Electronic devices and method of generating personalized content

Abstract

An operation method for an electronic device according to an embodiment may comprise an operation for receiving a request for generating personalized content from a user. The operation method may comprise an operation for collecting data to be used for generating the personalized content. The operation method may comprise an operation for preprocessing collected data on the basis of privacy settings related to personal information concealment. The operation method may comprise an operation for generating a prompt on the basis of the preprocessed data. The operation method may comprise an operation for transmitting the prompt to a generative model.

Description

Electronic Devices and Methods for Creating Personalized Content

[0001] Embodiments of the present invention relate to an electronic device and a method for generating personalized content.

[0002] Generative models (e.g., generative artificial intelligence (AI)) have recently gained popularity, and are being utilized in areas such as article writing and blogging. Because the quality of the output from a generative model varies depending on the prompts inputted into the model, prompt engineering technology is attracting attention.

[0003] To utilize a generative model, users must directly input prompts into the model. If users wish to include personal information in the output of the generative model, they must do so within the prompt, which poses a risk of personal information being exposed. Furthermore, since users manually input prompts in natural language, the quality of the prompts depends on their knowledge and experience, which can also impact the quality of the output produced by the generative model.

[0004] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0005] A method of operating an electronic device according to one embodiment may include receiving a request for generating personalized content from a user. The method may include collecting data to be used in generating the personalized content. The method may include preprocessing the collected data based on privacy settings related to personal information concealment. The method may include generating a prompt based on the preprocessed data. The method may include transmitting the prompt to a generative model.

[0006] An electronic device according to one embodiment may include one or more processors. The electronic device may include a memory storing instructions. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to receive a request for generating personalized content from a user. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to collect data to be utilized in generating the personalized content. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to preprocess the collected data based on privacy settings related to personal information hiding. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to generate a prompt based on the preprocessed data. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to transmit the prompt to a generative model.

[0007] A method of operating an electronic device according to one embodiment may include receiving a request for generating personalized content from a user. The method may include collecting data to be utilized in generating the personalized content. The method may include preprocessing the collected data based on privacy settings related to personal information concealment. The method may include generating a prompt based on the preprocessed data. The method may include transmitting the prompt to a generative model. The method may include receiving an output of the generative model in response to the prompt. The method may include generating the personalized content by postprocessing the output to restore personal information not included in the output. The method may include providing the personalized content to the user in response to the generation request.

[0008] An electronic device according to one embodiment may include one or more processors. The electronic device may include a memory storing instructions. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to receive a request for generating personalized content from a user. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to collect data to be utilized in generating the personalized content. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to preprocess the collected data based on privacy settings related to personal information hiding. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to generate a prompt based on the preprocessed data. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to transmit the prompt to a generative model. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to receive an output of the generative model for the prompt. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to generate the personalized content by post-processing the output to restore personal information not included in the output. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to provide the personalized content to the user in response to the generation request.

[0009] FIG. 1 is a block diagram of an electronic device within a network environment, according to one embodiment.

[0010] FIGS. 2 to 4 are diagrams for explaining an operation of an electronic device generating personalized content according to one embodiment.

[0011] FIGS. 5 to 12 are diagrams for explaining data preprocessing operations according to one embodiment.

[0012] FIG. 13 is a diagram illustrating a prompt generated based on preprocessed data according to one embodiment.

[0013] FIG. 14 is a diagram for explaining a personal information restoration operation according to one embodiment.

[0014] FIG. 15 illustrates a flowchart of a method of operating an electronic device according to one embodiment.

[0015] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are assigned the same reference numerals regardless of the drawing numbers, and redundant descriptions thereof will be omitted.

[0016]

[0017] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100), according to one embodiment.

[0018] 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 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)).

[0019] 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).

[0020] According to one embodiment, the processor (120) may be implemented as a circuit (e.g., a processing circuit) such as a system on chip (SoC) or an integrated circuit (IC). The processor (120) may include one or more processors. For example, the processor (120) may include a combination of one or more processors such as a CPU, a GPU, an MPU, an AP, and a CP.

