Electronic device, method for providing speech balloon function including message thereof, and recording medium thereof

Abstract

An electronic device according to an embodiment may comprise: a display; a processor; and a memory for storing instructions executable by the processor, wherein the instructions cause the electronic device to: receive text input in a message input window; transmit the input text as an input value of an artificial intelligence engine to obtain at least one first recommended emoji optimized for the text from the artificial intelligence engine; and display, on at least a portion of the display, a first message in which the obtained at least one first recommended emoji is disposed on the outer border of a speech balloon including the text.

Description

Method for providing speech bubble function including electronic device and message thereof, recording medium thereof The present disclosure relates to an electronic device and a method for providing a speech bubble function including a message thereof, and a recording medium thereof. Electronic devices can provide message services such as SMS (short message service) or MMS (multimedia message service) that allow users to send messages to other parties. Recently, message services based on RCS (rich communication service) are being supported, which can replace legacy services such as SMS or MMS. RCS is a data-based next-generation text messaging standardized by the GSMA (Global System for Mobile Communications Association). Compared to legacy services such as SMS or MMS, it has various advantages such as increased message length, provision of read receipt function, and ease of integration with other applications, and is being widely used. Meanwhile, the message service of electronic devices can transmit not only text but also pictures or videos. In addition, the message service supports not only emoticons that express emotions with a combination of texts, but also emojis that are expressed as one image or multiple image frames. Users can effectively convey their intentions or emotional states by using emojis. The above information may be provided as related art for the purpose of assisting in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art related to the present disclosure. When it comes to sending messages on electronic devices, the methods of expression can be seen as limited, such as sending text or sending emojis / emoticons. Accordingly, there may be a need for a variety of expression methods that can convey fun and emotion to users within the chat window that provides the message service. The problem to be solved in the present disclosure is not limited to the problem mentioned above, and may be expanded in various ways without departing from the spirit and scope of the present disclosure. An electronic device according to one embodiment may include a display, a processor, and a memory storing instructions executable by the processor. The instructions according to one embodiment may cause the electronic device to receive a text input into a message input window. The instructions according to one embodiment may cause the electronic device to transmit the input text as an input value of an artificial intelligence engine to obtain at least one first recommended emoji optimized for the text. The instructions according to one embodiment may cause the electronic device to display a first message, in which the obtained at least one first recommended emoji is arranged around a speech bubble including the text, on at least a part of the display. A method for providing a message speech bubble function of an electronic device according to one embodiment may include an operation of receiving a text input into a message input window. The method according to one embodiment may include an operation of transmitting the input text as an input value of an artificial intelligence engine and obtaining at least one first recommended emoji optimized for the text from the artificial intelligence engine. The method according to one embodiment may include an operation of displaying a first message, in which the obtained at least one first recommended emoji is arranged around an outer perimeter of the speech bubble including the text, on at least a portion of the display. A non-transitory computer-readable medium storing instructions according to one embodiment may include instructions that, when executed by a processor of an electronic device, cause an operation to be performed: receiving a text input into a message input window. The computer-readable medium according to one embodiment may include instructions that cause an operation to be performed: transmitting the input text as an input value of an artificial intelligence engine; and obtaining at least one first recommended emoji optimized for the text from the artificial intelligence engine. The computer-readable medium according to one embodiment may include instructions that cause an operation to be performed: displaying a first message, in which the obtained at least one first recommended emoji is arranged around an outer periphery of a speech bubble including the text, on at least a portion of the display. An electronic device according to one embodiment may include a computer-readable recording medium having recorded thereon a program for implementing a method for providing a speech bubble function including a message. Electronic devices, methods and recording media according to various embodiments can automatically recommend emojis that can decorate a speech bubble based on emotions and keywords appearing in a message text based on generative AI (e.g., generative AI), and send a message speech bubble decoration effect together with the message, thereby reflecting the user's emotions in the speech bubble as well as providing fun. The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be variously expanded from the description below to a person having ordinary skill in the art to which the present disclosure belongs, without departing from the spirit and scope of the present disclosure. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. FIG. 1A is a block diagram of an electronic device within a network environment according to one embodiment. FIG. 1b illustrates a generative artificial intelligence (AI) system according to one embodiment. FIGS. 2A and 2B illustrate a method for providing a message bubble function of an electronic device according to one embodiment. FIG. 3 is a diagram for explaining a processing method of an emoji recommendation engine according to one embodiment. FIGS. 4A and 4B illustrate screens providing a message bubble function of an electronic device according to one embodiment. FIGS. 5 and 6 illustrate drawings for explaining automatic emoji placement and effect application of speech bubble decoration according to one embodiment. FIG. 7 illustrates screens providing a speech bubble function of an electronic device according to one embodiment. FIG. 8 illustrates a method for providing a speech bubble function of an electronic device according to one embodiment. FIG. 9 illustrates examples of transmitted and received messages to which speech bubble decoration effects are applied by an electronic device according to one embodiment. FIG. 10 illustrates screens providing a speech bubble function of an electronic device according to one embodiment. FIGS. 11A and 11B illustrate screens providing a speech bubble function of an electronic device according to one embodiment. The electronic device according to the embodiments disclosed in this document may be a variety of devices. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a home appliance device. The electronic device according to the embodiments of this document is not limited to the above-described devices. FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment. Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)). The processor (120) may control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing, for example, software (e.g., a program (140)), and may perform various data processing or calculations. According to one embodiment, as at least a part of the data processing or calculations, the processor (120) may store a command or data received from another component (e.g., a sensor module (176) or a communication module (190)) in the volatile memory (132), process the command or data stored in the volatile memory (132), and store result data in the nonvolatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphic processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together therewith. For example, if the electronic device (101) includes a main processor (121) and a secondary processor (123), the secondary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a given function. The secondary processor (123) may be implemented separately from the main processor (121) or as a part thereof. The auxiliary processor (123) may control at least a portion of functions or states associated with at least one of the components of the electronic device (101) (e.g., the display module (160), the sensor module (176), or the communication module (190)), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing device) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. Such learning may be performed, for example, in the electronic device (101) on which artificial intelligence is performed, or may be performed through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to or as an alternative to a hardware structure, the artificial intelligence model may include a software structure. The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or nonvolatile memory (134). The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146). The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen). The audio output module (155) can output an audio signal to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes such as multimedia playback or recording playback. The receiver can be used to receive an incoming call. According to one embodiment, the receiver can be implemented separately from the speaker or as a part thereof. The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) can include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) can include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch. The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can obtain sound through an input module (150), or output sound through an audio output module (155), or an external electronic device (e.g., an electronic device (102)) (e.g., a speaker or a headphone) directly or wirelessly connected to the electronic device (101). The sensor module (176) can detect an operating state (e.g., power or temperature) of the electronic device (101) or an external environmental state (e.g., user state) and generate an electric signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor. The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface. The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., the electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector). The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that a user can perceive through a tactile or kinesthetic sense. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device. The camera module (180) can capture still images and moving images. According to one embodiment, the camera module (180) can include one or more lenses, image sensors, image signal processors, or flashes. The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC). The battery (189) can power at least one component of the electronic device (101). In one embodiment, the battery (189) can include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell. The communication module (190) may support establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., the electronic device (102), the electronic device (104), or the server (108)), and performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., the application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module or a power line communication module). Among these communication modules, a corresponding communication module may communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) may use subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196) to identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199). The wireless communication module (192) can support a 5G network and next-generation communication technology after a 4G network, for example, NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), terminal power minimization and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) may support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) may support various requirements specified in an electronic device (101), an external electronic device (e.g., an electronic device (104)), or a network system (e.g., a second network (199)). According to one embodiment, the wireless communication module (192) may support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL) each, or 1 ms or less for round trip) for URLLC realization. The antenna module (197) can transmit or receive signals or power to or from the outside (e.g., an external electronic device). According to one embodiment, the antenna module (197) can include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) can include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), can be selected from the plurality of antennas by, for example, the communication module (190). A signal or power can be transmitted or received between the communication module (190) and the external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) can be additionally formed as a part of the antenna module (197). In one embodiment, the antenna module (197) can form a mmWave antenna module. In one embodiment, the mmWave antenna module can include a printed circuit board, an RFIC positioned on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) positioned on or adjacent a second side (e.g., a top side or a side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band. At least some of the above components may be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, a general purpose input and output (GPIO), a serial peripheral interface (SPI), or a mobile industry processor interface (MIPI)). In one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). In one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform at least a part of the function or service. One or more external electronic devices that have received the request may execute at least a part of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a part of a response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide an ultra-low latency service by using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an IoT (Internet of Things) device. The server (108) may be an intelligent server using machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology. An electronic device (101) according to one embodiment may support a generative artificial intelligence (AI) (or on-device AI) function / service. The generative AI function may refer to a technology that generates new content based on previously learned data and can generate a new form of AI content by utilizing given input data or information. Here, the AI content may refer to content (e.g., emoji, image, video, audio, or text) that is entirely generated (or reconstructed / edited) or partially generated (or reconstructed / edited) based on the generative AI. An electronic device (101) according to one embodiment may support a generative AI function (or AI service) in conjunction with a server (108). At least one of the electronic device (101) or the server (108) according to one embodiment may include a configuration of a generative AI system as illustrated in FIG. 1b. For example, FIG. 1b illustrates a configuration of a generative AI system according to one embodiment. As illustrated in FIG. 1b, the generative AI system may include a user interface (10100), an AI framework (10200), a generative AI model (10300), an application and service component (10400), and a database component (10500). A user interface (e.g., a user query / response interface) (10100) according to one embodiment may receive a user query. The user query input may be in the form of natural language, an image, and a video. The user interface (10100) may transmit not only data regarding the user query input, but also context information to the AI framework (10200). The context information may include various additional information at the time of user input. In addition, the user query input may also be in a form in which the above-described natural language, image, sound, and context information are mixed. In addition, the user query input may also be in a non-natural language form that does not generate natural language, such as a menu selection (e.g., a creation request or a modification request). The user interface (10100) may output the results of a generative artificial intelligence system to the user. The output may be in the form of natural language or a specific content, and may also be provided in the form of an action requested by the user. An AI framework (10200) according to one embodiment may receive a user query input, and may coordinate and control each component necessary to perform a user's intention based on the user's query input. The AI framework (10200) may include a prompt design component (10210), an application and plug-in management component (APIs / Plugins Management component (10230), and an output modification component (10250). A user query or action entered in a user interface (10100) according to one embodiment may be sent to a prompt design component (10210). The prompt design component (10210) may be used to generate prompts suitable for input into a large language model (LLM) or large multimodal models (LMM). The prompt design component (10210) may be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (10210) may access a database component (10500) (e.g., a knowledge component) containing user preference data, a prompt library, and prompt examples to generate the prompts and pass them to the large language model (LLM) or large multimodal models (LMM). The application and plug-in management component (10230) according to one embodiment may communicate with external information when there is a request for additional information when transmitting user input as an input of a generative model. The application and plug-in management component (10230) establishes a channel that can communicate with the outside of the application and service component (10400) (e.g., AI Interface) through an application programming interface (API), thereby enabling access to various data sources. In addition, the application and plug-in management component (10230) may request an action to perform a user query in the end, rather than an intermediate result, through the API when the action needs to be performed in the application or service. Information acquired from the outside may be transmitted as an input of the generative model together with the user input. An output modification component (10250) according to one embodiment can fine-tune the output result from a generative model. For example, the output modification component (10250) can verify whether the content generated through a language model (LLM) or a large-scale multi-modal model (LMM) is irrelevant, biased, or harmful. In addition, the output modification component (10250) can determine to what extent it matches a result desired by a user and, if necessary, can proceed with the additional process. Additionally, the output modification component (10250) can configure a hint to