Reminder method based on user action and electronic device thereof

Abstract

Various embodiment of the present invention may comprise: a display (160); a memory (130) storing instructions; and a processor (120). The instructions stored in the memory, when executed by the processor, may instruct the electronic device to: collect at least one of information stored in an application installed in the electronic device, information stored in the memory, an event received through the application, information stored in the memory, or setting information set in the electronic device; analyze the collected information to determine a usage pattern of a user; generate prompt information to be provided to generative artificial intelligence by analyzing the usage pattern of the user; generate AI notification information through the generative artificial intelligence on the basis of the prompt information; and provide the AI notification information if an action predicted through the generative artificial intelligence is not performed. Various embodiments are possible.

Description

Reminder method based on user action and electronic device thereof

[0001] Various embodiments of the present disclosure relate to a reminder method and an electronic device based on a user action.

[0002] With the advancement of digital technology, various types of electronic devices, such as mobile terminals, personal digital assistants (PDAs), electronic notebooks, smartphones, tablet PCs (personal computers), and wearable devices, are becoming widely used. These electronic devices are constantly being improved, both in hardware and / or software, to support and enhance their functionality.

[0003] Electronic devices can provide reminder services based on schedule information registered in a calendar application. For example, users can register events or alarms on their electronic devices for things they need to remember, want to remember, or need to review.

[0004] Users face the inconvenience of having to manually register reminders for desired actions on their electronic devices. While users can register reminders on their electronic devices via voice commands, the inconvenience of having to use voice commands remains.

[0005] In one embodiment, a method and device may be disclosed for analyzing information stored in an application installed on an electronic device, an external device connected to the electronic device (e.g., an IoT device, a wearable device), sensing information, information stored in an external server or a memory of the electronic device, and displaying AI notification information at a time when a reminder is required based on the analyzed result.

[0006] An electronic device (101) according to one embodiment of the present disclosure includes a display (160), a memory (130) for storing instructions, and a processor (120), and the instructions stored in the memory, when executed by the processor, cause the electronic device to collect at least one of information stored in an application installed in the electronic device, an event received through an application, information stored in the memory, or setting information set in the electronic device, analyze the collected information to determine a user's usage pattern, analyze the user's usage pattern to generate prompt information to be provided to a generative artificial intelligence, generate AI notification information through the generative artificial intelligence based on the prompt information, and provide the AI ​​notification information when an action predicted by the generative artificial intelligence is not performed.

[0007] An operating method of an electronic device (101) according to an embodiment of the present disclosure may include an operation of collecting at least one of information stored in an application installed in the electronic device, information stored in the memory, or setting information set in the electronic device, an operation of analyzing the collected information to determine a user's usage pattern, an operation of analyzing the user's usage pattern to generate prompt information to be provided to generative artificial intelligence, an operation of generating AI notification information through the generative artificial intelligence based on the prompt information, and an operation of providing the AI ​​notification information when an action predicted through the generative artificial intelligence is not performed.

[0008] In one embodiment, the system can remind the user of things to do without the user having to register a schedule or set an alarm.

[0009] In one embodiment, the user may be reminded of an action they are currently trying to do, an action they were trying to do but forgot to do, or an action they would like to do.

[0010] According to one embodiment, the user's desired schedule can be predicted and automatically guided by analyzing the user's usage pattern, intention or preference based on various information stored in the electronic device.

[0011] In one embodiment, if it is determined that the current reminder provision is not appropriate, the reminder time may be adjusted to a time appropriate for the user to perform the action based on the user's usage pattern or the current usage status of the electronic device.

[0012] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0013] FIG. 2 is a block diagram illustrating an example of providing a reminder based on a pattern used in an electronic device according to one embodiment.

[0014] FIG. 3 is a flowchart illustrating an operating method of an electronic device according to one embodiment.

[0015] FIG. 4 is a diagram illustrating a configuration for generating AI notification information based on information collected from an electronic device according to one embodiment.

[0016] FIG. 5 is a flowchart illustrating a method for collecting various information in an electronic device according to one embodiment.

[0017] FIG. 6 is a diagram illustrating an example of providing AI notification information in an electronic device according to one embodiment.

[0018] FIGS. 7A to 7C are diagrams illustrating an example of providing AI notification information in an electronic device according to one embodiment.

[0019] FIG. 8 is a flowchart illustrating a method for providing AI notification information in an electronic device according to one embodiment.

[0020] FIG. 9 is a diagram illustrating an example of displaying AI notification information in an electronic device according to one embodiment.

[0021] FIGS. 10A and 10B are diagrams illustrating an example of displaying AI notification information in an electronic device according to one embodiment.

[0022] FIG. 11 is a diagram illustrating an example of displaying AI notification information in an electronic device according to one embodiment.

[0023] FIG. 12 is a block diagram illustrating a generative artificial intelligence system according to one embodiment.

[0024] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0025] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0026] 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.

[0027] 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.

[0028] 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).

[0029] 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).

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] 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).

[0040] 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.

[0041] 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).

[0042] 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.

[0043] 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).

[0044] 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.

[0045] 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)).

[0046] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0047] 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.

[0048] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0049] 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).

[0050] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0051] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0052] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0053] FIG. 2 is a diagram illustrating an example of providing a reminder based on a heuristic pattern in an electronic device according to one embodiment.

[0054] Referring to FIG. 2, a processor (e.g., the processor 120 of FIG. 1) of an electronic device (e.g., the electronic device 101 of FIG. 1) according to an embodiment may analyze information stored in the electronic device (101) or information acquired from an external device connected to the electronic device (101) to determine a user's motion (or action) pattern. The information stored in the electronic device (101) may include information stored (or registered) in an application installed in the electronic device (101), information registered in the settings of the electronic device (101), and information stored in a memory (e.g., the memory 130 of FIG. 1) of the electronic device (101). For example, the information stored in an application may include schedule information stored in a schedule application, conversation information stored in a messenger application, alarm information stored in an alarm application, documents stored in a document application (e.g., Word, Excel, PDF), and contact information stored in a contact application. Such examples are provided merely to aid understanding of the invention, and the invention is not limited by the examples.

[0055] The information registered in the settings of the electronic device (101) is the setting information of the electronic device (101), and may include, for example, information such as connection information (e.g., wifi, Bluetooth), connection information with external devices, mode / routine, sound / vibration, and screen brightness. The information stored in the memory (130) may include downloaded images, videos, audio, documents, installation files, sensing information, or application usage records (e.g., when and how much it was used). The sensing information may be a measurement value obtained from a sensor module included in the electronic device (101) (e.g., the sensor module (176) of FIG. 1). The external device may include an IoT (Internet of Things) device such as a washing machine, a TV, a refrigerator, a Bluetooth speaker, a wearable device such as a Bluetooth earphone, or an external electronic device such as a laptop or a computer. The information obtained from the external device may include an identifier of the external device, a notification of the external device (e.g., a laundry completion notification), a status of the external device (e.g., a power saving mode), or data stored in the external device (e.g., an image, a file, a favorite information). The processor (120) may collect and analyze information stored (or registered) in an external server (e.g., a cloud server) registered with the user account of the electronic device (101) to determine the user's motion (or action) pattern.

[0056] The processor (120) collects (or acquires) and analyzes screen information (or content) (e.g., an application execution screen, a home screen) displayed on a display (e.g., a display module (160) of FIG. 1), and uses connection information or GPS information of the electronic device (101) to collect (or acquire) and analyze location information of the electronic device (101) to determine an action the user takes at a specific location at a specific time. For example, the user may wake up at 7 a.m. from Monday to Friday (e.g., location: home, alarm information analysis), move to another location (e.g., work) from 8 a.m. to 9 a.m. (e.g., location change, transportation card record), buy coffee at AA (e.g., credit card record), eat lunch between 12 p.m. and 1 p.m. (e.g., credit card record), move home from 6 p.m. to 7 p.m., and watch TV or use a computer (e.g., game) at home from 7 p.m. to 12 p.m. Since the user always carries the electronic device (101) with him / her even when moving from location to location, purchasing a product, or staying at home, the processor (120) can determine the user's usage pattern by using all information obtained through the electronic device (101) (e.g., usage pattern of the electronic device (101)).