[0021] According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0022] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

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

[0024] According to one embodiment, the memory (130) may include one or more memories. The instructions stored in the memory (130) may be stored in a single memory. The instructions stored in the memory (130) may be divided and stored in a plurality of memories. The instructions stored in the memory (130) may be individually or collectively executed by the processor (120) to cause the electronic device (101) (e.g., the electronic device (200) of FIG. 2) to perform and / or control the personalized content generation method described with reference to FIGS. 2 to 15. The instructions stored in the memory (130) may be individually or collectively executed by a plurality of processors to cause the electronic device (101) (e.g., the electronic device (2000) of FIG. 2) to perform and / or control the personalized content generation method described with reference to FIGS. 2 to 15. According to one embodiment, the memory (130) may include volatile memory (132) or non-volatile memory (134).

[0025] 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).

[0026] 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).

[0027] 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.

[0028] 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. In 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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).

[0033] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0034] 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.

[0035] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least a part of a power management integrated circuit (PMIC).

[0036] 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.

[0037] 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).

[0038] 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.

[0039] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0040] In one embodiment, 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.

[0041] 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)).

[0042] 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.

[0043]

[0044] FIGS. 2 to 4 are diagrams for explaining an operation of an electronic device generating personalized content according to one embodiment.

[0045] According to one embodiment, the electronic device (200) can provide personalized content to the user. Personalized content may be content created based on the user's individual tastes, interests, behavioral patterns, and data. Personalized content may be tailored to meet the user's unique needs and preferences. Providing personalized content may require the collection of user data. User data (e.g., personal information) may include the user's activity history, search history, purchase history, click patterns, location information, and / or social media activity. By utilizing personal information stored within the electronic device (200), the electronic device (200) can provide personalized content to the user.

[0046] According to one embodiment, the electronic device (200) can support prompt engineering using personal information. The electronic device (200) can improve the quality of prompts for input into a generative model (e.g., generative artificial intelligence (AI)) (e.g., a language model) while maintaining the security of personal information. The prompts provided to the generative model can maintain the security of personal information. The electronic device (200) can generate personalized content by collaborating with an external generative model (e.g., a generative model running on a server (201)) through prompts with high security and high quality.

[0047] In one embodiment, a user can adjust the weights associated with data utilization (e.g., through weight settings) to customize the usability of data used for personalized content generation. Privacy settings related to personal information allow the user to selectively protect their personal information. The electronic device (200) can enhance the user experience when requesting personalized content generation.

[0048] Referring to FIG. 2, according to one embodiment, an electronic device (200) (e.g., the electronic device (101) of FIG. 1) and a server (201) (e.g., the server (108) of FIG. 1) may be connected via a local area network (LAN), a wide area network (WAN), a value added network (VAN), a mobile radio communication network, a satellite communication network, or a combination thereof. The electronic device (200) and the server (201) may communicate with each other via a wired communication method or a wireless communication method (e.g., wireless LAN (WiFi), Bluetooth, Bluetooth low energy, ZigBee, WiFi direct (WFD), ultra wide band (UWB), infrared data association (IrDA), near field communication (NFC)).

[0049] According to one embodiment, the electronic device (200) may be implemented as at least one of a smartphone, a tablet personal computer, a mobile phone, a speaker (e.g., an AI speaker), a video phone, an e-book reader, a desktop personal computer, a laptop personal computer, a netbook computer, a workstation, a server, a personal digital assistant (PDA), a portable multimedia player (PMP), an MP3 player, a mobile medical device, a camera, or a wearable device.

[0050] According to one embodiment, the electronic device (200) may include one or more processors (220) (e.g., the processor (120) of FIG. 1). The electronic device (200) may include a memory (230) (e.g., the memory (130) of FIG. 1). The processor (220) (e.g., an application processor) may access the memory (230) to execute one or more instructions. The memory (230) may store various data used by at least one component (e.g., the processor (220)) of the electronic device (200).

