Electronic device and method for processing information for protecting personal information

Abstract

An electronic device disclosed herein comprises: a communication circuit; a display; an audio device; a camera; at least one processor; and instructions stored in memory. The instructions stored in memory, when executed individually or collectively by the at least one processor, may cause the electronic device to: acquire data; acquire a user input; determine whether personal information is included in the data; if personal information is included in the data, convert the personal information into fake personal information; integrate at least one of data not including the personal information, data including the fake personal information, data including actual personal information, data excluding the personal information, abstract information, encrypted metadata, or the personal information; acquire content on the basis of at least one of the integrated data or the user input; process the content on the basis of the actual personal information; and execute the processed content.

Description

Methods for processing information for electronic devices and privacy protection

[0001] The present disclosure relates to an electronic device and a method for processing information for the protection of personal information.

[0002] Recently, users can generate new content or results by utilizing machine learning and / or artificial intelligence.

[0003] For example, generative artificial intelligence learns the characteristics and distributions of data based on large-scale datasets and can generate probabilistically probable outcomes based on the learned characteristics and distributions. Generative AI is utilized in various fields to enhance user convenience by enabling customized tasks and reducing content creation time.

[0004] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0005] An electronic device according to one embodiment of the present disclosure may include a communication circuit.

[0006] An electronic device according to one embodiment of the present disclosure may include a display.

[0007] An electronic device according to one embodiment of the present disclosure may include an acoustic device.

[0008] An electronic device according to one embodiment of the present disclosure may include a camera.

[0009] An electronic device according to one embodiment of the present disclosure may include at least one processor.

[0010] Instructions stored in memory according to one embodiment of the present disclosure can enable the electronic device to acquire data when executed individually or collectively by at least one processor.

[0011] Instructions stored in memory according to one embodiment of the present disclosure can enable the electronic device to obtain user input when executed individually or collectively by at least one processor.

[0012] Instructions stored in memory according to one embodiment of the present disclosure, when executed individually or collectively by at least one processor, can cause the electronic device to determine whether the data contains personal information.

[0013] Instructions stored in memory according to one embodiment of the present disclosure, when executed individually or collectively by at least one processor, can cause the electronic device to convert the personal information into fake personal information if the data contains the personal information.

[0014] Instructions stored in memory according to one embodiment of the present disclosure, when executed individually or collectively by the at least one processor, may cause the electronic device to integrate at least one of data that does not contain personal information, data that includes the fake personal information, data that includes the actual personal information, data from which personal information is excluded, abstract information, encrypted metadata, or the personal information.

[0015] Instructions stored in memory according to one embodiment of the present disclosure, when executed individually or collectively by at least one processor, can enable the electronic device to acquire content based on at least one of the integrated data and the user input.

[0016] Instructions stored in memory according to one embodiment of the present disclosure, when executed individually or collectively by at least one processor, can cause the electronic device to process the content based on actual personal information.

[0017] Instructions stored in memory according to one embodiment of the present disclosure can cause the electronic device to execute processed content when executed individually or collectively by the at least one processor.

[0018] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of acquiring data.

[0019] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of obtaining user input.

[0020] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of determining whether the data contains personal information.

[0021] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of converting the personal information into fake personal information if the personal information is included in the data.

[0022] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of integrating at least one of data that does not contain personal information, data that includes the fake personal information, data that includes the actual personal information, data from which personal information is excluded, abstract information, encrypted metadata, or personal information.

[0023] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of obtaining content based on at least one of integrated data and user input.

[0024] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of processing the content based on actual personal information.

[0025] A method for processing information for the protection of personal information of an electronic device according to one embodiment of the present disclosure may include an operation of executing processed content.

[0026] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0027] FIG. 1 is a block diagram of an exemplary electronic device capable of performing the operations described in the present disclosure.

[0028] FIG. 2 is a drawing showing a block diagram of an electronic device according to one embodiment of the present disclosure.

[0029] FIG. 3 is a block diagram schematically showing a general area and a security area of ​​a memory according to one embodiment of the present disclosure.

[0030] FIG. 4 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0031] FIG. 5 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0032] FIGS. 6a, FIGS. 6b and FIGS. 6c are drawings illustrating the operation of receiving data and user input in an electronic device according to one embodiment of the present disclosure.

[0033] FIGS. 7a, 7c, and 7b are drawings illustrating an operation for determining the sensitivity of personal information in an electronic device according to one embodiment of the present disclosure.

[0034] FIGS. 8a and 8b are drawings illustrating the operation of processing personal information in an electronic device according to one embodiment of the present disclosure.

[0035] FIGS. 9a and 9b are drawings illustrating the operation of an external electronic device generating content according to one embodiment of the present disclosure.

[0036] FIGS. 10a, FIGS. 10b, and FIGS. 10c are drawings illustrating the operation of an electronic device according to one embodiment of the present disclosure processing received content based on actual personal information.

[0037] FIG. 11 is a diagram illustrating the operation of creating content through an electronic device and an external electronic device according to one embodiment of the present disclosure.

[0038] FIGS. 12a and FIGS. 12b are drawings illustrating the operation of receiving data and user input in an electronic device according to one embodiment of the present disclosure.

[0039] FIG. 13 is a diagram illustrating the operation of analyzing screen context in an electronic device according to an embodiment of the present invention.

[0040] FIG. 14 is a diagram illustrating an operation for determining personal information of an electronic device according to one embodiment of the present disclosure.

[0041] FIG. 15 is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure converting personal information into fake personal information.

[0042] FIG. 16 is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure converting personal information into fake personal information.

[0043] FIG. 17 is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure generating content based on a prompt.

[0044] FIG. 18 is a drawing showing a user interface that can set a processing method according to the sensitivity of personal information in an electronic device according to one embodiment of the present disclosure.

[0045] FIGS. 19a, FIGS. 19b, and FIGS. 19c are drawings illustrating an operation to request a modification to content generated in an electronic device according to one embodiment of the present disclosure.

[0046] FIGS. 20a, FIGS. 20b, FIGS. 20c and FIGS. 20d are drawings illustrating an operation of generating content based on text included in an application running on an electronic device according to one embodiment of the present disclosure.

[0047] FIGS. 21a, FIGS. 21b, FIGS. 21c, FIGS. 21d, FIGS. 21e and FIGS. 21f are drawings illustrating an operation to generate content when data containing personal information is found in an electronic device according to one embodiment of the present disclosure.

[0048] FIG. 22 is a drawing illustrating a method for processing an image containing personal information in an electronic device according to one embodiment of the present disclosure.

[0049] FIG. 23 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0050] FIG. 24 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0051] FIG. 25 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0052] FIG. 26 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0053] FIG. 27 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0054] FIG. 28 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0055] FIG. 29 is a flowchart illustrating a method for processing information for privacy protection of an electronic device according to one embodiment of the present disclosure.

[0056] FIG. 30 is a drawing illustrating an operation to request modification to generated content according to one embodiment of the present disclosure.

[0057] FIG. 31 is a drawing illustrating an operation to request modification to generated content according to one embodiment of the present disclosure.

[0058] When a user creates new content using machine learning and / or artificial intelligence, there is a risk that personal information may be unintentionally leaked by the user as the electronic device transmits personal information to an external electronic device to create the content.

[0059] Alternatively, when a user creates new content using machine learning and / or artificial intelligence, there is a difficulty in that electronic devices collectively delete or blur personal information and transmit it to external electronic devices, resulting in the creation of unintended or inaccurate content.

[0060] The electronic device and method for processing information for privacy protection of the present disclosure can determine a method of processing personal information based on sensitivity to personal information when data containing personal information is received.

[0061] The electronic device and method for processing information for privacy protection of the present disclosure can generate content based on a method of processing determined personal information.

[0062] The electronic device and method for processing information for privacy protection of the present disclosure can generate content based on sensitivity to personal information.