[0057] The processor (120) can determine the current location information (213) (e.g., home) of the electronic device (101) by using the record (e.g., screen mirroring) (211) of the electronic device (101) being connected to an external device (e.g., TV) of the home or the Wi-Fi connection information of the home. The processor (120) can collect alarm information stored in an alarm application or schedule information (215) stored in a schedule application at the current location.

[0058] The processor (120) may include a specialized prompt generation module that goes through an iterative writing evaluation step to generate a prompt that provides an optimized result from the output of the generative AI. The processor (120) may generate prompt information through the prompt generation module. The generative AI may be included within the electronic device (101) or may be included in an external server. The generative AI may refer to an artificial intelligence neural network that creates a new type of data depending on user input information. The generative AI is a model trained to output the most statistically appropriate output value based on input values, and representative examples thereof include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, the generative AI can recognize various types of data input, such as text, images, and voice, and generate new data corresponding thereto, and is therefore called a large multimodal model (LLM).

[0059] A large-scale language model can refer to an artificial neural network-based language model that has learned a large amount of text data through pre-training. Large-scale language models can contain significantly more parameters (e.g., over 10 billion) than conventional general language models. A large-scale language model can utilize a transformer artificial neural network architecture based on an attention mechanism. The attention mechanism is a technology that helps an AI model focus (attention) on important parts of the input data. The attention mechanism can predict the extent to which a portion of time-series input data (e.g., input data such as voice or video, or input data from a layer of a neural network) contributes to the intermediate or final output of the neural network, which can then be used to predict output data. Recurrent neural networks (RNNs), which sequentially process each element of a sequence, can exhibit poor prediction performance when there is information dependence between long time-series intervals. The attention mechanism can account for information dependence between long time-series intervals by controlling the degree of weight concentration (attention) within the overall (or partial) context of the input data.

[0060] A transformer can be structured as an encoder-decoder. The encoder processes input data and outputs compressed information (e.g., a contextual representation), and the decoder processes the compressed information and outputs token-based data. The encoder and decoder can each include an independent attention network, and a cross-attention network connecting the encoder and decoder.

[0061] For example, LLM learning may involve pre-training and / or fine-tuning. Pre-training is the process of acquiring general linguistic knowledge using large amounts of text data. For example, this may involve self-supervised learning, where previous word sequences in a text string are used to predict the next word. Fine-tuning is the process of training the LLM to be suitable for a specific domain (e.g., chatbot, translation, summarization, Q&A) or task. The LLM may be further supervised (or adaptively trained) using a dataset tailored to the domain's purpose, based on the pre-trained model. The LLM can perform tasks with text inputs containing natural language, called prompts.

[0062] For example, fine-tuning can be omitted during LLM learning. Users can control the prompts provided to the LLM to improve performance on their desired tasks. Similar to in-context learning or zero-shot / few-shot learning, prompts can provide additional task examples and / or guidance for performing the task. Publicly available LLMs include BERT (Bidirectional Encoder Representations from Transformer) and GPT (generative pre-trained transformer).

[0063] Here, the term "LLM" can refer to the language neural network model itself, but can also mean the model of an LLM-based application (e.g., chatbot, translation, summarization, text classification, sentence generation). For example, an LLM-based chatbot such as ChatGPT or an LLM-based translator can also be referred to as "LLM." An LLM may also include an inference engine using an LLM neural network model. For example, "inputting an input prompt into an LLM" can mean "inputting the input prompt into an LLM-based inference engine." For example, "the output of the LLM for the input prompt" can mean the output information of the last neural network layer of the LLM obtained when input prompts are input into an LLM-based inference engine.

[0064] The processor (120) can generate prompt information to be provided to the LLM based on the collected information. Since the prompt information has inputs and outputs that indicate what produces the most satisfactory results, learning is possible. The process of learning the prompt information is performed in advance, and the generative AI that has learned the prompt information can be included in the electronic device (101). The processor (120) including the generative AI (e.g., AI processor, learned library) can generate optimized prompt information based on the collected information. The processor (120) including the generative AI can generate AI notification information (217) based on the prompt information.

[0065] For example, the AI ​​notification information (217) may guide the user about an action that the user intended to do, an action that the user intended to do but forgot, or an action that would be good to do. In the calendar application of the electronic device (101), the schedule information for 3 days from the current time may be stored as Mom's birthday, and Mom may be stored as a contact in the contact application under the name Mom. Mom's contact may be set to the 'Family' group, and another contact (e.g., the younger sibling's name) may be stored in the same family group. The processor (120) may analyze the keywords 'Mom', 'Birthday', and 'Gift' in the conversation with the younger sibling this afternoon (e.g., conversation information stored in the messenger application), and analyze the schedule information (e.g., Mom's birthday in 3 days) to determine that the card record has not yet been used to purchase a birthday present for Mom. The processor (120) may provide AI notification information (217) when the home screen of the electronic device (101) is displayed on the display module (160) for a specified period of time (e.g., 1 minute, 3 minutes) at the current location, i.e., at home. Alternatively, the processor (120) may provide reminder information AI notification information (217) before the user falls asleep when no movement of the electronic device (101) is detected for a specified period of time (e.g., 5 minutes, 10 minutes) when the user arrives home. The present invention is expected to require a necessary action, and is intended to provide assistance when the user does not perform the action. The above examples are only intended to aid understanding of the invention and do not limit the scope of the invention.

[0066] As notification accuracy decreases, users may perceive them as spam. Therefore, by providing as much information as possible to generative AI, it can help generate prompts or AI notifications. For example, the processor (120) may be configured to: "Current time: 17:20, Location information: London Tottenham Stadium, Connected external device: Friend's car (or Headset), Activity information: Stopped (e.g., no movement of electronic device), Recent conversation / message content (e.g., "Card payment content, recent message content with friend"), Stored user's schedule information (e.g., Calendar application - Watching a soccer game on 2024.01.22 18:00 ~ 20:00, Visiting parents' house on (Tue) 2024.01.23 09:30, AAA application - 2024.01.28 09:00 ~ 10:00, 2024.01.29 Schedule B), BBB application (e.g., Schedule D ~ Schedule E)), Some of the taste list (Preferred: YouTube, Front seat, Discount coupon, Soccer, Beer, Son Heung-min, Lee Kang-in, Starbucks, Lager, Not preferred: Fast food, Overconsumption, Arsenal, ketchup, baseball, red clothing, soju, rainy day, Netflix, highway, …), currently used applications (e.g., driving completion screen of a route finding application, execution screen of a music streaming application, conversation screen with friend OO of a messenger application) can be collected. The taste list can be distinguished by measuring scores such as agreement / disagreement in the conversation contents of a messenger application, and preferred subjects can be selected by analyzing stored images. For example, the processor (120) can identify the color and object of the photo in mainly taken food photos, activity photos, and downloaded photos to determine preference or dislike.

[0067] The processor (120) can display the product code (e.g., QWEASD2310) included in the AI ​​notification information (217) to distinguish it from other text. The processor (120) can blink the product code or display it in bold (or shaded) color compared to other text. When a user selects a product code, the processor (120) can execute a shopping application that sells the product corresponding to the product code, thereby guiding the user to easily purchase a birthday present for their mother through the AI ​​notification information (217). For example, the processor (120) can display an execution screen of the shopping application including a page that sells the product corresponding to the product code, and can blink a 'purchase button' on the execution screen of the shopping application or provide text such as 'buy now'. The AI ​​notification information (217) can include at least one of text, audio, image, or video. The AI ​​notification information (217) can be displayed on the display module (160) or output as voice through a speaker (e.g., the audio output module (155) of FIG. 1). AI notification information (217) includes a user action guide, and the user action guide is related to user interaction and may guide a touch location, long press, drag, scroll, double click, swipe, or swipe direction.