[0051] According to one embodiment, the processor (220) may be implemented as a circuit (e.g., a processing circuit) such as a system on chip (SoC) or an integrated circuit (IC). The processor (220) may include one or more processors. For example, the processor (220) may include a combination of one or more processors such as a CPU, a GPU, an MPU, an AP, and a CP.

[0052] According to one embodiment, the memory (230) may include one or more memories. The instructions stored in the memory (230) may be stored in a single memory. The instructions stored in the memory (230) may be divided and stored in multiple memories. The instructions stored in the memory (230) may be individually or collectively executed by the processor (220) to cause the electronic device (200) to perform and / or control the personalized content generation method described with reference to FIGS. 2 to 15. The instructions stored in the memory (230) may be individually or collectively executed by multiple processors to cause the electronic device (200) to perform and / or control the personalized content generation method described with reference to FIGS. 2 to 15.

[0053] According to one embodiment, the electronic device (200) can collect data (e.g., data to be used for creating personalized content) (e.g., image data and / or text data) through the data management module (211). The data to be used for creating personalized content may be stored in an application running within the electronic device (200). The data management module (211) can collect data to be used for creating personalized content from the application and manage the data. When the data management module (211) receives a data transmission request from the personalized content management module (212), the data management module (211) can first check the permission to use the requested data. The permission to use the requested data may vary depending on the application that received the creation request from the user (or transmitted the creation request to the personalized content management module (212). The data management module (211) can transmit only data with the permission to the personalized content management module (212).

[0054] According to one embodiment, the electronic device (200) can generate a prompt through the personalized content management module (212). The prompt can be data that conveys a user's input or request to a generative model (e.g., generative AI) (e.g., a neural network model, a subfield of machine learning and artificial intelligence, that analyzes given data and generates new data or content based on it) (e.g., a language model). The generative model can analyze the prompt and generate an appropriate response accordingly. A properly written prompt can help the generative model output the content desired by the user. The personalized content management module (212) can preprocess the data received from the data management module (211) (e.g., by hiding personal information and / or assigning weights to the data) and generate a prompt based on the preprocessed data.

[0055] In one embodiment, the electronic device (200) may transmit a prompt to the server (201). The prompt may be in a state where personal information is kept secure. The electronic device (200) may receive the output of a generative model for the prompt from the server (201). The electronic device (200) may generate personalized content by post-processing the output of the generative model (e.g., restoring personal information).

[0056] Referring to FIG. 3, according to one embodiment, the personalized content management module (212) may include a settings manager (301), a weight setting module (302), a personal information identification module (303), a personal information encoder (304), a prompt generator (305), and a personal information decoder (306).

[0057] According to one embodiment, the settings manager (301) can manage privacy settings related to personal information concealment and / or weight settings related to data utilization (e.g., see FIG. 7 ). The privacy settings and / or related weight settings may be obtained from each of the applications executable on the electronic device (200). The personalized content management module (212) can preprocess data based on the privacy settings and / or weight settings of the application that received the creation request from the user (or transmitted the creation request to the personalized content management module (212)).

[0058] According to one embodiment, the weight setting module (302) can selectively assign weights to collected data (e.g., image data and / or text data). The weight setting module (302) can identify weight setting targets from the collected data and selectively assign weights to the weight setting targets based on the weight settings. The weight settings may be obtained by a request for creating personalized content and / or a user's settings (e.g., see FIG. 6). The weight settings for the same data may vary for each application executable on the electronic device (200). Additionally, the privacy settings for the same data may vary for each application executable on the electronic device (200).

[0059] According to one embodiment, the personal information identification module (303) can identify a masking target (e.g., personal information) among collected data (e.g., image data and / or text data). The specific operation of the personal information identification module (303) will be described in detail with reference to FIG. 4.

[0060] According to one embodiment, the personal information encoder (304) may mask at least a portion of the masking target (e.g., personal information) based on privacy settings. The personal information encoder (304) may be configured to encode specific personal information based on the user's settings. The personal information may include sensitive information such as an ID, password, or account number. The specific operation of the personal information encoder (304) will be described in detail with reference to FIG. 4.

