenger application) of the electronic device (100).

[0055] In one embodiment, the second user may be any one of multiple users whose contact information is stored in the electronic device (100). The contact information may include information (e.g., phone number, ID) necessary for interaction between users using a communication application.

[0056] In one embodiment, the electronic device (100) may obtain interaction data between a first user and a second user based on an interaction between the first user and the second user using the electronic device (100). The interaction may include actions of the first user and the second user exchanging various messages, content, etc. The interaction data may include message content exchanged between the first user and the second user. The message content may include text messages, images, videos, voice messages, files, etc.

[0057] For example, interaction between a first user and a second user may be performed via a communication application. The communication application may be installed on the first user's electronic device (100) and the second user's electronic device, respectively. The first user may transmit message content to the second user and receive message content from the second user via the communication application. The electronic device (100) may obtain message content transmitted to the second user's electronic device and / or message content received from the second user's electronic device, thereby obtaining interaction data between the first user and the second user.

[0058] In one embodiment, the electronic device (100) may store interaction data for each second user in the memory (120). The first user may interact with multiple second users through a communication application. For example, the communication application may provide a personal chat service for one-on-one conversations between individuals and a group chat service for conversations among multiple people. The first user may converse with the second user in a personal chat room or converse with multiple second users in a group chat room. The electronic device (100) may obtain interaction data between the first user and the second user, associate the interaction data with identification information (e.g., name, ID, or contact information) of the second user, and store the association in a storage of the electronic device (100). The storage may be referred to as a knowledge graph storage.

[0059] In operation 220, the electronic device (100) can obtain multiple keywords based on interaction data.

[0060] In one embodiment, a keyword may include a word that represents the core content (or topic) of the message content. However, the present disclosure is not limited thereto, and a keyword may also include a phrase or clause.

[0061] The electronic device (100) can obtain at least one keyword from a message. The message may be a text message or a text converted from a voice message.

[0062] For example, the electronic device (100) can parse a message to break down the message into a plurality of components and extract at least one keyword from among the plurality of components.

[0063] For example, the electronic device (100) can extract at least one keyword from a message using an artificial intelligence model (e.g., natural language processing (NLP)). The electronic device (100) can analyze the message using a pre-trained language model, identify the meaning and context of words within the message, extract important words within the message, and obtain at least one keyword.

[0064] The electronic device (100) can obtain at least one keyword from an image or video. When analyzing a video, the electronic device (100) can use an image of the video (e.g., a thumbnail image or an image frame of the video).

[0065] For example, the electronic device (100) can classify an image through image analysis (e.g., image captioning, image classification, object recognition, etc.) and obtain a class of the image as a result of the classification, thereby obtaining at least one keyword. Alternatively, the electronic device (100) can cluster images by topic and obtain the topic of the image, thereby obtaining at least one keyword. Alternatively, the electronic device (100) can extract a text description of the image through image analysis and obtain at least one keyword from the text description.

[0066] At least one keyword can be acquired from information tagged to an image of an electronic device (100). The tag may include a word indicating the subject or class of the image. The tag may be automatically generated when the image is created (or captured). Alternatively, the tag may be manually entered by a user. For example, the electronic device (100) may provide a user interface for entering a tag for the image. The user interface may be provided through various applications (e.g., a camera application, a gallery application, a photo editing application).

[0067] In operation 230, the electronic device (100) can obtain a knowledge graph for the second user based on a plurality of keywords.

[0068] In one embodiment, a knowledge graph may be a network representation of information of interest between a first user and a second user. The knowledge graph may include nodes and edges. Nodes may correspond to the first user, the second user, and keywords, and edges may represent relationships between nodes. For example, the electronic device (100) may create a knowledge graph by connecting a keyword to the first user, the second user, or other keywords that have a relationship or association with the keyword. The knowledge graph may be replaced with other representations, such as an interest knowledge graph.

[0069] In one embodiment, the electronic device (100) can create a knowledge graph using keywords extracted from interaction data, a preset number of which is greater than or equal to a plurality of keywords.

[0070] For example, the electronic device (100) can identify the number of keywords extracted from the message content for each keyword, and generate a knowledge graph using only keywords that are extracted in a preset number or more among all keywords obtained from the message content. The preset number can be set during the manufacturing or initial use of the electronic device (100), or can be set and changed by user input. Accordingly, a knowledge graph can be generated based on keywords that are relatively frequently mentioned between the first user and the second user through messages during the interaction process and / or keywords related to content that are relatively frequently shared between the first user and the second user, and keywords that users are interested in can be reflected in the knowledge graph.

[0071] In operation 240, the electronic device (100) can identify content of interest of the second user based on an interest graph for the second user.

[0072] In one embodiment, the electronic device (100) can identify priorities of multiple keywords included in a knowledge graph for a second user.