[0068] An electronic device (101) according to an embodiment of the present disclosure includes a display (160), a memory (130) for storing instructions, and a processor (120), and the instructions stored in the memory, when executed by the processor, cause the electronic device to collect at least one of information stored in an application installed in the electronic device, information stored in the memory, an event received through an application, information stored in the memory, or setting information set in the electronic device, analyze the collected information to determine a user's usage pattern, analyze the user's usage pattern to generate prompt information to be provided to a generative artificial intelligence, generate AI notification information through the generative artificial intelligence based on the prompt information, and provide the AI ​​notification information when an action predicted by the generative artificial intelligence is not performed.

[0069] The instructions, when executed by the processor, may cause the electronic device to generate the prompt information related to the user action based on at least one of a current state of the electronic device, content displayed on the display, conversation content of a messenger application, conversation content of an SNS application, user action collected at a specific time, or user preference.

[0070] The above instructions, when executed by the processor, may cause the electronic device to display, as the AI ​​notification information, an indicator guiding the execution of a specific application, the execution of a specific function of an application, or the interaction of a user.

[0071] The above instructions, when executed by the processor, may cause the electronic device to generate new AI notification information based on an operational state of the electronic device by the user when no user input for the displayed AI notification information is detected.

[0072] The above instructions, when executed by the processor, may cause the electronic device to delete the AI ​​notification information after generating the AI ​​notification information without providing it to the user based on a current state of the electronic device, content displayed on the display, or a current user action.

[0073] The above instructions, when executed by the processor, may cause the electronic device to update a user's usage pattern based on a user action on the electronic device when no user input for the displayed AI notification information is detected, and to analyze the updated user's usage pattern to generate new prompt information to be provided to the generative artificial intelligence.

[0074] The above instructions, when executed by the processor, may cause the electronic device to determine the user's usage pattern by analyzing the current time, the current operating state of the electronic device, location information of the electronic device, information obtained from an external server registered with a user account of the electronic device, or an external device connected to the electronic device.

[0075] The above instructions, when executed by the processor, may cause the electronic device to learn content displayed on the display at a specific time and user actions on the electronic device to determine a usage pattern of the user.

[0076] The above instructions, when executed by the processor, may cause the electronic device to provide the AI ​​notification information when at least one of the current time, the current operating state of the electronic device, or the location information of the electronic device corresponds to a condition for providing the AI ​​notification.

[0077] Figure 3 is a flowchart (300) illustrating an operating method of an electronic device according to one embodiment.

[0078] Referring to FIG. 3, in operation 301, a processor (e.g., the processor 120 of FIG. 1) of an electronic device (e.g., the electronic device 101 of FIG. 1) according to an embodiment may collect and analyze information based on a usage history. The usage history may include which application a user uses, how long the application is used, and at what location. The usage history may include not only the time the application is being used, but also what the application was turned on and what was done. Which application was turned on and what action was performed in which situation (e.g., time, location, display status) may be grouped and added to the usage history. Information within an application is information stored (or registered) in the application, and may include, for example, conversation information stored in a messenger application, schedule information stored in a calendar application, alarm information stored in an alarm application, documents stored in a document application, and contact information stored in a contact application. Information within an application may include information on the location and content of photos stored in a gallery application. For example, the processor (120) can identify preferred sports, people with whom one travels, preferred places, or preferred food information from stored images.

[0079] The processor (120) can analyze information collected from applications. The processor (120) can analyze information collected from the applications over a specified period of time, such as one day, one week, or two weeks, to determine which applications are used, when, where, and for how long. The processor (120) can analyze the actions taken by the user as events are received from the applications. The processor (120) can analyze the information collected from the applications through generative AI to determine the user's usage pattern. The user's usage pattern may refer to actions taken by the user at a specific time or location. The user's actions may include playing music with wireless earphones through a music application while riding the subway, or performing a specific function of a specific application. The processor (120) can learn the user's usage pattern and analyze the user's intention or preference based on the information collected from the applications. The processor (120) can learn the user's usage pattern and learn the user's intention or preference.

[0080] In operation 303, the processor (120) may determine whether an AI notification is necessary through generative AI. The generative AI (or generative AI engine) may be included within the electronic device (101). Generative AI may generally refer to an artificial intelligence neural network that creates new types of data based on user input information. Generative AI is a model trained to output the most statistically appropriate output value based on input values, and may typically utilize a large language model (LLM). The processor (120) may also determine whether an AI notification is necessary through generative AI through operation 301 alone. Operation 303 may be omitted.

[0081] Generative AI can generate a predicted list of actions a user should perform at the current time based on the user's usage patterns. The predicted list includes schedule information. For example, the generative AI can determine that the user usually shops at home after work by referencing the user's usage patterns of the electronic device (101). The generative AI can collect information from a messenger application, such as that a user recently expressed a desire to purchase product B during a conversation with partner A, and that partner A advised that there would be a discount benefit if they used application C when purchasing product B. The generative AI can predict actions (e.g., purchasing product A through application C) that should be performed under specific conditions (e.g., no scheduled events, 7 PM, at home). AI notifications can be time-based or condition-based. The generative AI can determine which condition, time-based or condition-based, will provide the most optimized notification.

[0082] The processor (120) may determine, through generative AI, that an AI notification is necessary if the user does not perform an action included in the above-mentioned prediction list. For example, if a user registered to "purchase product A through application C at home at 7 PM, when no scheduled event has been registered," but purchased a similarly colored product at an earlier time, or additionally communicated with A about a change in purchasing intent, the generative AI may view this as an intended cancellation of the event. If the generative AI determines, based on sensing information from the electronic device (101) that the user is riding a bicycle or driving a long distance, it may determine this as an unintended cancellation of the event and change the timing of the AI ​​notification. These examples are provided merely to aid understanding of the invention and do not limit the invention.

[0083] Generative AI can determine whether an AI notification is necessary based on (1) the context of the conversation: when the core topic identified through the context and keywords of the conversation in messages, SNS, etc. matches the user's taste, (2) schedule: when the schedule / notification registered directly by the user or by the generative AI arrives, (3) location: when the location (connected device (car), location information (wifi, gps, payment information, conversation content, etc.) matches the user's taste or the user's application usage pattern (e.g., when it is confirmed to be at Tottenham Hotspur Stadium in London, when it is determined to be the parent's house), (4) other: when an external device is disconnected / registered (car disconnected, TV disconnected), when the battery of an electronic device (1010 (e.g., battery (189) of FIG. 1)) falls below a certain level, or when the electronic device (101) is not used for a certain period of time (1 hour).

[0084] In operation 305, the processor (120) may generate prompt information to be provided to the generative AI. As the accuracy of the notification decreases, the user may perceive the notification as spam. Therefore, by providing as much information as possible to the generative AI, the generative AI can assist in generating prompt information or AI notification information. For example, the processor (120) may transmit the current time (17:20), location (e.g., Tottenham Hotspur Stadium in London), connected external device (e.g., a friend's car or headset), activity information (e.g., while stopped, saved user's schedule information (e.g., calendar application - watching a soccer match on 1.22 from 18:00 to 20:00), taste information (e.g., preferred: YouTube, front seat, discount coupon, soccer, beer, disliked: fast food, Arsenal, ketchup, baseball, red clothing), and current user-used application (e.g., driving completion screen of a route-finding application) to the generative AI, and may generate a prompt such as "Recommend something to do right now. If an immediate recommendation is needed, let me know, and if it is not needed right away, register it as a schedule." Alternatively, if the prompt information is a condition other than a time (e.g., change of location, execution of a specific application, start of a specific conversation, Idle state lasting for 1 hour), the processor may generate prompt information such as "Register it in a routine to notify me at that time, and also determine and register the number of repetitions."