[0063] The electronic device and method for processing information for privacy protection of the present disclosure can prevent personal information from being leaked to unintended external devices by generating content based on the sensitivity of personal information.

[0064] The electronic device and method for processing information for privacy protection of the present disclosure prevent the creation of content by collectively deleting or blurring personal information, thereby enabling the user to obtain the content intended.

[0065] FIG. 1 is a block diagram of an exemplary electronic device (100) capable of performing the operations described in the present disclosure.

[0066] Referring to FIG. 1, the electronic device (100) may be one of various forms of electronic devices, such as a notebook (190), smartphones (191) having various form factors (e.g., a bar-type smartphone (191-1), a foldable-type smartphone (191-2), or a sliderable (or rollable)-type smartphone (191-3)), a tablet (192), a cellular phone (not shown), and other similar computing devices (not shown). The components, their relationships, and their functions illustrated in FIG. 1 are illustrative only and are not intended to limit the implementations described or claimed in this disclosure. The electronic device (100) may be referred to as a mobile device, a user device, a multifunction device, a portable device, or a server.

[0067] The electronic device (100) may include components comprising at least one processor (110) (hereinafter referred to as processor (110)), at least one memory (120) (hereinafter referred to as memory (120)), at least one display (140) (hereinafter referred to as display (140)), at least one image sensor (150) (hereinafter referred to as image sensor (150)), at least one communication circuit (160) (hereinafter referred to as communication circuit (160)), and / or at least one sensor (170) (hereinafter referred to as sensor (170)). The components are merely exemplary. For example, the electronic device (100) may include other components (e.g., power management integrated circuitry (PMIC), audio processing circuit, antenna, rechargeable battery, or input / output interface). For example, some components may be omitted from the electronic device (100). For example, some components may be integrated into a single component.

[0068] The processor (110) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing operations. The processor (110) may include at least one electrical circuit and may process instructions (or programs, data, etc.) stored in memory (120) individually or collectively in a distributed manner. The processor (110) may include a processor assembly comprising one or more processing circuits. The processor (110) may include any processing circuit that is operative to control the performance and operations of one or more components of the electronic device (100) (e.g., memory (120), display (140), image sensor (150), communication circuit (160), and / or sensor (170)). For example, the processor (110) (e.g., application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or chipset). For example, the processor (110) may be implemented with a plurality of cores (or at least one core circuit), a plurality of chips, or a plurality of chipsets. For example, the processor (110) may include one or more processing circuits. For example, the processor (110) may include one or more processing circuits configured to perform the various functions of the present disclosure individually and / or collectively. As an example without limitation, at least a portion of the processor (110) may be included in a first chip of the electronic device (100), and at least another portion of the processor (110) may be included in a second chip of the electronic device (100) different from the first chip of the electronic device (100).

[0069] For example, the processor (110) may include a central processing unit (111), a graphics processing unit (112), a neural processing unit (113), an image signal processor (114), a display controller (115), a memory controller (116), a storage controller (117), a communication processor (118), and / or a sensor interface (119). These components of the processor (110) are merely exemplary. For example, the processor (110) may include other components. For example, some components of the processor (110) may be omitted from the processor (110). For example, some components of the processor (110) may be included as separate components of the electronic device (100) outside of the processor (110). For example, some components of the processor (110) (e.g., memory controller (116)) may be included in other components (e.g., at least part of memory (120), an interface (e.g. available for connection to at least one component of the electronic device (100)), a display (140) and / or an image sensor (150)).

[0070] The processor (110) may cause other components of the electronic device (100) to perform various operations by executing instructions stored in memory (120). The CPU (111) (or central processing circuit) may be configured to control the components of the processor (110) based on the execution of instructions stored in memory (120) (e.g., volatile memory (121) and / or non-volatile memory (122)). The GPU (112) (or graphics processing circuit) may be configured to execute parallel operations (e.g., rendering). The NPU (113) (or neural processing circuit, or AI (artificial intelligence) chip) may be configured to execute operations for an artificial intelligence model (e.g., convolution computation). An ISP (114) (or image signal processing circuit) may be configured to process a raw image acquired through an image sensor (150) into a format suitable for a component within the electronic device (100) or a component of the processor (110). A display controller (115) (or display control circuit, or DPU (display processing unit)) may be configured to process an image acquired from a CPU (111), GPU (112), ISP (114), or memory (120) (e.g., volatile memory (121)) into a format suitable for a display (140). A memory controller (116) (or memory control circuit) may be configured to control reading data from the volatile memory (121) and writing data to the volatile memory (121). A storage controller (117) (or storage control circuit) may be configured to control reading data from the non-volatile memory (122) and writing data to the non-volatile memory (122).The CP (118) (communication processing circuit) may be configured to process data obtained from a component of the processor (110) into a format suitable for transmitting to another electronic device via the communication circuit (160), or to process data obtained from another electronic device via the communication circuit (160) into a format suitable for processing by the component of the processor (110). For example, the communication circuit (160) may include one or more communication circuits. The sensor interface (119) (or sensing data processing circuit, sensor hub) may be configured to process data regarding the state of the electronic device (100) and / or the state around the electronic device (100), obtained through the sensor (170), into a format suitable for the component of the processor (110).

[0071] Memory (120) may include one or more storage media (or one or more storage devices). For example, memory (120) may include a memory assembly comprising one or more storage media. For example, the one or more storage media may include a hard drive, a permanent memory such as flash memory, read-only memory (ROM) (e.g., non-volatile memory (122)), a semi-permanent memory such as random access memory (RAM) (e.g., volatile memory (121)), any other suitable type of storage (or storage assembly), or any combination thereof. Memory (120) may include a cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (100). As an example not limited to, the cache memory may be included within the processor (110). The memory (120) may be fixedly embedded within the electronic device (100) or incorporated into one or more suitable types of components (e.g., a SIM (subscriber identity module) card and / or an SD (secure digital) card) that can be repeatedly inserted into and removed from the electronic device (100).

[0072] For example, memory (120) may store one or more software applications, such as operating system (or system) software applications, firmware software applications, driver software applications, plugin (e.g., add-in, add-on, and / or applet) software applications, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (110). For example, memory (120) may store instructions that can be called by an application programming interface (API). For example, memory (120) may store instructions within a library.

[0073] FIG. 2 is a block diagram of an electronic device (100) according to one embodiment of the present disclosure.

[0074] In one embodiment, the electronic device (100) can communicate with an external electronic device (300) through a communication circuit (160).

[0075] In one embodiment, the electronic device (100) may include an on-device artificial intelligence (AI) engine (210) and a screen artificial intelligence (AI) (220).

[0076] In one embodiment, the on-device AI engine (210) may include an LLM (large language model) AI (artificial intelligence) engine (211), an MLLM (multi-modal large language model) AI (artificial intelligence) engine (212), and an LVM (large vision model) AI (artificial intelligence) engine (213).

[0077] In one embodiment, the screen AI (220) may include a data collector (221), an on-device prompt (222), a cloud prompt (223), and data (224).

[0078] In one embodiment, the external electronic device (300) may include an LLM AI engine (311), an MLLM AI engine (312), and an LVM AI engine (313). The external electronic device (300) may include an external generative AI service. The expression external electronic device (300) may be replaced with an external generative AI service.

[0079] In one embodiment, the on-device AI engine (210) may include software that enables artificial intelligence functions to be performed on an electronic device (100) (e.g., a device) without relying on an external electronic device (300) (e.g., a cloud AI server).

[0080] For example, the on-device AI engine (210) may include machine learning frameworks, algorithms, models, software libraries, applications and / or services.

[0081] In one embodiment, the machine learning framework may include software for developing and training artificial intelligence models. The algorithm may include deep learning algorithms and reinforcement learning algorithms. The model may include software such as a neural network model. The algorithm and the model can learn the characteristics and distribution of data and perform probabilistically probable decisions based on the learned characteristics and distribution of data.