avoid unwanted output and provide it to the user. A generative AI model (10300) according to one embodiment generally refers to an artificial intelligence neural network that creates new types of data based on user input information. A model that generates an image may typically include a generative adversarial network (GAN) and a variational auto encoder (VAE). For example, a generative AI model may be a Diffusion-based generative model that uses a VAE and a Transformer structure. In addition, a model that generates language may refer to a model that is trained to output the most appropriate output value statistically based on an input value. Among generative AI models (10300), a model that generates language may be, for example, a model such as CHAT-GPT 3 or CHAT-GPT 4. As another example, a large multimodal model (LMM) may be a model that recognizes various types of data input such as text, images, and voices and generates new data corresponding thereto. An electronic device (101) according to one embodiment may generate a recommended emoji using an AI model different from the generative AI model illustrated in FIG. 1b and support a speech bubble decoration function related to the recommended emoji. According to one embodiment, the memory (130) may store instructions executable by the processor (120) or the electronic device (101). Such instructions may include arithmetic and logical operations, data movement, or control commands such as input / output that may be processed by the processor (120). According to one embodiment, the processor (120) may be operatively, functionally, and / or electrically connected to the display module (160) (e.g., a touchscreen display), and / or the memory (130). The processor (120) may be configured to perform operations or data processing related to control and / or communication of each component of the electronic device (101), and may be formed of one or more processors. The operations and data processing functions that the processor (120) may implement on the electronic device (201) are not limited, but in the present disclosure, various operations related to the speech bubble function or the speech bubble decoration service may be processed. An electronic device (101) according to one embodiment may be implemented to provide AI service functions using a part of the AI system of FIG. 1b, but is not limited thereto. An electronic device (101) according to one embodiment can provide an AI service function using an AI model implemented in relation to a recommended emoji. An electronic device (101) according to one embodiment may include a display (e.g., a display module (160)), a processor (120), and a memory (130) that stores instructions executable by the processor (120). The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to receive text input into a message input window. The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to determine a number of recommended emojis based on a speech bubble width according to a number of characters of the text. The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to transmit the input text as an input value of an artificial intelligence engine to obtain at least one first recommended emoji optimized for the text. The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to display a first message in which the obtained at least one first recommended emoji is arranged around a speech bubble including the text, on at least a portion of the display. Instructions according to one embodiment may cause an electronic device (101) or a processor (120) to display a first UI (user interface) screen including the message input window and the conversation window on the display, display a speech bubble decoration window on at least a portion of the first UI screen based on the text being received in the message input window, and display the first message and message transmission items in the message decoration window. An electronic device (101) according to one embodiment further includes a communication circuit (e.g., a communication module (190)), and the instructions may cause the electronic device (101) or the processor (120) to transmit, to a counterpart electronic device, speech bubble decoration data including at least one first recommended emoji placed around the speech bubble in the text through the communication circuit based on an input of selecting the message transmission item, and to display the first message in the chat window. According to one embodiment, the artificial intelligence engine may include an emoji recommendation engine based on generative artificial intelligence. Instructions according to one embodiment may cause the electronic device (101) or the processor (120) to extract a new word keyword for an input sentence corresponding to the text, convert the new word keyword into a substitute word, delete at least one of a profanity and a specific type of word in the input sentence to obtain a filtered text, and transmit at least one of a first criterion value for determining the appropriateness of an object emoji, a second criterion value for determining the appropriateness of an emotion emoji, and a number of emoji requests determined based on a speech bubble width of the first message as an input value of the artificial intelligence engine. According to one embodiment, the neologism keyword, the substitute word, the vulgar word and the specific type of word may be characterized as being preset. Instructions according to one embodiment may be characterized in that the electronic device (101) or the processor (120) obtains at least one first recommended emoji, the instructions including obtaining at least one first emoji from the artificial intelligence engine, obtaining at least one second emoji corresponding to a new word keyword extracted in an input sentence corresponding to the text, and combining the first emoji and the second emoji to obtain the at least one first recommended emoji. Instructions according to one embodiment may be characterized by causing the electronic device (101) or the processor (120) to display the first message on at least a portion of the display, wherein a decoration pattern for placing an emoji on an outer periphery of the speech bubble is determined based on a score of the at least one first recommended emoji, and the at least one first recommended emoji is displayed on the outer periphery of the speech bubble based on a number of emojis, an emoji text size, an emoji placement, and an emoji position defined in the determined decoration pattern. Instructions according to one embodiment may cause the electronic device (101) or the processor (120) to display an additional refresh item in the message decoration window, and in response to a user input selecting the refresh item, to drive the artificial intelligence engine to obtain at least one second recommended emoji and to display a first message converted into the second recommended emoji instead of the first recommended emoji around a speech bubble including the text. In the description of the electronic device (101) according to the embodiments of the present invention disclosed below, components that are substantially the same as the configuration disclosed in FIG. 1 described above are given the same reference numbers, and redundant descriptions of their functions may be omitted. An electronic device (101) according to one embodiment may support a message / chat function that transmits a message (conversation) entered in an input window to an electronic device of the other party, receives a message transmitted from the electronic device of the other party, and outputs the transmitted messages in chronological order in a chat window. The electronic device (101) may display a user interface (UI) including a chat window and an input window on a display in response to execution of a message function (e.g., execution of a message / chat application). When a transmission request is detected from a user who has entered a message (e.g., a text message, a character string) in the input window, the electronic device (101) may transmit the message entered in the input window to the other party and output the transmitted message in the chat window at the same time. The messages (e.g., text messages, character strings) output in the chat window may be included in each speech bubble (or text bubble, text box) so that the transmitted and received messages can be distinguished from each other. The output of a speech bubble in the chat window may mean that messages have already been exchanged with the other party. An electronic device (101) according to one embodiment may generate a recommended emoji corresponding to a text message input based on artificial intelligence (AI) (e.g., an emoji recommendation engine based on generative AI). The electronic device (101) according to one embodiment may request a recommended emoji based on AI from a server (e.g., the server (108) of FIG. 1) and receive a recommended emoji generated based on the generative AI of the server from the server. An electronic device (101) according to one embodiment may support a function of recommending emojis corresponding to a text message input into an input window based on AI (e.g., an emoji recommendation engine or AI model based on generative AI). For example, the emoji recommendation engine may newly generate an emotional emoji corresponding to a text input and an emoji corresponding to a specific keyword through a deep learning program, or extract or select an optimal emoji corresponding to the input text from an emoji database (DB). An electronic device (101) according to one embodiment may support a function of suggesting a speech bubble decoration effect suitable for a message to a user by using recommended emojis as visual objects (or decoration objects) that decorate the periphery or outline of a