Electronic device for generating recommended responses, operating method thereof, and recording medium

Abstract

Disclosed are an electronic device for generating recommended responses and an operating method thereof. The electronic device may comprise at least one processor including a processing circuit. The electronic device may comprise a memory including one or more storage media storing instructions. The instructions, when executed individually or collectively by at least one processor, may enable the electronic device to: parse conversations of a plurality of participants who participated in a communication application; divide the parsed conversations of the plurality of participants into an entire conversation and individual conversations for respective participants and analyze same; generate recommended responses respectively for the plurality of participants on the basis of the analyzed entire conversation and individual conversations; and combine participant information related to the recommended responses with the recommended responses and display same on a display.

Description

Electronic device for generating a recommendation response, method of operation thereof, and recording medium

[0001] Embodiments of the present disclosure relate to an electronic device for generating a recommendation response, a method of operating the same, and a recording medium.

[0002] Electronic devices provide conversational capabilities with other participants through chat applications. Recently, users have increasingly utilized group chats, allowing multiple participants to converse with each other, in addition to one-on-one conversations.

[0003] The above information may be provided as background art to aid 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.

[0004] According to one embodiment, an electronic device may include at least one processor comprising a processing circuit. The electronic device may include a memory comprising one or more storage media storing instructions. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to parse a conversation of a plurality of participants participating in a communication app, analyze the parsed conversation of the plurality of participants by dividing the conversation into the entire conversation and individual conversations for each participant, generate a recommended response for each of the plurality of participants based on the analyzed overall conversation and individual conversations, and combine participant information related to the recommended response with the recommended response and display the result on a display.

[0005] According to one embodiment, a method of operating an electronic device may parse a conversation between multiple participants in a communication app. The method of operating the electronic device may analyze the parsed conversation between multiple participants by dividing it into the entire conversation and individual conversations for each participant. The method of operating the electronic device may generate a recommended response for each of the multiple participants based on the analyzed overall conversation and individual conversations. The method of operating the electronic device may combine participant information related to the recommended response with the recommended response and display the result on a display.

[0006] According to one embodiment, instructions recorded on a computer-readable recording medium, when executed by one or more processors, can cause the electronic device to perform operations of a method of operating the electronic device.

[0007] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0008] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0009] FIG. 2 is a diagram illustrating the overall configuration of an electronic device for generating a recommendation response according to one embodiment.

[0010] FIG. 3 is a diagram illustrating a method for analyzing individual conversations of participants in a group chat according to one embodiment and providing a recommended response for each participant.

[0011] FIG. 4 is a diagram illustrating a method for providing a recommended response to each participant by utilizing the context of the entire conversation of participants participating in a group chat according to one embodiment.

[0012] FIG. 5 is a diagram illustrating a method for displaying a recommended response in a conversation window of a group chat according to one embodiment.

[0013] FIG. 6 is a diagram illustrating a method for displaying a recommended response generated based on a specific link in a group chat conversation window according to one embodiment.

[0014] FIG. 7 is a diagram illustrating a method for displaying a recommended response for a specific conversation selected by a user in a conversation window of a group chat according to one embodiment.

[0015] FIG. 8 is a diagram illustrating a method for displaying a recommended response generated based on attached content in a conversation window of a group chat according to one embodiment.

[0016] FIG. 9 is a diagram illustrating how a changed recommended response is displayed in a group chat conversation window as conversations of other participants are added according to one embodiment.

[0017] FIG. 10 is a diagram illustrating a method for generating a recommendation response when video content is attached according to one embodiment.

[0018] FIG. 11 is a diagram illustrating a method for generating a recommendation response based on a request to a user according to one embodiment.

[0019] FIG. 12a and FIG. 12b are diagrams illustrating a method for generating a recommended response in a notification pop-up state of a communication app according to one embodiment.

[0020] FIG. 13 is a diagram illustrating a method for generating a recommendation response based on relationships between participants participating in a group chat according to one embodiment.

[0021] FIG. 14 is a diagram illustrating a method for generating a recommended response when an original message is deleted during a conversation among participants in a group chat according to one embodiment.

[0022] FIG. 15 is a diagram illustrating a method for generating a recommendation response based on user status information according to one embodiment.

[0023] FIG. 16 is a diagram illustrating a method for generating a recommended response based on the degree of response of other participants to a user's message according to one embodiment.

[0024] FIG. 17 is a diagram illustrating a method for generating a recommendation response of an electronic device according to one embodiment.

[0025] Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In the description with reference to the attached drawings, identical components will be assigned the same reference numerals regardless of the drawing numbers, and redundant descriptions thereof will be omitted.

[0026] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the 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)).

[0027] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). The processor (120) may also be implemented as a system on chip (SoC) or an integrated circuit (IC) that performs processing. The processor (120) may include one or more processors, and the operations of the electronic device (101) described in the present disclosure may be performed by a single processor or by a combination of multiple processors. When the operations of the electronic device (101) are performed by a combination of multiple processors, any one processor included in the combination of processors may perform some of the operations of the electronic device (101). For example, the processor (120) may correspond to multiple processors that collectively perform a plurality of operations by dividing them among the processors.

[0028] According to one embodiment, the processor (120) may be implemented as a circuit (e.g., a processing circuit) such as a system on chip (SoC) or an integrated circuit (IC). The processor (120) may include one or more processors. For example, the processor (120) may include a combination of one or more processors such as a CPU, a GPU, an MPU, an AP, and a CP.

[0029] 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 graphics 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 with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0030] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), 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 unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can 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 can include multiple 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 alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0031] The memory (130) can store various data used by at least one component (e.g., the processor (120) or the sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., the program (140)) and input data or output data for commands related thereto. The memory (130) can include a volatile memory (132) or a non-volatile memory (134). The memory (130) can store at least one instruction executable by the processor (120). The memory (130) can include one or more memories, and instructions for controlling the processor (120) to perform operations of the electronic device (101) described in the present disclosure can be stored in one memory or can be divided and stored in multiple memories.

[0032] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0033] 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).

[0034] The audio output module (155) can output audio signals 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 incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0035] The display module (160) can visually provide information to an external device (e.g., a user) of the electronic device (101). The display module (160) may 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) may 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 display module (160) may be implemented with an illustrative foldable structure and / or a rollable structure. For example, the size of the display screen of the display module (160) may be reduced when folded, and may be expanded when unfolded.