[0082] In one embodiment, the on-device AI engine (210) may include generative AI.

[0083] In one embodiment, the LLM AI engine (211) may include software regarding a large-scale language model. The LLM AI engine (211) may perform natural language processing (NLP) tasks based on learned text data. The LLM AI engine (211) may perform text generation, translation, summarization, and / or question answering tasks.

[0084] In one embodiment, the LLM AI engine (311) included in the external electronic device (300) can perform the same function as the LLM AI engine (211) included in the electronic device (100). However, it is not limited thereto, and the LLM AI engine (311) included in the external electronic device (300) may have a larger scale of learned data and can perform a wider variety of functions than the LLM AI engine (211) included in the electronic device (100).

[0085] In one embodiment, the LLM AI engine (211) can perform sentence writing, storytelling, article writing, and text generation operations. The LLM AI engine (211) can perform language understanding operations such as question answering, document summarization, and translation. The LLM AI engine (211) can perform chatbot and virtual assistant operations such as answering questions or assisting with tasks through conversation with a user. The LLM AI engine (211) can perform code generation and analysis operations such as automatically generating programming code. The LLM AI engine (211) can perform knowledge retrieval operations such as searching for information in a large database and responding.

[0086] In one embodiment, the MLLM AI engine (212) may include software for a multimodal large-scale language model. The MLLM AI engine (212) can process various forms of data, such as images, voice, and video, as well as text, in an integrated manner. The MLLM AI engine (212) can, for example, analyze and explain text and images simultaneously, or perform interactions that combine voice and text. The MLLM AI engine (212) can maintain consistency between different data types and process data in an integrated format.

[0087] In one embodiment, the MLLM AI engine (312) included in the external electronic device (300) can perform the same function as the MLLM AI engine (212) included in the electronic device (100). However, it is not limited thereto, and the MLLM AI engine (312) included in the external electronic device (300) may have a larger scale of learned data than the MLLM AI engine (212) included in the electronic device (100) and may perform a wider variety of functions.

[0088] In one embodiment, the MLLM AI engine (212) may be represented as a Large Multimodal Model (LMM). The MLLM AI engine (212) can simultaneously learn and process various forms of data, such as text, images, audio, and video.

[0089] In one embodiment, the MLLM AI engine (212) can perform text and image combination operations, such as providing text answers based on images to questions. The MLLM AI engine (212) can perform image captioning operations, such as generating text descriptions for images. The MLLM AI engine (212) can perform image creation and editing operations, such as generating images based on text. The MLLM AI engine (212) can perform voice and text integration operations, such as voice-to-text conversion operations and text-to-speech generation operations. The MLLM AI engine (212) can perform education and content creation operations, such as creating educational materials using composite data.

[0090] In one embodiment, the LVM AI engine (213) may include software regarding a large-scale visual model. The LVM AI engine (213) may process visual data based on learned images and videos. The LVM AI engine (213) may collect, learn, and / or generate visual data.

[0091] In one embodiment, the LVM AI engine (313) included in the external electronic device (300) can perform the same function as the LVM AI engine (213) included in the electronic device (100). However, it is not limited thereto, and the LVM AI engine (313) included in the external electronic device (300) may have a larger scale of learned data and can perform more diverse functions than the LVM AI engine (213) included in the electronic device (100).

[0092] In one embodiment, the LVM AI engine (213) can perform an operation to process visual tasks by learning visual data such as images.

[0093] In one embodiment, the LVM AI engine (213) can perform image classification operations such as object recognition operations and image classification operations.

[0094] In one embodiment, the LVM AI engine (213) can perform an image generation operation such as a text-to-image generation operation.

[0095] In one embodiment, the LVM AI engine (213) can perform video analysis operations such as object tracking operations in video and action recognition operations.

[0096] In one embodiment, the LVM AI engine (213) can perform multimodal operations such as search and generation operations combining text and images.

[0097] In one embodiment, the LVM AI engine (213) can perform medical image analysis tasks, such as medical image data analysis operations like X-ray, MRI, etc.

[0098] In one embodiment, the screen AI (220) may include software capable of understanding and analyzing screen context. The screen AI (220) may provide information and / or functions to the user based on the analyzed screen context.

[0099] In one embodiment, the screen context may include information displayed on a screen on the display (140) and the environment and situation in which the information is used. The screen context may include not only the content displayed on the screen, but also information regarding interaction with the user, the state of the application, and the surrounding environment.

[0100] In one embodiment, the screen context may include various user interface elements displayed on the screen, such as buttons, menus, icons, and text fields.

[0101] In one embodiment, the screen context may include actions in which a user interacts with the screen, such as touch, click, swipe, or gesture on the display (140).

[0102] In one embodiment, the screen context may include the task currently being performed by the application, the state of the data, or the state of the network connection.

[0103] In one embodiment, the screen context may include physical environment information such as the user's location, time zone, ambient noise, or lighting conditions.

[0104] In one embodiment, the screen context may include information regarding various types of content displayed on the screen, such as text, images, videos, or animations.

[0105] In one embodiment, the screen AI (220) can provide customized content and features by understanding the user's current situation and preferences based on the screen context.

[0106] In one embodiment, the screen AI (220) can optimize user interface elements to enable the user to perform tasks more quickly and intuitively.

[0107] In one embodiment, the screen AI (220) can support situational awareness. For example, the screen AI (220) can identify the surrounding environment and user status to provide appropriate feedback and notifications.

[0108] In one embodiment, the screen AI (220) can analyze the screen currently being viewed by the user on the electronic device (100).

[0109] In one embodiment, the electronic device (100) can exchange information with an external electronic device (300) through an external generative AI engine API. For example, the screen AI (220) can exchange information with an external electronic device (300) through an external generative AI engine API.

[0110] In one embodiment, the data collector (221) may collect data (224) regarding information displayed on the screen, the environment and situation in which the information is used, content displayed on the screen, interaction with the user, the state of the application, and the surrounding environment, and store it in memory (120).

[0111] In one embodiment, a data collector (221) may collect personal information used in a Personalized Data Core (PDC) based electronic device (100). In one embodiment, an on-device prompt (222) may generate based on data (224) or receive and store a prompt input from a user in the electronic device (100).

[0112] In one embodiment, the cloud prompt (223) may be generated based on data (224) or may store a prompt received from a cloud server (e.g., an external electronic device (300)).

[0113] In one embodiment, the on-device prompt (222) and / or cloud prompt (223) may generate a prompt for generating fake personal information for images, text, or video related to personal information.

[0114] In one embodiment, the on-device prompt (222) and the cloud prompt (223) may include software that generates, receives, and saves the prompt.

[0115] In one embodiment, the prompt may include text or a question entered to instruct an artificial intelligence engine (e.g., on-device AI engine (210), screen AI (220)) to perform a task or to receive information. The prompt may include input that requests the artificial intelligence engine (e.g., on-device AI engine (210), screen AI (220)) to perform a task, provide information, or output content. The prompt may be generated by user input or by the artificial intelligence engine (e.g., on-device AI engine (210), screen AI (220)).

[0116] In one embodiment, the electronic device (100) may further include an AI agent. The AI ​​agent may perform AI processing operations, screen analysis operations, data collection, and prompt processing operations in the electronic device (100). The AI ​​agent may include, for example, a screen AI (220). The AI ​​agent may perform operations of, for example, the screen AI (220).

[0117] In one embodiment, the electronic device (100) may include an AI agent, a data collector (221), an on-device prompt (222), a cloud prompt (223), and data (224).

[0118] In one embodiment, the electronic device (100) may further include an externally generated AI engine API (application programming interface) and a personal data core (PDC).

[0119] In one embodiment, the electronic device (100) can exchange information with an external electronic device (300) through an externally generated AI engine API. For example, an AI agent can exchange information with an external electronic device (300) through an externally generated AI engine API.