speech bubble. According to one embodiment, each of the embodiments described with reference to FIGS. 2a to 11b can operate independently as one embodiment. According to one embodiment, at least two of the embodiments described with reference to FIGS. 2a to 11b can be combined and operated. In one embodiment, when at least two embodiments are combined and operated, at least some of the components and / or at least some of the operations included in each embodiment may be omitted. FIGS. 2A and 2B illustrate a method for providing a message bubble function of an electronic device according to one embodiment. In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel. Referring to FIGS. 2A and 2B , a processor (120) of an electronic device (101) (e.g., a transmitting electronic device) according to one embodiment may receive a text message input (or a character string input) in operation 210. For example, the processor (120) may display a user interface (UI) for sending and receiving messages based on the execution of a message or chat application. The UI may include a conversation window, an input window, and a keypad. The processor (120) may output text corresponding to characters (e.g., characters / letters) input using the keypad in real time to the input window. According to one embodiment, the processor (120) may display speech bubble decoration items (e.g., menus and icons) on the display based on text (or strings) being entered into the input window. In operation 220, the processor (120) may perform filtering on an input text message (e.g., an input sentence, a string) to be provided as input data for an emoji recommendation engine. For example, filtering (or text message filtering) may perform at least one of the following operations: keyword extraction, converting new words to substitute words, removing profanity, and / or removing specific types of words, as illustrated in FIG. 2b. Specifically describing the filtering operations, as illustrated in FIG. 2b, in operation 221, the processor (120) can determine whether a pre-specified keyword (e.g., a neologism keyword) exists and extract the keyword. Here, a neologism (or buzzword) may mean a word / term that is not recognized as a standard word among newly created words / terms. For example, keywords (e.g., new word keywords) are exemplified in [Table 1] below, but are not limited thereto, and it may be possible to update and / or register (or designate) new keywords depending on the user environment. Distinction KeywordAlternative wordAbbreviationWord of mouthGood, good, good, notificationDerivative wordGood, good, happy, hungry, child, bottle, compound wordSpecial wordHappiness, joy, newbie, child, chick, laugh, sad, new wordDaengdaeng, puppy, puppy, cute, happinessOther1I don't know, I don't know. Talented, strange, foreign wordTMI(too much information)Embarrassed, troubledTMT(too much talker)I don't like, I'm tired In operation 222, the processor (120) can convert a new word keyword into a substitute word. For example, when the text (or word, string) “dog profit” is entered in the message input window, the processor (120) can convert the text “dog profit” into the word “good” or “happy.” In operation 223, the processor (120) can delete a word (or string) classified as a profanity. For example, profanity or violent words or certain types of words can be pre-designated (or set, stored). The processor (120) can delete text or words that are classified as designated profanity if they exist. In operation 224, the processor (120) can delete a specific type of word (or string). For example, the processor (120) can classify words that fall into sensitive categories such as termination, race, gender, disgust, hatred, murder, suicide, and / or drugs, identify words that may fall into the sensitive categories, and delete the identified words. The processor (120) can obtain a filtered text sentence (or a filtered text message) by performing operations 221 to 224. In operation 230, the processor (120) can drive an emoji recommendation engine based on the filtered text sentence and obtain a result. The driving of the emoji recommendation engine and obtaining a result will be specifically described in FIG. 3. The processor (120) can obtain recommended emojis as a result of operating the emoji recommendation engine. For example, the emoji recommendation engine can output up to three emojis and / or emoji scores as output data, but is not limited thereto. Although not shown in the drawing, the processor (120) may obtain a keyword emoji as a recommended emoji independently of the emoji recommendation engine operation, if there is a keyword emoji (or a basic emoji, a model emoji) corresponding to the keyword. The keyword emoji (or a basic emoji, a model emoji) may mean an emoji that is basically mapped to a pre-specified keyword. For example, a puppy emoji may be mapped to a keyword “puppy” or “doggy.” In operation 240, the processor (120) can combine recommended emojis. For example, the processor (120) may select optimized recommended emojis (or final emojis) corresponding to the input text message based on recommended emojis and / or keyword emojis and determine a speech bubble decoration pattern. The operation of combining and / or selecting emojis will be described in detail in FIG. 3. According to one embodiment, the processor (120) can automatically arrange recommended images by selecting a decoration pattern according to the horizontal width of a speech bubble corresponding to a text message, and can also apply an animation effect. Hereinafter, the decoration pattern and animation effect will be described with reference to FIGS. 5 and 6. In operation 250, the processor (120) can output a speech bubble decoration effect to the display based on recommended emojis. For example, the processor (120) may display a speech bubble decoration window on at least a portion of the display based on an input for selecting a speech bubble decoration item in the input window. The processor (120) may display a visual effect in which a recommended emoji is applied around or outside a speech bubble including a text message entered in the input window in the speech bubble decoration window. The user may check the speech bubble decoration effect corresponding to the text message through the speech bubble decoration window. In operation 260, the processor (120) can determine a user requested action based on user input. For example, a speech bubble decoration window might contain a Send item, a Refresh item, and a Cancel item. If the user input action is an input requesting input modification (e.g., modifying text characters entered in an input window) (e.g., input modification in action 260), the processor (120) may return to action 210 and repeat actions 220 to 260 based on the text (or characters, string) newly entered in the message window. If the user input action is an input for selecting a refresh item (e.g., refresh in action 260), the processor (120) may return to action 230 to recommend a new emoji and repeat actions 240 to 260. In operation 270, the processor (120) may transmit a message (e.g., a text message) including speech bubble decoration data to the other party's electronic device if the user input is an input for selecting a message transmission item (e.g., transmission in operation 260). FIG. 3 is a diagram for explaining a processing method of an emoji recommendation engine according to one embodiment. Referring to FIG. 3, the processor (120) of the electronic device (101) can check an input sentence (or text message) input through an input window (e.g., a message input window) in operation 310. In operation 320, the processor (120) can extract keywords (e.g., new word keywords) from an input sentence. For example, as described in Fig. 2b, keywords can be extracted from input text based on predefined / specified keyword information. For example, if a user inputs the sentence “I’m out for a walk right now and there are so many dogs here. They’re so cuteㅠㅠ” into a message input window, the processor (120) can extract the keywords “dogs” and “cute.” In operation 330, the processor (120) may drive an emoji recommendation engine to output a result. According to one embodiment, the processor (120) may transmit filtered text data (e.g., filtered input sentence, filtered string) as input data of the emoji recommendation engine based on the filtering operations illustrated in FIG. 2b (e.g., converting new keywords (e.g., dog, cute) in an input sentence into alternative words (e.g., puppy, cute), or deleting vulgar words / specific types of words). In one embodiment, the emoji recommendation engine is driven by generative AI, and can generate new emotional emojis corresponding to text messages and emojis corresponding to specific keywords for input text through a deep learning program, or extract or select recommended emojis from an emoji database. According to one embodiment, the processor (120) may transmit at least one of the filtered text data, a first criterion for determining the appropriateness of an object emoji, a second criterion for determining the appropriateness of an emotion emoji, and a number of emoji requests determined based on a speech bubble width of a message as input values (or input data) of the emoji recommendation engine. The first criterion and the second criterion may mean criterion values from which an AI model (e.g., an emoji recommendation engine) derives a result. For example, in relation to the emoji recommendation engine, the first criterion for an object emoji may be initially set to 0.73, and the second criterion for an emotion emoji may be initially set to 0.77, but is not limited thereto. In one embodiment, the emoji recommendation engine may calculate emoji appropriateness scores for all emojis corresponding to an input text (e.g., a filtered input sentence), and determine