Electronic device, method, and computer-readable storage medium for obtaining text to be input to neural network

Abstract

An electronic device according to an embodiment is configured to obtain a first text on the basis of receiving a first user input from a user. The electronic device is configured to generate a second text for obtaining a second user input by using a keyword corresponding to a portion of the first text, and obtain template information indicating a format corresponding to a neural network for obtaining output information related to the first text. The electronic device is configured to obtain a third text obtained on the basis of a second user input after outputting the second text. The electronic device is configured to obtain a fourth text having the format and based on the first text and the third text by using the template information.

Description

Electronic device, method, and computer-readable storage medium for obtaining text to be input to a neural network

[0001] The present disclosure relates to an electronic device, a method, and a computer-readable storage medium for obtaining text to be input to a neural network.

[0002] A large language model (LLM) can refer to a conversational language model comprised of an artificial neural network with multiple parameters. Large language models can be trained using unlabeled training data, either supervised or unsupervised. To improve the quality of the output from a large language model, prompt engineering can be used to adjust the input values ​​of the large language model.

[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] An electronic device according to one embodiment may include at least one processor including a memory and a processing circuit, storing instructions and including one or more storage media. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain a first text based on receiving a first user input from a user. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate a second text for obtaining a second user input using a keyword corresponding to a portion of the first text and to obtain template information representing a format corresponding to a neural network for obtaining output information related to the first text. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain a third text obtained based on the second user input after outputting the second text. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain a fourth text based on the first text and the third text in the format using the template information.

[0005] A method of an electronic device according to one embodiment may include an operation of obtaining a first text based on receiving a first user input from a user. The method may include an operation of generating a second text for obtaining a second user input using a keyword corresponding to a portion of the first text and obtaining template information representing a format corresponding to a neural network for obtaining output information related to the first text. The method may include an operation of obtaining a third text obtained based on the second user input after outputting the second text. The method may include an operation of obtaining a fourth text based on the first text and the third text with the format using the template information.

[0006] A computer-readable storage medium storing one or more programs according to one embodiment, wherein the one or more programs, when executed by a processor of an electronic device, cause the electronic device to obtain a first text based on receiving a first user input from a user. The one or more programs, when executed by the processor of the electronic device, cause the electronic device to generate a second text for obtaining a second user input using a keyword corresponding to a portion of the first text and to obtain template information representing a format corresponding to a neural network for obtaining output information related to the first text. The one or more programs, when executed by the processor of the electronic device, cause the electronic device to obtain a third text obtained based on the second user input after outputting the second text. The one or more programs, when executed by the processor of the electronic device, cause the electronic device to obtain a fourth text based on the first text and the third text having the format using the template information.

[0007] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0008] FIG. 2 illustrates an example block diagram of an electronic device according to one embodiment.

[0009] FIG. 3 illustrates an example of an operation of an electronic device according to one embodiment to obtain a keyword.

[0010] FIG. 4A illustrates an example of a flowchart illustrating the operation of an electronic device according to one embodiment.

[0011] FIG. 4b illustrates an example of an operation of an electronic device according to one embodiment of the present invention to obtain sub-question information using an additional question.

[0012] FIG. 5 illustrates an example of a template obtained by an electronic device according to one embodiment.

[0013] FIG. 6 illustrates an example of an operation of an electronic device generating a prompt according to one embodiment.

[0014] FIG. 7 illustrates an example of a user interface for obtaining a prompt according to one embodiment.

[0015] FIG. 8 illustrates an example of a flowchart illustrating the operation of an electronic device according to one embodiment.

[0016] FIG. 9 is a block diagram illustrating an integrated intelligence system according to various embodiments.

[0017] FIG. 10 is a diagram showing the form in which relationship information between concepts and operations according to various embodiments is stored in a database.

[0018] FIG. 11 is a diagram illustrating a screen for processing voice input received through an intelligent app by an electronic device according to various embodiments.

[0019] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0020] 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 the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the server (108) via a second network (199) (e.g., a long-range wireless communication network). In 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)).

[0021] 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). 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.

[0022] 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.

[0023] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0024] 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).

[0025] 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).

[0026] 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.

[0027] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., 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).

[0032] The 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. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0033] 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.

[0034] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0035] 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.

[0036] 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 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).

[0037] 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.

[0038] 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, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected 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).

[0039] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In 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.

[0040] 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)).

[0041] 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 1304) 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, 1304, or 1308). 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.

[0042] Fig. 2 illustrates an example of a block diagram of an electronic device according to one embodiment. The electronic device (101) of Fig. 2 may include the electronic device (101) of Fig. 1.

[0043] Referring to FIG. 2, an electronic device (101) according to one embodiment may include at least one of a processor (210) (e.g., the processor (120) of FIG. 1), a memory (220) (e.g., the memory (130) of FIG. 1), a display (250) (e.g., the display module (160) of FIG. 1), a microphone (260) (e.g., the input module (150) of FIG. 1), a speaker (270) (e.g., the audio output module (155) of FIG. 1), or a communication circuit (280) (e.g., the communication module (190) of FIG. 1). The processor (210), the memory (220), the display (250), the microphone (260), the speaker (270), and the communication circuit (280) may be electrically and / or operably coupled with each other by an electronic component such as a communication bus (202). In one embodiment, the hardware of the electronic device (101) being operatively coupled may mean that a direct connection or an indirect connection is established between the hardwares, either wired or wireless, such that the second hardware is controlled by the first hardware among the hardwares. Although illustrated based on different blocks, the embodiment is not limited thereto, and some of the hardware of FIG. 2 (e.g., at least a portion of the processor (210), the memory (220), and the communication circuit (280)) may be included in a single integrated circuit, such as a system on a chip (SoC). The type and / or number of hardware included in the electronic device (101) is not limited to that illustrated in FIG. 2. For example, the electronic device (101) may include only some of the hardware components illustrated in FIG. 2.

[0044] According to one embodiment, the processor (210) of the electronic device (101) may include hardware for processing data based on one or more instructions. The hardware for processing data may include, for example, an arithmetic and logic unit (ALU), a floating point unit (FPU), a field programmable gate array (FPGA), a central processing unit (CPU), and / or an application processor (AP). The number of processors (210) may be one or more. For example, the processor (210) may have a multi-core processor structure such as a dual core, a quad core, or a hexa core.

[0045] According to one embodiment, the memory (220) of the electronic device (101) may include hardware components for storing data and / or instructions input and / or output to the processor (210). The memory (220) may include, for example, volatile memory such as random-access memory (RAM) and / or non-volatile memory such as read-only memory (ROM). The volatile memory may include, for example, at least one of dynamic RAM (DRAM), static RAM (SRAM), cache RAM, and pseudo SRAM (PSRAM). The non-volatile memory may include, for example, at least one of programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, hard disk, compact disc, solid state drive (SSD), and embedded multimedia card (eMMC).

[0046] According to one embodiment, a display (250) of an electronic device (101) can output visualized information to a user. For example, the display (265) can be controlled by a processor (210) including a circuit such as a GPU (graphic processing unit) to output visualized information to the user. The display (250) can include a flat panel display (FPD) and / or electronic paper. The FPD can include a liquid crystal display (LCD), a plasma display panel (PDP), and / or one or more light emitting diodes (LEDs). The LEDs can include organic LEDs (OLEDs).

[0047] According to one embodiment, the display (250) of the electronic device (101) may include a sensor (e.g., a touch sensor panel (TSP)) for detecting an external object (e.g., a user's finger) on the display (250). For example, based on the TSP, the electronic device (101) may detect an external object that is in contact with the display (250) or floating on the display (250). In response to detecting the external object, the electronic device (101) may execute a function related to a specific visual object corresponding to a position of the external object on the display (250) among visual objects displayed within the display (250).

[0048] A speaker (270) according to one embodiment can output an audio signal. For example, the electronic device (101) can receive audio data from an external device (e.g., the electronic device (102) of FIG. 1, the server (108) of FIG. 1, a smartphone, a PC, a PDA, or an access point). The electronic device (101) can output the received audio data using the speaker (270). For example, the speaker (270) can receive an electrical signal. The speaker (270) can convert the electrical signal into a sound wave signal. The speaker (270) can output an audio signal including the converted sound wave signal. For example, the electronic device (101) can output an audio signal representing text. Based on outputting the audio signal representing the text, the electronic device can obtain a voice signal representing a response to the text to the user through the microphone (260).