[0036] 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 acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0037] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. 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.

[0038] 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)). In 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.

[0039] The connection terminal (178) may include a connector that allows the electronic device (101) to be physically connected to an external electronic device (e.g., 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).

[0040] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0041] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0042] 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, for example, as at least a part of a power management integrated circuit (PMIC).

[0043] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0044] The communication module (190) may support the 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., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., 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 Wi-Fi communication module, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) 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, the corresponding communication module can 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 can 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) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0045] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power 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) can 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) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can 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), or 1 ms or less for round trip) for URLLC realization.

[0046] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may 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), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0047] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed 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) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band.

[0048] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0049] According to 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). According to 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 the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion 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 portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing 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.

[0050] FIG. 2 is a diagram illustrating the overall configuration of an electronic device for generating a recommendation response according to one embodiment.

[0051] Referring to FIG. 2, one or more processors (e.g., the processor (120) of FIG. 1) included in an electronic device (e.g., the electronic device (101) of FIG. 1) can control the operations of a conversation parsing unit (210), a conversation analysis unit (220), and a response generation unit (230) to provide a recommended response in a group chat situation in which three or more people are having a conversation.

[0052] First, one or more processors may parse conversations occurring in a group chat of a communication app (240) via a conversation parsing unit (210). In this case, parsing may mean breaking down conversations, i.e., messages, occurring in a group chat of the communication app (240) into meaningful units. For example, the communication app (240) may include a short message service (SMS), which is a supplementary service of a mobile phone, or a chat app such as KakaoTalk or Telegram. However, the types of such communication apps are merely examples and are not limited to the above examples.

[0053] One or more processors may analyze a conversation parsed by a conversation parsing unit (210) using a conversation analysis unit (220). At this time, the conversation analysis unit (220) may analyze the conversations of multiple participants in a group chat by dividing them into the entire conversation and individual conversations for each participant.

[0054] One or more processors may generate a recommended response for each of the plurality of participants through the response generation unit (230) based on the conversations of the plurality of participants analyzed through the conversation analysis unit (220). For example, in a group chat room, when Participant A and Participant C are counterparts and Participant B is the speaker and Participant B performs input through the user interface (250) of the electronic device, one or more processors may generate a recommended response for Participant A and a recommended response for Participant C through the response generation unit (230), respectively, and provide the results through the display unit (260) (e.g., the display module (160) of FIG. 1). At this time, when the one or more processors display each recommended response generated through the response generation unit (230) on the display unit (260), they may provide the recommended response by combining characters or images that can designate the counterpart so that it is possible to distinguish which counterpart the recommended response displayed on the display unit (260) is for.

[0055] According to one embodiment, the electronic device (101) may include at least one processor (120) including a processing circuit. The electronic device (101) may include a memory (130) including one or more storage media for storing instructions. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to parse conversations of a plurality of participants participating in a communication app, analyze the parsed conversations of the plurality of participants by dividing them into the entire conversation and individual conversations for each participant, generate a recommendation response for each of the plurality of participants based on the analyzed entire conversation and individual conversations, and combine participant information related to the recommendation response with the recommendation response to display the result on a display.

[0056] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to, when uniform resource locator (URL) information is received from another participant through a communication app, analyze a webpage or content corresponding to the URL information, and generate a recommendation response corresponding to the URL information based on the analysis result of the webpage or content corresponding to the URL information, the analysis result of the entire conversation, and the analysis result of an individual conversation of the other participant who provided the URL information.

[0057] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to, when content corresponding to an image or video is received from another participant through a communication app, analyze the content, and generate a recommendation response corresponding to the content based on the analysis results of the content, the analysis results of the entire conversation, and the analysis results of individual conversations of the other participant who provided the content.

[0058] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to generate a recommendation response for the content itself based on the results of the analysis of the content.

[0059] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to analyze a relevance between content and a user based on the analysis result of the content, and, if the analyzed relevance is above a preset standard, generate a recommendation response with information related to the user.

[0060] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to, when a specific conversation is selected from among conversations of multiple participants, generate a recommended response corresponding to the selected specific conversation based on the analysis results of the selected specific conversation and the analysis results of the entire conversation.

[0061] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to identify a response request conversation requesting a response from a user based on the analyzed overall conversation and individual conversations, retrieve specific information related to the response request conversation using a search function of the electronic device, and generate a search result for the specific information retrieved through the search function as a recommended response corresponding to the response request conversation.

[0062] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to combine conversations of other participants related to the recommended response with the recommended response and display them on the display.

[0063] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), cause the electronic device (101) to display recommended responses generated for each of a plurality of participants in order of priority, wherein the priority of the recommended responses may be such that the more recent a conversation is displayed in the communication app and the higher the urgency of the request for a response to the conversation, the higher the priority given to the conversation.

[0064] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to analyze relationships between a plurality of participants participating in a communication app and determine a tone of the recommended response based on the analyzed relationships between the plurality of participants.

[0065] According to one embodiment, the instructions, when individually or collectively executed by at least one processor (120), may cause the electronic device (101) to select and analyze a conversation corresponding to a specific topic or a specific period of time among conversations of multiple participants participating in a communication app.

[0066] FIG. 3 is a diagram illustrating a method for analyzing individual conversations of participants in a group chat according to one embodiment and providing recommended responses for each participant. The operations illustrated in FIG. 3 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0067] Referring to Figure 3, the conversation parsing unit (310) can monitor conversations between participants in a group chat and parse the monitored conversations. More specifically, the conversation parsing unit (310) can decompose the conversations, i.e., messages, of group chat participants into meaningful units. These meaningfully decomposed conversations can be used for subsequent conversation analysis.

[0068] The conversation analysis unit (320) can analyze the conversations of group chat participants that have been broken down into meaningful units through the conversation parsing unit (310). More specifically, the conversation analysis unit (320) can divide the conversations of group chat participants into the entire conversation and individual conversations for each participant. Based on the entire conversation and individual conversations for each participant that have been divided in this way, the conversation analysis unit (320) can generate input data for the response generation unit (330) to generate a recommended response for each participant. According to one embodiment, the conversation analysis unit (320) can generate input data for the response generation unit (330) using only the individual conversation of participant A to generate a recommended response for participant A. Alternatively, according to one embodiment, the conversation analysis unit (320) can generate input data for the response generation unit (330) using not only the individual conversation of participant B but also a portion of the entire conversation to generate a recommended response for participant B. At this time, a part of the entire conversation used to generate input data may correspond to the context of the entire data or summary information of the entire conversation.