emojis that receive a higher score than a first criterion or a second criterion for each emoji as candidates. The emoji recommendation engine may select (e.g., randomly, or in order of highest score) emojis corresponding to the number of emoji requests from the candidate group and output them as recommended emojis. The number of recommended emojis output by the emoji recommendation engine may be at most three, but is not limited thereto. Independently or in parallel with operation 330, in operation 340, the processor (120) can obtain a keyword emoji (or a basic emoji, an exemplary emoji) corresponding to the extracted keyword as a recommended emoji. For example, the processor (120) can obtain a keyword emoji if there is a keyword emoji mapped to the extracted keyword. According to one embodiment, keyword emojis may be stored in an emoji database (DB). The processor (120) may obtain keyword emojis from the emoji DB. According to one embodiment, the processor (120) may perform a keyword extraction operation illustrated in FIG. 2b, an operation of converting new words into substitute words, an operation of deleting profanity, and / or a filtering process of deleting a specific type of word in the process of obtaining a keyword emoji. In operation 350, the processor (120) may combine emojis based on at least one of the emoji recommendation engine results and / or keyword emojis, as described in FIGS. 2A and 2B . In the 360 motion, the processor (120) can select optimized final emojis corresponding to the input sentence based on the combined emojis. The final emoji is only referred to for convenience of explanation and may mean some of the recommended emojis. According to one embodiment, the processor (120) may select final emojis by combining at least one of three emojis and / or N keyword emojis (e.g., N is a natural number) obtained from an emoji recommendation engine according to the following rules, but is not limited thereto. For example, Rule 1: If an emoji recommended as a result of an emoji recommendation engine overlaps with a keyword emoji, it can be preferentially included in the final emoji. Rule 2: If an emoji recommended as a result of an emoji recommendation engine and a keyword emoji have conflicting emotion emojis (e.g., a smiling face emoji and a crying face emoji), the emoji corresponding to the keyword emoji can be removed. Rule 3: If there are three emotion emojis in the emoji recommendation engine result and one object emoji is included in the keyword emoji, the emotion emoji with a lower score among the emotion emojis can be excluded from the final emoji and the object emoji can be included in the final emoji. Conversely, if there are three object emojis in the emoji recommendation engine result and one emotion emoji is included in the keyword emoji, the emoji with a lower score among the object emojis can be excluded from the final emoji and the emotion emoji can be included in the final emoji. Meanwhile, the score of keyword emoji can be specified as 0.88. The processor (120) can apply a speech bubble decoration effect based on the final emojis and output (or display) it in the speech bubble decoration window. FIGS. 4A and 4B illustrate screens providing a message bubble function of an electronic device according to one embodiment. Referring to FIG. 4a and FIG. 4b, <401> As illustrated, the electronic device (101) can display a first UI (user interface) screen including a dialogue window (410), a keypad (420), and an input window (430) on the display. A user can input text characters through the keypad (420), and the input text characters can be displayed in real time on the input window (430). <402> As illustrated, the electronic device (101) may display a second UI screen that calls (or displays) a speech bubble decoration item (440) in the input window (430) when a text character is entered in the input window (430). In the second UI screen, the emoticon item (445) may mean a menu that calls an emoji or emoticon list. According to one embodiment, when a specified number of text characters are entered into the input window (430), the electronic device (101) may display a second UI screen that calls (or displays) a speech bubble decoration item (440) in the input window (430). According to one embodiment, the electronic device (101) may be configured to: <401> When displaying the first UI screen as shown in , it may be implemented so that a speech bubble decoration item (440) is displayed. For example, when a user selects a transmission item (450), the electronic device (101) may transmit a text message entered in the input window (430) to the other party's electronic device and simultaneously display a speech bubble (not shown) including the text message entered in the conversation window (410). <403> As illustrated, when a user selects a speech bubble decoration item (440) after entering a text message in an input window (430), the electronic device (101) may display a third UI screen that switches the keypad (420) to a speech bubble decoration window (460). The transmission item (450) may disappear from the input window (430) and the transmission item (450) may be displayed in the speech bubble decoration window (460). The electronic device (101) can display a speech bubble decoration effect of a text message (470) entered in the input window (430) in the speech bubble decoration window (460) based on the recommended emoji (or final emoji) described in FIGS. 2a / 2b and 3. Meanwhile, if an animation effect is applied to the recommended emoji (475), the recommended emojis can be output sequentially with the animation effect. For example, <403> This is an example screen showing the first recommended emoji (475) printed with an animation effect. <404> This may be an example screen showing a situation where all recommended emojis (475) are printed with a speech bubble decoration effect. <404> As illustrated, when a user checks the speech bubble decoration effect through the speech bubble decoration window (460) and selects a transmission item (450), a text message (470) including the speech bubble decoration data can be transmitted to the other party's electronic device, and a message (490) with the speech bubble decoration effect applied can be displayed in the chat window (410). For example, a text message (470) including speech bubble decoration data (e.g., bubble decorate value) may be a message that additionally includes “[Emoji] is decorated” in a text sentence included in an input window (430) (e.g., “Like a fried egg on top of warm rice, lazily”). The speech bubble decoration data (e.g., bubble decorate value) is information in which the speech bubble decoration data is stored in a JSON format, and the JSON format can be defined as follows. <Example> { "BUBBLE_DECO" = "♥,☏, ☞", "BUBBLE_DECO_PATTERN"= 8, "BUBBLE_DECO_ANIMATION"="101,202,203" } Here, BUBBLE_DECO can mean a string of text data of three emoji i applied to the speech bubble, separated by ','. BUBBLE_DECO_PATTERN can mean a numeric number of an emoji expression pattern (or decoration pattern) applied to the speech bubble. BUBBLE_DECO_ANIMATION means information on the animation effect to be played, and the value can be generated by adding the animation numbers by expressing the A pattern as 100 and the B pattern as 200. In one embodiment, the electronic device (101) may re-run the emoji recommendation engine based on user input selecting a refresh item (480) to re-display a speech bubble decoration effect based on a new recommended emoji in the message window (460). According to one embodiment, the electronic device (101) may receive recommendations for new emojis by lowering the threshold values (e.g., the first threshold value and the second threshold value described in FIG. 3) transmitted as input values of the emoji recommendation engine by a set value (e.g., 0.03) each time the refresh item (480) is pressed. For example, if the first threshold value of the initially set object emoji is 0.73 and the second threshold value of the emotion emoji is set to 0.77, the first threshold value may be transmitted to the emoji recommendation engine as 0.70 and the second threshold value may be transmitted to the emoji recommendation engine as 0.74 by selecting the refresh item (480). According to one embodiment, the electronic device (101) can cancel the speech bubble decoration effect and deactivate the display of the speech bubble decoration window (460) based on a user input selecting a cancel item (485). According to one embodiment, when the input window (430) is selected to modify input text characters, the electronic device (101) can remove the speech bubble decoration window (460) and call up and display the keypad (430) again. FIGS. 5 and 6 illustrate drawings for explaining automatic emoji placement and effect application of speech bubble decoration according to one embodiment. Referring to FIGS. 5 and 6, according to one embodiment, the electronic device (101) can automatically arrange recommended images by selecting a decoration pattern (or decoration template) according to the horizontal width of a speech bubble corresponding to a text message, and can also apply an animation effect. According to one embodiment, a decoration pattern (or decoration template, hereinafter, may be referred to as a pattern) may be defined as illustrated in <Figure 5>, for example, nine decoration patterns may be defined, but this is only an example and is not limited thereto. Decoration patterns (or decoration templates) are distinguished by the speech bubble width, and each decoration pattern can define the number of emoji expressions, emoji text size, emoji placement information, and emoji position information. The definition of each decoration pattern can be as shown in [Table 2] below. Pattern indexEmoji countEmoji text sizeEmoji placementEmoji position (dp)11