[0049] According to one embodiment, a microphone (260) of an electronic device (101) may receive audio data (e.g., a user's voice). For example, the electronic device (101) may include one or more microphones. The microphone (260) may be disposed in a portion of a housing of the electronic device (101). The microphone (260) may be referred to as a feedback microphone on the side where it is disposed adjacent to a speaker (270). The microphone (260) may be disposed in a portion of the housing where a sensor (e.g., a sensor module of FIG. 1) of the electronic device (101) is included. The microphone (260) may be referred to as a feedforward microphone on the side where it is disposed toward the outside of the electronic device (101). However, the present invention is not limited thereto. The electronic device (101) may obtain text corresponding to the utterance (or speech) based on receiving a voice signal representing the user's utterance using the microphone (260). For example, the electronic device (101) can obtain the text based on speech to text (STT) and / or automatic speech recognition (ASR) based on receiving a voice signal.

[0050] In one embodiment, the communication circuit (280) of the electronic device (101) may include hardware components for supporting transmission and / or reception of electrical signals between the electronic device (101) and an external electronic device (e.g., a server providing a large language model). The communication circuit (280) may include, for example, at least one of a modem (modulator and demodulator (MODEM), an antenna, and an optical / electronic (O / E) converter. The communication circuit (480) may support transmission and / or reception of electrical signals based on various types of protocols, such as Ethernet, a local area network (LAN), a wide area network (WAN), wireless fidelity (WiFi), Bluetooth, Bluetooth low energy (BLE), ZigBee, long term evolution (LTE), 5G new radio (NR), and / or 6G.

[0051] According to one embodiment, one or more instructions (or commands) representing operations and / or actions to be performed on data by the processor (210) may be stored within the memory (220) of the electronic device (101). A set of one or more instructions may be referred to as firmware, an operating system, a process, a routine, a sub-routine, and / or an application (e.g., the application (146) of FIG. 1). For example, the electronic device (101) and / or the processor (210) may perform at least one of the operations of FIG. 4A and FIG. 8 when a set of a plurality of instructions distributed in the form of an operating system, firmware, a driver, and / or an application is executed. Hereinafter, the fact that an application is installed in an electronic device (101) may mean that one or more instructions provided in the form of an application are stored in the memory (220) of the electronic device (101), and that the one or more applications are stored in a format executable by the processor (210) of the electronic device (101) (e.g., a file having an extension specified by the operating system of the electronic device (101)).

[0052] According to one embodiment, the memory (220) of the electronic device (101) may include an input processing unit (223) and / or an output processing unit (245). The input processing unit (223) may include a neural network that generates text to be input to the output processing unit (245). The input processing unit (223) may be implemented based on a rule-based method, a statistical method (e.g., a neural network), a knowledge graph-based method, or a combination thereof.

[0053] For example, the electronic device (101) can identify a first user input from a user through an input device (e.g., a microphone (260)). The first user input can represent an audio signal. The first user input can be a touch input identified through the display (250). The first user input can represent text. For example, the first user input can represent a main question for obtaining output information to be output through the output processing unit (245). The main question can be represented as the text (e.g., "Recommend a travel destination").

[0054] For example, the electronic device (101) can identify a first text obtained based on receiving a first user input using a keyword identifier (225). The electronic device (101) can identify a portion of the first text. The electronic device (101) can identify the portion representing a keyword. The electronic device (101) can identify the keyword using mapping data or a morphological analyzer based on the execution of the keyword identifier (225). For example, the electronic device (101) can analyze morphemes of the first text using a morphological analyzer to identify a portion representing a noun. The electronic device (101) can identify a keyword corresponding to the portion. Based on identifying the keyword, the electronic device (101) can obtain one or more keyword categories corresponding to the keyword. The electronic device (101) may utilize a question generator (230) to generate a second text for obtaining user input related to a keyword category.

[0055] For example, the electronic device (101) may generate a second text representing a question based on the keyword (or number of keywords) identified through the keyword identifier (225) based on the execution of the question generator (230). The second text may include at least one sentence. The electronic device (101) may obtain a second user input from the user based on outputting the second text. The second user input may represent a third text representing an answer to the second text. The electronic device (101) may output the second text based on displaying the second text on the display (250). The electronic device (101) may output the second text based on outputting an audio signal representing the second text through the speaker (270). However, the present invention is not limited thereto.

[0056] For example, the electronic device (101) may change the third text based on receiving the second user input. The third text may represent an answer provided by the user to the electronic device (101). If the third text represents a sentence (e.g., "I prefer the color red"), the electronic device (101) may store the third text as sub-question information. The sub-question information may be referred to as answer information from the perspective that the third text represents an answer. If the third text represents a word (e.g., "red"), the electronic device (101) may change the third text into a sentence (e.g., "I prefer the color red") that includes the word. The electronic device (101) may change the word into a sentence using mapping data corresponding to the word. For example, the electronic device (101) may change the word into a sentence through a neural network for changing the word into a sentence. The electronic device (101) may store the text changed into a sentence as sub-question information. For example, if the third text represents a sentence (e.g., “I will go for 2 nights and 3 days”), the electronic device (101) can change it to another sentence (e.g., “I will go for 2 nights and 3 days”) having a format corresponding to the output processing unit (245). However, this is not limited thereto.

[0057] For example, the electronic device (101) may obtain template information having a format corresponding to the output processing unit (245) based on the execution of the template generator (235). The electronic device (101) may change at least a portion of the first text received from the user to obtain the template information. The template information may include sentence structure, sentence rules, and / or language information about the sentence. The template information may include slots for detailed search conditions. The electronic device (101) may use mapping data for keywords corresponding to the first text to obtain the template information. If the electronic device (101) cannot obtain the template information using the mapping data, the electronic device (101) may obtain the template information from the first text using a neural network that generates a template. The mapping data may include information indicating frequently used questions and answers to the questions.

[0058] For example, the electronic device (101) may obtain a fourth text to be input into the output processing unit (245) based on the execution of the prompt generator (240). The electronic device (101) may obtain the fourth text using main question information, sub-question information, and / or template information. For example, the fourth output information obtained by inputting the fourth text into the output processing unit (245) may include relatively more information than the first output information obtained by inputting the first text obtained from the user into the output processing unit (245) by the electronic device (101). However, the present invention is not limited thereto.

[0059] For example, the electronic device (101) can input the fourth text into the output processing unit (245) to obtain output information. The output information can represent an answer to the fourth text. Referring to FIG. 2, the output processing unit (245) is illustrated as being included within the electronic device (101), but the output processing unit (245) can be included in an external electronic device. The electronic device (101) can obtain output information by transmitting the fourth text to an external electronic device connected via a communication circuit.

[0060] For example, the output processing unit (245) may include a large language model (LLM). The large language model may refer to a deep learning model for recognizing, converting, processing, or generating specific text, images, and / or videos based on data. The large language model may include a language model that is a type of neural network including a plurality of parameters and can output (or infer) data without fine-tuning using a method such as few-shot learning. The output processing unit (245) may include at least a portion of a transformer model. The output processing unit (245) may be an example of a neural network trained to generate a response to a natural language input. The electronic device (101) may input a fourth text composed of a natural language into the output processing unit (245) to obtain output information composed of a natural language. The electronic device (101) may obtain output information that is understandable to a user.

[0061] As described above, the electronic device (101) according to one embodiment can change the first text obtained from the user into a fourth text using the input processing unit (223) before inputting the first text into the output processing unit (245). The fourth text can include the first text. The fourth text can include content of the first text or meaning of the first text. The electronic device (101) can input the fourth text into the output processing unit (245) to provide the user with a more detailed answer than the answer to the first text. The electronic device (101) can provide a service that allows the user to more easily utilize the output processing unit (245) through the input processing unit (223) for obtaining the fourth text.

[0062] Hereinafter, with reference to FIG. 3, an example of an operation in which an electronic device (101) identifies a keyword using a first text obtained from a user is described.