[0069] According to one embodiment, the conversation analysis unit (320) may analyze the conversations of participants based on the current conversation topic received in the group chat window. For example, if the current conversation topic is identified as travel, the conversation analysis unit (320) may extract only travel-related conversations from the entire conversations of the participants and generate them as input data for the response generation unit (330). In this way, the travel-related conversations extracted by the conversation analysis unit (320) and generated as input data may be given a high weight when the response generation unit (330) generates recommended responses in the future.

[0070] Additionally, the conversation analysis unit (320) can analyze the conversations of participants based on the recent conversation history of the participants received in the conversation window of the group chat. For example, the conversation analysis unit (320) can extract only the conversations within a period set by the user, such as the last 6 months or the last 1 year, from the entire conversations of the participants and generate them as input data for the response generation unit (330). In this way, conversations related to a specific period extracted by the conversation analysis unit (320) and generated as input data can be given a high weight when the response generation unit (330) generates a recommended response in the future.

[0071] The response generation unit (330) can generate a recommended response for each participant based on the analysis results of individual conversations for each participant analyzed by the conversation analysis unit (320). At this time, the response generation unit (330) can generate a recommended response for each participant using the analysis results of individual conversations of the participants to which different weights are assigned based on the current conversation topic or recent conversation history of the participants. When the response generation unit (330) displays the generated recommended responses for each participant on a display, it can provide the recommended responses by combining characters and / or images that can designate the participants so that the recommended responses displayed on the display can be distinguished for which participant they are responses.

[0072] Alternatively, the response generation unit (330) may generate a recommended response for all participants, rather than a recommended response for each participant, based on the analysis results of the entire conversation of the participants analyzed by the conversation analysis unit (320). Similarly, the response generation unit (330) may generate a recommended response for all participants by using the analysis results of the entire conversation of the participants, to which different weights are assigned based on the participants' current conversation topic or recent conversation history. In this case, when the response generation unit (330) displays the generated recommended responses for all participants on the display, the recommended responses for all participants displayed on the display may be displayed so as to be distinct from the recommended responses for each participant.

[0073] Meanwhile, some or all of the operations performed by the conversation analysis unit (320) and the response generation unit (330) among the components of FIG. 3 may be performed through an external server. According to one embodiment, the electronic device may transmit the conversation of group chat participants parsed through the conversation parsing unit (310) to an external server (e.g., a chat service provider's server, an IMS (ip multimedia subsystem) server, an RCS (rich communication services) server) through an application programming interface (API), and then receive the conversation analysis results performed on the external server and generate a recommended response through the response generation unit (330). In this case, the conversation analysis unit (320) among the components of FIG. 3 may be omitted. Alternatively, the electronic device may transmit the conversation analysis results performed through the conversation analysis unit (320) to an external server through an API, and then receive the recommended response generation results performed on the external server and display them on a display. Similarly, in this case, the response generation unit (330) among the components of FIG. 3 may be omitted.

[0074] FIG. 4 is a diagram illustrating a method for providing recommended responses to each participant in a group chat using the context of the entire conversation among the participants, according to one embodiment. The operations illustrated in FIG. 4 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0075] Referring to Figure 4, the conversation parsing unit (410) can monitor conversations between participants in a group chat and parse the monitored conversations. More specifically, the conversation parsing unit (410) can decompose the conversations, i.e., messages, of group chat participants into meaningful units. These meaningfully decomposed conversations can be used for subsequent conversation analysis.

[0076] The conversation analysis unit (420) can analyze the conversations of group chat participants that have been broken down into meaningful units through the conversation parsing unit (410). More specifically, the conversation analysis unit (420) can divide the conversations of group chat participants into the entire conversation and individual conversations for each participant. Based on the entire conversation and individual conversations for each participant that have been divided in this way, the conversation analysis unit (420) can generate input data for the response generation unit (430) to generate recommended responses for each participant. According to one embodiment, the conversation analysis unit (420) can generate input data for the response generation unit (430) using only the individual conversation of participant A to generate a recommended response for participant A. Alternatively, according to one embodiment, the conversation analysis unit (420) can generate input data for the response generation unit (430) using not only the individual conversation of participant B but also a portion of the entire conversation to generate a recommended response for participant B. At this time, a part of the entire conversation used to generate input data may correspond to the context of the entire data or summary information of the entire conversation.

[0077] The response generation unit (430) can generate a recommended response for each participant based on the analysis results of the entire conversation of group chat participants analyzed by the conversation analysis unit (420) and the analysis results of the individual conversations of each participant. According to one embodiment, the response generation unit (430) can provide a recommended response for participant A based on input data generated using only the individual conversation of participant A. According to one embodiment, the response generation unit (430) can provide a recommended response for participant A based on input data generated using not only the individual conversation for participant A but also a portion of the entire conversation. In this case, the response generation unit (430) can generate the recommended response for participant A without going beyond the context of the entire conversation.

[0078] Meanwhile, the response generation unit (430) can determine priorities for multiple recommended responses. In this case, the response generation unit (430) can assign a higher priority to a recommended response based on a recent conversation involving a specific participant considered for generating a recommended response. For example, the response generation unit (430) can determine priorities by applying a higher weight to a recommended response generated based on a recent conversation involving a specific participant in a group chat, i.e., a conversation that is closer to the previous conversation.

[0079] In addition, the response generation unit (430) may assign a higher priority to a recommended response when a conversation of a specific participant considered in generating a recommended response has a higher relevance to the user. For example, if a phrase, such as a name or nickname, that can identify the user is identified in the conversation of a specific participant participating in a group chat, the response generation unit (430) may determine the priority by applying a high weight to the recommended response generated based on the conversation of the specific participant. Alternatively, if the conversation of a specific participant participating in a group chat is analyzed as one that asks or makes a request to the user, the response generation unit (430) may determine the priority by applying a high weight to the recommended response generated based on the conversation of the specific participant.

[0080] Additionally, the response generation unit (430) may assign a higher priority to a recommended response based on the urgency of a conversation involving a specific participant considered for generating a recommended response. For example, if a phrase implying danger or warning (e.g., "Be careful," "Never open the link") or a phrase indicating urgency (e.g., "Quickly," "Urgent") is identified in a conversation involving a specific participant in a group chat, the response generation unit (430) may assign a higher weight to the recommended response generated based on the conversation involving the specific participant to determine the priority.