[0073] The electronic device (100) can calculate scores of multiple keywords included in a knowledge graph for a second user.

[0074] For example, the electronic device (100) can identify the score of each keyword based on the number of each keyword extracted from the interaction data for each keyword. The electronic device (100) can assign a relatively high score to a keyword as the number of keywords increases, and can assign a relatively low score to a keyword as the number of keywords decreases. For example, the memory (120) can store a plurality of scores corresponding to a plurality of ranges. The memory (120) can store a score s1 corresponding to a range in which the number of keywords is greater than d1 and less than or equal to d2, a score s2 corresponding to a range in which the number of keywords is greater than d2 and less than or equal to d3, ..., a score s3 corresponding to a range in which the number of keywords is d n-1 larger than d n Score s corresponding to the range below n-1 can be stored. n is a natural number greater than 1, and d1 <d2<...<d n-1 <d n and s1 <s2<...<s n-1 The electronic device (100) can identify a range to which a number of keywords belong among multiple ranges, and identify a score corresponding to the range as the keyword score. However, the present disclosure is not limited thereto. For example, the electronic device (100) can assign a score to a keyword equal to the number of keywords.

[0075] The electronic device (100) can apply weights to the scores of multiple keywords and identify priorities of multiple keywords based on the scores of the multiple keywords to which the weights are applied.

[0076] For example, the electronic device (100) may apply a weight to the score of each of a plurality of keywords based on at least one of the user who transmitted the interaction data from which the keyword was extracted, the type of application that generated the interaction data from which the keyword was extracted, whether the user visited a location corresponding to the keyword, and the time point of sharing the interaction data from which the keyword was extracted. Applying a weight to the score may include adding the weight to the score. However, the present disclosure is not limited thereto, and applying a weight to the score may also include multiplying the score by the weight.

[0077] For example, the electronic device (100) can apply different weights to the score of a keyword depending on whether the user who transmitted the interaction data from which the keyword was extracted is the first user or the second user.

[0078] The person who transmitted the interaction data from which keywords are extracted may be the first user, the second user, or the first user and the second user. For example, if the user who transmitted the interaction data from which keywords are extracted is the first user, the electronic device (100) may apply a weight w1 to the score of the keyword. If the user who transmitted the interaction data from which keywords are extracted is the second user, the electronic device (100) may apply a weight w2 to the score of the keyword. If the users who transmitted the interaction data from which keywords are extracted are the first user and the second user, the electronic device (100) may apply a weight w3 to the score of the keyword. Here, w1 <w2<w3이다. 예를 들어, w1=1, w2=2, w3=3일 수 있으나, 본 개시는 이에 한정되는 것은 아니다. 인터렉션 과정에서 사용자들이 함께 언급한 키워드이거나, 함께 공유한 콘텐츠와 관련된 키워드이면, 해당 키워드에 대한 사용자들의 관심이 높은 것으로 볼 수 있다. 따라서, 키워드를 공유한 사용자가 제1 사용자 및 제2 사용자, 제2 사용자 또는 제1 사용자인지에 따라 순차적으로 높은 가중치가 키워드의 스코어에 적용될 수 있다.

[0079] For example, the electronic device (100) may apply different weights to the score of a keyword depending on the type of application that generated the interaction data from which the keyword was extracted.

[0080] An application that generates interaction data may include an application that generates message content transmitted to a counterpart through a communication application during an interaction between users. For example, a text message or voice message may be generated through a communication application, and an image or video may be generated through a camera application or a photo editing application. Additionally, a file may be generated through an application that can generate document files, memo files, etc. For example, if the application that generated the interaction data from which keywords were extracted is a first application (e.g., an application that can generate files that can be shared with the counterpart other than messages, images, or videos), the electronic device (100) may apply a weight w1 to the score of the keyword. If the application that generated the interaction data from which keywords were extracted is a second application (e.g., a communication application), the electronic device (100) may apply a weight w2 to the score of the keyword. If the application that generated the interaction data from which keywords were extracted is a third application (e.g., a camera application or a photo editing application), the electronic device (100) may apply a weight w3 to the score of the keyword. Here, w1 <w2<w3이다. 예를 들어, w1=1, w2=2, w3=3일 수 있으나, 본 개시는 이에 한정되는 것은 아니다. 인터렉션 과정에서 사용자가 메시지보다 이미지 또는 동영상을 상대방에게 전송한 것은 사용자가 해당 주제에 대해 관심이 높은 것으로 볼 수 있다. 따라서, 이미지 또는 동영상으로부터 추출된 키워드의 스코어에 가장 높은 가중치가 적용되고, 메시지로부터 추출된 키워드의 스코어에 다음으로 높은 가중치가 적용될 수 있다.

[0081] For example, the electronic device (100) may apply different weights to the keyword's score depending on whether a first user or a second user has visited a location corresponding to the keyword. For example, a location corresponding to the keyword may be a location whose name is the keyword.