[0063] FIG. 3 illustrates an example of an operation of an electronic device according to one embodiment of the present invention to acquire a keyword. The electronic device (101) of FIG. 3 may include the electronic device (101) of FIGS. 1 and 2.

[0064] Referring to FIG. 3, an electronic device (101) according to one embodiment can obtain a first text based on a first user input received from a user. The electronic device (101) can obtain a keyword using the first text based on the execution of a keyword identifier (225).

[0065] For example, the electronic device (101) can obtain keywords in the first text using dictionary information (310). The electronic device (101) can identify morphemes in the first text. The electronic device (101) can identify a part representing a noun in the first text. For example, when the electronic device (101) obtains the first text (e.g., “Recommend a travel destination”), the electronic device (101) can analyze the morphemes of the first text to identify a noun, a connective ending, and / or a sentence-closing ending. The electronic device (101) can obtain keywords representing the noun. However, the present invention is not limited thereto.

[0066] For example, the electronic device (101) can determine a keyword category (315) mapped to the keyword based on the keyword acquired. For example, if the keyword is 'region', the keyword category (315) can be determined using information related to the keyword, such as 'Seoul', 'Daejeon', 'Daegu', and 'Busan'. For example, the electronic device (101) can identify the keyword category (315) using the keyword based on regular expression matching. A regular expression can represent a set of strings having a specific rule. Regular expression matching can mean a method for identifying a pattern of characters. The electronic device (101) can extract a keyword category (315) related to the keyword through regular expression matching representing a plurality of keyword categories from the keyword.

[0067] For example, the electronic device (101) may analyze the first text based on named entity recognition (NER). If the electronic device (101) identifies the first text (e.g., "Recommend places to visit in Busan"), the electronic device (101) may refrain from acquiring a keyword category (e.g., region) corresponding to the named entity (or designated word) (e.g., "Busan") in the first text. However, this is not limited thereto.

[0068] For example, the electronic device (101) can identify keywords by using a keyword inference unit (320) for inferring the context of a text. The keyword inference unit (320) may be an example of a language model (LM) that assigns a probability value to each component constituting a sentence. The electronic device (101) can obtain a probability value for each component (e.g., words) included in the first text. For example, the probability value for each component (e.g., words) included in the first text may be represented as probability information (325). The electronic device (101) can obtain keywords (325-1) having a probability value exceeding a specified threshold by using the probability information (325). For example, each of the keywords (325-1) may be mapped to a keyword category.

[0069] For example, the electronic device (101) can remove overlapping keywords from among the first keyword obtained using the dictionary information (310) and the second keyword obtained through the keyword inference unit (320). By removing overlapping keywords from among the first keyword and the second keyword, the electronic device (101) can obtain a keyword (330) to be processed by the question generator (e.g., the question generator (230) of FIG. 2). For example, the electronic device (101) can use the dictionary information (310) and / or the keyword inference unit (320) to obtain the keyword (330). When the electronic device (101) obtains the keyword (330) by using one of the dictionary information (310) and the keyword inference unit (320), the operation of removing the overlapping keyword can be omitted.

[0070] Below, with reference to FIGS. 4a and 4b, an example of an operation in which an electronic device (101) generates a question from a keyword is described.

[0071] FIG. 4A illustrates an example of a flowchart illustrating an operation of an electronic device according to an embodiment. FIG. 4B illustrates an example of an operation of an electronic device according to an embodiment for obtaining sub-question information using an additional question. The electronic devices of FIGS. 4A and 4B may include the electronic device (101) of FIGS. 1 to 3 . At least one of the operations of FIG. 4A may be performed by the electronic device (101) of FIG. 2 . At least one of the operations of FIG. 4A may be controlled by the processor (210) of FIG. 2 . Each of the operations of FIG. 4A may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each of the operations may be changed, and at least two operations may be performed in parallel.

[0072] Referring to FIG. 4A, an electronic device according to one embodiment may identify a keyword at operation 410. The electronic device may obtain a first text corresponding to a user's speech based on a voice signal received through a microphone. Based on the first text obtained, the electronic device may identify a keyword corresponding to a portion of the first text. The first text may be referenced as main question information related to output information to be obtained through an output processing unit (e.g., the output processing unit (245) of FIG. 2).

[0073] Referring to FIG. 4A, an electronic device according to an embodiment may generate a question using a keyword in operation 420. For example, a question generator (e.g., the question generator (230) of FIG. 2) may generate a question from a keyword. The electronic device may generate a second text (e.g., “Do you have a favorite brand?”) to obtain a second user input related to a keyword category (e.g., a brand) mapped to a keyword representing a specified word from a user. The second text may represent a question to obtain an answer from the user. The electronic device may set the number of second texts to be generated based on the number of keywords. However, the present invention is not limited thereto. The electronic device may generate the question to obtain sub-question information to supplement main question information from the user.

[0074] Referring to FIG. 4A, an electronic device according to one embodiment may acquire user input based on outputting a question at operation 430. The user input may represent a response to the question, but is not limited thereto. For example, the question may be referred to as an additional question, as it is used to acquire additional information to further explain the content contained in the first text. For example, the electronic device may acquire a third text based on acquiring the user input.

[0075] Referring to FIG. 4B, an electronic device (101) according to one embodiment can output a second text (421) obtained from a keyword (330) through a question generator (230). The electronic device (101) can display the second text (421) on a display (e.g., the display (250) of FIG. 2) or output an audio signal representing the second text (421) through a speaker. After outputting the second text (421), the electronic device (101) can obtain a third text (441) based on a user input. The user input may include a voice signal received through a microphone or a touch input obtained through the display. For example, after outputting an audio signal representing the second text (421) through a speaker, the electronic device (101) can obtain a third text (441) based on a user input representing a user utterance through a microphone. The electronic device (101) may obtain a third text (441) as a response to the second text (421). From the perspective of processing data representing interaction with the user, the question generator (230) may be referred to as an interaction module.

[0076] Referring to FIG. 4A, an electronic device according to an embodiment may, in operation 440, identify whether text corresponding to a user input corresponds to a template. For example, the electronic device may identify whether the text indicated by the user input is a sentence by tokenizing the text. The electronic device may identify whether the text has a specified template format. The electronic device may perform operation 440 using a deep learning model (or neural network) for classifying specified text having a specified template format. However, the present invention is not limited thereto. Tokens may include words and / or phrases.

[0077] Referring to FIG. 4A, if the text corresponds to the template (operation 440 - Yes), the electronic device according to one embodiment may store the text corresponding to the user input as sub-question information (or answer information) in operation 450. For example, the electronic device may store the text as sub-question information based on changing the text into a text having a format corresponding to an output processing unit (e.g., output processing unit (245) of FIG. 2).

[0078] Referring to FIG. 4A, if the text does not correspond to the template (or if the text corresponding to the user input is a single word) (operation 440-No), in operation 460, the electronic device according to one embodiment may change the text not corresponding to the template to another text corresponding to the template. For example, if the user input represents a single word, the electronic device may obtain a text representing a sentence including the single word. For example, if the third text obtained from the user (e.g., the third text (441) of FIG. 4B) after the electronic device outputs a second text (e.g., Is there a place you want to go?) is a word (e.g., Jeju Island), the electronic device may change the region to a text (or sentence) including the word (e.g., Jeju Island) (e.g., I want to go to Jeju Island).

[0079] For example, an electronic device may obtain a third text (e.g., Jeju Island) that provides additional information about the main question and does not correspond to the template, and then change the third text to another text (e.g., Preferred Region: Jeju Island) that corresponds to the template. In other words, the other text may have the format of the template and may not consist of a single sentence.

[0080] In operation 470 according to one embodiment, the electronic device may store other text as sub-question information. The sub-question information may be included in one area of ​​the template information.

[0081] Below, with reference to FIG. 5, an example of an operation of an electronic device obtaining a template corresponding to text obtained from a user is described.

[0082] FIG. 5 illustrates an example of a template acquired by an electronic device according to one embodiment. Referring to FIG. 5, the electronic device (101) of FIG. 5 may include the electronic device (101) of FIGS. 1 to 4B.