[0120] In one embodiment, a personal data core (PDC) may generate personal information or personalized data from data collected from a data collector (221) (e.g., app data, usage data, system data). The personal information or personalized data may include context, preference, and memory.

[0121] In one embodiment, the context may include personal context information. For example, personal context information may include the regularity, repetition, or frequent movements and stays of the user of the electronic device (100) as context information measured or calculated from collected data. Personal context information may include spatial context, behavior context, and temporal context.

[0122] In one embodiment, preferences may include information about an individual's profile and relationships, such as age, occupation, and gender, titles and profiles of others, and an individual's interests and preferences.

[0123] In one embodiment, the memory may include an activity (e.g., movement), content containing information about the object that is the purpose of the activity (e.g., destination), and an engram (e.g., travel) containing a set of connections between the activity and the content that constitute a meaningful experience.

[0124] FIG. 3 is a block diagram schematically showing a general area (320) and a security area (330) of a memory (120) according to one embodiment of the present disclosure.

[0125] In one embodiment, the memory (120) may include a general area (320) and a security area (330). The general area (320) may include an application (321), a response sentence generation module (322), and an AI engine (323). The security area (330) may include a personal information database (324).

[0126] In one embodiment, the general area (320) and the security area (330) are isolated and can exchange information through a security protocol or interface (e.g., API).

[0127] In one embodiment, the general area (320) is a space where general tasks and applications are executed, where all processes are accessible, and security restrictions may be relatively low.

[0128] In one embodiment, the application (321), the response module generation module (322), and the AI ​​engine (323) can be executed in a general area (320).

[0129] In one embodiment, the AI ​​engine (323) may include the on-device AI engine (210) of FIG. 2 and / or the screen AI (220) of FIG. 2. A response sentence generation module (322) may be included in the AI ​​engine (323). The response sentence generation module (322) may include software that understands the context of a request or data input by a user and generates a response.

[0130] In one embodiment, the security area (330) is an area where access to hardware or software is restricted based on a security policy, and may include a space where a personal information database (324) requiring security is stored. The security area (330) can maintain data confidentiality and integrity. The security area (330) may be accessible only to specific trusted code and applications. For example, data such as encryption keys, certificates, or personal information may be stored.

[0131] FIG. 4 is a flowchart illustrating a method for processing information for privacy protection of an electronic device (100) according to one embodiment of the present disclosure.

[0132] In one embodiment, in operation 401, instructions stored in memory (120) can cause the electronic device (100) to acquire data when executed individually or collectively by at least one processor (110).

[0133] In one embodiment, in operation 401, instructions stored in memory (120) can cause an electronic device (100) to receive data when executed individually or collectively by at least one processor (110).

[0134] In one embodiment, the electronic device (100) can generate content based on data under the control of at least one processor (110).

[0135] In one embodiment, for creating content using the electronic device (100), the user can input data necessary for content creation into the electronic device (100).

[0136] In one embodiment, the data may include at least one of text, images, voice, and / or video. The data may be input in the form of a file.

[0137] In one embodiment, user input may include text input and voice input by the user, as well as touch input and gesture input.

[0138] In one embodiment, the electronic device (100) can execute an application or user interface capable of acquiring data and / or user input, and can display the execution screen on a display (140).

[0139] In one embodiment, the electronic device (100) can execute an application or user interface capable of receiving data and / or user input, and can display the execution screen on a display (140).

[0140] For example, a user may input a physical key, touch key interaction, gesture, and / or wake word into the electronic device (100) to execute an application or user interface capable of receiving data and / or user input. The wake word or awake word may be input into the electronic device (100) as voice and / or text.

[0141] In one embodiment, when an input to a physical key, a touch key interaction, a gesture, and / or a wake word is received, instructions stored in memory (120) can cause the electronic device (100) to execute an application or user interface capable of receiving data and / or user input when executed individually or collectively by at least one processor (110).

[0142] In one embodiment, an application or user interface capable of receiving data and user input may include an interface to an on-device AI engine (210). The on-device AI engine (210) may include an interface capable of interacting with a user.

[0143] In one embodiment, in operation 403, instructions stored in memory (120) can cause the electronic device (100) to obtain user input when executed individually or collectively by at least one processor (110).

[0144] In one embodiment, in operation 403, instructions stored in memory (120) can cause the electronic device (100) to receive user input when executed individually or collectively by at least one processor (110).

[0145] In one embodiment, the electronic device (100) is exemplified by performing the 401 operation and the 403 operation separately, but the 401 operation and the 403 operation may be performed simultaneously.

[0146] In one embodiment, the electronic device (100) can generate content based on user input under the control of at least one processor (110).

[0147] In one embodiment, for creating content using the electronic device (100), the user can input user input required for content creation into the electronic device (100).

[0148] In one embodiment, in operation 403, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to recognize a request from user input. The request may include, for example, at least one of a prompt, a command, a question, a message, or an input.

[0149] In one embodiment, in operation 403, instructions stored in memory (120) can cause the electronic device (100) to check a prompt in user input when executed individually or collectively by at least one processor (110).

[0150] In one embodiment, in operation 403, instructions stored in memory (120) can cause the electronic device (100) to check a prompt in user input based on an on-device prompt (222) when executed individually or collectively by at least one processor (110).

[0151] In one embodiment, the on-device prompt (222) may be generated based on data (224) or may receive and store a prompt input from a user in the electronic device (100).

[0152] In one embodiment, the prompt may include text or a question entered to instruct an artificial intelligence engine (e.g., on-device AI engine (210), screen AI (220)) to perform a task or to receive information. The prompt may include input that requests the artificial intelligence engine (e.g., on-device AI engine (210), screen AI (220)) to perform a task, provide information, or output content. The prompt may be generated by user input or by the artificial intelligence engine (e.g., on-device AI engine (210), screen AI (220)).

[0153] In one embodiment, in operation 405, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to determine whether the data contains personal information.

[0154] In one embodiment, instructions stored in memory (120) may cause the electronic device (100) to collect personal information, such as information regarding personal details, communication and location information, social information, mental information, physical information, media content, or automatically generated information, when executed individually or collectively by at least one processor (110).

[0155] In one embodiment, information regarding personal details may include identity information and unique identification information. For example, identity information may include a name, date of birth, gender, address, telephone number, and email address. Unique identification information may include a resident registration number, passport number, and driver's license number.

[0156] In one embodiment, communication and location information may include communication record information and location information. For example, communication record information may include call history, text message content, and incoming / outgoing call records. Location information may include real-time location data via GPS and usage history of location-based services.

[0157] In one embodiment, social information may include contact information and information regarding social network activities. For example, contact information may include a list of contacts stored in an address book. Information regarding social network activities may include SNS account information, a list of friends, and the content of posts and comments.

[0158] In one embodiment, mental information may include information regarding preferences and tendencies, and information regarding beliefs and ideologies. For example, information regarding preferences and tendencies may include interests based on app usage patterns and search and viewing history. Information regarding beliefs and ideologies may include religious and political orientations.

[0159] In one embodiment, physical information may include health and medical information and biometric information. For example, health and medical information may include exercise records, heart rate, and sleep patterns through a health app. Biometric information may include fingerprint, facial, and iris information.

[0160] In one embodiment, property information may include financial information and payment records. For example, financial information may include bank account numbers, credit card information, and transaction history. Payment records may include usage history of mobile payment services.

[0161] In one embodiment, information regarding media content may include photos and videos, personal and family photos, videos, voice recordings, call recordings, and audio information.

[0162] In one embodiment, the automatically generated information may include device information and log data. For example, the device information may include IMEI, UUID, and MAC address. The log data may include app usage history, system logs, and IP address.

[0163] In one embodiment, personal information may include not only data for identifying a specific individual, but also all data related to the individual.