[0061] In one embodiment, the prompt generator (305) may generate prompts based on preprocessed data. As described above, the prompts may be data that conveys a user's input or request to the generative model. The prompts generated by the prompt generator (305) may maintain the security of personal information (e.g., based on privacy settings). The prompts generated by the prompt generator (305) may reflect the user's intentions regarding data utilization (e.g., based on weight settings).

[0062] In one embodiment, the personal information decoder (306) can post-process the output of the generative model (e.g., restore personal information). The output of the generative model may also maintain the security of personal information. By restoring personal information through the personal information decoder (306), the electronic device (200) can generate personalized content.

[0063] Referring to FIG. 4, according to one embodiment, the personal information identification module (303) may include a face image detector (401), an optical character recognition (OCR) module (402), and a named entity recognition (NER) module (403). The personal information encoder (304) may include an image encoder (411), a rule-based text encoder (412), and a language model (LM)-based sentence encoder (413).

[0064] In one embodiment, a face image detector (401) can identify a face image from collected image data. An image encoder (411) can blur the face image or add noise to the face image based on a privacy setting (e.g., see FIG. 8).

[0065] In one embodiment, the OCR module (402) can identify text in the collected image data. The image encoder (411) can blur the text or add noise to the text based on the privacy settings (e.g., see FIG. 9).

[0066] According to one embodiment, the NER module (403) can identify a named entity corresponding to the collected text data. The rule-based text encoder (412) can replace the collected text data with a word corresponding to the named entity based on privacy settings (e.g., see FIG. 10). For example, for the collected text data (e.g., Kim Samsung goes to Everland on Christmas), the NER module (403) can obtain a named entity recognition result (e.g., Kim Samsung (PERSON) goes to Everland (LOCATION) on Christmas (DATE). The rule-based text encoder (412) can replace the collected text data with a word corresponding to the named entity based on privacy settings (e.g., DATE hiding and PERSON hiding) (e.g., Christmas -> replaced with DATE_1, Kim Samsung -> replaced with PERSON_1). The rule-based text encoder (412) can derive preprocessed data (e.g., PERSON_1 goes to Everland on DATE_1).

[0067] According to one embodiment, the language model-based sentence encoder (413) can perform sentence encoding on the collected text data. The language model-based sentence encoder (413) can input the collected text data into a generative model stored in the electronic device (200) based on privacy settings to obtain an embedding vector (e.g., see FIG. 11). The generative model stored in the electronic device (200) may be transfer-learned based on an embedding model of a generative model stored outside the electronic device (200) (e.g., a generative model stored in the server (201) of FIG. 2).

[0068]

[0069] FIGS. 5 to 12 are diagrams for explaining data preprocessing operations according to one embodiment.

[0070] Referring to FIG. 5 , according to one embodiment, collected data (500) can be verified for use in generating personalized content. The data (500) may be original collected data or a prompt containing personal information. For example, an electronic device (e.g., the electronic device (200) of FIG. 2 ) may preprocess the collected data and generate a prompt that does not contain personal information based on the preprocessed data. For example, the electronic device (200) may first generate a prompt containing personal information and then postprocess the prompt to generate a prompt that does not contain personal information. The following description focuses on the operation of preprocessing the collected data.

[0071] Referring to FIG. 6 , according to one embodiment, the electronic device (200) may display a settings screen (600) associated with personalized content. The settings screen (600) associated with personalized content may include the type of data to be collected (e.g., content used for recording), the style of the personalized content (e.g., diary style settings), and privacy settings related to personal information hiding (e.g., permissions). However, the user interface associated with the settings associated with personalized content is not limited to the user interface illustrated in FIG. 6 .