[0082] The electronic device (100) can identify whether a user among the first user and the second user has visited a location corresponding to a keyword. For example, the electronic device (100) can analyze the content of messages exchanged between the first user and the second user using an artificial intelligence model to identify whether the first user and the second user have visited a location corresponding to the keyword. Alternatively, the electronic device (100) can analyze information tagged in an image to identify whether the first user and the second user have visited a location corresponding to the keyword. The information tagged in the image may include information about a person, a location, etc. The information tagged in the image may be automatically tagged when the image is generated or may be manually tagged by the user. Alternatively, the electronic device (100) can identify whether the first user and the second user have visited a location corresponding to the keyword based on schedule information. The schedule information may be input through a calendar application of the electronic device (100). The electronic device (100) can analyze the contents of the schedule information using an artificial intelligence model to identify whether the first user and the second user have visited a location corresponding to the keyword.

[0083] The electronic device (100) may apply a weight w1 to the score of the keyword if neither the first user nor the second user has visited the location corresponding to the keyword. If only the first user has visited the location corresponding to the keyword, the electronic device (100) may apply a weight w2 to the score of the keyword. If only the second user has visited the location corresponding to the keyword, the electronic device (100) may apply a weight w3 to the score of the keyword. If both the first user and the second user have visited the location corresponding to the keyword, the electronic device (100) may apply a weight w4 to the score of the keyword. Here, w1 <w2<w3<w4이다. 예를 들어, w1=1, w2=2, w3=3, w4=4일 수 있으나, 본 개시는 이에 한정되는 것은 아니다. 인터렉션 과정에서 사용자가 자신이 방문한 장소를 언급하거나, 그와 관련된 콘텐츠를 공유하면, 해당 장소에 대한 사용자의 관심이 높은 것으로 볼 수 있다. 따라서, 제1 사용자 및 제2 사용자가 모두 방문한 장소에 대응하는 키워드의 스코어에 가장 높은 가중치가 적용되고, 방문자가 제2 사용자, 제1 사용자인 순으로 순차적으로 높은 가중치가 키워드의 스코어에 적용될 수 있다.

[0084] For example, the electronic device (100) can apply different weights to the score of a keyword depending on the time point at which the interaction data from which the keyword is extracted is shared.

[0085] The time point at which the interaction data from which the keywords are extracted is shared may be the time point at which the first user transmits the message content to the second user or the time point at which the first user receives the message content from the second user. The electronic device (100) may apply a relatively higher weight to the keyword score as the time point at which the interaction data from which the keywords are extracted is closer to the present time point, and may apply a relatively lower weight to the keyword score as the time point at which the interaction data from which the keywords are extracted is farther away from the present time point. For example, the memory (120) may store a plurality of weights corresponding to a plurality of ranges. The electronic device (100) may identify a range to which the sharing time point of the interaction data belongs among the plurality of ranges, and apply a weight corresponding to the range to the keyword score. For example, if the sharing time point of the interaction data from which the keywords are extracted belongs to a first time range, the electronic device (100) may apply a weight w1 to the keyword score. The first time range may be from the present time point to a first time point (e.g., one year ago). If the time point of sharing of interaction data from which keywords are extracted falls within a second time range, the electronic device (100) may apply a weight w2 to the score of the keyword. The second time range may be a range from the current time point to within a first time point and prior to the second time point (e.g., within 1 year and prior to 6 months). If the time point of sharing of interaction data from which keywords are extracted falls within a third time range, the electronic device (100) may apply a weight w3 to the score of the keyword. The third time range may be a range from the current time point to within a second time point and prior to the third time point (e.g., within 6 months and prior to 1 month). If the time point of sharing of interaction data from which keywords are extracted falls within a fourth time range, the electronic device (100) may apply a weight w4 to the score of the keyword. The fourth time range may be a range from the current time point to within a third time point and prior to the fourth time point (e.g., within 1 month and prior to 2 weeks).The electronic device (100) may apply a weight w5 to the keyword score if the time point of sharing the interaction data from which the keyword is extracted falls within the fifth time range. The fifth time range may be within the fourth time range (e.g., within two weeks) from the current time. Here, w1 <w2<w3<w4<w5이다. 예를 들어, w1=1, w2=2, w3=3, w4=4, w5=5일 수 있으나, 본 개시는 이에 한정되는 것은 아니다. 인터렉션 과정에서 사용자들이 상대적으로 최근에 언급한 키워드 또는 공유한 콘텐츠와 관련된 키워드일수록 사용자들의 관심이 높은 것으로 볼 수 있다. 따라서, 키워드가 추출된 인터렉션 데이터의 공유 시점이 현재 시점에서 가까울수록 상대적으로 높은 가중치가 키워드의 스코어에 부여될 수 있다.