[0083] An electronic device (101) according to one embodiment may obtain a first text (510) based on receiving a user input from a user. Independently of identifying a keyword using the first text (510), the electronic device (101) may obtain a template (505) corresponding to the first text (510) based on the execution of a template generator (235). The electronic device (101) may change the format of a sentence included in the first text (510) into a format corresponding to an output processing unit (e.g., the output processing unit (245) of FIG. 2). The first text (510) may mean a request for output information to be output from the output processing unit. The first text (510) may be referred to as main question information in terms of meaning the request. The electronic device (101) may obtain a template (505) that includes at least a portion of the first text (510) and has a format corresponding to the output processing unit.

[0084] For example, the template (505) can be obtained based on the format of the input to be input to the output processing unit (e.g., the output processing unit (245) of FIG. 2). The template (505) can include a main question area (507) for including at least a portion of the first text (510). The template (505) can include a sub question area (517) for sub question information for specifying the main question information included in the main question area (507). For example, the electronic device (101) can wait until it obtains a third text (e.g., the third text (441) of FIG. 4b) from the user to include the sub question information in the template (505).

[0085] For example, the electronic device (101) can obtain a keyword (e.g., keyword (330) of FIG. 3) through a keyword identifier (e.g., keyword identifier (225) of FIG. 2) based on obtaining the first text (510).

[0086] For example, the electronic device (101) may acquire a second text (e.g., the second text (421) of FIG. 4B) based on the execution of a question generator (e.g., the question generator (230) of FIG. 2) based on acquiring a keyword. The second text may mean a question for acquiring sub-question information from the user. The electronic device (101) may guide the user to request sub-question information based on outputting the second text.

[0087] For example, after outputting the second text, the electronic device (101) may obtain a third text (e.g., the third text (441) of FIG. 4B) based on a user input received from the user. The electronic device (101) may identify whether the third text is a sentence. If the third text is a sentence, the electronic device (101) may store sub-question information indicating the third text. If the third text is a word, the electronic device (101) may generate a sentence including the word. The electronic device (101) may store the generated sentence as sub-question information.

[0088] For example, the electronic device (101) may place the sub-question information within the sub-question area (517) based on the sub-question information obtained.

[0089] According to one embodiment, an electronic device (101) may obtain a template (505) using a first text (510) representing a user's query. Based on the first text (510) obtained, the electronic device (101) may obtain a template (505) using mapping data matching the type of the first text (510). Based on the first text (510) obtained, the electronic device (101) may infer the context of the first text (510). The electronic device (101) may obtain a template (505) matching the context. The number of templates (505) obtained by the electronic device (101) may be one or more. The electronic device (101) may use at least one template selected by the user from among one or more templates. The electronic device (101) may use a user interface for selecting at least one template to identify an input from the user indicating selection of at least one template from among one or more templates. The electronic device (101) may identify the at least one template based on identifying the input, but is not limited thereto.

[0090] As described above, the electronic device (101) according to one embodiment can improve the quality of output information to be output from the output processing unit (245) based on acquiring the template (505). The electronic device (101) can generate a prompt to specifically indicate output information to be output from the output processing unit (245) based on identifying a request corresponding to the first text (510). Hereinafter, with reference to FIG. 6, an example of an operation in which the electronic device (101) generates a prompt to specifically indicate a result value of the output processing unit (245) will be described below.

[0091] FIG. 6 illustrates an example of an operation of an electronic device generating a prompt according to one embodiment. Referring to FIG. 6, the electronic device (101) of FIG. 6 may include the electronic device (101) of FIGS. 1 to 5.

[0092] According to one embodiment, an electronic device (101) can obtain main question information (605) from a user. The main question information (605) can be obtained by identifying a first text (510). For example, based on obtaining the main question information (605), the electronic device (101) can obtain a keyword (330) through a keyword identifier (225).

[0093] For example, the electronic device (101) may obtain a second text (421) through the question generator (230) based on obtaining a keyword (330). The second text (421) may mean a question for obtaining sub-question information (610) from the user. The second text (421) may include at least one sentence. The number of second texts (421) may be set based on the number of keywords (330). Depending on the number of second texts (421), the number of sub-questions included in a sub-question area (e.g., a sub-question area (517) of FIG. 5) may change.

[0094] For example, after outputting the second text (421), the electronic device (101) may obtain the third text (607) based on a user input received from the user (606). The third text (607) may represent the user's (606) answer to the second text (421). The electronic device (101) may identify whether the third text (607) is a sentence. If the third text (607) is a sentence (or if the third text (607) is a text corresponding to a template), the electronic device (101) may identify sub-question information (610) representing the third text. If the third text (607) is a word (or if the third text (607) is a text that does not correspond to a template), the electronic device (101) may generate a sentence (or a text corresponding to a template) including the word. The electronic device (101) can obtain sub-question information (610) representing the generated sentence.

[0095] According to one embodiment, an electronic device (101) can obtain a template (505) through a template generator (235) using a first text (510). The template (505) can be obtained based on a format corresponding to an output processing unit (245). The electronic device (101) can change the first text (510) into a sentence having a format corresponding to the output processing unit. The electronic device (101) can place the changed sentence in the main question area (507) of FIG. 5. In order to obtain an accurate output value as an answer to the context of the first text (510), the electronic device (101) can change the first text (510) into a sentence suitable as an input value for the output processing unit (245).

[0096] For example, the electronic device (101) can obtain a prompt (620) by inputting a template (505) and sub-question information (610) into the prompt generator (240). The electronic device (101) can obtain the prompt (620) by placing the sub-question information (610) in the sub-question area (e.g., the sub-question area (517) of FIG. 5) of the template (505). The prompt (620) may mean an input for generating a response from the output processing unit (245). The response may represent an answer to the prompt (620).

[0097] According to one embodiment, an electronic device (101) may input a prompt (620) to an output processing unit (245) and output output information in response to the prompt (620). The electronic device (101) may obtain the output information using an output processing unit (245) included in an external electronic device. In order to provide the output information to a user, the electronic device (101) may output an audio signal representing the output information through a speaker, or display text representing the output information on a display. The electronic device (101) may provide an interactive artificial intelligence service to a user using the output processing unit (245).

[0098] As described above, the electronic device (101) according to one embodiment can provide prompt engineering to the user. The electronic device (101) can input a first text (510) into the input processing unit (223) including a smaller number of parameters than the output processing unit (245), and generate a prompt (620) for obtaining output information from the output processing unit (245). The prompt (620) can mean a natural language command for obtaining second output information having a relatively higher quality than the first output information for the first text. For example, since the content included in the output information may vary depending on the input input to the output processing unit (245), the electronic device (101) can change the text based on the user's input into a prompt in order to obtain output information having a higher quality. Based on changing the text into a prompt, the electronic device (101) can provide the user with a prompt engineering service that allows for more convenient use of an interactive artificial intelligence service.

[0099] FIG. 7 illustrates an example of a user interface for obtaining a prompt according to one embodiment. The electronic device (101) of FIG. 7 may include the electronic device (101) of FIGS. 1 to 6.

[0100] Referring to FIG. 7, an electronic device (101) according to one embodiment may display a screen (705) on a display (e.g., a display (250) of FIG. 2) for generating a prompt (710) to be input to an output processing unit (e.g., an output processing unit (245) of FIG. 2) based on the execution of an input processing unit (e.g., an input processing unit (223)).

[0101] An electronic device (101) according to one embodiment can identify a user input indicating a first text (510) through a display (250). Based on the identification of the first text (510), the electronic device (101) can identify a keyword (e.g., a travel destination) corresponding to a portion of the first text (510). Based on the identification of the keyword, the electronic device (101) can identify a keyword category (e.g., a place, a period, and / or a cost) mapped to the keyword. Based on the identification of the keyword category, the electronic device (101) can obtain a second text (421). The number of second texts (421) can vary depending on the number of keywords (or keyword categories) corresponding to the first text (510).

[0102] For example, the electronic device (101) may output a subtext (421-1) representing at least one question among the second texts (421). The electronic device (101) may display a text object representing the subtext (421-1) on the display (250). After outputting the subtext (421-1), the electronic device (101) may receive a user input representing an answer to the subtext (421-1). Based on receiving the user input, the electronic device (101) may obtain the subtext (441-1).