[0081] The response generation unit (430) can determine priorities for multiple recommended responses by individually using or combining multiple methods for determining priorities of the recommended responses mentioned above.

[0082] Meanwhile, some or all of the operations performed by the conversation analysis unit (420) and the response generation unit (430) among the components of FIG. 4 may be performed through an external server. According to one embodiment, the electronic device may transmit the conversation of group chat participants parsed through the conversation parsing unit (410) to an external server through an API, and then receive the conversation analysis results performed on the external server and generate a recommended response through the response generation unit (430). In this case, the conversation analysis unit (420) among the components of FIG. 4 may be omitted. Alternatively, the electronic device may transmit the conversation analysis results performed through the conversation analysis unit (420) to an external server through an API, and then receive the recommended response generation results performed on the external server and display them on a display. Similarly, in this case, the response generation unit (430) among the components of FIG. 4 may be omitted.

[0083] FIG. 5 is a diagram illustrating a method for displaying a recommended response in a group chat conversation window according to one embodiment. The operations illustrated in FIG. 5 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0084] In one embodiment, when a communication app is activated and a chat window for a specific group chat is created on the running screen, the electronic device may analyze the entire conversation displayed in the chat window to generate a recommended response. If the user's input for the chat window is identified through the user interface, the electronic device may display the generated recommended response in a portion of the chat window. In this case, the recommended response displayed in the portion of the chat window may include participant information that can identify the participant to determine which participant the recommended response is for.

[0085] More specifically, the electronic device may generate a recommendation response including a color, ID, participant name, and / or an image (e.g., a profile picture) to distinguish the participants corresponding to the recommendation response. For example, referring to FIG. 5, if a recommendation response for participant A is generated, the electronic device may combine (511) the generated recommendation response with the profile picture of participant A and display it in an area (510) of the chat window. Alternatively, if a recommendation response for participant A is generated, the electronic device may combine (512) the generated recommendation response with the name or ID of participant A and display it in an area (510) of the chat window. Alternatively, if a recommendation response for participant C is generated in a situation where the background colors of each participant's speech bubble are different, the electronic device may combine (513) the generated recommendation response with the background color of the speech bubble of participant C and display it in an area (510) of the chat window. However, the method for distinguishing participants in this way is not limited to the above example and is not limited to the above example.

[0086] When one of the recommended responses displayed in an area (510) of the corresponding conversation window is selected, the electronic device can identify a conversation of a specific participant that is most relevant to the selected recommended response. If a conversation of a specific participant that is most relevant to the selected recommended response is identified, the electronic device can bind the identified conversation of the specific participant to the selected recommended response and display them in the conversation window. In this case, the electronic device can first display the conversation of the specific participant and the recommended response for the bound conversation of the specific participant, and then display the recommended response below the displayed conversation of the specific participant. Alternatively, the electronic device can first display the bound recommended response, and then display the conversation of the specific participant below the displayed recommended response. However, this method of displaying the conversation and recommended response of the bound specific participant is merely an example and is not limited to the above example.

[0087] For example, referring to FIG. 5, when a recommended response (511) for participant A is selected from among recommended responses displayed in an area (510) of a conversation window, the electronic device can identify a conversation of participant A that is most relevant to the selected recommended response (511). If the second conversation (520) of participant A is identified as the conversation that is most relevant to the selected recommended response (511), the electronic device can first display the identified second conversation (520) of participant A, and then bind the selected recommended response (511) below the displayed second conversation (520) of participant A and display it (530) in the conversation window. Alternatively, the electronic device can first display the selected recommended response (511), and then display the identified second conversation (520) of participant A below it.

[0088] If multiple conversations (520, 540) of participant A are identified as the most relevant conversations to the selected recommended response (511), the electronic device may bind the multiple conversations (520, 540) of the identified participant A to the selected recommended response (511) and display them in a conversation window (550). In this case, the electronic device may provide the binding result of the identified participant's conversation and the selected recommended response in a preview manner so that the user can respond while recognizing which conversation the recommended response is for.

[0089] Meanwhile, if the conversation of a specific participant most relevant to the selected recommended response is not identified, the electronic device may display only the selected recommended response in the chat window. Furthermore, if another participant's conversation is updated in the group chat window, the electronic device may generate a new recommended response based on the updated conversation. If an unrelated recommended response is generated based on the existing conversation history, the electronic device may update and display the recommended response.

[0090] FIG. 6 is a diagram illustrating a method for displaying a recommended response generated based on a specific link in a group chat conversation window according to one embodiment. The operations illustrated in FIG. 6 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0091] Referring to FIG. 6, when a communication app is activated and a conversation window for a specific group chat is created on the execution screen, the conversation analysis unit (610) can identify whether the user has checked a specific link (e.g., a uniform resource locator (URL)) in the conversation window. If it is determined that the user has checked a specific link, the conversation analysis unit (610) can analyze the content of the specific link checked by the user. For example, when a user clicks a specific link and a webpage or content is loaded, the conversation analysis unit (610) can analyze the loaded webpage or content.

[0092] The response generation unit (620) can provide a recommendation response using the analysis results of a specific link analyzed by the conversation analysis unit (610). For example, the response generation unit (620) can additionally reflect the analysis results of a web page or content for a specific link in the conversation analysis results of participants participating in a group chat to generate a recommendation response for the specific link. For example, as shown in FIG. 6, when a specific link related to a restaurant is input by participant A and the user clicks the specific link, the conversation analysis unit (610) can analyze a web page related to the restaurant loaded through the specific link. The response generation unit (620) can additionally reflect the analysis results of the web page related to the restaurant in the conversation analysis results of participants participating in the group chat to generate a recommendation response for the specific link, such as "A: The food is good."

[0093] Meanwhile, FIG. 6 describes a method of displaying a recommended response generated based on a specific link in a group chat conversation window, but this display method is only one example and is not limited to the above example, and the method can be performed substantially in the same way for a 1:1 chat conversation window.