[0086] In the above example, the electronic device (100) is described as calculating the score of a keyword based on the number of keywords and applying various weights to the score, but the present disclosure is not limited thereto. For example, the electronic device (100) may calculate the score of each of a plurality of keywords based on at least one of the number of keywords, the user who transmitted the interaction data from which the keywords were extracted, the type of the application that generated the interaction data from which the keywords were extracted, whether the user visited a location corresponding to the keywords, and the time point of sharing the interaction data from which the keywords were extracted.

[0087] In one embodiment, the electronic device (100) can identify priorities of multiple keywords based on scores of the multiple keywords.

[0088] The electronic device (100) can identify the priority of each keyword based on multiple weighted scores. For example, the electronic device (100) can identify keywords with higher weighted scores as having higher priorities. However, the present disclosure is not limited thereto. For example, the electronic device (100) can identify keywords with higher scores as having higher priorities without applying weights.

[0089] In one embodiment, the electronic device (100) can identify a keyword of interest of a second user among a plurality of keywords based on the priorities of the plurality of keywords.

[0090] For example, the electronic device (100) may identify a preset number of keywords having a relatively high priority (or score) among a plurality of keywords as keywords of interest to the second user. The preset number may be set during the manufacturing or initial use of the electronic device (100), or may be set and changed by user input. However, the present disclosure is not limited thereto. For example, the electronic device (100) may also identify a keyword having a priority (or score) higher than a preset value among a plurality of keywords as keywords of interest to the second user. The preset value may be set during the manufacturing or initial use of the electronic device (100), or may be set and changed by user input.

[0091] In one embodiment, the electronic device (100) can identify content of interest of the second user based on keywords of interest of the second user.

[0092] For example, the electronic device (100) can search and retrieve content related to a keyword of interest of the second user among the contents stored in the memory (120). The contents stored in the memory (120) may include images and / or videos stored in the media storage of the electronic device (100).

[0093] For example, the electronic device (100) may search for at least one content that matches a keyword of interest. Alternatively, the electronic device (100) may search for at least one content among the contents stored in the electronic device (100) by referencing the keyword of interest. For example, the electronic device (100) may search for at least one content that matches a word (e.g., a synonym, an analogue, etc.) related to the keyword of interest. Alternatively, the electronic device (100) may search for content corresponding to the keyword of interest using metadata of the content. The metadata of the content may include, but is not limited to, the title, description, shooting location, shooting date, person information, location information, tags, etc. of the content. In addition, the metadata of the content may also include information about various objects included in the content. The information about the various objects included in the metadata of the content may be obtained by the electronic device (100) classifying the content, detecting objects within the content, and performing object recognition.

[0094] In operation 250, the electronic device (100) may display content of interest of the second user on the display (130).

[0095] In one embodiment, the electronic device (100) may display the content of interest of the second user on the display (130) while providing a user interface for interaction with the second user. The user interface may be a screen provided by a communication application. For example, when a conversation window for a first user to converse with a second user is displayed on the display (130), and a user input for displaying the content of interest of the second user is received, the electronic device (100) may display the content of interest of the second user at the bottom of the conversation window. However, the present disclosure is not limited thereto. For example, the electronic device (100) may display the content of interest of the second user in various locations along with the conversation window, or may stop displaying the conversation window and display the content of interest of the second user. When a user input for selecting the content of interest of the second user is received, the electronic device (100) may transmit the content of interest to the electronic device of the second user via a server using the communication circuit (140).

[0096] FIG. 3 is a diagram illustrating an example of an operation of an electronic device acquiring a keyword according to one embodiment.

[0097] Referring to FIG. 3, the electronic device (100) can execute a communication application and display a user interface (310) through the communication application.

[0098] In one embodiment, a communication application may provide a private chat service. For example, a first user and a second user may interact by conversing with each other in a private chat room. The first user may use a keyboard interface displayed on the electronic device (100) to input a message to be sent to the second user and select content to be sent to the second user. The electronic device (100) may use the communication circuit (140) to transmit the message and / or content to the second user's electronic device via a server. The electronic device (100) may also use the communication circuit (140) to receive the message and / or content transmitted by the second user from the second user's electronic device via the server.

[0099] The user interface (310) may display a conversation window (311) of a personal chat room. The conversation window (311) may display message content (e.g., text messages, images, etc.) exchanged between a first user and a second user in chronological order. The left area of ​​the conversation window (311) may display message content transmitted by the second user to the first user, and the right area of ​​the conversation window (311) may display message content transmitted by the first user to the second user.

[0100] In one embodiment, the electronic device (100) can obtain multiple keywords from interaction data including message content.