[0085] In operation 307, the processor (120) may generate AI notification information through the generative AI. The generative AI may generate AI notification information based on the prompt information. For example, when the user arrives at the AA Stadium registered in the schedule information, the generative AI may generate AI notification information such as, "You have arrived at the stadium. Tickets can be purchased at the main gate. Please prepare a discount coupon." When the user selects the AI ​​notification information, the generative AI may generate AI notification information for finding a discount coupon, such as, "Home screen → Gallery → Coupon photo album → Discount coupon." Alternatively, the generative AI may generate AI notification information such as, "Gallery? Coupon photo album? Discount coupon" at the main gate of the AA Stadium. Alternatively, when entering the 3rd floor of the AA Stadium and there is no history of purchasing beer, the generative AI may generate AI notification information such as, "It seems you have not purchased beer. You can purchase OO Lager on the 2nd floor." According to one embodiment, the processor (120) may transmit the prompt information to an intelligent server (e.g., the server (108) of FIG. 1) through a communication module (e.g., the communication module (190) of FIG. 1) and receive the AI ​​notification information from the server (108).

[0086] In operation 309, the processor (120) may provide AI notification information if the predicted action through the generative artificial intelligence is not performed. If the current location of the electronic device (101) is "AA Stadium Main Gate" and the user does not move to the ticket issuing location or does not issue a ticket, the processor (120) may provide AI notification information such as "You have arrived at the stadium. Tickets can be issued at the main gate. Please prepare a discount coupon." In addition, if a user input for selecting AI notification information is detected for a user who does not remember where a discount coupon is stored, the processor (120) may provide AI notification information that guides the user on the screen in the order of "Gallery? Coupon Photo Album? Discount Coupon" as a detailed guide where a discount coupon exists. The processor (120) recognizes the 3rd floor of the AA stadium based on the wifi connection, current location, altitude information, and conversation with a friend, but if there is no OO beer card payment text, it can provide AI notification information such as, "It seems like you have not purchased beer. You can purchase OO lager on the 2nd floor."

[0087] The processor (120) generates prompt information based on information collected and analyzed in real time, and can remove, add, or change AI notification information at any time based on the prompt information using the generative artificial intelligence. The AI ​​notification information may include at least one of text, audio, image, or video. The processor (120) can display the AI ​​notification information on the display module (160) or output a voice for the AI ​​notification information through a speaker (e.g., the audio output module (155) of FIG. 1). When the electronic device (101) is connected to an external device such as a wearable device, the AI ​​notification information may be provided through the wearable device.

[0088] According to one embodiment, the processor (120) may provide the AI ​​notification information when a reminder request is received from a user. The processor (120) may provide the AI ​​notification information when a specified voice command (e.g., reminder) is input, a specified button (e.g., voice recognition service button) is selected, or a specified text (e.g., remind me) is input.

[0089] According to one embodiment, if no user input is detected for the displayed AI notification information, the processor (120) may update the user's usage pattern based on the user's action on the electronic device (101). If no user input is detected for the AI ​​notification information, the AI ​​notification information may not be what the user wants. In this case, the processor (120) may update the user's usage pattern to more accurately reflect the user's intent, thereby generating AI notification information.

[0090] According to one embodiment, if no user input is detected for the displayed AI notification information, the processor (120) may generate new prompt information based on the current state of the electronic device (101), screen information (or content) displayed on the display module (160), or current user action. The processor (120) may generate new prompt information to generate new AI notification information that reflects the user's intention.

[0091] According to one embodiment, if no user input for the AI ​​notification information is detected, the processor (120) may generate new AI notification information based on the operating state of the electronic device (101) by the user. If no user input for the AI ​​notification information is detected, the processor (120) may determine that the AI ​​notification information does not understand the user's intention and generate new AI notification information.

[0092] FIG. 4 is a diagram illustrating a configuration for generating AI notification information based on information collected from an electronic device according to one embodiment.

[0093] Referring to FIG. 4, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may include an information acquisition component (410), a learning / analysis and prompt generation component (430), a Gen AI notification schedule generation component (450), and an AI notification provision component (470). The information acquisition component (410) may directly transmit the acquired (or collected) information to the prompt generation module (435), or may transmit the information to the prompt generation module (435) through a situational app usage pattern learning module (431) or a user intention and preference analysis module (433). The Gen AI notification schedule generation component (450) may be included within the generative AI. The learning / analysis and prompt generation component (430) and the AI ​​notification provision component (470) may or may not be included in the generative AI. The generative AI may generally refer to an artificial intelligence neural network that creates new types of data based on user input information. Generative AI can be a model trained to output statistically most appropriate output values ​​based on input values.

[0094] The information acquisition component (410) may include app execution and operation record information (401), device status information and sensing information (403), conversation, schedule, and notification information (405), and stored data information (407). The app execution and operation record information (401) may be record information about when, where, and how much the application is used. The device status information and sensing information (403) may include the communication connection status of the electronic device (101) (e.g., Wi-Fi, Bluetooth), when, where, and with which external device the electronic device (101) is connected, and sensing information measured by the sensor module of the electronic device (101) (e.g., the sensor module (176) of FIG. 1). The conversation, schedule, and notification information (405) may refer to information stored in the application. For example, conversation, schedule, and notification information (405) may include conversation information stored in a messenger application, schedule information stored in a schedule application, alarm information stored in an alarm application, images (or videos) stored in a gallery application, and posts stored (or registered) in a posting application. Saved data information (407) may include various information stored in the memory of the electronic device (101) other than the application (e.g., the memory (130) of FIG. 1). For example, saved data information (407) may include information such as mode / routine, sound / vibration, and screen brightness.

[0095] The learning / analysis and prompt generation component (430) may include a context-specific app usage pattern learning module (431), a user intent and preference analysis module (433), and a prompt generation module (435). The context-specific app usage pattern learning module (431) is about actions that a user mainly performs by time and / or location. For example, it may store an action that a user made on an electronic device (101) and define and classify the action for which the user is performing the action. The context-specific app usage pattern learning module (431) may define and classify the usage pattern using a learned library or module. The context-specific app usage pattern learning module (431) classifies and patternizes user actions and may utilize a library or module included in the memory of the electronic device (101) (e.g., the memory (130) of FIG. 1). A generative AI implementing the present invention may be learned and included in a library or module. An AI learning technology such as machine learning may be used as a learning method.

[0096] The user intent and preference analysis module (433) can analyze what actions the user intends to perform based on usage patterns, and what the user likes (e.g., dogs, plants) and dislikes (e.g., exercise). The prompt generation module (435) can monitor whether there is something the user needs to do at the current point in time by considering learned usage patterns, learned user intents, or preferences, and generate prompt information requesting the generation of AI notification information about things the user must do, should do, or needs to do. The more accurate the prompt information is, the more refined the AI ​​notification information can be generated.

[0097] The Gen AI notification schedule generation component (450) may include situation judgment and customized action prediction (451) and screen-specific interaction guide generation (453). The situation judgment and customized action prediction (451) may determine the current situation based on the connection information or location information of the electronic device (101), such as where the electronic device (101) is currently located, whether the user is currently using the electronic device (101) based on the sensing information of the electronic device (101), and what the user is currently viewing based on the screen information (or content) displayed on the display module (160). The situation judgment and customized action prediction (451) may predict an action that the user should perform or a recommended action based on the determined current situation. For example, the recommended action may include recommending a movie of about 2 hours in length, considering the user's bedtime (e.g., 12 midnight), when the user is viewing the home screen of the electronic device (101) at 10 PM. The action of providing a notification when a purchase is not made even after the washing machine has been operated (detergent consumed) can generate a prompt based on the washing machine operation and the lack of detergent, and generate a notification (outcome) predicting the user's need to purchase detergent through generative AI, and provide a notification if the user does not purchase detergent for a certain period of time.