[0094] FIG. 7 is a diagram illustrating a method for displaying a recommended response to a specific conversation selected by a user in a group chat conversation window according to one embodiment. The operations illustrated in FIG. 7 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0095] Referring to FIG. 7, when a communication app is activated and a conversation window for a specific group chat is created on the execution screen, the electronic device can identify a specific conversation selected by the user from among all conversations displayed in the conversation window. When the specific conversation selected by the user is identified, the electronic device can generate a recommended response based on the context of the selected specific conversation and the entire conversation of the participants participating in the group chat, and display the generated recommended response in an area (710) of the conversation window. When any one of the recommended responses displayed in an area (710) of the conversation window is selected, the electronic device can bind the selected recommended response (e.g., the second speech bubble of participant A) with the specific conversation that is the basis of the selected recommended response and display it in the conversation window (720).

[0096] In addition, when a reply function (e.g., long press) is performed on a previously displayed specific conversation by performing a screen scroll among the entire conversations displayed in the conversation window, the electronic device may provide a separate window object (730) in the form of a pop-up that can provide a recommended response for the specific conversation (e.g., the first speech bubble of participant A) in an area adjacent to the specific conversation for which the reply function was performed. However, the method of providing a recommended response for the specific conversation for which the reply function was performed in this way is only one example and is not limited to the above example.

[0097] Meanwhile, FIG. 7 describes a method of displaying a recommended response for a specific conversation selected by a user in a group chat conversation window, but this display method is only one example and is not limited to the above example, and the method can be performed substantially in the same way for a 1:1 chat conversation window.

[0098] FIG. 8 is a diagram illustrating a method for displaying a recommended response generated based on attached content in a group chat conversation window according to one embodiment. The operations illustrated in FIG. 8 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0099] Referring to FIG. 8, the conversation parsing unit (810) can monitor conversations between participants in a group chat and parse the monitored conversations. In this case, if content is shared from another participant via a communication app, the conversation parsing unit (810) can parse the shared content.

[0100] If the shared content is an image or video, the conversation analysis unit (820) can analyze the parsed image or video, and the response generation unit (830) can additionally reflect the analysis results of the parsed image or video in the conversation analysis results of the participants participating in the group chat to generate a recommendation response for the image or video. At this time, the response generation unit (830) can provide a recommendation response for the image itself or the video itself using only the analysis results of the parsed image or video. For example, if the shared content is an image, and the analysis result of the parsed image determines that the image is related to a concert, the response generation unit (830) can generate a recommendation response for the image itself, such as "A: Did you go to the concert?"

[0101] Alternatively, if the parsed image or video is identified as being related to the user by analyzing the relevance between the parsed image or video and the user, the response generation unit (830) may additionally reflect the analysis results of the parsed image or video in the conversation analysis results of the participants participating in the group chat to provide a recommended response that does not deviate from the context of the entire conversation. For example, if the response generation unit (830) determines that the parsed image is related to a concert of a specific singer as a result of the analysis of the parsed image, and if the user's previous conversation history confirms that the user has attended a concert of the specific singer, the response generation unit (830) may generate a recommended response that is more personalized to the user while maintaining the context of the entire conversation, such as "A: That was cool."

[0102] Meanwhile, the response generation unit (830) can bind content shared by other participants and a recommended response generated based on the shared content and display it in one area of ​​the conversation window, thereby enabling the user to distinguish which content the recommended response is for.

[0103] Meanwhile, FIG. 8 describes a method of displaying a recommended response generated based on attached content in a group chat conversation window, but this display method is only one example and is not limited to the above example, and the method can be performed substantially the same way for a 1:1 chat conversation window.

[0104] FIG. 9 is a diagram illustrating a method for displaying a changed recommended response in a group chat conversation window as other participants' conversations are added, according to one embodiment. The operations illustrated in FIG. 9 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0105] Referring to FIG. 9, the conversation parsing unit (910) can monitor conversations between participants in a group chat and parse the monitored conversations. In this case, if content is shared from a specific participant via a communication app, the conversation parsing unit (910) can parse the shared content.

[0106] The conversation analysis unit (920) can analyze the parsed content, and the response generation unit (930) can additionally reflect the analysis results of the parsed content in the conversation analysis results of the participants participating in the group chat to generate a recommended response for the shared content.

[0107] At this time, if other participants' conversations are added to the content shared by a specific participant, the conversation analysis unit (920) may analyze the conversations of the other participants added, and the response generation unit (930) may update the recommended response based on the additional conversations of the other participants analyzed. In this case, the response generation unit (930) may update the recommended response for the shared content by considering only the additional conversations related to the shared content, excluding additional conversations unrelated to the shared content among the conversations of the other participants added.

[0108] FIG. 10 is a diagram illustrating a method for generating a recommendation response when video content is attached according to one embodiment. The operations illustrated in FIG. 10 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0109] Referring to FIG. 10, the conversation parsing unit (1010) can monitor conversations between participants in a group chat and parse the monitored conversations. In this case, if video content is shared from another participant via a communication app, the conversation parsing unit (1010) can parse the shared video content.

[0110] The conversation analysis unit (1020) can analyze the content of all frames of the shared video content using the parsed video content, and the response generation unit (1030) can additionally reflect the analysis results of the parsed video content to the conversation analysis results of the participants participating in the group chat to provide a recommended response for the corresponding video content. At this time, when the video content is shared through a communication app, the electronic device can provide a preview interface (1040) for the corresponding video content near the input window. At this time, the preview interface (1040) can also provide a timeline of the video content so that the user can view the frames of a desired time period. If the user selects a timeline of a specific point in time, the response generation unit (1030) can generate a recommended response using the analysis results from the first frame to the frames of the point in time of the selected timeline. Alternatively, the response generation unit (1030) can also generate a recommended response using the frame analysis results for the timeline of a specific point in time selected by the user.

[0111] Meanwhile, FIG. 10 describes a method of generating a recommended response and displaying it in a group chat conversation window when video content is attached. However, this display method is only one example and is not limited to the above example, and the method can be performed substantially the same way in a 1:1 chat conversation window.

[0112] FIG. 11 is a diagram illustrating a method for generating a recommendation response based on a request from a user according to one embodiment. The operations illustrated in FIG. 11 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0113] Referring to Figure 11, the conversation parsing unit (1110) can monitor conversations among participants in a group chat and parse the monitored conversations. More specifically, the conversation parsing unit (1110) can decompose the conversations among group chat participants into meaningful units. The conversations among group chat participants, decomposed into meaningful units, can be used for subsequent conversation analysis.