[0164] For example, personal information may include at least one of basic identifying information, sensitive information, financial information, online activity information, employment and educational information, location and environment information, customer and consumer information, social relationship information (e.g., family and relationship information), personal hobbies and interests, or personal settings (e.g., user settings of a service or application).

[0165] In one embodiment, the basic identification information may include information capable of directly identifying an individual. For example, the basic identification information may include at least one of a name, a resident registration number, a passport number, a driver's license number, an address (e.g., home address, work address), an email address, a telephone number, or an IP address.

[0166] In one embodiment, sensitive information may include information containing an individual's privacy or sensitive characteristics. For example, sensitive information may include at least one of health information (e.g., medical history, diagnostic records, medication history), biometric information (e.g., fingerprints, iris, facial features, DNA), race, ethnicity, nationality, political views, religion, philosophical beliefs, sexual orientation, criminal records and legal issues, or sexual identity.

[0167] In one embodiment, financial information may include information related to financial and economic activities. For example, financial information may include at least one of bank account numbers, credit card information, tax information, salary and income information, or transaction history.

[0168] In one embodiment, online activity information may include personal activity data collected in a digital environment. For example, online activity information may include browsing history, search history, cookies and log data, location information, social media activity, or digital photo and video metadata.

[0169] In one embodiment, employment and educational background information may include information related to an individual's occupation and studies. For example, employment and educational background information may include at least one of occupation and position, work history, educational background and degree, certifications and awards, or letters of recommendation and transcripts.

[0170] In one embodiment, location and environment information may include data related to an individual's real-time or recorded location. For example, location and environment information may include GPS data, travel records, smartphone location records, or vehicle driving data.

[0171] In one embodiment, customer and consumer information may include data related to the use of products and services. For example, customer and consumer information may include at least one of purchase history, preferred products and services, customer feedback, or membership and point information.

[0172] In one embodiment, if the data contains personal information, the instructions stored in memory (120) can cause the electronic device (100) to branch from operation 405 to operation 407 when executed individually or collectively by at least one processor (110).

[0173] In one embodiment, if the data does not contain personal information, the instructions stored in memory (120) can cause the electronic device (100) to branch from operation 405 to operation 409 when executed individually or collectively by at least one processor (110).

[0174] In one embodiment, in operation 407, instructions stored in memory (120) can cause the electronic device (100) to convert personal information contained in data into fake personal information when executed individually or collectively by at least one processor (110).

[0175] In one embodiment, in order to convert personal information contained in data into fake personal information, in operation 407, instructions stored in memory (120) can cause the electronic device (100) to classify the sensitivity of personal information contained in data when executed individually or collectively by at least one processor (110).

[0176] In one embodiment, to convert personal information contained in data into fake personal information, in operation 407, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to determine a method of processing personal information based on the sensitivity of the classified personal information.

[0177] In one embodiment, in order to convert personal information contained in data into fake personal information, in operation 407, instructions stored in memory (120) are executed individually or collectively by at least one processor (110), allowing the electronic device (100) to process the personal information according to the processing method.

[0178] For example, the electronic device (100) may store information regarding the sensitivity of personal information in a database in memory (120). The sensitivity of personal information may be classified based on the impact on an individual when personal information is disclosed or leaked.

[0179] In one embodiment, the sensitivity of personal information can be classified into highly sensitive information, sensitive information, and non-sensitive information.

[0180] In one embodiment, sensitive information may include information that could have a significant impact on an individual's safety, health, financial status, or social reputation if leaked or misused.

[0181] In one embodiment, sensitive information may include high-risk personal information.

[0182] For example, sensitive information may include at least one of biometric information (e.g., fingerprint, iris, facial recognition data, voice data).

[0183] In one embodiment, important information may include information that is highly likely to infringe upon an individual's privacy if leaked. Important information may include information that can identify an individual and could cause significant damage if leaked.

[0184] In one embodiment, important information may include medium-risk personal information.

[0185] For example, important information may include location information, information that can identify an individual (e.g., resident registration number, passport number, driver's license number, name), or financial information (e.g., account number, card number, credit information).

[0186] In one embodiment, general information may include information that identifies an individual but does not pose a significant risk to the individual even if disclosed.

[0187] In one embodiment, general information may include low-risk personal information.

[0188] For example, general information may include at least one of gender, date of birth, place of residence, telephone number, or email address.

[0189] However, this is not limited to this, and the sensitivity of personal information may further include de-identified information. De-identified information is information that has been de-identified so that individuals cannot be identified, and it may include information with low sensitivity unless the original data is restored. For example, de-identified information may include statistical data that cannot identify individuals.

[0190] In one embodiment, in operation 407, instructions stored in memory (120) can cause the electronic device (100) to determine how to process personal information based on the sensitivity of the classified personal information when executed individually or collectively by at least one processor (110).

[0191] In one embodiment, the processing method may include at least one of a method of excluding personal information from data, a method of converting personal information into fake personal information, or a method of not processing personal information separately.

[0192] In one embodiment, in operation 407, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to determine fake personal information based on a prompt.

[0193] In one embodiment, in operation 407, instructions stored in memory (120) can cause the electronic device (100) to generate fake personal information that replaces personal information based on the context included in the prompt when executed individually or collectively by at least one processor (110).

[0194] In one embodiment, in operation 407, instructions stored in memory (120) can cause the electronic device (100) to generate fake personal information containing information similar to personal information based on the context included in the prompt when executed individually or collectively by at least one processor (110).

[0195] In one embodiment, the electronic device (100) can determine the context based on the prompt based on the on-device AI engine (210) and / or the screen AI (220).

[0196] In one embodiment, in operation 407, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to generate fake personal information containing information similar to personal information based on an analysis of actual personal information or a user profile. The user profile may include at least one piece of information regarding the user's characteristics, tendencies, tastes, behaviors, personality, preferences, or social relationships.

[0197] In one embodiment, in operation 407, instructions stored in memory (120) can generate metadata for maintaining a relationship between real personal information and fake personal information when executed individually or collectively by at least one processor (110).

[0198] In one embodiment, metadata is not transmitted to an external electronic device (300) or an externally generated AI service, and can be processed only in the electronic device (100).

[0199] In one embodiment, when an external electronic device (300) converts fake personal information into actual personal information in content generated based on fake personal information, the instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), thereby enabling the electronic device (100) to convert the fake personal information included in the externally generated content into actual personal information based on metadata.

[0200] In one embodiment, when the electronic device (100) converts fake personal information into actual personal information in content generated based on fake personal information, the instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), thereby enabling the electronic device (100) to convert the fake personal information included in the content generated based on metadata into actual personal information.

[0201] In one embodiment, in operation 407, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to generate structured abstract information based on metadata.

[0202] In one embodiment, the structured abstract information may be transmitted to an external electronic device (300) or an external generative AI service. The external electronic device (300) or the external generative AI service may generate content based on the structured abstract information.

[0203] In one embodiment, the electronic device (100) can generate content based on structured abstract information.

[0204] In the present disclosure, structured abstract information may be described interchangeably with abstract information.

[0205] In one embodiment, the composition of the structured abstract information may be as shown in Table 1. In one embodiment, the structured abstract information may include abstract hints from which actual personal information cannot be inferred.

[0206] {"entities": [{"type": "name", "hint": "User's name"},{"type": "occupation", "hint": "User's occupation (general occupation categories)"}]}

[0207] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may transmit only structured abstract information to an external electronic device (300) or an external generative AI service.

[0208] For example, abstract information may include abstract descriptions such as a user's name instead of a real name. Abstract information may include abstract descriptions such as a job category (e.g., worker) instead of a job title (e.g., office worker).

[0209] In one embodiment, an external electronic device (300) or an external generative AI service generates content based on structured abstract information, so connectivity with actual personal information can be secured while maintaining privacy.