[0101] For example, referring to FIG. 3, the electronic device (100) can obtain keywords (320) of “Jennifer,” “Sophia,” “picture,” and “health” from messages (e.g., text messages) exchanged between a first user and a second user (e.g., user 2). In addition, the electronic device (100) can obtain keywords (332) of “family” and “picture” from an image (331) transmitted by the first user to the second user, and can obtain keyword (334) of “picture” from an image (333) transmitted by the first user to the second user.

[0102] FIG. 4 illustrates an example of a knowledge graph for a second user generated by an electronic device according to one embodiment.

[0103] Referring to FIG. 4, a knowledge graph (410) for a second user may be generated based on a plurality of keywords (e.g., family, health, picture, kindergarten, Sophia, our grandchild, daughters, picture, Jennifer, school) obtained from message contents exchanged between a first user (e.g., user 1) and a second user (e.g., user 2) through a communication application. The electronic device (100) may analyze the user who transmitted the message contents, the contents and / or context of the message contents, etc., to identify correlations between users and keywords, and may connect nodes (441, 442, 443, 444, 445, 446, 447, 448, 449, 451) corresponding to keywords associated between a node (420) corresponding to the first user and a node (430) corresponding to the second user to generate the knowledge graph (410).

[0104] In some embodiments, the electronic device (100) may generate a knowledge graph for a second user using location information related to message content. For example, the electronic device (100) may obtain a plurality of keywords from the message content and location information related to the message content, and generate a knowledge graph for the second user based on the plurality of keywords. For example, the electronic device (100) may analyze the content and / or context of a message (e.g., a text message, a voice message) using an artificial intelligence model to obtain keywords indicating a location from the message content. Alternatively, the electronic device (100) may obtain keywords indicating a location from location information tagged to content (e.g., an image, a video). Alternatively, the electronic device (100) may obtain a location where the content was created (or photographed) based on metadata of the content, and thereby obtain keywords indicating a location.

[0105] FIG. 5 illustrates an example of a knowledge graph for a second user generated by an electronic device according to one embodiment. Comparing the knowledge graph (510) illustrated in FIG. 5 with the knowledge graph (410) illustrated in FIG. 4 , nodes (511, 512, 153) corresponding to location-related keywords such as "United States," "Seoul," and "Sydney" may be further added to the knowledge graph (510).

[0106] FIGS. 6A and 6B illustrate an example of an operation of an electronic device recommending content of interest to a second user according to one embodiment.

[0107] Referring to 601 of FIG. 6A, the electronic device (100) may display a user interface (610) provided by a communication application. The user interface (610) may display a conversation window (611) for interaction between a first user and a second user (e.g., user 2).

[0108] Referring to 601 and 602 of FIG. 6A, when a user input of touching a gallery button (612) displayed on a user interface (610) is received, the electronic device (100) may display keywords of interest (e.g., “Sophia,” “Jennifer,” “health,” “travel”) (621) of the second user acquired based on a knowledge graph for the second user and contents of interest (622) corresponding to the keywords of interest (621). At least some of the searched contents of interest may be displayed, and the remaining contents may be displayed according to a touch input (e.g., scroll). When a user input of touching at least one of the contents of interest (622) and touching a transmit button is received, the electronic device (100) may transmit the selected contents to the electronic device of the second user through a server using the communication circuit (140) and display the selected contents in a chat window (611).

[0109] Referring to 602 and 603 of FIG. 6B , when a user input is received to select only the keyword of interest "travel" from among the keywords of interest (611), the electronic device (100) may display content of interest (632) corresponding to the keyword of interest "travel." For example, when the keywords of interest (621) are selected, the user input for selecting the keyword of interest "travel" may include a user input for deselecting the keywords of interest "Sophia," "Jennifer," and "health" by touching them. However, the present disclosure is not limited thereto. For example, the user input for selecting only the keyword of interest "travel" may also include a user input for touching the keyword of interest "travel."

[0110] FIG. 7 illustrates an example of an operation in which an electronic device recommends content of interest to a second user according to one embodiment.

[0111] Referring to 701 and 702 of FIG. 7, the electronic device (100) may display a user interface (710) provided by a communication application. The electronic device (100) may use messages exchanged between a first user and a second user (e.g., user 3) to identify that the second user's keyword of interest is "plant," and may display a button (721) for providing interest content corresponding to "plant" in a dialog box (711) of the user interface (710). For example,

[0112] Referring to 702 and 703 of FIG. 7, when a user input of touching a button (721) is received, the electronic device (100) can search for contents corresponding to “plants” among contents stored in the media storage of the electronic device (100) and display the searched contents of interest (731).

[0113] In one embodiment, the electronic device (100) can identify common interest keywords of a plurality of second users based on a knowledge graph for the plurality of second users included in the group.

[0114] For example, a first user and multiple second users can interact by conversing with each other in a group chat room using a communication application. The multiple second users included in the group may be users included in the group chat room with the first user.