[0103] For example, the electronic device (101) can identify whether the subtext (441-1) is a sentence. The electronic device (101) can identify the subtext (441-1) containing a single word (e.g., Jeju Island). Using the single word, the electronic device (101) can obtain a sentence containing the single word (e.g., "I want to go to Jeju Island"). The sentence can be obtained based on a template format corresponding to the output processing unit.

[0104] For example, the electronic device (101) may output subtext (421-2) representing at least one question among the second texts (421). The electronic device (101) may display a text object representing the subtext (421-2) on the display (250). After outputting the subtext (421-2), the electronic device (101) may obtain subtext (441-2) representing the user's answer to the subtext (421-2). Based on obtaining the subtext (441-2), the electronic device (101) may identify whether the subtext (441-2) is a sentence. The electronic device (101) may identify the subtext (441-2) representing a sentence (e.g., "I'll go for 2 nights and 3 days"). The electronic device (101) may store the subtext (441-2) as sub-question information. However, the present invention is not limited thereto. For example, the electronic device (101) can change a sentence representing a subtext (441-2) into another sentence corresponding to the format of the output processing unit (e.g., "I plan to go for 2 nights and 3 days"). The electronic device (101) can obtain sub-question information representing the changed other sentence.

[0105] For example, the electronic device (101) may output subtext (421-3) indicating at least one question among the second texts (421). The electronic device (101) may display a text object indicating the subtext (421-3) on the display (250). After outputting the subtext (421-3), the electronic device (101) may receive a user input indicating an answer to the subtext (421-3). Based on receiving the user input, the electronic device (101) may obtain the subtext (441-3). Based on identifying the subtext (441-3) including a single word, the electronic device (101) may generate a sentence including the single word (e.g., “I will spend about 1 million won”). The electronic device (101) may store the sentence as sub-question information. Subtexts (441-1, 441-2, 441-3) may be included in the third text (441) from the perspective of representing user responses to the second text (421).

[0106] According to one embodiment, an electronic device (101) may generate a prompt (710) based on acquiring a third text (441). The electronic device (101) may generate a fourth text based on the first text (510) and the third text (441). The electronic device (101) may display a prompt (710) indicating the fourth text on the display. The electronic device (101) may place main question information indicating the first text (510) in a main question area (710-1). The electronic device (101) may place a sentence acquired using the first text (510) and having a format for input of an output processing unit in the main question area (710-1). For example, the electronic device (101) may place sub-question information acquired using the third text (441) in a sub-question area (710-2). The electronic device (101) can display a prompt (710) on the display (250).

[0107] According to one embodiment, the electronic device (101) can provide the user with output information obtained by inputting a fourth text representing the prompt (710) into the output processing unit, independently of displaying the prompt (710). For example, the electronic device (101) can obtain main question information representing the first text (510) and sub-question information representing the third text (441). The electronic device (101) can input a fourth text (e.g., text representing the prompt (710)) including the main question information and the sub-question information to assist the main question information into the output processing unit, and output information representing an answer to the main question information.

[0108] For example, when the electronic device (101) utilizes an output processing unit included in an external electronic device, the electronic device (101) may provide a URL (uniform resource locator) for a screen representing the output information to the user. For example, the electronic device (101) may input a fourth text representing a prompt (710) to the output processing unit and display a text object representing the output information on the display (250). The operation of the electronic device (101) providing the user with the output information acquired through the output processing unit is not limited to the above-described embodiment. As an example, the electronic device (101) may output an audio signal representing the output information through a speaker.

[0109] The electronic device (101) described above can reduce the usage of data resources by using the input processing unit (223) that includes relatively smaller parameters than the output processing unit (e.g., the output processing unit (245) of FIG. 2). The electronic device (101) can reduce battery consumption based on the reduced usage of data resources. For example, when using the output processing unit included in an external server, a cost may be incurred based on the number of inputs. The electronic device (101) can reduce the above cost by generating a prompt (710) using the input processing unit (223).

[0110] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0111] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (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.

[0112] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0113] Various embodiments of the present document may be implemented as software (e.g., a program (140) of FIG. 1) including one or more commands stored in a storage medium (e.g., an internal memory (136) or an external memory (138) of FIG. 1) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120) of FIG. 1) of the machine (e.g., an electronic device (101)) may call at least one command among the one or more commands 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 command called. The one or more commands 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.

[0114] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a commodity 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) via 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 an intermediary server.

[0115] 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.

[0116] FIG. 8 illustrates an example of a flowchart illustrating the operation of an electronic device according to an embodiment. The electronic device of FIG. 8 may include the electronic device (101) of FIGS. 1 to 7. At least one of the operations of FIG. 8 may be performed by the electronic device (101) of FIG. 2. At least one of the operations of FIG. 8 may be controlled by the processor (210) of FIG. 2. Each of the operations of FIG. 8 may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each of the operations may be changed, and at least two operations may be performed in parallel.

[0117] Referring to FIG. 8, an electronic device according to one embodiment may obtain a first text based on receiving a first user input from a user in operation 810. The electronic device may obtain the first text based on obtaining a voice signal representing the first text using a microphone (e.g., a microphone (260) of FIG. 2). The electronic device may obtain the first text based on a touch input identified through a display (e.g., a display (250) of FIG. 2).

[0118] Referring to FIG. 8, an electronic device according to an embodiment may, in operation 820, generate a second text for obtaining a second user input using a keyword corresponding to a portion of a first text and obtain template information representing a format corresponding to a neural network for obtaining output information related to the first text. The electronic device may extract a keyword from the first text based on the execution of a keyword identifier (e.g., the keyword identifier (225) of FIG. 2). The electronic device may obtain a second text representing a question related to the context of the first text using the keyword through a question generator (e.g., the question generator (230) of FIG. 2). The electronic device may obtain template information having a format corresponding to the first text through a template generator (e.g., the template generator (235) of FIG. 2). The format may include a format corresponding to an input of an output processing unit (e.g., the output processing unit (245) of FIG. 2).

[0119] Referring to FIG. 8, an electronic device according to an embodiment may, in operation 830, after outputting a second text, obtain a third text obtained based on a second user input. The electronic device may output an audio signal representing the second text through a speaker or display a text object representing the second text on a display. The electronic device may obtain a third text representing a response to the second text based on the second user input. The electronic device may identify whether the third text is a sentence. The electronic device (101) may identify the third text representing a sentence as sub-question information.

[0120] Referring to FIG. 8, an electronic device according to an embodiment may, in operation 840, obtain a fourth text based on a first text and a third text in a format using template information. For example, the electronic device may obtain main question information indicating the first text and sub-question information indicating the third text. The electronic device may obtain the fourth text including the main question information and the sub-question information for assisting the main question information. The fourth text may indicate a prompt to be input to an output processing unit. The electronic device may input the fourth text to the output processing unit and output the output information indicating an answer to the main question information.

[0121] FIG. 9 is a block diagram illustrating an integrated intelligence system according to various embodiments.

[0122] Referring to FIG. 9, an integrated intelligent system of one embodiment may include an electronic device (101), an intelligent server (900) (e.g., server (108) of FIG. 1), and a service server (990) (e.g., server (108) of FIG. 1).

[0123] The electronic device (101) of one embodiment may be a terminal device (or electronic device) that can connect to the Internet, and may be, for example, a mobile phone, a smart phone, a personal digital assistant (PDA), a laptop computer, a TV, white goods, a wearable device, an HMD, or a smart speaker.

[0124] According to the illustrated embodiment, the electronic device (101) may include an interface (177), an input module (150), an audio output module (155), a display module (160), a memory (130), or a processor (120). The above-listed components may be operatively or electrically connected to each other.

[0125] An interface (177) of one embodiment may be configured to connect to an external device and transmit and receive data. An input module (150) of one embodiment may receive sound (e.g., user speech) and convert it into an electrical signal. An audio output module (155) of one embodiment may output the electrical signal as sound (e.g., voice).

[0126] The display module (160) of one embodiment may be configured to display an image or video. The display module (160) of one embodiment may also display a graphical user interface (GUI) of a running app (or application program). The display module (160) of one embodiment may receive touch input via a touch sensor. For example, the display module (160) may receive text input via a touch sensor in an on-screen keyboard area displayed within the display module (160).