[0210] In one embodiment, by transmitting only structured abstract information to an external electronic device (300) or an external generative AI service, the information sent to the external electronic device (300) or the external generative AI service may not be directly linked to actual personal information.

[0211] However, it is not limited thereto, and the abstract information may be transmitted to an external electronic device (300) or an external generative AI service along with the fake personal information. The external electronic device (300) or the external generative AI service may generate content based on the structured abstract information and the fake personal information.

[0212] In one embodiment, abstract information may include generalized data that can explain the relationship between fake personal information and actual personal information or provide context, without directly including personal information.

[0213] In one embodiment, the abstract information may include at least one of an entity type, a context hint, or a purpose of use.

[0214] For example, entity types can include data attributes (e.g., name, job, location, etc.). Context hints can include abstract descriptions explaining the meaning and role of the data. The purpose of use can include purpose information that external AI can refer to when processing the data.

[0215] In one embodiment, Table 2 represents abstract information, and Table 3 represents metacode.

[0216] Referring to Tables 2 and 3, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding names and occupations is described as follows.

[0217] {"entities": [{"type": "name", "hint": "This is the user's name."},{"type": "occupation", "hint": "This is the user's occupation, which falls under a general occupation category."}]}

[0218] {"real_data": {"name": "Kim Samsung", "occupation": "Office Worker"},"fake_data": {"name": "Hong Gil-dong", "occupation": "Freelancer"},"metadata": {"entities": [{"type": "name", "hint": "This is the user's name."},{"type": "occupation", "hint": "This is the user's occupation, which falls under a general occupation category."}]}}

[0219] Referring to Tables 2 and 3, the abstract information of Table 2 is transmitted to an external electronic device (300), and the metacode of Table 3 is stored in the electronic device (100) and is not transmitted to the external electronic device (300). In the present disclosure, metacode may be described interchangeably with metadata.

[0220] For example, actual personal information may include Name: Kim Sam-seong, Occupation: Office Worker. The electronic device (100) may generate fake personal information based on actual personal information. The fake personal information may include Name: Hong Gil-dong, Occupation: Freelancer.

[0221] For example, abstract information regarding actual personal information such as Name: Kim Samsung and Occupation: Office Worker may include "User's Name" or "User's Occupation, falls under a general category."

[0222] For example, metadata may include abstract information about the relationship and entity type between real personal information such as Name: Kim Samsung, Occupation: Office Worker and fake personal information such as Name: Hong Gil-dong, Occupation: Freelancer.

[0223] Referring to Tables 2 and 3, the data transmitted to the external electronic device (300) does not contain the actual personal information because the electronic device (100) has changed the actual personal information into fake personal information.

[0224] Referring to Tables 2 and 3, when an external electronic device (300) generates content based on fake personal information, it is necessary to transmit abstract information along with the fake personal information to maintain the context and connectivity of the data. Since the abstract information does not contain personal information and is used to explain the meaning and context of the data, it is possible to achieve both privacy protection and connectivity maintenance simultaneously.

[0225] In one embodiment, the electronic device (100) may use metadata to restore real personal information to content generated based on abstract information along with fake personal information.

[0226] In one embodiment, Table 4 represents abstract information, and Table 5 represents metacode.

[0227] Referring to Tables 4 and 5, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding addresses and contacts is described as follows.

[0228] {"entities": [{"type": "address", "hint": "This is the user's residential area and must be written in road name address format."},{"type": "contact", "hint": "This is written in phone number format and is for personal use."}]}

[0229] {"real_data": {"address": "123, Teheran-ro, Gangnam-gu, Seoul", "contact": "010-1234-5678"},"fake_data": {"address": "45, Toegye-ro, Jung-gu, Seoul", "contact": "010-5678-1234"},"metadata": {"entities": [{"type": "address", "hint": "This is the user's residential area and must be written in road name address format."},{"type": "contact", "hint": "This must be written in phone number format and is for personal use."}]}}

[0230] Referring to Tables 4 and 5, the abstract information of Table 4 is transmitted to an external electronic device (300), and the metacode of Table 5 is stored in the electronic device (100) and is not transmitted to the external electronic device (300). In the present disclosure, metacode may be described interchangeably with metadata.

[0231] Referring to Tables 4 and 5, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding addresses and contacts is described as follows.

[0232] For example, actual personal information may include address: 123, Teheran-ro, Gangnam-gu, Seoul, and contact number: 010-1234-5678. The electronic device (100) may generate fake personal information based on actual personal information. The fake personal information may include address: 45, Toegye-ro, Jung-gu, Seoul, and contact number: 010-5678-1234.

[0233] For example, abstract information regarding actual personal information, such as address: 123 Teheran-ro, Gangnam-gu, Seoul, and contact number: 010-1234-5678, may include "This is the user's residential area and must be written in the road name address format" or "This must be written in the phone number format and is for personal use."

[0234] For example, metadata may include abstract information about the relationship and entity type between actual personal information, such as address: 123 Teheran-ro, Gangnam-gu, Seoul, contact: 010-1234-5678, and fake personal information, such as address: 45 Toegye-ro, Jung-gu, Seoul, contact: 010-5678-1234.

[0235] Referring to Tables 4 and 5, the data transmitted to the external electronic device (300) does not contain the actual personal information because the electronic device (100) has changed the actual personal information into fake personal information.

[0236] Referring to Tables 4 and 5, when an external electronic device (300) generates content based on fake personal information, it is necessary to transmit abstract information along with the fake personal information to maintain the context and connectivity of the data. Since the abstract information does not contain personal information and is used to explain the meaning and context of the data, it is possible to achieve both privacy protection and connectivity maintenance simultaneously.

[0237] In one embodiment, the electronic device (100) may use metadata to restore real personal information to content generated based on abstract information along with fake personal information.

[0238] In one embodiment, Table 6 represents abstract information, and Table 7 represents metacode.

[0239] Referring to Tables 6 and 7, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding education and career is described as follows.

[0240] {"entities": [{"type": "education", "hint": "Includes user's education information, including university and major."},{"type": "experience", "hint": "Includes user's career information, including years of work experience and industry."}]}

[0241] {"real_data": {"education": "Graduated from Seoul National University, Department of Computer Science", "experience": "Worked at an IT company for 5 years"},"fake_data": {"education": "Graduated from Hanyang University, Department of Electrical Engineering", "experience": "Worked at a startup for 3 years"},"metadata": {"entities": [{"type": "education", "hint": "Includes user's educational background information, including university and major."},{"type": "experience", "hint": "Includes user's career information, including years of work experience and industry."}]}}

[0242] Referring to Tables 6 and 7, the abstract information of Table 6 is transmitted to an external electronic device (300), and the metacode of Table 7 is stored in the electronic device (100) and is not transmitted to the external electronic device (300). In the present disclosure, metacode may be described interchangeably with metadata.

[0243] Referring to Tables 6 and 7, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding education and career is described as follows.

[0244] For example, actual personal information may include: Education: Graduate of Seoul National University, Department of Computer Engineering, and experience: 5 years of work experience at an IT company. The electronic device (100) may generate fake personal information based on actual personal information. The fake personal information may include: Education: Graduate of Hanyang University, Department of Electronic Engineering, and experience: 3 years of work experience at a startup.

[0245] For example, abstract information regarding actual personal information such as education: graduated from the Department of Computer Science at Seoul National University, and career: worked at an IT company for 5 years may include "includes the user's education information, including university and major" or "includes the user's career information, including years of service and industry."

[0246] For example, metadata may include abstract information about the relationship and entity type between actual personal information such as education: graduated from Seoul National University Department of Computer Science, career: worked at an IT company for 5 years, and fake personal information such as education: graduated from Hanyang University Department of Electrical Engineering, career: worked at a startup for 3 years.