[0046] [1]

[0020] 21

[0031] [1]

[0033] 31

[0031] [1][5]42[31,31][1,2][9,5]52[31,31][0,1][3,0]62[48,31][1,2][16,2]73[37,18,18][1,2,3][15,5,2]83[47,31,31][0,1,2][5,20,5]93[31,31,31][1,2,3][19,5,5] With regard to image placement information and emoji location information, based on Fig. 6, <601> As shown in , there may be placement coordinates (625) at the top and bottom based on the speech bubble (610). For example, there may be a “0” coordinate at the top of the speech bubble (610), and “1”, “2”, and “3” coordinates at the bottom of the speech bubble. At this time, <602> The outgoing speech bubble (620) shown in <603> The received speech bubble (630) shown in is expressed as a left-right inversion, so the 0 coordinate can move to the right and left boundaries shown, respectively. In the case of the coordinates “1” “2” “3” at the bottom of the speech bubble, the received speech bubble (623) can have the arrangement coordinates (635) of [1,2,3], and the sending speech bubble (620) can have the arrangement coordinates (625) of [3,2,1]. Regarding the emoji location information <604> As shown in , looking at pattern 8 as an example, the emoji position means the distance from the boundary of the speech bubble or the neighboring emoji, and when the emoji placement coordinates are [0, 1, 2], the emoji position according to the distance [5, 20, 5] can be confirmed. Looking at speech bubbles in which emojis (e.g., recommended emojis or final emojis) are automatically placed by the decoration patterns defined based on [Table 1], the electronic device (101) divides speech bubbles corresponding to text messages entered in the input window into three sections according to the speech bubble width, and can select one of nine patterns according to the speech bubble width (e.g., horizontal width). For example, if the speech bubble width is less than 102 dp, <501> The speech bubble (510) of pattern 1 shown in <502> The speech bubble (520) of pattern 2 shown in or <503> It can be expressed as a speech bubble (530) of pattern 3 shown in . If the width of the speech bubble is between 102 dp and 155 dp, <504> Speech bubble (540) of pattern 4 shown in <505> Speech bubble (550) of pattern 5 shown in or <506> It can be expressed as a speech bubble (560) of pattern 6 shown in . If the width of the speech bubble is greater than 155 dp, <507> Speech bubble (570) of pattern 7 shown in <508> The speech bubble (580) of pattern 8 shown in , or <509> It can be expressed as a speech bubble (590) of pattern number 9 as shown in . According to one embodiment, the electronic device (101) can obtain score values of recommended emojis as output values of the emoji recommendation engine, calculate an average score for the recommended emojis as shown in the following [Table 3], and select a decoration pattern in which the emojis are to be expressed according to the range of the average scores shown in [Table 4]. Emoji score score > 0.93 <= 0.9, > 0.82 <= 0.8, > 0.71 According to one embodiment, the electronic device (101) may select (or determine) the number of patterns to be expressed based on [Table 4] according to the range (e.g., tier) of the average scores of recommended emojis, as the higher the average score of the recommended emojis, the closer it is to the “optimized emoji.” Tier-based score pattern 1>= 2.31,6,82>=1.52,5,93<1.53,4,7 For example, even if the speech bubbles are the same width, the total area / size where the emojis are expressed may be different for each pattern. For example, if we look at the patterns [7, 8, 9] where three emojis are shown, <508> The emojis of pattern 8 shown in the figure are placed the largest and most widely. <507> It can be confirmed that the emojis of the 7 patterns illustrated in are expressed in the smallest size. According to one embodiment, the electronic device (101) can apply an animation effect to emojis applied to speech bubble decoration. For example, the electronic device (101) can apply an animation effect to emojis when recommended emojis are first displayed (or output, appear) in a speech bubble decoration window, or when a message to which a speech bubble effect is applied is first displayed in a chat window (e.g., a received chat window or an outgoing chat window). According to one embodiment, the electronic device (101) may determine an animation to be applied to the emoji based on [Table 5] depending on the size of the text of the emoji. Distinction AB condition >= 37dp <37dp animation bounce bounce rotate rotate Position scale For example, if the size of the emoji (or the text size) is greater than 37dp, one of the two A animations may be played randomly, and if it is less than 37dp, one of the four B animations may be played randomly. The animation effects of each emoji may be selected so as not to overlap each other. According to one embodiment, the electronic device (101) may also select an animation to be applied to the emoji based on the score of the emoji obtained from the emoji recommendation engine based on [Table 6]. Emoji scoreAnimation>= 0.9[1]bounce<0.9,>= 0.8[2]rotate<0.8m >= 0.7[3]position The smaller the animation number, the more dynamic the effect can be, and the higher the emoji score (e.g., the appropriateness score described in FIG. 3) transmitted from the emoji recommendation engine, the more dynamic the animation can be executed. If the bounce effect is applied first to one of the emojis applied in the speech bubble, the animation effect of the next number can be applied to the other emoji. FIG. 7 illustrates screens providing a speech bubble function of an electronic device according to one embodiment. Referring to FIG. 7, according to one embodiment, the electronic device (101) may not change the decoration pattern of the speech bubble and the position of the emoji even if the size of the text message, the screen magnification, the base font size, the resolution, or the line break of the speech bubble is changed. for example, <701> The electronic device (101) displays a message UI screen with a font size of 82%. <702> can display a message UI screen with a font magnification of 171% of an electronic device (101). The message UI screen can include a conversation window (710), a speech bubble decoration window (720), and an input window (730). The speech bubble decoration window (720) includes a refresh item (760) and a cancel item (770), and although not shown in the drawing, can further include a transmission item (not shown). The message (740) contained in the speech bubble () with the emoji (750) applied is displayed according to the font size. <701> As shown in , it can be expressed in one line, <702> As shown in , it can be expressed in two lines. However, since the arrangement and position of the emoji are specified based on the width of the speech bubble (e.g., horizontal width), it can be confirmed that only the overall size ratio changes and the emoji arrangement position and pattern do not change. The decoration pattern described in the present disclosure may not change the decoration pattern of the speech bubble and the position of the emoji even if the display structure changes, such as in a rollable device, or the screen width changes, such as in landscape mode. FIG. 8 illustrates a method for providing a speech bubble function of an electronic device according to one embodiment, and FIG. 9 illustrates examples of transmitted and received messages to which a speech bubble decoration effect of an electronic device is applied according to one embodiment. Referring to FIG. 8, a processor (120) of an electronic device (101) (e.g., a receiving electronic device) according to one embodiment may receive a message including speech bubble decoration data in operation 810. In operation 820, the processor (120) can determine whether decoding (or data processing) of speech bubble decoration data is possible. In operation 830, if the processor (120) is an electronic device capable of supporting decoding of speech bubble decoration data (e.g., supported in operation 820), the speech bubble decoration data (e.g., “[Emoji] is decorated”) can be removed to confirm the original text message. In operation 831, the processor (120) may parse speech bubble decoration data (e.g., BubbleDecorateValue). Information on speech bubble decoration emoji, decoration pattern, and / or animation effect may be obtained. For example, the processor (120) may parse the BubbleDecorateValue value as Json to extract at least one of the speech bubble decoration emoji, decoration pattern, and / or animation effect value. As an example, the processor (120) may check pattern information to be placed by the Bubble_Deco_PATTERN value, and may check emoji text by dividing the Bubble_Deco PATTERN value with a ',' delimiter. Alternatively, when BUBBLE_DECO_ANIMATION is included, the processor (120) may check an animation effect to be applied to the emoji by the BUBBLE_DECO_ANIMATION value. In operation 832, the processor (120) can output a message with a speech bubble decoration effect applied based on the parsed value to the