[0114] The conversation analysis unit (1120) can analyze conversations of group chat participants, broken down into meaningful units by the conversation parsing unit (1110), to determine whether there is a request from the user. For example, the conversation analysis unit (1120) can determine that there is a request from the user in conversations in which interrogative endings or interrogative punctuation marks (e.g., question marks (?)) indicating interrogative sentences are identified among the group chat participants. However, the method for determining whether there is a request from the user is merely one example and is not limited to the above example.

[0115] The response generation unit (1130) can generate a recommended response to a user request identified through the conversation analysis results of group chat participants analyzed by the conversation analysis unit (1120). For example, if a request for a photo with a specific condition is identified from another participant, such as "Do you have any family photos taken on vacation?", the response generation unit (1130) can search for photos related to the specific condition using the search function within the user's electronic device. The response generation unit (1130) can filter the search results for photos related to the specific condition and provide a single photo as a recommended response. Alternatively, the response generation unit (1130) can provide a separate window object in the form of a pop-up window so that the user can directly select a photo from the search results related to the specific condition. This allows the user to avoid having to leave the communication app to select specific content from the gallery. At this time, the user can select at least one photo included in the window object through the swipe function, and the response generation unit (1130) can provide the photo selected by the user as a recommended response.

[0116] In addition, if a request for specific information, such as "Does anyone know XX's phone number?", is identified from another participant, the response generation unit (1130) can search for the specific information by utilizing the search function within the user's electronic device. Similarly, the response generation unit (1130) can perform filtering on the search results for specific information and provide one of the determined pieces of information as a recommended response. Alternatively, the response generation unit (1130) can provide a separate window object in the form of a pop-up so that the user can directly select the search results for specific information. At this time, the user can select at least one specific information included in the window object by using the swipe function, and the response generation unit (1130) can provide the specific information selected by the user as a recommended response.

[0117] Meanwhile, FIG. 11 describes a method of generating a recommended response based on a request from a user and displaying it in a conversation window of a group chat. However, this display method is only an example and is not limited to the above example, and the method can be performed substantially in the same way for a conversation window of a 1:1 chat.

[0118] FIGS. 12A and 12B are diagrams illustrating a method for generating a recommended response in a notification pop-up state of a communication app according to one embodiment. The operations illustrated in FIGS. 12A and 12B may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0119] Referring to FIG. 12A, if a message is received while the user is not within the communication app, the electronic device may provide the received message in the form of a pop-up window, depending on the settings of the communication app. In this case, if the received message is from another participant in the group chat, the response generation unit (1210) may filter and provide only the recommended response for the participant who sent the message. For example, if Participant A, Participant B, and Participant C are participating in the group chat, and a message is received from Participant C and provided in the form of a pop-up window, the response generation unit (1210) may filter and provide only the recommended response for Participant C (1220).

[0120] Referring to FIG. 12b, in a situation (1230) where a user responds using a pop-up window, if another participant's conversation is added, the electronic device can update the pop-up window with the added conversation of the other participant (1240). Alternatively, if a user interaction is identified (1250), such as clicking a refresh button before the pop-up window closes, the electronic device can update the pop-up window (1240). In this case, the response generation unit (1210) can update the recommended response by additionally considering the conversation of the other participant added to the pop-up window.

[0121] Meanwhile, when responding via a pop-up window, there are cases where other participants' conversations prior to the response may not be acknowledged. Therefore, when responding via a pop-up window, the communication app can determine that the user has acknowledged only the conversations of other participants corresponding to the response, and handle message acknowledgement synchronization within the conversation window as an exception (e.g., removing the "1").

[0122] Meanwhile, FIGS. 12a and 12b illustrate a method of generating a recommended response in a notification pop-up state of a communication app and displaying it in a conversation window of a group chat. However, this display method is only one example and is not limited to the above example, and the method can be performed substantially in the same way for a conversation window of a 1:1 chat.

[0123] FIG. 13 is a diagram illustrating a method for generating a recommended response based on relationships between participants participating in a group chat according to one embodiment. The operations illustrated in FIG. 13 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0124] Referring to Figure 13, the conversation parsing unit (1310) can monitor conversations between participants in a group chat and parse the monitored conversations. More specifically, the conversation parsing unit (1310) can decompose the conversations between group chat participants into meaningful units.

[0125] The conversation analysis unit (1320) can analyze the conversations of group chat participants that have been broken down into meaningful units through the conversation parsing unit (1310). More specifically, the conversation analysis unit (1320) can perform analysis by dividing the conversations of group chat participants into the entire conversation and individual conversations for each participant. Based on the entire conversation and individual conversations for each participant that have been divided in this way, the conversation analysis unit (1320) can generate input data for the response generation unit (1330) to generate recommended responses for each participant. According to one embodiment, the conversation analysis unit (1320) can generate input data for the response generation unit (1330) using only the individual conversation of participant A to generate a recommended response for participant A. Alternatively, according to one embodiment, the conversation analysis unit (1320) can generate input data for the response generation unit (1330) using not only the individual conversation of participant B but also a portion of the entire conversation to generate a recommended response for participant B. At this time, a part of the entire conversation used to generate input data may correspond to the context of the entire data or summary information of the entire conversation.

[0126] The response generation unit (1330) may generate a recommended response for each participant based on the results of conversation analysis of the participants participating in the group chat. At this time, the response generation unit (1330) may additionally analyze the relationships between the participants participating in the group chat and determine the tone of the sentences constituting the recommended response based on the results of the analysis. For example, if the relationship between Participants A and B participating in the group chat is determined to be a relationship of high intimacy, such as a peer group or family members, the response generation unit (1330) may generate the sentences constituting the recommended response in casual language. Conversely, if the relationship between Participants A and B participating in the group chat is determined to be a formal relationship, such as a work colleague or superior, the response generation unit (1330) may generate the sentences constituting the recommended response in honorific language. However, the method of determining the tone of the sentences constituting the recommended response based on the relationships between the participants participating in the group chat is merely an example and is not limited to the above example.

[0127] At this time, the response generation unit (1330) can analyze the relationship between the user who participated in the group chat and other participants and the relationship between other participants by using the conversation included in the group chat or the past conversation history between the participants.