[0098] The Gen AI notification schedule generation component (450) can generate AI notification information based on the above prompt information. If a user searches for laundry detergent, but prior purchase history and washing machine usage patterns indicate that there is likely to be detergent remaining, the Gen AI notification schedule generation component (450) can generate AI notification information based on the remaining amount of laundry detergent, indicating the need to purchase laundry detergent later. The Gen AI notification schedule generation component (450) can determine the user's usage pattern, generate prompt information based on the usage pattern, and generate AI notification information based on the prompt information.

[0099] The above AI notification information may include not only guidance for actions but also guidance for user interactions. Screen-specific interaction guide generation (453) may generate user interactions such as guidance for touch locations, long presses, drags, scrolls, double-clicks, swipes, or swipe directions as AI notification information.

[0100] The AI ​​notification provision component (470) may include a recommended action notification (471) and a screen-specific action guide (473). The recommended action notification (471) may provide AI notification information appropriate to the current situation of the electronic device (101) based on the AI ​​notification information. The screen-specific action guide (473) may provide AI notification information appropriate to the current time, location, or situation based on the AI ​​notification information. The AI ​​notification information may vary by application and may vary by function within the application. The screen-specific action guide (473) may display an indicator (e.g., arrow, text) that guides the user to perform an action on each screen based on the AI ​​notification information. If a purchase is not made even after the washing machine has been operated (detergent consumed), the AI ​​notification provision component (470) may provide AI notification information guiding the user to purchase detergent. In other words, the AI ​​notification provision component (470) may provide AI notification information when an action predicted through generative AI is not performed.

[0101] FIG. 5 is a flowchart (500) illustrating a method for collecting various information based on events in an electronic device according to one embodiment. FIG. 5 may further specify operations 301 and 303 of FIG. 3.

[0102] Referring to FIG. 5, in operation 501, a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1) according to an embodiment may receive an event through an application. The event may include a push message of an application installed in the electronic device (101). For example, the event may be a message received from an application for controlling an IoT device (e.g., Smart Things), a message received from a messenger application, an advertisement received from a shopping application, a post notification received from an SNS application, or a discount notification received from a BB application.

[0103] In operation 503, the processor (120) may collect device status information and location information. The device status information may include the communication connection status (e.g., Wi-Fi, Bluetooth) of the electronic device (101), when, where, and with which external device the electronic device (101) is connected, and sensing information measured by the sensor module (e.g., the sensor module (176) of FIG. 1) of the electronic device (101). For example, when there is an event that needs to be confirmed in device B while device A is in use, when devices A and B are in the same space or when devices A and B are connected to each other in communication, if the event is not confirmed, the generative AI may provide AI notification information to device A to check the event of device B. Generative AI may generally refer to an artificial intelligence neural network that creates a new form of data based on user input information. Generative AI may be a model trained to output the most appropriate output value statistically based on input values. The processor (120) can collect location information on whether the electronic device (101) is a home or a company based on information obtained from the GPS module of the electronic device (101) and the communication connection status of the electronic device (101).

[0104] In operation 505, the processor (120) may analyze files and / or stored data within the electronic device (101). For example, the files or data may be stored in the memory of the electronic device (101) (e.g., the memory (130) of FIG. 1). The processor (120) may analyze conversation information stored in a messenger application, schedule information stored in a calendar application, alarm information stored in an alarm application, contact information stored in a contact application, and posts stored (or registered) in a posting application as the files or data. The processor (120) may analyze the files or data to analyze the user's intentions, patterns, or preferences.

[0105] According to one embodiment, the processor (120) can collect and analyze the main usage behavior, usage time, and usage location for each application. For example, the electronic device (101) may be connected to AA wifi, the screen of the electronic device may be turned off at 8 PM, and a shopping application may be mainly executed at 9 PM. When the electronic device (101) is connected to AA wifi, the processor (120) may determine that the location information is home, or when the location information through the GPS module is home, the processor (120) may determine that the electronic device (101) is connected to AA wifi. The processor (120) may analyze when, where, and which application is used based on the usage status of the electronic device (101).

[0106] The processor (120) can analyze preference information based on the file or data. For example, data stored in a food delivery application may include restaurant name or type (e.g., Korean, Chinese, Japanese), food menu (e.g., chicken, tteokbokki, jajangmyeon, spaghetti), delivery time, and payment method (e.g., cash, card). Furthermore, data stored in a card application may include card usage history, including the time, location, store name, and amount of card payment. The processor (120) can analyze the user's preferences or dislikes based on the file or data.

[0107] In operation 507, the processor (120) may analyze data stored in an external device or an external server. The external device may include an IoT device such as a washing machine, a TV, a refrigerator, a Bluetooth speaker, a wearable device such as a Bluetooth earphone, or an external electronic device such as a laptop or a computer. Information obtained from the external device may include an identifier of the external device, a notification of the external device (e.g., a laundry completion notification), a status of the external device (e.g., a power saving mode), or data stored in the external device (e.g., an image, a file, a favorite information). The processor (120) may analyze the data stored in the external device to analyze the user's intention, pattern, or preference. Alternatively, the processor (120) may analyze the user's intention, pattern, or preference by analyzing data stored in an external server (e.g., a cloud server registered with a user account of the electronic device (1101)) (e.g., the server (108) of FIG. 1). The processor (120) may refer to information of other users for recommendations.

[0108] FIG. 6 is a diagram illustrating an example of providing AI notification information in an electronic device according to one embodiment.

[0109] Referring to FIG. 6, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may provide different AI notification information according to a state (e.g., situation, location), current time, or condition of the electronic device (101) by using generative AI. The generative AI may be included within the electronic device (101). The generative AI may refer to an artificial intelligence neural network that creates a new form of data depending on user input information. The generative AI is a model trained to output the most statistically appropriate output value based on an input value, and can recognize various forms of data input such as text, images, and voice, and generate new data corresponding thereto.

[0110] The processor (120) can generate prompt information such as, "Recommend what to do right now" based on the connected external device (e.g., a friend's car, a headset), activity information: while stopped, the user's saved schedule information (e.g., watching a soccer game from 18:00 to 20:00 in a calendar application), preference information (e.g., preferred: YouTube, front seat, discount coupon, soccer, beer, Son Heung-min, disliked: fast food, overconsumption, Arsenal, baseball, soju, rainy day, Netflix, highway), and the application (e.g., driving completion screen of a route finding application) displayed on the current display (e.g., the display module (160) of FIG. 1).

[0111] The generative AI generates a result (e.g., the first AI notification (601)) based on the above prompt information, and, based on the result to be generated, if the current location of the electronic device (101) has arrived at the AA stadium and no other action is performed, determines that the first AI notification (601) is necessary and instructs the processor (120) to provide the first notification information (610). The processor (120) can provide the first notification information (610) according to the instruction of the generative AI. The provision condition of the first AI notification (601) is 'immediately', and the generative AI can instruct the processor (120) to generate the first AI notification information (610) and provide it immediately. The user can check what to do through the AI ​​notification information (610). If the user selects the first AI notification information (610), the processor (120) can provide the first-second AI notification information (615). Users can quickly find discount coupons through the 1-2 AI notification information (615).

[0112] Alternatively, if the current location of the electronic device (101) is the main gate of the AA stadium, the generative AI may determine that a second AI notification (603) is necessary based on the prompt information and instruct the processor (120) to provide second AI notification information (630). The processor (120) may provide the second AI notification information (630) according to the instruction of the generative AI. The generative AI may instruct the processor (120) to provide second AI notification information (630) that is different from the first AI notification information (610) depending on the current situation of the electronic device (101). The provision condition of the second AI notification (603) may be 'upon arrival at the main gate of the AA stadium.' The user may check what to do now through the second AI notification information (630) and purchase soccer game tickets with a discount coupon. When the user selects the second AI notification information (630), the processor (120) can provide the second-second AI notification information (635). The user can quickly find a discount coupon through the second-second AI notification information (635).