[0127] In one embodiment, the memory (130) may store a client module (151), a software development kit (SDK) (153), and a plurality of apps (146). The client module (151) and the SDK (153) may constitute a framework (or solution program) for performing general functions. In addition, the client module (151) or the SDK (153) may constitute a framework for processing user input (e.g., voice input, text input, touch input).

[0128] The plurality of apps (146) stored in the memory (130) of one embodiment may be programs for performing a specified function. According to one embodiment, the plurality of apps (146) may include a first app (146-1) and a second app (146-2). According to one embodiment, each of the plurality of apps (146) may include a plurality of operations for performing a specified function. For example, the apps may include an alarm app, a message app, and / or a schedule app. According to one embodiment, the plurality of apps (146) may be executed by the processor (120) to sequentially execute at least some of the plurality of operations.

[0129] The processor (120) of one embodiment can control the overall operation of the electronic device (101). For example, the processor (120) can be electrically connected to an interface (177), an input module (150), an audio output module (155), and a display module (160) to perform a specified operation.

[0130] The processor (120) of one embodiment may also execute a program stored in the memory (130) to perform a designated function. For example, the processor (120) may execute at least one of the client module (151) or the SDK (153) to perform the following operations for processing user input. The processor (120) may control the operations of multiple apps (146), for example, through the SDK (153). The following operations described as operations of the client module (151) or the SDK (153) may be operations executed by the processor (120).

[0131] The client module (151) of one embodiment can receive user input. For example, the client module (151) can receive a voice signal corresponding to a user utterance detected through the input module (150). Alternatively, the client module (151) can receive a touch input detected through the display module (160). Alternatively, the client module (151) can receive a text input detected through a keyboard or a visual keyboard. In addition, the client module (151) can receive various forms of user input detected through an input module included in the electronic device (101) or an input module connected to the electronic device (101). The client module (151) can transmit the received user input to the intelligent server (900). The client module (151) can transmit status information of the electronic device (101) to the intelligent server (900) together with the received user input. The status information can be, for example, execution status information of an app.

[0132] The client module (151) of one embodiment can receive a result corresponding to the received user input. For example, the client module (151) can receive a result corresponding to the received voice input when the intelligent server (900) can produce a result corresponding to the received user input. The client module (151) can display the received result on the display module (160). In addition, the client module (151) can output the received result as audio through the audio output module (155).

[0133] In one embodiment, the client module (151) can receive a plan corresponding to the received user input. The client module (151) can display the results of executing multiple operations of the app according to the plan on the display module (160). For example, the client module (151) can sequentially display the results of executing multiple operations on the display and output audio through the audio output module (155). The electronic device (101) can, for example, display only some results of executing multiple operations (e.g., the result of the last operation) on the display module (160) and output audio through the audio output module (155).

[0134] According to one embodiment, the client module (151) may receive a request from the intelligent server (900) to obtain information necessary to produce a result corresponding to a user input. According to one embodiment, the client module (151) may transmit the necessary information to the intelligent server (900) in response to the request.

[0135] The client module (151) of one embodiment can transmit result information of executing multiple operations according to a plan to the intelligent server (900). The intelligent server (900) can use the result information to confirm that the received user input has been processed correctly.

[0136] The client module (151) of one embodiment may include a voice recognition module. According to one embodiment, the client module (151) may recognize voice inputs that perform limited functions through the voice recognition module. For example, the client module (151) may execute an intelligent app to process voice inputs to perform organic actions through designated inputs (e.g., "Wake up!").

[0137] An intelligent server (900) of one embodiment can receive information related to a user voice input from an electronic device (101) via a communication network. According to one embodiment, the intelligent server (900) can convert data related to the received voice input into text data. According to one embodiment, the intelligent server (900) can generate a plan for performing a task corresponding to the user voice input based on the text data.

[0138] In one embodiment, the plan may be generated by an artificial intelligence (AI) system. The AI ​​system may be a rule-based system, a neural network-based system (e.g., a feedforward neural network (FNN), a recurrent neural network (RNN), or a combination of the above, or another AI system. In one embodiment, the plan may be selected from a set of predefined plans, or may be generated in real time in response to a user request. For example, the AI ​​system may select at least one plan from a plurality of predefined plans.

[0139] An intelligent server (900) of one embodiment may transmit a result according to a generated plan to an electronic device (101), or transmit the generated plan to the electronic device (101). According to one embodiment, the electronic device (101) may display a result according to the plan on a display module (160). According to one embodiment, the electronic device (101) may display a result of executing an operation according to the plan on a display module (160).

[0140] An intelligent server (900) of one embodiment may include a front end (910), a natural language platform (920), a capsule DB (930), an execution engine (940), an end user interface (950), a management platform (960), a big data platform (970), or an analytic platform (980).

[0141] A front end (910) of one embodiment can receive user input from an electronic device (101). The front end (910) can transmit a response corresponding to the user input.

[0142] According to one embodiment, the natural language platform (920) may include an automatic speech recognition module (ASR module) (921), a natural language understanding module (NLU module) (923), a planner module (925), a natural language generator module (NLG module) (927), or a text to speech module (TTS module) (929).

[0143] The automatic speech recognition module (921) of one embodiment can convert voice input received from the electronic device (101) into text data. The natural language understanding module (923) of one embodiment can use the text data of the voice input to determine the user's intention. For example, the natural language understanding module (923) can perform syntactic analysis or semantic analysis on user input in the form of text data to determine the user's intention. The natural language understanding module (923) of one embodiment can use linguistic features (e.g., grammatical elements) of morphemes or phrases to determine the meaning of words extracted from the user input, and can match the meaning of the determined words to the intent to determine the user's intent. The natural language understanding module (923) can obtain intent information corresponding to the user's utterance. The intent information may be information indicating the user's intent determined by interpreting text data. The intent information may include information indicating an action or function that the user intends to execute using the device.

[0144] The planner module (925) of one embodiment can generate a plan using the intent and parameters determined by the natural language understanding module (923). According to one embodiment, the planner module (925) can determine a plurality of domains necessary to perform a task based on the determined intent. The planner module (925) can determine a plurality of operations included in each of the plurality of domains determined based on the intent. According to one embodiment, the planner module (925) can determine parameters necessary to execute the determined plurality of operations or result values ​​output by the execution of the plurality of operations. The parameters and the result values ​​can be defined as concepts of a specified format (or class). Accordingly, the plan can include a plurality of operations and a plurality of concepts determined by the user's intent. The planner module (925) can determine the relationship between the plurality of operations and the plurality of concepts in a stepwise (or hierarchical) manner. For example, the planner module (925) can determine the execution order of a plurality of actions based on the user's intention based on a plurality of concepts. In other words, the planner module (925) can determine the execution order of a plurality of actions based on parameters required for the execution of the plurality of actions and results output by the execution of the plurality of actions. Accordingly, the planner module (925) can generate a plan including association information (e.g., ontology) between the plurality of actions and the plurality of concepts. The planner module (925) can generate the plan using information stored in a capsule database (930) in which a set of relationships between concepts and actions is stored.

[0145] The natural language generation module (927) of one embodiment can convert specified information into text format. The information converted into text format may be in the form of natural language speech. The text-to-speech conversion module (929) of one embodiment can convert information in text format into information in speech format.

[0146] According to one embodiment, some or all of the functions of the natural language platform (920) may also be implemented in the electronic device (101).

[0147] The capsule database (930) may store information on the relationships between a plurality of concepts and actions corresponding to a plurality of domains. According to one embodiment, a capsule may include a plurality of action objects (or action information) and concept objects (or concept information) included in a plan. According to one embodiment, the capsule database (930) may store a plurality of capsules in the form of a concept action network (CAN). According to one embodiment, the plurality of capsules may be stored in a function registry included in the capsule database (930).