[0128] Meanwhile, as shown in FIG. 13, in addition to existing participants such as Participant A and Participant B, a new participant such as Participant C may participate in the group chat. In this case, the response generation unit (1330) may redefine the pre-defined relationship information within the group chat by analyzing additional conversations caused by the new participant. If the relationship information within the group chat is redefined in this way, the response generation unit (1330) may change the tone of the sentences that constitute the recommended response based on the redefined relationship information.

[0129] Meanwhile, some or all of the operations performed by the conversation analysis unit (1320) and response generation unit (1330) among the components of FIG. 13 may be performed via an external server. According to one embodiment, the electronic device may transmit the conversation of group chat participants parsed by the conversation parsing unit (1310) to an external server via an API, and then receive the conversation analysis results performed on the external server to generate a recommended response via the response generation unit (1330). In this case, the conversation analysis unit (1320) among the components of FIG. 13 may be omitted. Alternatively, the electronic device may transmit the conversation analysis results performed by the conversation analysis unit (1320) to an external server via an API, and then receive the recommended response generation results performed on the external server to display on the display. In this case, the recommended response generated by the external server may be a result in which the tone of the sentence is determined by the relationships between the participants participating in the group chat. Similarly, in this case, the response generation unit (1330) among the components of FIG. 13 may be omitted.

[0130] FIG. 14 is a diagram illustrating a method for generating a recommended response when an original message is deleted during a conversation among participants in a group chat according to one embodiment. The operations illustrated in FIG. 14 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0131] Referring to FIG. 14, if an original message is deleted during a conversation among participants in a group chat, the electronic device may generate additional recommended responses based on the content or deletion action of the deleted original message. For example, if participant C in a group chat accidentally uploads and then immediately deletes a nude image of himself, the electronic device may additionally generate recommended responses related to the content of the deleted original message, such as "Oh, be careful" or "What a mess." Alternatively, the electronic device may additionally generate recommended responses related to the deletion of the original message, such as "What was that about?"

[0132] Meanwhile, in a situation where a user is provided with recommended responses based on the conversations of participants in a group chat, if a particular participant deletes his or her original message, the electronic device may change the UI (user interface) to display the recommended response corresponding to the deleted original message. For example, the electronic device may display the recommended response corresponding to the deleted original message transparently or in a darkened state. However, the method of processing the recommended response corresponding to the deleted original image is merely an example and is not limited to the above example.

[0133] Meanwhile, Fig. 14 describes a method of generating a recommended response and displaying it in a group chat conversation window when the original message has been deleted. However, this display method is only an example and is not limited to the above example, and the method can be performed substantially the same way in a 1:1 chat conversation window.

[0134] FIG. 15 is a diagram illustrating a method for generating a recommendation response based on user status information according to one embodiment. The operations illustrated in FIG. 15 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0135] Referring to FIG. 15, an electronic device can detect a user's status information based on a sensor when receiving messages from other participants, and generate a recommended response based on the detected status information. For example, if a message is received from participant A in a group chat saying, "People who don't have time at 7 p.m. on Saturday," the electronic device can identify status information, such as whether the user is sleeping, exercising, or playing a game, at the time of receiving the message. If the identified status information determines that the user is sleeping, the electronic device can generate and provide a recommended response that reflects the user's status information, such as, "I'm sleeping right now, but I'll let you know as soon as I wake up."

[0136] Meanwhile, FIG. 15 describes a method of generating a recommended response based on the user's status information and then displaying it in a group chat conversation window. However, this display method is only one example and is not limited to the above example, and the method can be performed substantially in the same way for a 1:1 chat conversation window.

[0137] FIG. 16 is a diagram illustrating a method for generating a recommended response based on the degree of response of other participants to a user's message, according to one embodiment. The operations illustrated in FIG. 16 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0138] Referring to FIG. 16, the electronic device may check the number of reactions or replies from other participants to a message entered by a user, and if the number of confirmed reactions or replies exceeds or falls below a preset standard, the electronic device may generate a recommended response based on the degree of the reaction. For example, if a user enters the message "I failed this test ㅠㅠ" in a group chat, the electronic device may identify the degree of reaction based on the number of reactions or replies from other participants to the message. If the identified degree of reaction falls below the preset standard, the electronic device may generate and provide a recommended response that reflects the degree of reaction of other participants, such as "I know you're all busy, but please pay attention~."

[0139] Meanwhile, FIG. 16 describes a method of generating a recommended response based on the degree of reaction of other participants to a user's message and then displaying it in a group chat conversation window. However, this display method is only one example and is not limited to the above example, and the method can be performed substantially in the same way in a 1:1 chat conversation window.

[0140] FIG. 17 is a diagram illustrating a method for generating a recommended response in an electronic device according to one embodiment. In one embodiment, at least one of the operations in FIG. 17 may be performed simultaneously or in parallel with other operations, and the order of the operations may be changed. Furthermore, at least one of the operations may be omitted, and other operations may be additionally performed. The operations illustrated in FIG. 17 may be performed by at least one component of an electronic device (e.g., the electronic device (101) of FIG. 1 ).

[0141] According to one embodiment, in operation (1710), the electronic device may parse a conversation of multiple participants participating in a communication app. In operation (1720), the electronic device may analyze the parsed conversation of multiple participants by dividing it into the entire conversation and individual conversations for each participant. In operation (1730), the electronic device may generate a recommended response for each of the multiple participants based on the analyzed overall conversation and individual conversations. In operation (1740), the electronic device may combine participant information related to the recommended response with the recommended response and display it on a display.

[0142] In one embodiment, the operation of generating a recommendation response may analyze a webpage or content corresponding to a uniform resource locator (URL) information received from another participant via a communication app. The operation of generating a recommendation response may generate a recommendation response corresponding to the URL information based on the analysis results of the webpage or content corresponding to the URL information, the analysis results of the entire conversation, and the analysis results of individual conversations of the other participant who provided the URL information.

[0143] In one embodiment, the action of generating a recommended response may analyze content corresponding to an image or video received from another participant via a communication app. The action of generating a recommended response may generate a recommended response corresponding to the content based on the analysis results of the content, the analysis results of the entire conversation, and the analysis results of individual conversations of the other participant who provided the content.

[0144] According to one embodiment, the operation of generating a recommended response may generate a recommended response corresponding to a selected specific conversation based on an analysis result of the selected specific conversation and an analysis result of the entire conversation, when a specific conversation is selected from among conversations of multiple participants.