[0072] Referring to FIG. 7, according to one embodiment, an example of a settings table managed by a settings manager (e.g., settings manager (301) of FIG. 3) can be viewed. The settings table may be updated based on the settings screen described with reference to FIG. 6. Table (701) may include information on privacy settings related to personal information hiding. For example, in a contacts app, names may be set to be hidden (e.g., hide), relationships may be set not to be hidden (e.g., show), and numbers may be set to be hidden (e.g., hide). Table (702) may include information on weight settings related to data utilization. For example, if there is a request to create personalized content (e.g., diary), data from a calendar app may be given a weight of 10, and data from a gallery app may be given a weight of 5. Weight settings may be obtained from personalized content creation requests and / or user settings. Below, we describe the process of preprocessing collected data based on privacy settings.

[0073] Referring to FIG. 8, according to one embodiment, the electronic device (200) can identify a face image (811) from collected image data (810). Based on privacy settings, the electronic device (200) can blur the face image (811) or add noise to the face image (e.g., 820).

[0074] Referring to FIG. 9, according to one embodiment, the electronic device (200) can identify text (911) in collected image data (910). Based on privacy settings, the electronic device (200) can blur the text (911) (e.g., sensitive information) or add noise to the text (e.g., 920).

[0075] Referring to FIG. 10, according to one embodiment, the electronic device (200) can identify an entity name corresponding to the collected text data (1010). The electronic device (200) can replace at least a portion (1011 to 1014) of the collected text data (1010) with a word corresponding to the entity name based on the privacy setting. The text data (1011 to 1014) to be replaced with a word corresponding to the entity name may be determined based on the privacy setting. For example, for the collected text data (1011) (e.g., James), the electronic device (200) can obtain an entity name recognition result (e.g., James (PERSON)). The electronic device (200) can replace the collected text data (1011) with a word corresponding to the entity name (e.g., James -> replaced with PERSON_1) based on the privacy setting (e.g., PERSON hiding). The electronic device (200) can derive preprocessed data (1020).

[0076] Referring to FIG. 11, according to one embodiment, the electronic device (200) may perform sentence encoding on collected text data (1110). Text data (1111) on which sentence encoding is to be performed among the collected text data (1110) may be determined based on privacy settings (e.g., settings to hide specific phrases and / or specific text data). According to one embodiment, when the electronic device (200) uses a generative model stored in the electronic device (200), the electronic device (200) may not perform sentence encoding on the collected data. Based on the privacy settings, the electronic device (200) may input the collected text data (1111) into the generative model stored in the electronic device (200) to obtain an embedding vector (1121). The generative model stored in the electronic device (200) may be transfer-learned based on an embedding model of a generative model stored outside the electronic device (200) (e.g., a generative model stored in the server (201) of FIG. 2).

[0077] Referring to FIG. 12, according to one embodiment, the electronic device (200) can selectively assign weights to collected data. The electronic device (200) can identify a weight setting target (1210) from the collected data and assign a weight to the weight setting target (1210) based on the weight setting (e.g., see 1220). The weight setting may be obtained by a request for creation of personalized content and / or a user setting.

[0078]

[0079] FIG. 13 is a diagram illustrating a prompt generated based on preprocessed data according to one embodiment.

[0080] Referring to FIG. 13, according to one embodiment, an electronic device (e.g., electronic device (200) of FIG. 2) may generate a prompt (1320) based on collected data (1310) (e.g., data (500) of FIG. 5). The prompt (1320) may be in a state where personal information security is maintained. The prompt (1320) may be in a state where a weight related to data usability is assigned. The electronic device (200) may generate personalized content by collaborating with an external generative model (e.g., a generative model running on a server (201)) through a prompt (1320) having high security and high quality.

[0081]

[0082] FIG. 14 is a diagram for explaining a personal information restoration operation according to one embodiment.

[0083] Referring to FIG. 14, according to one embodiment, an external generative model (e.g., a generative model driven by a server (201)) can generate an output (1410) through a prompt transmitted by an electronic device (e.g., the electronic device (200) of FIG. 2). The output (1410) may maintain the security of personal information (e.g., see 1411 to 1415). The electronic device (200) can post-process the output (1410) (e.g., restore the personal information). By restoring the personal information through a personal information decoder (e.g., the personal information decoder (306) of FIG. 3), the electronic device (200) can generate personalized content (1420).