[0148] The capsule database (930) may include a strategy registry that stores strategy information required when determining a plan corresponding to a voice input. The strategy information may include reference information for determining a single plan when there are multiple plans corresponding to a user input. According to one embodiment, the capsule database (930) may include a follow-up registry that stores information on follow-up actions for suggesting follow-up actions to a user in a given situation. The follow-up actions may include, for example, follow-up utterances. According to one embodiment, the capsule database (930) may include a layout registry that stores layout information of information output through the electronic device (101). According to one embodiment, the capsule database (930) may include a vocabulary registry that stores vocabulary information included in capsule information. According to one embodiment, the capsule database (930) may include a dialog registry that stores information on dialogue (or interaction) with a user. The capsule database (930) may update stored objects through a developer tool. The developer tool may include, for example, a function editor for updating action objects or concept objects. The developer tool may include a vocabulary editor for updating vocabulary. The developer tool may include a strategy editor for creating and registering strategies that determine plans. The developer tool may include a dialog editor for creating dialogues with the user.The developer tool may include a follow-up editor that activates follow-up goals and allows editing of follow-up utterances that provide hints. The follow-up goals may be determined based on currently set goals, user preferences, or environmental conditions. In one embodiment, the capsule database (930) may also be implemented within the electronic device (101).

[0149] The execution engine (940) of one embodiment can produce a result using the generated plan. The end user interface (950) can transmit the produced result to the electronic device (101). Accordingly, the electronic device (101) can receive the result and provide the received result to the user. The management platform (960) of one embodiment can manage information used in the intelligent server (900). The big data platform (970) of one embodiment can collect user data. The analysis platform (980) of one embodiment can manage the quality of service (QoS) of the intelligent server (900). For example, the analysis platform (980) can manage the components and processing speed (or efficiency) of the intelligent server (900).

[0150] A service server (990) of one embodiment may include CP service A (991), CP service B (992), and CP service C (993). The service server (990) of one embodiment may provide a service (e.g., food ordering or hotel reservation) specified for the electronic device (101). According to one embodiment, the service server (990) may be a server operated by a third party. The service server (990) of one embodiment may provide information for generating a plan corresponding to the received user input to the intelligent server (200). The provided information may be stored in the capsule database (230). In addition, the service server (990) may provide result information according to the plan to the intelligent server (900).

[0151] In the integrated intelligence system of FIG. 9, the electronic device (101) can provide various intelligent services to the user in response to user input. The user input may include, for example, input via a physical button, touch input, or voice input.

[0152] In one embodiment, the electronic device (101) may provide a voice recognition service through an intelligent app (or voice recognition app) stored internally. In this case, for example, the electronic device (101) may recognize a user utterance or voice input received through the microphone and provide the user with a service corresponding to the recognized voice input.

[0153] In one embodiment, the electronic device (101) may perform a designated operation, either alone or in conjunction with the intelligent server and / or service server, based on the received voice input. For example, the electronic device (101) may execute an app corresponding to the received voice input and perform a designated operation through the executed app.

[0154] In one embodiment, when an electronic device (101) provides a service together with an intelligent server (900) and / or a service server (990), the electronic device (101) can detect a user's speech using the input module (150) and generate a signal (or voice data) corresponding to the detected user's speech. The electronic device (101) can transmit the voice data to the intelligent server (900) using the interface (177).

[0155] According to one embodiment, an intelligent server (900) may generate a plan for performing a task corresponding to a voice input received from an electronic device (101), or a result of performing an operation according to the plan, in response to a voice input. The plan may include, for example, a plurality of operations for performing a task corresponding to a user's voice input, and a plurality of concepts related to the plurality of operations. The concept may define parameters input to the execution of the plurality of operations, or result values ​​output by the execution of the plurality of operations. The plan may include association information between the plurality of operations and the plurality of concepts.

[0156] An electronic device (101) of one embodiment can receive the response using an interface (177). The electronic device (101) can output a voice signal generated within the electronic device (101) to the outside using the audio output module (155), or can output an image generated within the electronic device (101) to the outside using the display module (160).

[0157] FIG. 10 is a diagram showing the form in which relationship information between concepts and operations according to various embodiments is stored in a database.

[0158] The capsule database (e.g., the capsule database (930) of FIG. 9) of the intelligent server (e.g., the intelligent server (900) of FIG. 9) may store capsules in the form of a CAN (concept action network). The capsule database may store operations for processing tasks corresponding to a user's voice input and parameters necessary for the operations in the form of a CAN (concept action network).

[0159] The capsule database may store a plurality of capsules (capsule (A) (1001), capsule (B) (1004)) corresponding to each of a plurality of domains (e.g., applications). According to one embodiment, one capsule (e.g., capsule (A) (1001)) may correspond to one domain (e.g., location (geo), application). In addition, one capsule may correspond to at least one service provider (e.g., CP 1 (1002), CP 2 (1003), CP 3 (1006), or CP 4 (1005)) for performing a function for a domain related to the capsule. According to one embodiment, one capsule may include at least one operation (1010) and at least one concept (1020) for performing a specified function.

[0160] The natural language platform (e.g., the natural language platform (920) of FIG. 9) can generate a plan for performing a task corresponding to a received voice input using capsules stored in a capsule database. For example, the planner module of the natural language platform (e.g., the planner module (925) of FIG. 9) can generate a plan using capsules stored in a capsule database. For example, a plan (1007) can be generated using actions (1001-1, 1001-3) and concepts (1001-2, 1001-4) of capsule A (1001) and actions (1004-1) and concepts (1004-2) of capsule B (1004).

[0161] FIG. 11 is a diagram illustrating a screen for processing voice input received through an intelligent app by an electronic device according to various embodiments.

[0162] The electronic device (101) can execute an intelligent app to process user input through an intelligent server (e.g., the intelligent server (200) of FIG. 2).

[0163] According to one embodiment, on the screen (1110), when the electronic device (101) recognizes a designated voice input (e.g., wake up!) or receives an input via a hardware key (e.g., a dedicated hardware key), the electronic device (101) may execute an intelligent app for processing the voice input. For example, the electronic device (101) may execute an intelligent app while the schedule app is running. According to one embodiment, the electronic device (101) may display an object (e.g., an icon) (1111) corresponding to the intelligent app on a display module (e.g., the display module (160) of FIG. 1). According to one embodiment, the electronic device (101) may receive a voice input by a user's speech. For example, the electronic device (101) may receive a voice input such as "Tell me my schedule for this week!" According to one embodiment, the electronic device (101) can display a user interface (UI) (1113) (e.g., an input window) of an intelligent app displaying text data of received voice input on a display module (e.g., the display module (160) of FIG. 1).

[0164] According to one embodiment, on the screen (1120), the electronic device (101) may display a result corresponding to the received voice input on a display module (e.g., the display module (160) of FIG. 1). For example, the electronic device (101) may receive a plan corresponding to the received user input and display 'this week's schedule' on the display module (160) according to the plan.

[0165] An electronic device according to one embodiment may modify input values ​​to improve the quality of the output values ​​of a large-scale language model. The electronic device may generate a prompt related to the input values ​​obtained based on user input and having a format suitable for the large-scale language model. A method for the electronic device to generate a prompt having a format suitable for the large-scale language model may be required.

[0166] An electronic device (101) according to one embodiment as described above may include a memory (220) storing instructions and including one or more storage media, and at least one processor (210) including a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain a first text (510) based on receiving a first user input from a user. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate a second text (421) for obtaining a second user input using a keyword (330) corresponding to a portion of the first text and to obtain template information representing a format corresponding to a neural network (245) for obtaining output information related to the first text. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain a third text (441) obtained based on a second user input after outputting the second text. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain a fourth text based on the first text and the third text in the format using the template information.

[0167] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain main question information representing the first text and sub-question information representing the third text. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to input the fourth text, which includes the main question information and the sub-question information for assisting the main question information, to the neural network, and to output the output information representing an answer to the main question information.

[0168] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate the second text representing a question for obtaining the sub-question information from the user.

[0169] For example, the electronic device may further include a microphone (260). The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the first text corresponding to the utterance based on receiving the first user input representing the utterance of the user through the microphone.

[0170] For example, the electronic device may further include a speaker (270). The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to output an audio signal representing the second text through the speaker, and then obtain the third text based on the second user input representing another utterance of the user through the microphone.

[0171] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain, if the second user input represents a word, a third text representing a sentence including the word.