[0247] Referring to Tables 6 and 7, the data transmitted to the external electronic device (300) does not contain the actual personal information because the electronic device (100) has changed the actual personal information into fake personal information.

[0248] Referring to Tables 6 and 7, when an external electronic device (300) generates content based on fake personal information, it is necessary to transmit abstract information along with the fake personal information to maintain the context and connectivity of the data. Since the abstract information does not contain personal information and is used to explain the meaning and context of the data, it is possible to achieve both privacy protection and connectivity maintenance simultaneously.

[0249] In one embodiment, the electronic device (100) may use metadata to restore real personal information to content generated based on abstract information along with fake personal information.

[0250] In one embodiment, Table 8 represents abstract information, and Table 9 represents metacode.

[0251] Referring to Tables 8 and 9, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding general personal information (e.g., music records, video records) is described as follows.

[0252] {"entities": [{"type": "music", "hint": "This is the list of music recently played by the user."},{"type": "video", "hint": "This is the video content recently watched by the user."}]}

[0253] {"real_data": {"music": ["Imagine Dragons - Believer", "BTS - Dynamite"],"video": ["Watch movie 'Inception' on Netflix", "Watch 'Tesla Model S Review' on YouTube"]},"fake_data": {"music": ["Coldplay - Yellow", "Adele - Hello"],"video": ["Watch movie 'Interstellar' on Netflix", "Watch 'iPhone 15 Review' on YouTube"]},"metadata": {"entities": [{"type": "music", "hint": "This is a list of music recently played by the user."},{"type": "video", "hint": "This is video content recently watched by the user."}]}}

[0254] Referring to Tables 8 and 9, the abstract information of Table 8 is transmitted to an external electronic device (300), and the metacode of Table 9 is stored in the electronic device (100) and is not transmitted to the external electronic device (300). In the present disclosure, metacode may be described interchangeably with metadata.

[0255] Referring to Tables 8 and 9, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding music and video records is described as follows.

[0256] For example, actual personal information may include music records: "Imagine Dragons - Believer", "BTS - Dynamite", video records: "Watching the movie 'Inception' on Netflix", "Watching the 'Tesla Model S Review' on YouTube". The electronic device (100) may generate fake personal information based on actual personal information. The fake personal information may include music records: "Coldplay - Yellow", "Adele - Hello", video records: "Watching the movie 'Interstellar' on Netflix", "Watching the 'iPhone 15 Review' on YouTube".

[0257] For example, abstract information regarding actual personal information such as music history: "Imagine Dragons - Believer", "BTS - Dynamite", and video history: "Watched the movie 'Inception' on Netflix", "Watched 'Tesla Model S Review' on YouTube" may include "This is a list of music recently played by the user" or "This is video content recently watched by the user."

[0258] For example, metadata may include abstract information about the relationship and entity type between actual personal information such as music records: "Imagine Dragons - Believer", "BTS - Dynamite", video records: "Watched the movie 'Inception' on Netflix", "Watched 'Tesla Model S Review' on YouTube", and fake personal information such as education: music records: "Coldplay - Yellow", "Adele - Hello", video records: "Watched the movie 'Interstellar' on Netflix", "Watched 'iPhone 15 Review' on YouTube".

[0259] Referring to Tables 8 and 9, the data transmitted to the external electronic device (300) does not contain the actual personal information because the electronic device (100) has changed the actual personal information into fake personal information.

[0260] Referring to Tables 8 and 9, when an external electronic device (300) generates content based on fake personal information, it is necessary to transmit abstract information along with the fake personal information to maintain the context and connectivity of the data. Since the abstract information does not contain personal information and is used to explain the meaning and context of the data, it is possible to achieve both privacy protection and connectivity maintenance simultaneously.

[0261] In one embodiment, the electronic device (100) may use metadata to restore real personal information to content generated based on abstract information along with fake personal information.

[0262] In one embodiment, Table 10 represents abstract information, and Table 11 represents metacode.

[0263] Referring to Tables 10 and 11, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding account numbers and transaction history, which are sensitive personal information (e.g., financial transaction information), is described as follows.

[0264] {"entities": [{"type": "account", "hint": "This is the user's bank account number."},{"type": "transaction", "hint": "This is the user's recent financial transaction history."}]}

[0265] {"real_data": {"account": "123-456-789012 (KB Kookmin Bank)","transaction": ["December 1, 2023, Convenience store purchase 10,000 won", "December 2, 2023, Starbucks purchase 6,000 won"]},"fake_data": {"account": "987-654-321098 (Shinhan Bank)","transaction": ["December 1, 2023, Supermarket purchase 15,000 won", "December 2, 2023, Coffee shop purchase 5,500 won"]},"metadata": {"entities": [{"type": "account", "hint": "This is the user's bank account number."},{"type": "transaction", "hint": "User's recent financial transactions This is the history.

[0266] Referring to Tables 10 and 11, the abstract information of Table 10 is transmitted to an external electronic device (300), and the metacode of Table 11 is stored in the electronic device (100) and is not transmitted to the external electronic device (300). In the present disclosure, metacode may be described interchangeably with metadata.

[0267] Referring to Tables 10 and 11, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding account numbers and transaction history is described as follows.

[0268] For example, actual personal information may include account number: "123-456-789012 (Kookmin Bank)", transaction history: "December 1, 2023, convenience store purchase 10,000 won", "December 2, 2023, Starbucks purchase 6,000 won". The electronic device (100) may generate fake personal information based on actual personal information. The fake personal information may include account number: "987-654-321098 (Shinhan Bank)", transaction history: "December 1, 2023, supermarket purchase 15,000 won", "December 2, 2023, coffee shop purchase 5,500 won".

[0269] For example, abstract information regarding actual personal information such as account number: "123-456-789012 (Kookmin Bank)", transaction history: "December 1, 2023, convenience store purchase 10,000 won", "December 2, 2023, Starbucks purchase 6,000 won" may include "This is the user's bank account number." or "This is the user's recent financial transaction history."

[0270] For example, metadata may include abstract information about the relationship and entity type between actual personal information, such as account number: "123-456-789012 (Kookmin Bank)", transaction history: "December 1, 2023, convenience store purchase 10,000 won", "December 2, 2023, Starbucks purchase 6,000 won", and fake personal information, such as account number: "987-654-321098 (Shinhan Bank)", transaction history: "December 1, 2023, supermarket purchase 15,000 won", "December 2, 2023, coffee shop purchase 5,500 won".

[0271] Referring to Tables 10 and 11, the data transmitted to the external electronic device (300) does not contain the actual personal information because the electronic device (100) has changed the actual personal information into fake personal information.

[0272] Referring to Tables 10 and 11, when an external electronic device (300) generates content based on fake personal information, it is necessary to transmit abstract information along with the fake personal information to maintain the context and connectivity of the data. Since the abstract information does not contain personal information and is used to explain the meaning and context of the data, it is possible to achieve both privacy protection and connectivity maintenance simultaneously.

[0273] In one embodiment, the electronic device (100) may use metadata to restore real personal information to content generated based on abstract information along with fake personal information.

[0274] In one embodiment, Table 12 represents abstract information, and Table 13 represents metacode.

[0275] Referring to Tables 12 and 13, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding political views and health information, which are high-risk personal information (e.g., political views and health information), is described as follows.

[0276] {"entities": [{"type": "political_opinion", "hint": "This is about the user's political views."},{"type": "health", "hint": "This is about the user's health status and medical records."}]}

[0277] {"real_data": {"political_opinion": ["In favor of expanding local autonomy", "Support environmental protection bills"],"health": ["Hypertension, medication prescription record dated June 1, 2023"]},"fake_data": {"political_opinion": ["In favor of strengthening central government authority", "Support economic revitalization policies"],"health": ["Diabetes, medication prescription record dated May 10, 2023"]},"metadata": {"entities": [{"type": "political_opinion", "hint": "This contains information about the user's political views."},{"type": "health", "hint": "This contains information about the user's health status and medical records."}]}}

[0278] Referring to Tables 12 and 13, the abstract information of Table 12 is transmitted to an external electronic device (300), and the metacode of Table 13 is stored in the electronic device (100) and is not transmitted to the external electronic device (300). In the present disclosure, metacode may be described interchangeably with metadata.