[0115] The electronic device (100) can acquire a knowledge graph for each second user based on interaction data between the first user and each second user. The interaction data can be acquired from message content exchanged between the first user and the second user in a personal chat room or message content exchanged between the first user and the second user in a group chat room. Alternatively, the interaction data can also be acquired from message content exchanged between the first user and the second user in a personal chat room or a group chat room. Meanwhile, since the method of generating a knowledge graph using multiple keywords acquired from the interaction data and acquiring keywords of interest based on the knowledge graph has been described above, a repeated description will be omitted for the sake of brevity.

[0116] The electronic device (100) can identify common keywords of interest among keywords of interest between the first user and each second user. For example, the electronic device (100) can identify keywords of interest that are identical and / or related to each other (e.g., synonyms, similar words, etc.) among keywords of interest between the first user and each second user as common keywords of interest.

[0117] In one embodiment, the electronic device (100) may identify a second user having a common interest keyword of a plurality of second users included in the group as an interest keyword, and display a user interface on the display (130) for adding the second user to the group.

[0118] As mentioned above, the multiple second users included in the group may be users included in the group chat room together with the first user.

[0119] For example, the second user may be a user who has not participated in a group chat room corresponding to the group. The electronic device (100) may identify a second user who has a common interest keyword of the group as an interest keyword among the users who have not participated in the group chat room corresponding to the group. The second user having a common interest keyword as an interest keyword may include that the second user's interest keyword is identical to the common interest keyword, or that the second user's interest keyword is a keyword related to the common interest keyword (e.g., a synonym, an analogue, etc.). Meanwhile, since the method for acquiring the second user's interest keyword has been described above, a repeated description will be omitted for the sake of brevity.

[0120] The electronic device (100) may display a user interface on the display (130) for adding a second user to a group. For example, the electronic device (100) may display information about the second user (e.g., a name or image), and when a user input for selecting the second user is received, the electronic device (100) may add the second user to the group through a communication application.

[0121] FIG. 8 illustrates an example of an operation in which an electronic device recommends a second user corresponding to a group according to one embodiment.

[0122] Referring to FIG. 8, the electronic device (100) can display a user interface (801) for creating a group chat room through a communication application.

[0123] For example, the user interface (801) may display an interface element (811) for setting a name and image of a group chat room. For example, if a first user touches the interface element (811) and inputs “Group 1” using a keyboard interface, the electronic device (100) may set “Group 1” as the name of the group chat room and display “Group 1” on the interface element (811). In addition, if the first user touches the interface element (811) and selects one of the images stored in the electronic device (100), the electronic device (100) may set the image as the image of the group chat room and display the image on the interface element (811). The first user may select users to participate in the group chat room through the user interface (801). When users to participate in a group chat room are selected, information (e.g., name, image, etc.) (821) of the users participating in the group chat room, such as “Me,” “User 2,” and “User 3,” may be displayed on the user interface (801).

[0124] For example, the electronic device (100) may identify common interest keywords of “User 2” and “User 3” based on the interest keywords of “User 2” and “User 3” who participated in the group chat room, and display common interest keywords (831) of “dessert,” “wine,” and “pasta” on the user interface (801).

[0125] For example, the electronic device (100) may identify "User 4", "User 5", and "User 6" who have common interest keywords (831) of "dessert", "wine", and "pasta" as interest keywords among users who have not participated in the group chat room, and display information (e.g., name, image, etc.) (841) about "User 4", "User 5", and "User 6" on the user interface (801). When a user input for adding at least one of "User 4", "User 5", and "User 6" to the group chat room is received, the electronic device (100) may allow the selected user to participate in the group chat room.

[0126] Meanwhile, in the above-described example, the electronic device (100) was described as recommending a second user corresponding to the group during the process of creating a group chat room. However, the present disclosure is not limited thereto. After the group chat room is completed, the electronic device (100) may display a user interface for recommending a second user corresponding to the group. For example, the electronic device (100) may display a button on a user interface including a conversation window of the group chat room. When a user input touching the button is received, the electronic device (100) may display a user interface for adding a second user whose interest keyword is a common interest keyword of the users participating in the group chat room to the group.

[0127] In one embodiment, the electronic device (100) may identify common interest keywords of a plurality of second users based on knowledge graphs of a plurality of second users included in a group, and display common interest content for the plurality of second users on the display (130) based on the common interest keywords of the plurality of second users.

[0128] As previously mentioned, the multiple second users included in the group may be users included in the group chat room with the first user. Meanwhile, the method for identifying common keywords of interest among multiple second users included in the group has been previously described, so a repetitive description will be omitted for brevity.

[0129] For example, the electronic device (100) may search for content related to common interest keywords of multiple second users among the content stored in the memory (120) and display a user interface including the searched common interest content. Meanwhile, since the method of searching for content using keywords has been described above, a repeated description will be omitted for brevity.