[0172] For example, the instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to generate the second text for obtaining the second user input from the user related to the keyword category, using the keyword category mapped to the keyword representing the designated word. The second text may include at least one sentence.

[0173] For example, the electronic device may further include a display (250). The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the first text based on receiving the first user input using the screen (705) for obtaining the text. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display a first text object representing the second text on the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the third text based on receiving the second user input using the screen. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display a second text object representing the output information output by inputting the fourth text to the neural network on the display.

[0174] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to determine a number of the second texts based on the number of the keywords.

[0175] According to an embodiment of the electronic device (101) as described above, the method may include an operation of obtaining a first text (510) based on receiving a first user input from a user. The method may include an operation of generating a second text (421) for obtaining a second user input using a keyword (330) corresponding to a portion of the first text and obtaining template information indicating a format corresponding to a neural network (245) for obtaining output information related to the first text. The method may include an operation of obtaining a third text (441) obtained based on the second user input after outputting the second text. The method may include an operation of obtaining a fourth text based on the first text and the third text with the format using the template information.

[0176] For example, the operation of obtaining the fourth text may include an operation of obtaining main question information representing the first text and sub-question information representing the third text. The operation of obtaining the fourth text may include an operation of inputting the fourth text, including the main question information and the sub-question information for assisting the main question information, into the neural network, and outputting the output information representing an answer to the main question information.

[0177] For example, the method may include an action of generating the second text representing a question for obtaining the sub-question information from the user.

[0178] For example, the action of obtaining the first text may include an action of obtaining the first text corresponding to the utterance based on receiving the first user input representing the utterance of the user through a microphone (260).

[0179] For example, the operation of obtaining the third text may include an operation of obtaining the third text based on the second user input representing another utterance of the user through the microphone after outputting an audio signal representing the second text through the speaker (270).

[0180] For example, the action of obtaining the third text may include, when the second user input indicates one (a) word, an action of obtaining the third text indicating one sentence including the one word.

[0181] In a computer-readable storage medium storing one or more programs according to one embodiment as described above, the one or more programs, when executed by the processor (210) of the electronic device (101), may cause the electronic device to obtain a first text (510) based on receiving a first user input from a user. The one or more programs, when executed by the processor of the electronic device, may cause the electronic device to generate a second text (421) for obtaining a second user input using a keyword corresponding to a portion of the first text and to obtain template information representing a format corresponding to a neural network (245) for obtaining output information related to the first text. The one or more programs, when executed by the processor of the electronic device, may cause the electronic device to obtain a third text (441) obtained based on the second user input after outputting the second text. The one or more programs, when executed by the processor of the electronic device, may cause the electronic device to obtain a fourth text based on the first text and the third text having the format using the template information.

[0182] For example, the one or more programs, when executed by the processor of the electronic device, may cause the electronic device to obtain main question information representing the first text and sub-question information representing the third text. The one or more programs, when executed by the processor of the electronic device, may cause the electronic device to input the fourth text, which includes the main question information and the sub-question information for assisting the main question information, to the neural network, and to output the output information representing an answer to the main question information.

[0183] For example, the one or more programs, when executed by the processor of the electronic device, may cause the electronic device to generate the second text representing a question for obtaining the sub-question information from the user.

[0184] For example, the one or more programs, when executed by the processor of the electronic device, may cause the electronic device to obtain the first text corresponding to the utterance based on receiving the first user input representing the utterance of the user through the microphone (260).

[0185] For example, the one or more programs, when executed by the processor of the electronic device, may cause the electronic device to output an audio signal representing the second text through the speaker (270), and then obtain the third text based on the second user input representing another utterance of the user through the microphone.

[0186] The devices described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0187] Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may independently or collectively command the processing device. The software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0188] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. In this case, the medium may be one that continuously stores a computer-executable program or one that temporarily stores it for execution or download. In addition, the medium may be various recording or storage means in the form of a single or multiple hardware combinations, and is not limited to a medium directly connected to a computer system, but may also be distributed over a network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and those configured to store program commands, including ROM, RAM, and flash memory. In addition, examples of other media may include recording or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc.

[0189] Although the embodiments have been described with limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents. Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims

1. In an electronic device (101), A memory (220) storing instructions and including one or more storage media; At least one processor (210) comprising a processing circuit; The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Based on receiving a first user input from a user, a first text (510) is obtained; Using a keyword (330) corresponding to a portion of the first text, a second text (421) is generated for obtaining a second user input, and template information representing a format corresponding to a neural network (245) for obtaining output information related to the first text is obtained; After outputting the second text, a third text (441) obtained based on the second user input is obtained; and Using the above template information, causing a fourth text to be obtained based on the first text and the third text with the above format. Electronic devices.

2. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Obtaining main question information representing the first text and sub question information representing the third text, and Inputting the fourth text including the main question information and the sub-question information for assisting the main question information into the neural network, thereby causing the output information representing the answer to the main question information to be output. Electronic devices.

3. In any one of claims 1 and 2, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: causing said second text to be generated, which represents a question for obtaining said sub-question information from said user; Electronic devices.

4. In any one of claims 1 to 3, The electronic device further comprises a microphone (260), The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: causing said first text corresponding to said utterance to be obtained based on receiving said first user input representing said utterance of said user through said microphone; Electronic devices.

5. In any one of claims 1 to 4, The above electronic device further includes a speaker (270), The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: After outputting an audio signal representing the second text through the speaker, causing the third text to be acquired based on the second user input representing another utterance of the user through the microphone. Electronic devices.

6. In any one of claims 1 to 5, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: causing said second user input to obtain said third text representing a sentence containing said one word, if said second user input represents one (a) word; Electronic devices.

7. In any one of claims 1 to 6, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Generating the second text for obtaining the second user input related to the keyword category from the user by using the keyword category mapped to the keyword representing the specified word, and The second text above contains at least one sentence, Electronic devices.

8. In any one of claims 1 to 7, The electronic device further includes a display (250), The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Based on receiving the first user input using the screen (705) for obtaining the text, the first text is obtained, Displaying a first text object representing the second text on the display, Based on receiving the second user input using the above screen, the third text is obtained, and Causing a second text object representing the output information output by inputting the fourth text to the neural network to be displayed on the display. Electronic devices.

9. In any one of claims 1 to 8, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Causing the number of said second texts to be determined based on the number of said keywords, Electronic devices.

10. In the method of electronic device (101), An operation of obtaining a first text (510) based on receiving a first user input from a user; An operation of generating a second text (421) for obtaining a second user input using a keyword (330) corresponding to a portion of the first text and obtaining template information representing a format corresponding to a neural network (245) for obtaining output information related to the first text; After outputting the second text, an operation of obtaining a third text (441) obtained based on the second user input; and Using the above template information, an operation of obtaining a fourth text based on the first text and the third text with the above format is included. method.

11. In claim 10, The action of obtaining the above fourth text is: An operation of obtaining main question information representing the first text and sub question information representing the third text, and An operation of inputting the fourth text including the main question information and the sub-question information for assisting the main question information into the neural network and outputting the output information indicating an answer to the main question information, method.

12. In any one of claims 10 and 11, The above method, comprising an action of generating the second text representing a question for obtaining the sub-question information from the user; method.

13. In any one of claims 10 to 12, The action of obtaining the above first text is: An operation of obtaining said first text corresponding to said utterance, based on receiving said first user input representing said utterance of said user through a microphone (260), method.

14. In any one of claims 10 to 13, The action of obtaining the third text is as follows: An operation of obtaining the third text based on the second user input representing another utterance of the user through the microphone, after outputting an audio signal representing the second text through the speaker (270). method.

15. In a computer-readable storage medium storing one or more programs, When the above one or more programs are executed by the processor (210) of the electronic device (101), Based on receiving a first user input from a user, a first text (510) is obtained; Using a keyword corresponding to a portion of the first text, a second text (421) is generated for obtaining a second user input, and template information representing a format corresponding to a neural network (245) for obtaining output information related to the first text is obtained; After outputting the second text, a third text (441) obtained based on the second user input is obtained; and Using the above template information, causing the electronic device to obtain a fourth text based on the first text and the third text in the above format. Computer readable storage medium.

Images