[0145] In one embodiment, the action of generating a recommended response may identify a response request conversation requesting a response from the user based on the analyzed overall conversation and individual conversations. The action of generating a recommended response may retrieve specific information related to the response request conversation using the search function of the electronic device. The action of generating a recommended response may generate search results for the specific information retrieved through the search function as a recommended response corresponding to the response request conversation.

[0146] In one embodiment, the action of displaying on the display may combine conversations of other participants related to the recommended response with the recommended response and display them on the display.

[0147] In one embodiment, the display action may prioritize the recommended responses generated for each of the multiple participants. The priority of the recommended responses may be given to conversations displayed in the communication app that are more recent or have a higher urgency in the response request.

[0148] In one embodiment, an electronic device can analyze relationships between multiple participants in a communication app. The action of generating a recommended response can determine the tone of the recommended response based on the analyzed relationships between the multiple participants.

[0149] Electronic devices according to various embodiments disclosed in this disclosure 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 embodiments of this disclosure are not limited to the aforementioned devices.

[0150] The various embodiments of the present disclosure and the terminology used therein are not intended to limit the technical features described in the present disclosure 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 the present disclosure, 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 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.

[0151] The term "module" used in various embodiments of the present disclosure 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).

[0152] Various embodiments of the present disclosure 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) of FIG. 1). For example, a processor (e.g., a processor (120)) of a machine (e.g., an electronic device (101)) may call at least one command 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.

[0153] According to one embodiment, the method according to various embodiments disclosed in the present disclosure may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0154] 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 arranged 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.

[0155] The embodiments of the present invention disclosed in this specification and drawings are merely specific examples presented to easily explain the technical contents according to the embodiments of the present invention and to help understand the embodiments of the present invention, and are not intended to limit the scope of the embodiments of the present invention. Therefore, the scope of the embodiments of the present invention should be interpreted as including all changes or modified forms derived based on the technical idea of ​​the embodiments of the present invention in addition to the embodiments disclosed herein.

Claims

1. In an electronic device (101), At least one processor (120) comprising a processing circuit; and A memory (130) comprising one or more storage media storing instructions, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Parsing conversations between multiple participants in a communication app, The above parsed conversations of multiple participants are analyzed by dividing them into the entire conversation and individual conversations for each participant. Generate a recommended response for each of the plurality of participants based on the overall conversation and individual conversations analyzed above, To combine participant information related to the above recommended response with the above recommended response and display it on the display; Electronic device (101).

2. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: When URL (uniform resource locator) information is received from another participant through the above communication app, the web page or content corresponding to the URL information is analyzed, Generate a recommendation response corresponding to the URL information based on the analysis results of the web page or content corresponding to the URL information, the analysis results of the entire conversation, and the analysis results of individual conversations of other participants who provided the URL information. Electronic device (101).

3. In any one of paragraphs 1 and 2, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: If content corresponding to an image or video is received from another participant through the above communication app, the content is analyzed, Generate a recommendation response corresponding to the content based on the analysis results of the content, the analysis results of the entire conversation, and the analysis results of individual conversations of other participants who provided the content. Electronic devices (101).

4. In any one of paragraphs 1 to 3, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: To generate a recommendation response for the content itself based on the analysis results of the above content. Electronic devices (101).

5. In any one of paragraphs 1 to 4, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Based on the analysis results of the above content, the relevance between the content and the user is analyzed, If the analyzed relevance is higher than the preset standard, information related to the user is generated as a recommended response. Electronic devices (101).

6. In any one of paragraphs 1 to 5, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: When a specific conversation is selected from among the conversations of the above multiple participants, a recommendation response corresponding to the selected specific conversation is generated based on the analysis results of the selected specific conversation and the analysis results of the entire conversation. Electronic devices (101).

7. In any one of paragraphs 1 to 6, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Identify a response request conversation that requests a response from the user based on the overall conversation and individual conversations analyzed above, Search for specific information related to the above response request conversation by utilizing the search function of the electronic device, Generate a search result for the specific information searched through the above search function as a recommended response corresponding to the above response request conversation. Electronic devices (101).

8. In any one of paragraphs 1 to 7, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Combining conversations of other participants related to the above recommended response with the above recommended response and displaying them on the display; Electronic device (101).

9. In any one of paragraphs 1 to 8, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Display the recommended responses generated for each of the above multiple participants in order of priority; The priority of the above recommended responses is: The more recent the conversation displayed in the above communication app is, and the higher the urgency of the request for a response to the conversation, the higher the priority given to the conversation. Electronic device (101).

10. In any one of paragraphs 1 to 9, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Analyze the relationships between multiple participants who participated in the above communication app, To determine the tone of the recommended response based on the relationships between the multiple participants analyzed above. Electronic device (101).

11. In any one of paragraphs 1 to 10, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: To select and analyze conversations of multiple participants in the above communication app, including conversations on a specific topic or during a specific period. Electronic device (101).

12. In the operating method of an electronic device (101), The act of parsing a conversation between multiple participants in a communication app; An action of analyzing the above-mentioned parsed conversation of multiple participants by dividing it into the entire conversation and individual conversations for each participant; An operation of generating a recommended response for each of the plurality of participants based on the overall conversation and individual conversations analyzed above; and An action of combining participant information related to the above recommended response with the above recommended response and displaying it on the display. A method of operation comprising:

13. In paragraph 12, The action of generating the above recommended response is: When URL (uniform resource locator) information is received from another participant through the above communication app, an action of analyzing a web page or content corresponding to the URL information; and An operation of generating a recommendation response corresponding to the URL information based on the analysis results of the web page or content corresponding to the URL information, the analysis results of the entire conversation, and the analysis results of individual conversations of other participants who provided the URL information. A method of operation comprising:

14. In any one of paragraphs 12 to 13, The action of generating the above recommended response is: When content corresponding to an image or video is received from another participant through the above communication app, an action of analyzing the content; and An action to generate a recommended response corresponding to the content based on the analysis results of the content, the analysis results of the entire conversation, and the analysis results of individual conversations of other participants who provided the content. A method of operation comprising:

15. In any one of paragraphs 12 to 14, The action of generating the above recommended response is: When a specific conversation is selected from among the conversations of the above multiple participants, an operation of generating a recommended response corresponding to the selected specific conversation based on the analysis results of the selected specific conversation and the analysis results of the entire conversation. A method of operation comprising:

Images