[0130] For example, when a user input for selecting at least one of common interest contents is received, the electronic device (100) may use the communication circuit (140) to transmit the selected contents to the electronic devices of each of the plurality of second users included in the group through the server, and display the selected contents in the conversation window of the group chat room.

[0131] FIG. 9 illustrates an example of an operation in which an electronic device recommends common interest content corresponding to a group according to one embodiment.

[0132] Referring to FIG. 9, the electronic device (100) may display a user interface (901) including content of common interest for a group through a communication application. For example, the electronic device (100) may display a button on a user interface including a conversation window of a group chat room, and upon receiving a user input touching the button, may display the user interface (901) including content of common interest for the group.

[0133] Information about the group chat room (e.g., name, image, etc.) (911), information about users participating in the group chat room (e.g., “me”, “user 2”, “user 3”, “user 4”) (e.g., name, image, etc.) (921), and common interest keywords of users participating in the group chat room (e.g., wine, cafe, travel, Friday) (931) may be displayed on the user interface (901).

[0134] The electronic device (100) can search for content corresponding to common interest keywords (931) such as “wine,” “cafe,” “travel,” and “Friday” among the content stored in the memory (120), and display the searched content (941) on the user interface (901). For example, the electronic device (100) can display the searched content (941) by categorizing it by topic.

[0135] In the above example, the electronic device (100) is described as providing content of interest to a second user who interacts with the first user through a communication application, but the present disclosure is not limited thereto.

[0136] In one embodiment, when content is selected, the electronic device (100) may display a user interface on the display (130) that recommends a second user related to the content based on a knowledge graph for a plurality of second users.

[0137] The electronic device (100) can display contents stored in the memory (120) on the display (130) and receive a user input for selecting at least one content from among the contents. For example, the contents stored in the memory (120) can include images and / or videos stored in the media storage of the electronic device (100).

[0138] The electronic device (100) may identify a second user having a keyword of interest corresponding to the selected content based on a knowledge graph for a plurality of second users. For example, the electronic device (100) may identify a keyword of interest of each of the plurality of second users based on the knowledge graph for each of the plurality of second users, and may identify a second user having a keyword corresponding to the selected content as a keyword of interest. The keyword corresponding to the content may be obtained through image analysis of the content, or may be obtained from information tagged to the content. The second user having a keyword of interest corresponding to the content may include that the second user's keyword of interest is identical to the keyword corresponding to the content, or that the second user's keyword of interest is a keyword related to the keyword corresponding to the content (e.g., a synonym, an analogue, etc.).

[0139] The electronic device (100) may display a user interface recommending a second user on the display (130). For example, the electronic device (100) may display information about the second user (e.g., name, image, etc.). Upon receiving a user input selecting the second user, the electronic device (100) may transmit content to the second user's electronic device via a communication application and display a user interface for interaction with the second user. For example, the content transmitted to the second user may be displayed in a dialog box of the user interface.

[0140] FIG. 10 illustrates an example of an operation in which an electronic device recommends a second user related to content according to one embodiment.

[0141] Referring to 1001 of FIG. 10, the electronic device (100) can display content (1010) stored in the memory (120) through a gallery application. At least some of the content stored in the memory (120) can be displayed, and the remaining content can be displayed according to a touch input (e.g., scroll).

[0142] Referring to 1001 and 1002 of FIG. 10, when at least some of the contents (1010) are selected, the electronic device (100) can identify "User 2", "User 3", "User 4", and "Group 1" that have keywords corresponding to the selected contents (1021, 1022, 1023) as keywords of interest, and display information (e.g., names, images, etc.) (1030) about "User 2", "User 3", "User 4", and "Group 1". "User 2", "User 3", and "User 4" are second users that have keywords related to the contents (1021, 1022, 1023) as keywords of interest, and "Group 1" can be a group that has keywords related to the contents (1021, 1022, 1023) as common keywords of interest.

[0143] For example, when a user input touching "User 2" among "User 2", "User 3", and "User 4" is received, the electronic device (100) may transmit content (1021, 1022, 1023) to the electronic device of "User 2" through a communication application and display a user interface including a chat window for interaction with "User 2". The chat window may display content (1021, 1022, 1023).

[0144] For example, when a user input touching "Group 1" is received, the electronic device (100) may transmit content (1021, 1022, 1023) to the electronic devices of each user participating in "Group 1" through a communication application and display a user interface including a dialogue window for interaction with the users participating in "Group 1". The dialogue window may display content (1021, 1022, 1023).

[0145] In the present disclosure, the artificial intelligence model may be implemented in the form of an on-device, included in the electronic device (100). Alternatively, the artificial intelligence model may be stored in an external electronic device (e.g., a server) connected to the electronic device (100). If the artificial intelligence model is stored in the server, the electronic device (100) may communicate with the server via the communication circuit (140) to utilize the artificial intelligence model.