[0084] According to one embodiment, the electronic device (200) can support prompt engineering using personal information. The electronic device (200) can improve the quality of prompts for input into a generative model (e.g., generative artificial intelligence (AI)) (e.g., a language model) while maintaining the security of personal information. The prompts provided to the generative model can maintain the security of personal information. The electronic device (200) can generate personalized content (1420) by collaborating with an external generative model (e.g., a generative model running on a server (201)) through high-security and high-quality prompts.

[0085]

[0086] FIG. 15 illustrates a flowchart of a method of operating an electronic device according to one embodiment.

[0087] Actions 1510 to 1550 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of each action (1510 to 1550) may be changed, and at least two actions may be performed in parallel.

[0088] According to one embodiment, operations 1510 to 1550 may be understood to be performed in a processor (e.g., processor (220) of FIG. 3) of an electronic device (e.g., electronic device (200) of FIG. 2).

[0089] In operation 1510, an electronic device according to one embodiment may receive a request from a user to create personalized content. The request may include at least one of the following: the type of personalized content, the style of the personalized content, or the type of data to be collected. Providing personalized content may require the collection of user data.

[0090] In operation 1520, an electronic device according to one embodiment may collect data to be used in generating personalized content from at least one application. The electronic device may collect data from each application executable on the electronic device (e.g., the electronic device).

[0091] In operation 1530, an electronic device according to one embodiment may preprocess collected data based on privacy settings related to personal information concealment. The privacy settings may be obtained from the user's settings. The electronic device may preprocess (e.g., add noise, blur, or replace with other data) the collected data (e.g., text data, image data) based on the privacy settings.

[0092] In operation 1540, an electronic device according to one embodiment may generate a prompt based on preprocessed data. The prompt may be data that conveys a user's input or request to a generative model (e.g., generative artificial intelligence (AI)) (e.g., a language model). A properly written prompt can help the generative model output the content desired by the user.

[0093] In operation 1550, an electronic device according to one embodiment may transmit a prompt to a generative model. The prompt transmitted (e.g., provided) to the generative model may maintain the security of personal information. The electronic device may collaborate with an external generative model (e.g., a generative model running on the server (201) of FIG. 2) through a highly secure and high-quality prompt to generate personalized content.

[0094]

[0095] According to one embodiment, a method of operating an electronic device (e.g., electronic device 101 of FIG. 1 or electronic device 200 of FIG. 2) may include an operation of receiving a request for generating personalized content from a user. The method may include an operation of collecting data to be utilized for generating the personalized content. The method may include an operation of preprocessing the collected data based on privacy settings related to personal information hiding. The method may include an operation of generating a prompt based on the preprocessed data. The method may include an operation of transmitting the prompt to a generative model.

[0096] In one embodiment, the method may further include receiving an output of the generative model for the prompt. The method may further include generating the personalized content by post-processing the output to restore personal information not included in the output. The method may further include providing the personalized content to the user in response to the generation request.

[0097] In one embodiment, the generation request may include at least one of the type of the personalized content, the style of the personalized content, or the type of data to be collected.

[0098] In one embodiment, the operation of preprocessing the collected data may include identifying weighting targets from the collected data. The operation of preprocessing the collected data may include selectively assigning weights to the weighting targets based on weighting settings associated with data utilization. The weighting settings may be obtained from the generation request or the user's settings.

[0099] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying masking targets in the collected data. The operation of preprocessing the collected data may include an operation of masking at least some of the masking targets based on the privacy settings. The privacy settings may be obtained from the user's settings.

[0100] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying a facial image from the collected image data. The operation of preprocessing the collected data may include an operation of blurring the facial image or adding noise to the facial image based on the privacy setting.

[0101] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying text in the collected image data through optical character recognition (OCR). The operation of preprocessing the collected data may include an operation of blurring the text or adding noise to the text based on the privacy settings.

[0102] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying an entity name corresponding to the collected text data through named entity recognition (NER). The operation of preprocessing the collected data may include an operation of replacing the collected text data with a word corresponding to the entity name based on the privacy settings.