[0113] In addition, if the current location of the electronic device (101) is the 3rd floor of the AA stadium and no action to purchase beer has been performed (e.g., if there is no beer purchase history in the card statement), the generative AI may determine that a third AI notification (605) is necessary and instruct the processor (120) to provide third AI notification information (650). The processor (120) may provide the third AI notification information (650) according to the instruction of the generative AI. The condition for providing the third AI notification (605) may be 'if the current location is the 3rd floor of the AA stadium and there is no beer purchase history'. The generative AI may instruct the processor (120) to provide third AI notification information (650) that is different from the second AI notification information (630) depending on the current situation of the electronic device (101). The user may check what to do now through the third AI notification information (650) and purchase beer.

[0114] FIGS. 7A to 7C are diagrams illustrating an example of providing AI notification information in an electronic device according to one embodiment.

[0115] Referring to FIG. 7A, the first situation (710) can generate a notification using generative AI when an event is received, and can provide a notification to the user when the washing machine is approached but no action is taken. The electronic device (e.g., the electronic device (101) of FIG. 1) can determine the time, location, or function of the user's use of the external device based on connection information with the external device and information obtained from the external device through an IoT control application. For example, the user may primarily use the washing machine (701) on Wednesdays, Thursdays, or on weekends at 8 PM. Additionally, the user may primarily perform standard laundry on the washing machine (701) and use the dryer after the washing machine is finished. The electronic device (101) can transmit the user's usage pattern to the generative AI, and the electronic device (101) can generate prompt information based on the user's usage pattern, the current status of the electronic device (101), and the notification received from the washing machine (701) through the generative AI. The generative AI may refer to an artificial intelligence neural network that creates new types of data based on user input information. Generative AI is a model trained to produce the most statistically appropriate output based on input values. It can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them.

[0116] The generative AI can generate AI notification information based on the above prompt information and plan when to provide the AI ​​notification information. The plan may be modified midway. After the AI ​​notification information is generated by the generative AI, if the user approaches the washing machine but does not perform any action, as shown in the drawing, the electronic device (101) can provide the generated AI notification information to the user. The condition for providing the AI ​​notification information may be 'immediately' or after a specific time. If the generative AI determines that the user's schedule has free time or that tea time is appropriate, it can generate AI notification information based on the generated prompt information and instruct the processor (120) to provide the generated AI notification information. The condition for providing the AI ​​notification information may be a specific condition rather than a time. The condition for providing the AI ​​notification information may be when arriving at a specific location such as home or a cafe, or when it is recognized as the time to wake up or board public transportation.

[0117] Referring to FIG. 7B, the second situation (730) may be an example of generating AI notification information based on a usage empty pattern after the user (705) operates the washing machine (701). When the washing machine (701) is finished, the washing machine (701) may transmit a notification indicating the end of the washing process to the electronic device (101). If the user comes near the washing machine but does not take out the laundry, the generative AI may initially generate AI notification information such as "Please retrieve the laundry from the washing machine." If the operation predicted by the generative AI is not performed (e.g., if the user comes near the washing machine but does not take out the laundry), the electronic device (101) may initially provide AI notification information such as "Please retrieve the laundry from the washing machine" according to the instructions of the generative AI. After providing the primary AI notification information, if the user does not take out the laundry from the washing machine (e.g., if the user does not take out the laundry for a certain period of time), the electronic device (101) may regenerate prompt information providing a reminder notification. If the user's location information remains unchanged for a specified period of time (5 minutes) based on a laundry completion event or the user's location information (near the washing machine), the electronic device (101) may generate new prompt information to be provided to the generative AI. Based on the new prompt information, the generative AI may generate AI notification information such as, "If you do not retrieve your laundry from the washing machine immediately, damage may occur, so please retrieve your laundry quickly."

[0118] The electronic device (101) may determine that, depending on the usage pattern, the user (705) should take the laundry out of the washing machine (701) and put it in the dryer, but if the washing machine door is not detected to be opened or the dryer is not operated within a specified time (e.g., 5 minutes, 10 minutes) after receiving the laundry completion notification, the electronic device (101) may provide AI notification information notifying that the laundry should be taken out if the action predicted by the generative AI is not performed. In addition, the electronic device (101) may transmit the current situation to the generative AI if the laundry needs to be taken out quickly based on the washing mode (wool, blanket, etc.). Alternatively, the electronic device (101) may transmit the current situation to the generative AI if the laundry does not need to be taken out quickly. In this case, the generative AI may generate different AI notification information for cases where the laundry needs to be taken out quickly and for cases where the laundry does not need to be taken out quickly. Alternatively, the generative AI may instruct the electronic device (101) to provide different times for AI notification information when laundry needs to be taken out quickly and AI notification information when laundry does not need to be taken out quickly. Alternatively, the electronic device (101) may use the generative AI to determine whether to provide AI notification information, when to provide AI notification information, or whether to update the content of the AI ​​notification information provided.

[0119] If the dryer is not operated within a specified time after receiving the laundry completion notification, the electronic device (101) may generate AI notification information to place the laundry in the dryer. In the second situation (730) or earlier, the electronic device (101) may receive a laundry completion event and generate AI notification information through the generative AI. In the third situation (740), if the user (705) moves near the washing machine (701), the AI ​​notification information is not provided, but if the user (705) moves away from the washing machine (701) as in the fourth situation (750) without any action, the electronic device (101) may provide the user with AI notification information generated through the generative AI.

[0120] Referring to FIG. 7c, a fifth situation (760) may represent an example in which a user (705) converses with a third party (707). The electronic device (101) may not provide AI notification information for the user (705) conversing with the third party (707) as in the fifth situation (760). When the electronic device (101) detects that the user is moving near the washing machine (701), the electronic device (101) may perform an operation to provide AI notification information generated through generative AI. When the user (705) moves near the washing machine (701) as in the sixth situation (770), the electronic device (101) does not provide AI notification information, but when the user (705) moves away from the washing machine (701) as in the seventh situation (780) without performing any operation, the electronic device (101) may provide the user with AI notification information generated through generative AI.

[0121] In FIGS. 7B and 7C , the user may be wearing a wearable device (e.g., a watch or wireless earphones) connected to an electronic device (101). The electronic device (101) may output AI notification information through the wearable device. The AI ​​notification information may include at least one of text, audio, image, or video.

[0122] FIG. 8 is a flowchart (800) illustrating a method for providing AI notification information in an electronic device according to one embodiment.

[0123] Referring to FIG. 8, in operation 801, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may check time, location, and conditions. Generative AI may refer to an artificial intelligence neural network that creates new types of data depending on user input information. Generative AI is a model trained to statistically output the most appropriate output value based on input values, and may recognize various types of data input such as text, images, and voices, and generate new data corresponding thereto. Generative AI may generate a prediction list of actions that a user should perform at the current time, at the current location, or when at least one of specific conditions is met based on the user's usage pattern. The prediction list includes schedule information, and may include, for example, an action (e.g., running a washing machine) that should be performed at a specific time (e.g., 7 PM) and where (e.g., at home).

[0124] Generative AI can determine that an AI notification is necessary if the user does not perform an action included in the above-mentioned prediction list. Generative AI can generate prompt information for actions requiring user action based on information collected from an electronic device (101), an external device, an external server, or an application. Generative AI can generate AI notification information based on the generated prompt information.

[0125] In operation 803, the processor (120) can identify whether the user has confirmed for a specified period of time. The processor (120) can identify whether the user performs an action predicted through the generative AI, for example, an action that the user must perform, an action that the user should perform, or an action that the user needs to perform.

[0126] In operation 805, the processor (120) can determine whether the user has confirmed. If it is confirmed that the user has performed the action predicted through the generative AI, the processor (120) can perform operation 807, and if it is confirmed that the user has not performed the action predicted through the generative AI, the processor (120) can perform operation 811.