[0146] According to the embodiments of the present disclosure as described above, the electronic device (100) can identify content that is expected to be of interest to the second user based on interactions between the first user and the second user, and provide the first user with a user interface that allows the first user to share the content with the second user. In this way, the electronic device (100) can recommend content of interest to the second user to the first user for sharing with the second user. Accordingly, the burden of searching and selecting content for the first user can be reduced, and effective content sharing can be enabled.

[0147] Various embodiments of the present document may be implemented as software including one or more instructions stored in a storage medium (e.g., memory (120)) readable by a machine (e.g., electronic device (100)). For example, a processor (e.g., processor (110)) of the machine (e.g., electronic device (100)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0148] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). ™) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0149] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0150] Although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person having ordinary skill in the art to which the present disclosure pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present disclosure.

Claims

1. In electronic devices, display; memory that stores instructions; and At least one processor comprising processing circuitry; The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Obtaining interaction data between the first user and the second user based on an interaction performed by the first user of the electronic device with the second user using the electronic device; Obtain multiple keywords based on the above interaction data, Obtaining a knowledge graph for the second user based on the plurality of keywords, Identifying content of interest of the second user based on the above knowledge graph, An electronic device that displays the content of interest on the display.

2. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Identify the priorities of the plurality of keywords included in the above knowledge graph, Identifying the keyword of interest of the second user among the plurality of keywords based on the above priority, An electronic device that identifies the content of interest corresponding to the keyword of interest.

3. In paragraph 2, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Identify the score of each keyword based on the number of each keyword extracted from the above interaction data, For each of the keywords, a weight is applied to the score of each of the plurality of keywords based on at least one of the user who transmitted the interaction data from which the keyword was extracted, the type of application that generated the interaction data from which the keyword was extracted, whether the user visited a place corresponding to the keyword, and the time point of sharing the interaction data from which the keyword was extracted. An electronic device that identifies priorities of the plurality of keywords based on the plurality of scores to which the weights are applied.

4. In paragraph 3, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that applies different weights to the score of the keyword depending on whether the user who transmitted the interaction data from which the keyword was extracted is the first user or the second user.

5. In paragraph 3, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that applies different weights to the score of the keyword depending on the type of application that generated the interaction data from which the keyword was extracted.

6. In paragraph 3, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that applies different weights to the score of a keyword depending on whether a user among the first user and the second user has visited a place corresponding to the keyword.

7. In paragraph 3, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that applies different weights to the score of a keyword depending on the time point at which the interaction data from which the keyword is extracted is shared.

8. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that displays content of interest for the second user on the display while providing a user interface for interaction with the second user.

9. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that, when content is selected, displays a user interface on the display that recommends a second user related to the content based on a knowledge graph for a plurality of second users.

10. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Identifying common interest keywords of multiple second users based on a knowledge graph of multiple second users included in the group, An electronic device that displays a user interface on the display for adding a second user having the common interest keyword as an interest keyword to the group.

11. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Identifying common interest keywords of multiple second users based on the knowledge graph of each of the multiple second users included in the group, An electronic device that displays common interest content for a plurality of second users on the display based on common keywords of the plurality of second users.

12. In a method for recommending content for an electronic device, An operation of obtaining interaction data between a first user and a second user based on an interaction performed by a first user of the electronic device with a second user using the electronic device; An operation of obtaining multiple keywords based on the above interaction data; An operation of obtaining a knowledge graph for the second user based on the plurality of keywords; An operation of identifying content of interest of the second user based on the knowledge graph; and A content recommendation method, comprising: an action of displaying the above content of interest.

13. In paragraph 12, The above identifying action is, An operation of identifying the priorities of the plurality of keywords included in the above knowledge graph; An operation of identifying a keyword of interest of the second user among the plurality of keywords based on the above priorities; and A content recommendation method, comprising: an operation of identifying the content of interest corresponding to the keyword of interest.

14. In paragraph 13, The action of identifying the above priorities is: An operation of identifying a score of each keyword based on the number of each keyword extracted from the interaction data; An operation of applying a weight to the score of each of the plurality of keywords based on at least one of the user who transmitted the interaction data from which the keyword was extracted, the type of application that generated the interaction data from which the keyword was extracted, whether the user visited a place corresponding to the keyword, and the time point of sharing the interaction data from which the keyword was extracted, for each of the keywords; and A content recommendation method, comprising: an operation of identifying priorities of the plurality of keywords based on the plurality of scores to which the weights are applied.

15. In paragraph 14, The action of applying the above weights is: A content recommendation method, comprising: an operation of applying different weights to the score of the keyword depending on whether the user who transmitted the interaction data from which the keyword was extracted is the first user or the second user.

Images