chat window. For example, the message with the speech bubble decoration effect applied can be in the same message format as the example of operation 832. According to one embodiment, the speech bubble decoration pattern of the receiving electronic device may be displayed in a left-right reversed arrangement with respect to the speech bubble decoration pattern of the transmitting electronic device. As an example, FIG. 9 <901> The electronic device (101) on the transmitting side may be a chat window and the electronic device (102) on the receiving side may be a chat window. The electronic device (101) on the transmitting side may transmit a message (910) including a speech bubble decoration emoji (920) saying “Hello. Nice to meet you.” If the electronic device (102) on the receiving side is an electronic device capable of supporting decoding of speech bubble decoration data, <901> As shown in , a message (911) with a speech bubble decoration emoji (921) with the decoration pattern reversed left and right can be displayed in a chat window. In operation 840, if the processor (120) is an electronic device that does not support decoding of speech bubble decoration data (e.g., not supported in operation 820), the processor (120) may output a plain text message including speech bubble decoration information. The plain text message may be a sentence including “[Emoji] is decorated” in the original message. For example, the plain text message may be in the form of a message as in the example of operation 840. for example, <902> As illustrated, the transmitting electronic device (101) can transmit a message (930) including a speech bubble decoration emoji (940) saying “I want to eat ice cream.” However, if the receiving electronic device (102) is an electronic device that does not support decoding of speech bubble decoration data, <902> As shown in , the decoration value is ignored, and a text speech bubble (941) such as “I want to eat ice cream” is decorated with an emoji” may be displayed in the chat window. FIG. 10 illustrates screens providing a speech bubble function of an electronic device according to one embodiment. Referring to FIG. 10, the message UI (1010) according to the comparative embodiment (or conventional) <1001> As illustrated, speech bubble messages (1011, 1021) containing text messages may be displayed in a chat window. 1011 may be a sending message, and 1021 may be a receiving message. A message UI (1020) with a speech bubble decoration effect applied according to the present disclosure <1002> As illustrated, a first message (1030) transmitted from an electronic device may be a message to which a speech bubble decoration effect (1035) corresponding to a text message “I want to eat ice cream today” is applied, and a second message (1040) may be a message to which a speech bubble decoration effect (1045) corresponding to a text message “Shall we go to Vera and eat ice cream?” is applied from the other party’s electronic device. A third message (1035) may be a message to which a speech bubble decoration effect is not applied. FIGS. 11A and 11B illustrate screens providing a speech bubble function of an electronic device according to one embodiment. Referring to FIGS. 11A and 11B , an electronic device (101) according to one embodiment may support a speech bubble decoration function for a message including an image. For example, when transmitting a single image in an MMS message or transmitting an MMS consisting of only a single text, the electronic device may support a speech bubble decoration function. for example, <1101> As illustrated, the electronic device (101) may display a first UI (user interface) screen including a chat window (410), a keypad (420), and an input window (430) on the display. The electronic device (101) may receive a user input for transmitting an image, for example, an input for selecting a gallery icon (1105). <1102> As illustrated, the electronic device (101) may display a second UI screen that switches the keypad (420) to a gallery list screen (1130) based on an input of selecting a gallery icon (1105). The gallery list screen may display thumbnails corresponding to images stored in the electronic device (101). The user may select a thumbnail of an image to be sent as a message from the gallery list screen (1130). The electronic device (101) can switch to a third UI screen that displays a speech bubble decoration window (460) in one area of the dialog box (410) based on a user input of selecting at least one image (1110). <1102> The speech bubble decoration window (460) illustrated in may include a thumbnail of an image (1110) to be sent as a message and a speech bubble decoration item (440). The electronic device (101) <1103> As illustrated, based on a user input selecting a speech bubble decoration item (440), a speech bubble decoration window (460) may be displayed to display a speech bubble decoration effect (1120) of a message including an image (1110) based on a recommended emoji. <1103> In the case of the screen, the transmission item (450) may disappear in the input window (430) and the transmission item (450) may be displayed in the speech bubble decoration window (460). For example, the electronic device (101) can apply a speech bubble decoration effect (1120) to a message including an image (1110) based on the recommended emoji (or final emoji) described in FIGS. 2a / 2b and 3. The electronic device (101) can perform text recognition (e.g., “Happy New Year”) on an image (1110) selected by a user input in various ways (e.g., OCR technology on the image (1110)) to extract keywords such as metadata and tag information related to the image (1110). The electronic device (101) can obtain a recommended emoji (1120) (e.g., a lucky bag emoji, two smiling emojis) by obtaining a result by driving an emoji recommendation engine and / or a combination of mapped keyword emojis for the extracted keyword (e.g., “bok”) in the manner described in FIGS. 2a / 2b and 3. The electronic device (101) can apply a speech bubble decoration effect (1120) to a message including an image (1110) by automatically arranging a decoration pattern selection and recommended emoji according to the width of the message including the image (1110). <1104> As illustrated, the electronic device (101) may transmit a message including speech bubble decoration data to the other party's electronic device based on a user input for selecting a transmission item (450), and may switch to a fourth UI screen that displays a message with a speech bubble decoration effect (1120) applied in the chat window (410). According to the present disclosure, even if a user inputs only a text message, emojis that automatically decorate the surroundings of a speech bubble are recommended and automatic placement and / or animation effects are applied, thereby providing user convenience as well as fun and individuality. The embodiments of this document and the terminology used herein 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 dictates 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, 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) is referred to as "coupled" or "connected" to another (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. The term "module" used in the 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, for example. A module may be an integrally configured component or a minimum unit of the component or a part thereof 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). One embodiment of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., the electronic device (101)) 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. According to one embodiment, the method according to one embodiment disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded between sellers and buyers as a commodity. The computer program product may be distributed in the form of a storage medium that can be read by a machine (e.g., compact disc read only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online (e.g., by download or upload). In the case of online distribution, at least a part 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, a server of an application store, or an intermediary server. According to one embodiment, each component (e.g., a module or a program) of the above-described components may include a single or multiple entities, and some of the multiple entities may be separated and arranged in other components. According to one embodiment, one or more components or operations of the above-described corresponding 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 one component. In this case, the integrated component may perform one or more functions of each of the multiple components identically or similarly to those performed by the corresponding component of the multiple components before the integration. According to one embodiment, the operations performed by the module, program, or other component may be executed sequentially, in parallel, repeatedly, 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.