[0127] If it is confirmed that the user has performed the action predicted by the generative AI, the processor (120) may delete the AI ​​notification information at step 807. Since the user has performed the predicted action, the processor (120) may delete the AI ​​notification information. Alternatively, the processor (120) may provide recommendation information among the generated AI notification information based on the current state of the electronic device (101). This is merely an implementation issue and does not limit the invention.

[0128] At operation 809, the processor (120) may perform an information collection and analysis process. The information collection and analysis process may include operations 301 and 303 of FIG. 3, or operations 5 or 6. The processor (120) may collect and analyze information to determine the user's usage patterns, intentions, and preferences (or tastes) in order to provide more accurate AI notification information.

[0129] If it is determined that the user does not perform the action predicted by the generative AI, in operation 811, the processor (120) may provide AI notification information. The AI ​​notification information may include an indicator that guides application execution, execution of a specific function of the application, and user interaction. The user may perform an action that the user must perform, should perform, or needs to perform by referring to the AI ​​notification information. The AI ​​notification information may include at least one of text, audio, image, or video. The AI ​​notification information may be displayed on a display (e.g., the display module (160) of FIG. 1) or output through a speaker (e.g., the audio output module (155) of FIG. 1).

[0130] In operation 813, the processor (120) may wait for a specified period of time. While waiting for the specified period of time, the processor (120) may determine whether a user input for the AI ​​notification information is detected. If a user input for the AI ​​notification information is detected, the processor (120) may determine that the user input is due to the AI ​​notification information in operation 805 and perform operation 807. If a user input for the AI ​​notification information is not detected, the processor (120) may update the user's usage pattern based on a user action on the electronic device (101). If a user input for the AI ​​notification information is not detected, the AI ​​notification information may not be desired by the user. In this case, the processor (120) may update the user's usage pattern so that the AI ​​notification information can be generated by more accurately reflecting the user's intention.

[0131] According to one embodiment, if no user input for the AI ​​notification information is detected, the processor (120) may generate new prompt information based on the current state of the electronic device (101), screen information (or content) displayed on the display module (160), or current user action. The processor (120) may generate new prompt information to generate new AI notification information that reflects the user's intention.

[0132] According to one embodiment, if no user input for the AI ​​notification information is detected, the processor (120) may generate new AI notification information based on the operating state of the electronic device (101) by the user. If no user input for the AI ​​notification information is detected, the processor (120) may determine that the AI ​​notification information does not understand the user's intention and generate new AI notification information.

[0133] FIG. 9 is a diagram illustrating an example of displaying AI notification information in an electronic device according to one embodiment.

[0134] Referring to FIG. 9, a processor (e.g., the processor 120 of FIG. 1) of an electronic device (e.g., the electronic device 101 of FIG. 1) according to an embodiment may identify a user's usage pattern (e.g., identify a pattern based on various information from a usage-specific app usage pattern learning module (431) or an AI module), predict that the user will perform a specific action using generative AI, and, if the predicted action is not performed, provide AI notification information generated through the generative AI. For example, when the first user interface (910) is displayed and the user does not perform the action predicted by the generative AI, a second user interface (930) or a third user interface (950) may be displayed on a display (e.g., the display module (160) of FIG. 1). The first user interface (910) may include a home screen of the electronic device (101). The second user interface (930) may be an example of providing the first AI notification information (931) to the user by blinking. The first AI notification information (931) may also be an example in which the third user interface (950) displays second AI notification information (951) that blinks the application icon. The processor (120) may display second AI notification information (951) even after displaying the first AI notification information (931) if the user does not touch the application icon. The second AI notification information (951) may provide a different indicator than the first AI notification information (931).

[0135] FIGS. 10A and 10B are diagrams illustrating an example of displaying AI notification information in an electronic device according to one embodiment.

[0136] Referring to FIG. 10A, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may analyze schedule information (1010) stored in a schedule application and conversation information (1020) stored in a messenger application to generate prompt information. The generative AI may generate AI notification information based on the prompt information. The generative AI may be included within the electronic device (101) or may be included in an external server. The generative AI may refer to an artificial intelligence neural network that creates new types of data depending on user input information. The generative AI is a model trained to output statistically most appropriate output values ​​based on input values, and may recognize various types of data input such as text, images, and voice, and generate new data corresponding thereto. The schedule information (1010) may include a schedule such as Mom's birthday three days from the current time. The conversation information (1020) may be a conversation with a younger sibling stored in a family group in a contact application. The processor (120) can extract and analyze keywords such as 'Mom', 'Birthday Gift', 'C Shopping App', and 'QWEASD2310' from schedule information (1010) and conversation information (1020).

[0137] The processor (120) can determine that the user has not yet purchased a birthday present for his / her mother based on the card record obtained from the card application, the account transfer history obtained from the banking application, or the order history obtained from the shopping application. The processor (120) can analyze the collected information, and generate prompt information that transmits the current state of the electronic device (101) such that the user is holding the electronic device (101) and the home screen is displayed on the display (e.g., the display module (160) of FIG. 1) to the generative AI and requests that an AI notification be generated. If the action predicted by the generative AI is not performed, the processor (120) can provide a first user interface (1130). The first user interface (1130) can display the icon (1131) of the shopping application differently from the icons of other applications and can include a first reminder text (1033).

[0138] When the icon (1131) of the shopping application is selected, the processor (120) may display a second user interface (1140) on the display module (160). The second user interface (1140) may display a product code of 'QWEASD2310' in a search field within the shopping application, cause a search button (1041) to blink, and include a second reminder text (1043). When the search button (1041) is selected in the second user interface (1140), the processor (120) may display a third user interface (1150) on the display module (160). The third user interface (1150) may cause an order button (1051) to blink within a product page corresponding to the product code of 'QWEASD2310', and include a third reminder text (1053).

[0139] The user can easily purchase a birthday gift for his mother by sequentially following the AI ​​notification information displayed on the first user interface (1130), the second user interface (1140), and the third user interface (1150).

[0140] FIG. 11 is a diagram illustrating an example of displaying AI notification information in an electronic device according to one embodiment.

[0141] Referring to FIG. 11, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may display a first user interface (1110) including a first user interaction as first AI notification information (1101) on a display (e.g., the display module (160) of FIG. 1). The processor (120) may provide the first user interface (1110) when an action predicted through the generative AI is not performed (e.g., when the user needs to adjust the screen brightness but does not do so). The first AI notification information (1101) may guide a user interaction such that the user makes an input of dragging downwards in the center of the display module (160) in the upper bezel area of ​​the display module (160). Alternatively, the processor (120) may display a second user interface (1150) including the second user interaction as second AI notification information (1153) on the display module (160). The second AI notification information (1153) may provide a guide to select a control bar for adjusting screen brightness (1151).

[0142] FIG. 12 is a block diagram illustrating a generative artificial intelligence system according to one embodiment.

[0143] Referring to FIG. 12, a generative artificial intelligence system (e.g., an intelligent server, server (108) of FIG. 1) according to one embodiment may include a user interface (1210), a database (1220), an application and service component (1230), an AI framework (1250), and a generative AI model (1270).

[0144] The user interface (1210) can receive a user query. The user query can be in the form of natural language, images, or videos. Additionally, context information can be transmitted along with the user query. As another example, the user query can also be a non-natural language input that does not generate natural language, such as a design request or modification. Furthermore, the query can be a mixed form of natural language, images, sounds, and context information as described above. Furthermore, the user interface (1210) can output the results of the generative artificial intelligence system to the user. The output can be in the form of natural language or specific content, and can also be provided in the form of an action requested by the user.

[0145] The AI ​​framework (1250) can receive user queries and coordinate and control each component necessary to fulfill the user's intent. The AI ​​framework (1250) may include a prompt design component (251), an application and plug-in management component (APIs / Plugins Management component) (1253), and an output modification component (1255).

[0146] A user query or action entered in the user interface (1210) can be transmitted to a prompt design component (1251). The prompt design component (1251) can be used to generate prompts suitable for input into a large language model (LLM) or a large multimodal model. The prompt design component (1251) can be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (1251) can access a knowledge component containing user preference data, a prompt library, and prompt examples to generate prompts and pass them to the large language model (LLM) or the large multimodal model (LMM).