[0103] In one embodiment, the operation of preprocessing the collected data may include an operation of inputting the collected text data into a generative model stored in the electronic device to obtain an embedding vector based on the privacy settings. The generative model stored in the electronic device may be transfer-learned based on an embedding model of a generative model stored outside the electronic device.

[0104] In one embodiment, the privacy settings or weight settings related to data utilization may be obtained from each of the at least one application. The operation of preprocessing the collected data may be performed based on the privacy settings or weight settings of the application that received the generation request.

[0105] A method of operating an electronic device (e.g., the electronic device 101 of FIG. 1 or the electronic device 200 of FIG. 2) according to one embodiment may include receiving a request for generating personalized content from a user. The method may include collecting data to be utilized in generating the personalized content. The method may include preprocessing the collected data based on privacy settings related to personal information hiding. The method may include generating a prompt based on the preprocessed data. The method may include transmitting the prompt to a generative model. The method may include receiving an output of the generative model in response to the prompt. The method may include generating the personalized content by postprocessing the output to restore personal information not included in the output. The method may include providing the personalized content to the user in response to the generation request.

[0106] According to one embodiment, the preprocessed data may be preprocessed based on weight settings related to data utilization as well as the privacy settings.

[0107] In one embodiment, the generation request may include at least one of the type of the personalized content, the style of the personalized content, or the type of data to be collected.

[0108] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying masking targets in the collected data. The operation of preprocessing the collected data may include an operation of masking at least some of the masking targets based on the privacy settings. The privacy settings may be obtained from the user's settings.

[0109] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying a facial image from the collected image data. The operation of preprocessing the collected data may include an operation of blurring the facial image or adding noise to the facial image based on the privacy setting.

[0110] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying text in the collected image data through optical character recognition (OCR). The operation of preprocessing the collected data may include an operation of blurring the text or adding noise to the text based on the privacy settings.

[0111] In one embodiment, the operation of preprocessing the collected data may include an operation of identifying an entity name corresponding to the collected text data through named entity recognition (NER). The operation of preprocessing the collected data may include an operation of replacing the collected text data with a word corresponding to the entity name based on the privacy settings.

[0112] In one embodiment, the operation of preprocessing the collected data may include an operation of inputting the collected text data into a generative model stored in the electronic device to obtain an embedding vector based on the privacy settings. The generative model stored in the electronic device may be transfer-learned based on an embedding model of a generative model stored outside the electronic device.

[0113] An electronic device according to one embodiment (e.g., electronic device 101 of FIG. 1 or electronic device 200 of FIG. 2) may include one or more processors (e.g., processor 120 of FIG. 1 or processor 220 of FIG. 2). The electronic device may include a memory (e.g., memory 130 of FIG. 1 or memory 230 of FIG. 2) that stores instructions. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to receive a request for generating personalized content from a user. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to collect data to be utilized in generating the personalized content. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to preprocess collected data based on privacy settings related to personal information hiding and weight settings related to data usability. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to generate a prompt based on the preprocessed data. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to transmit the prompt to a generative model.

[0114] In one embodiment, the instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to receive an output of the generative model for the prompt. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to generate the personalized content by post-processing the output to restore personal information not included in the output. The instructions, when individually or collectively executed by the one or more processors, may cause the electronic device to provide the personalized content to the user in response to the generation request.

[0115]

[0116] 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.

[0117] 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.

[0118] 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).

[0119] Various embodiments of the present document may be implemented as software (e.g., a program) including one or more instructions stored in a storage medium (e.g., built-in memory or external memory) readable by a machine (e.g., an electronic device). For example, a processor (e.g., a processor) of the machine (e.g., an electronic device) 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 instruction called. 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' only means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0120] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0121] 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.