Claims

1. In electronic devices, display; processor; and comprising a memory storing instructions executable by the processor; The above instructions cause the electronic device to: Receives text entered in the message input window, The input text is passed as an input value of an artificial intelligence engine to obtain at least one first recommended emoji corresponding to the text from the artificial intelligence engine, An electronic device that causes a first message to be displayed on at least a portion of the display, wherein at least one first recommended emoji obtained is placed within an outer periphery of the speech bubble including the text.

2. In paragraph 1, The above instructions cause the electronic device to: Determine the number of emojis based on the speech bubble width according to the number of characters in the above text, An electronic device that additionally transmits the number of the determined emojis to the input value of the artificial intelligence engine and obtains at least one and up to the number of the determined emojis as first recommended emojis from the artificial intelligence engine.

3. In paragraph 1, The above instructions cause the electronic device to display a first UI (user interface) screen including the message input window and the dialogue window on the display, Displaying a speech bubble decoration window on at least a portion of the first UI screen based on the text being received in the message input window; An electronic device that displays the first message and message transmission items in the message decoration window.

4. In paragraph 3, Further comprising a communication circuit, The above instructions cause the electronic device to: An electronic device that transmits to a counterpart electronic device, through the communication circuit, speech bubble decoration data including at least one first recommended emoji placed around the speech bubble, based on an input selecting the message transmission item, and displays the first message in the chat window.

5. In paragraph 3, An electronic device comprising an emoji recommendation engine based on generative artificial intelligence, wherein the artificial intelligence engine is 6. In paragraph 5, The above instructions cause the electronic device to: Extracting new word keywords for input sentences corresponding to the above text, converting the new word keywords into substitute words, and deleting at least one of vulgar words and specific types of words in the input sentence to obtain filtered text, The first criterion for determining the appropriateness of the object emoji, the second criterion for determining the appropriateness of the emotion emoji, and the filtered text are transmitted as input values of the artificial intelligence engine. An electronic device characterized in that the above-mentioned new word keyword, the above-mentioned substitute word, the above-mentioned vulgar word and the above-mentioned specific type of word are preset.

7. In paragraph 6, The above instructions cause the electronic device to perform operations of obtaining at least one first recommended emoji, Obtaining at least one first emoji as an output value from the artificial intelligence engine, Obtain at least one second emoji corresponding to a new word keyword extracted from an input sentence corresponding to the above text, An electronic device characterized in that the at least one first recommended emoji is obtained by combining the first emoji and the second emoji.

8. In paragraph 6, The above instructions cause the electronic device to display the first message on at least a portion of the display, Determine a decoration pattern for placing an emoji around the speech bubble based on the score of at least one first recommended emoji; An electronic device characterized in that it displays at least one first recommended emoji on the outer edge of the speech bubble based on the number of emojis, emoji text size, emoji placement, and emoji position defined in the determined decoration pattern.

9. In paragraph 6, Add more refresh items to the message decoration window above, The above instructions cause the electronic device to: In response to a user input selecting the refresh item, the first reference value and the first reference value are changed, and then the artificial intelligence engine is driven to obtain at least one second recommended emoji, An electronic device that causes a first message to be displayed with the second recommended emoji instead of the first recommended emoji in the speech bubble surrounding the text.

10. A method for providing a message bubble function of an electronic device, The action of receiving text entered into the message input window; An operation of transmitting the input text as an input value of an artificial intelligence engine and obtaining at least one first recommended emoji corresponding to the text from the artificial intelligence engine; and A method comprising the action of displaying a first message on at least a portion of a display, wherein at least one first recommended emoji obtained is positioned within an outer periphery of the speech bubble including the text.

11. In paragraph 9, Further comprising an action of determining the number of emojis based on the speech bubble width according to the number of characters in the above text, An action of obtaining at least one first recommended emoji corresponding to the above text A method characterized in that the number of the determined emojis is additionally transmitted to the input value of the artificial intelligence engine to obtain at least 1 to at most the number of the determined emojis as first recommended emojis from the artificial intelligence engine.

12. In paragraph 11, Further comprising an action of displaying a first UI (user interface) screen including the message input window and the conversation window on the display, The action of displaying the first message on at least a portion of the display is: A method characterized in that a speech bubble decoration window is displayed on at least a part of the first UI screen based on the text being received in the message input window, and the first message and message transmission items are displayed in the speech bubble decoration window.

13. In paragraph 11, The action of displaying the first message and message transmission items above is: A method further comprising: an action of transmitting to a counterpart electronic device, through a communication circuit, the speech bubble decoration data including the at least one first recommended emoji placed around the speech bubble in the text based on an input selecting the message transmission item; and an action of displaying the first message in the chat window.

14. In paragraph 13, The action of displaying the first message on at least a portion of the display An operation of determining a decoration pattern for placing an emoji around the speech bubble based on a score of at least one first recommended emoji; and A method further comprising an action of displaying at least one first recommended emoji on the outer edge of the speech bubble based on the number of emojis, emoji text size, emoji placement and emoji position defined in the determined decoration pattern.

15. A computer-readable recording medium having recorded thereon a computer program for executing a method for providing a message bubble function of an electronic device, The action of receiving text entered into the message input window; An operation of transmitting the input text as an input value of an artificial intelligence engine and obtaining at least one first recommended emoji corresponding to the text from the artificial intelligence engine; and A computer-readable recording medium having recorded thereon a computer program, characterized in that it includes actions of displaying a first message on at least a part of a display, wherein at least one first recommended emoji obtained is placed on the outer periphery of the speech bubble including the text.

Images