[0147] The application and plugin management component (1253) can communicate with external information when a request for additional information is made when user input is passed as input to the generative model. The application and plugin management component (1253) establishes a channel for communication with external entities within the AI ​​interface via an application programming interface (API), thereby enabling access to various data sources. Furthermore, the application and plugin management component (1253) can request actions via the API that ultimately fulfill a user query, rather than intermediate results, if the application or service needs to perform such actions. Information obtained from external sources can be passed as input to the generative model along with user input.

[0148] The output modification component (1255) can fine-tune the output from the generative model. For example, the output modification component (1255) can verify that content generated through a language model (LLM) or a large-scale multimodal model (LMM) is not irrelevant, does not contain biased content, or does not contain harmful content. In addition, the output modification component (1255) can determine the degree to which the content matches the user's desired result and, if necessary, can perform additional processing. Additionally, the output modification component (1255) can configure and provide hints to the user to avoid undesired output.

[0149] Generative AI models (1270) generally refer to artificial intelligence neural networks that create new forms of data based on user input information. Representative models that generate images include generative adversarial networks (GANs) and variational autoencoders (VAEs). Recently, diffusion-based generative models that use VAEs and transformer structures are also called generative models. In addition, language models are models trained to statistically produce the most appropriate output based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, since they can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them, they are called large multimodal models (LMMs).

[0150] An operating method of an electronic device (101) according to an embodiment of the present disclosure may include an operation of collecting at least one of information stored in an application installed in the electronic device, information stored in the memory, an event received through an application, information stored in the memory, or setting information set in the electronic device, an operation of analyzing the collected information to determine a user's usage pattern, an operation of analyzing the user's usage pattern to generate prompt information to be provided to generative artificial intelligence, an operation of generating AI notification information through the generative artificial intelligence based on the prompt information, and an operation of providing the AI ​​notification information when an action predicted through the generative artificial intelligence is not performed.

[0151] The operation of generating the above prompt information may include an operation of generating the prompt information related to the user action based on at least one of the current state of the electronic device, content displayed on the display, conversation content of a messenger application, conversation content of an SNS application, user action collected at a specific time, or user preference.

[0152] The above-mentioned displayed action may include, as the AI ​​notification information, an action of executing a specific application, executing a specific function of an application, or displaying an indicator that guides user interaction.

[0153] The method may further include an operation of generating new AI notification information based on an operational state of the electronic device by the user when no user input for the AI ​​notification information is detected.

[0154] The method may further include an action of deleting the AI ​​notification information after generating the AI ​​notification information without providing it to the user based on the current state of the electronic device, the content displayed on the display, or the current user action.

[0155] The method may further include an operation of updating the user's usage pattern based on a user action on the electronic device when no user input for the AI ​​notification information is detected; and an operation of analyzing the updated user's usage pattern to generate new prompt information to be provided to the generative artificial intelligence.

[0156] The above-determined operation may include an operation of determining the user's usage pattern by analyzing the current time, the current operating status of the electronic device, location information of the electronic device, information obtained from an external server registered with a user account of the electronic device, or an external device connected to the electronic device.

[0157] The above-determined action may include an action of learning content displayed on the display at a specific time and user actions on the electronic device to determine the user's usage pattern.

[0158] The above-mentioned providing operation may include an operation of providing the AI ​​notification information when at least one of the current time, the current operating status of the electronic device, or the location information of the electronic device corresponds to the provision condition of the AI ​​notification.

[0159] The various embodiments of the present invention disclosed in this specification and drawings are merely specific examples presented to facilitate easy explanation of the technical content of the present invention and aid understanding thereof, and are not intended to limit the scope of the present invention. Therefore, the scope of the present invention should be interpreted to include all modifications or variations derived based on the technical concept of the present invention, in addition to the embodiments disclosed herein.

Claims

1. In an electronic device (101), Display (160), Memory (130) for storing instructions, and Contains a processor (120), The instructions stored in the above memory, when executed by the processor, cause the electronic device to: Collect at least one of information stored in an application installed on the electronic device, an event received through the application, information stored in the memory, or setting information set on the electronic device, By analyzing the collected information above, we determine the user's usage patterns, Generate prompt information to be provided to generative artificial intelligence by analyzing the usage patterns of the above users, Generate AI notification information through the generative artificial intelligence based on the above prompt information, An electronic device that provides AI notification information when an action predicted by the generative artificial intelligence is not performed.

2. In the first paragraph, when the instructions are executed by the processor, the electronic device, An electronic device that generates the prompt information related to the user action based on at least one of the current status of the electronic device, the content displayed on the display, the conversation content of a messenger application, the conversation content of an SNS application, the user action collected at a specific time, or the user's preference.

3. In the second paragraph, the instructions, when executed by the processor, cause the electronic device to: An electronic device that displays an indicator that guides the execution of a specific application, the execution of a specific function of an application, or the user's interaction as the above AI notification information.

4. In the first paragraph, when the instructions are executed by the processor, the electronic device, An electronic device that generates new AI notification information based on the operational status of the electronic device by the user when no user input for the above AI notification information is detected.

5. In the first paragraph, when the instructions are executed by the processor, the electronic device, An electronic device that generates the above AI notification information, and then deletes the AI notification information without providing it to the user based on the current state of the electronic device or the current user action.

6. In the first paragraph, the instructions, when executed by the processor, cause the electronic device to: If no user input is detected for the above AI notification information, the user's usage pattern is updated based on the user's actions on the electronic device, An electronic device that analyzes the updated user's usage pattern to generate new prompt information to be provided to the generative artificial intelligence.

7. In the first paragraph, the instructions, when executed by the processor, cause the electronic device to: An electronic device that determines the user's usage pattern by analyzing the current time, the current operating status of the electronic device, location information of the electronic device, information obtained from an external server registered with a user account of the electronic device, or information obtained from an external device connected to the electronic device.

8. In the first paragraph, the instructions, when executed by the processor, cause the electronic device to: An electronic device that learns content displayed on said display at a specific time and user actions on said electronic device to determine the usage pattern of said user.

9. In the first paragraph, the instructions, when executed by the processor, cause the electronic device to: An electronic device that provides AI notification information when at least one of the current time, the current operating status of the electronic device, or the location information of the electronic device satisfies the conditions for providing the AI notification.

10. In the operating method of an electronic device (101), An action of collecting at least one of information stored in an application installed on the electronic device, an event received through the application, information stored in the memory, or setting information set on the electronic device; An action to determine the user's usage pattern by analyzing the collected information; An action of generating prompt information to be provided to generative artificial intelligence by analyzing the usage pattern of the above user; An action of generating AI notification information through the generative artificial intelligence based on the above prompt information; and A method including an action of providing AI notification information when an action predicted through the generative artificial intelligence is not performed.

11. In paragraph 10, the operation of generating the prompt information is: A method comprising an action of generating the prompt information related to the user action based on at least one of the current state of the electronic device, the content displayed on the display, the conversation content of a messenger application, the conversation content of an SNS application, the user action collected at a specific time, or the user's preference.

12. In paragraph 10, the indicated action is: A method including, as the above AI notification information, an action of executing a specific application, executing a specific function of an application, or displaying an indicator that guides user interaction.

13. In paragraph 10, A method further comprising an action of generating new AI notification information based on an operational state of the electronic device by the user when no user input for the AI notification information is detected.

14. In paragraph 10, A method further comprising an action of deleting the AI notification information after generating the AI notification information without providing it to the user based on the current state of the electronic device, the content displayed on the display, or the current user action.

15. In paragraph 10, If no user input is detected for the AI notification information displayed above, an action of updating the user's usage pattern based on the user's action on the electronic device; and A method further comprising an action of analyzing the updated user's usage pattern to generate new prompt information to be provided to the generative artificial intelligence.

Images