Claims

1. In the operating method of an electronic device (101; 200), An action to receive a request for creation of personalized content from a user; An action of collecting data from at least one application to be used in generating the personalized content; An action to preprocess collected data based on privacy settings related to personal information hiding; An action to generate a prompt based on preprocessed data; and The action of sending the above prompt to the generative model; A method of operating an electronic device (101; 200), comprising:

2. In paragraph 1, An action for receiving the output of the generative model for the above prompt; An operation of generating personalized content by post-processing the output to restore personal information not included in the output; and In response to the above creation request, an action is taken to provide the personalized content to the user. A method of operation, further comprising:

3. In either of paragraphs 1 and 2, The above creation request is, Including at least one of the type of personalized content, the style of the personalized content, or the type of data to be collected. How it works.

4. In any one of paragraphs 1 to 3, The action of preprocessing the collected data is as follows: An operation for identifying a weight setting target from the collected data; and An action to selectively assign weights to the weight setting target based on weight settings related to data utilization. Including, The above weight settings are, Obtained from the above creation request or the user's settings, How it works.

5. In any one of paragraphs 1 to 4, The action of preprocessing the collected data is as follows: An action for identifying a masking target from the collected data; and An operation of masking at least some of the masking targets based on the above privacy settings, The above privacy settings are: Obtained from the above user's settings, How it works.

6. In any one of paragraphs 1 to 5, The action of preprocessing the collected data is as follows: An action of identifying a face image from collected image data; and An action of blurring the face image or adding noise to the face image based on the privacy setting. A method of operation, comprising:

7. In any one of paragraphs 1 to 6, The action of preprocessing the collected data is as follows: An action to identify text from collected image data through OCR (optical character recognition); and An action to blur the text or add noise to the text based on the privacy settings. A method of operation, comprising:

8. In any one of paragraphs 1 to 7, The action of preprocessing the collected data is as follows: An action to identify the entity name corresponding to the collected text data through NER (named entity recognition); and An action of replacing the collected text data with a word corresponding to the entity name based on the above privacy settings. A method of operation, comprising:

9. In any one of paragraphs 1 to 8, The action of preprocessing the collected data is as follows: Based on the above privacy settings, the method comprises an operation of inputting the collected text data into a generative model stored in the electronic device (101; 200) to obtain an embedding vector. The generative model stored in the above electronic device (101; 200) is Transfer-learned based on the embedding model of the generative model stored outside the electronic device (101; 200). How it works.

10. In any one of paragraphs 1 to 9, The above privacy settings or weight settings related to data utilization are: obtained from each of the above at least one application, The action of preprocessing the collected data is as follows: It is performed based on the privacy settings or weight settings of the application that received the above generation request. How it works.

11. In an electronic device (101; 200), One or more processors (120; 220); and Memory for storing instructions (130; 230) Including, The above instructions, when individually or collectively executed by the one or more processors (120; 220), cause the electronic device (101; 200) to: Receive requests for creation of personalized content from users; Collect data to be used in creating the above personalized content, Based on privacy settings related to personal information hiding, the collected data is preprocessed, Based on the preprocessed data, generate prompts, Send the above prompt to the generative model, Receive the output of the generative model for the above prompt, By post-processing the output to restore personal information not included in the output, the personalized content is generated, In response to the above creation request, to provide the personalized content to the user, , Electronic devices (101; 200).

12. In paragraph 11, The above preprocessed data is, Preprocessed based on the above privacy settings as well as weight settings related to data utilization. Electronic devices (101; 200).

13. In either of paragraphs 11 and 12, The above creation request is, Including at least one of the type of personalized content, the style of the personalized content, or the type of data to be collected. Electronic devices (101; 200).

14. In any one of paragraphs 11 to 13, The above instructions, when individually or collectively executed by the one or more processors (120; 220), cause the electronic device (101; 200) to: Identify the masking target from the collected data above, Based on the above privacy settings, at least some of the masking targets are masked, The above privacy settings are: Obtained from the above user's settings, Electronic devices (101; 200).

15. In any one of paragraphs 11 to 14, The above instructions, when individually or collectively executed by the one or more processors (120; 220), cause the electronic device (101; 200) to: Identify facial images from collected image data, Based on the above privacy settings, blurring the face image or adding noise to the face image; Electronic devices (101; 200).

Images