[0279] Referring to Tables 12 and 13, the method for generating fake personal information, metadata, and abstract information based on actual personal information regarding political views and health information is described as follows.

[0280] For example, actual personal information may include political views: "in favor of expanding local autonomy," "support for environmental protection bills," and health information: "hypertension, drug prescription record dated June 1, 2023." The electronic device (100) may generate fake personal information based on actual personal information. The fake personal information may include political views: "in favor of strengthening central government authority," "support for economic revitalization policies," and health information: "diabetes, drug prescription record dated May 10, 2023."

[0281] For example, abstract information regarding actual personal information such as political views: "in favor of expanding local autonomy," "support for environmental protection bills," and health information: "hypertension, drug prescription record as of June 1, 2023" may include "content regarding the user's political views." or "content regarding the user's health status and medical records."

[0282] For example, metadata may include abstract information about the relationship and entity type with actual personal information such as political views: "in favor of expanding local autonomy," "support for environmental protection bills," and health information: "hypertension, medication prescription record dated June 1, 2023," and fake personal information such as political views: "in favor of strengthening central government authority," "support for economic revitalization policies," and health information: "diabetes, medication prescription record dated May 10, 2023."

[0283] Referring to Tables 12 and 13, the data transmitted to the external electronic device (300) does not contain the actual personal information because the electronic device (100) has changed the actual personal information into fake personal information.

[0284] Referring to Tables 12 and 13, when an external electronic device (300) generates content based on fake personal information, it is necessary to transmit abstract information along with the fake personal information to maintain the context and connectivity of the data. Since the abstract information does not contain personal information and is used to explain the meaning and context of the data, privacy protection and connectivity maintenance can be achieved simultaneously.

[0285] In one embodiment, the electronic device (100) may use metadata to restore real personal information to content generated based on abstract information along with fake personal information.

[0286] However, not limited to this, in operation 409, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to encrypt metadata.

[0287] In one embodiment, instructions stored in memory (120) can cause an electronic device (100) to transmit encrypted metadata and fake personal information to an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0288] In one embodiment, an external electronic device (300) can generate content based on encrypted metadata and fake personal information. The electronic device (100) can decrypt the content generated based on encrypted metadata and fake personal information to restore it to include actual personal data.

[0289] However, not limited thereto, in operation 407, instructions stored in memory (120) can cause the electronic device (100) to transmit fake personal information to an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0290] In one embodiment, an external electronic device (300) can generate content based on fake personal information. The electronic device (100) can restore the content generated based on the fake personal information to include actual personal data.

[0291] However, not limited thereto, in operation 407, instructions stored in memory (120) may cause the electronic device (100) to transmit fake personal information to an external electronic device (300) based on the sensitivity of the personal information when executed individually or collectively by at least one processor (110). When instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may cause personal information with low sensitivity to be converted into fake personal information and then transmitted to an external electronic device (300). When instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can generate content containing actual personal information based on an on-device AI engine (210) and / or screen AI (220) without transmitting personal information with high sensitivity to external electronic device (300).

[0292] In one embodiment, the electronic device (100) can generate a user profile by analyzing at least one piece of information about a user's characteristics, tendencies, tastes, behaviors, personality, preferences, or social relationships based on an on-device AI engine (210) and / or a screen AI (220).

[0293] In one embodiment, in operation 407, instructions stored in memory (120) can cause the electronic device (100) to process personal information according to a processing method when executed individually or collectively by at least one processor (110).

[0294] In one embodiment, the processing method may include at least one of the following: a method of processing data that does not contain personal information at an AI server (e.g., an external electronic device (300)); a method of processing personal information on an on-device (e.g., an electronic device (100)) and processing data excluding personal information at an AI server (e.g., an external electronic device (300)); a method of converting personal information into fake personal information and processing data containing fake personal information at an AI server (e.g., an external electronic device (300)); or a method of processing data containing personal information at an AI server (e.g., an external electronic device (300)) without processing personal information separately.

[0295] However, it is not limited to this, and the electronic device (100) may transmit only abstract information instead of fake personal information to an AI server (e.g., an external electronic device (300)).

[0296] In one embodiment, when transmitting fake personal information to an AI server (e.g., external electronic device (300)), the electronic device (100) may transmit only the fake personal information to the AI ​​server (e.g., external electronic device (300)).

[0297] In one embodiment, when transmitting fake personal information to an AI server (e.g., external electronic device (300)), the electronic device (100) can transmit fake personal information and abstract information to the AI ​​server (e.g., external electronic device (300)).

[0298] In one embodiment, when transmitting fake personal information to an AI server (e.g., external electronic device (300)), the electronic device (100) can transmit the fake personal information and encrypted metadata to the AI ​​server (e.g., external electronic device (300)).

[0299] For example, if the personal information included in the data is biometric information (e.g., fingerprint, iris, facial recognition data, voice data), the instructions stored in the memory (120) can be executed individually or collectively by at least one processor (110) to cause the electronic device (100) to process the biometric information on the device (e.g., electronic device (100)) and to transmit the data excluding the biometric information to an AI server (e.g., external electronic device (300)) through a communication circuit (160).

[0300] For example, if the personal information included in the data is biometric information (e.g., fingerprint, iris, facial recognition data, voice data), the instructions stored in the memory (120) can be executed individually or collectively by at least one processor (110) to cause the electronic device (100) to convert the biometric information into fake personal information and transmit the data containing the converted personal information to an AI server (e.g., external electronic device (300)) through a communication circuit (160).

[0301] For example, if the personal information included in the data is location information or information that can identify an individual, the instructions stored in the memory (120) can be executed individually or collectively by at least one processor (110) to cause the electronic device (100) to convert the personal information into fake personal information and transmit the data containing the converted personal information to an AI server (e.g., an external electronic device (300)) through a communication circuit (160).

[0302] For example, if the personal information contained in the data identifies an individual but does not pose a significant risk to the individual even if disclosed, the instructions stored in the memory (120) can be executed individually or collectively by at least one processor (110), thereby causing the electronic device (100) to transmit the data containing the personal information to an AI server (e.g., an external electronic device (300)) through the communication circuit (160) without separately processing the personal information.

[0303] In one embodiment, in operation 409, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to incorporate at least one of data that does not contain personal information, data that contains processed fake personal information, data that contains actual personal information, abstract information, encrypted metadata, or data from which personal information is excluded.

[0304] In one embodiment, the data may include at least one of data that does not contain personal information, personal information that can be converted into fake personal information (e.g., important information, or sensitive information), personal information that must be excluded (e.g., sensitive information, or important information), abstract information, encrypted metadata, or personal information that does not require separate processing (e.g., general information).

[0305] In one embodiment, the sensitivity of personal information may vary depending on the settings of the electronic device (100). If the data contains sensitive information, the electronic device (100) may process the personal information based on at least one of a method of excluding personal information from the data or a method of converting it into fake personal information. If the data contains important information, the electronic device (100) may process the personal information based on at least one of a method of excluding personal information from the data or a method of converting it into fake personal information. A method of converting into fake personal information may include at least one of a method of converting actual personal information into fake personal information, a method of converting it into abstract information, or a method of converting it into encrypted metadata.

[0306] For example, one piece of data may include personal information having at least one sensitivity. Each of the multiple pieces of data may include at least one of data that does not include personal information or data that includes personal information.

[0307] In one embodiment, in operation 409, instructions stored in memory (120) can cause the electronic device (100) to process (or change) and integrate at least one piece of personal information (e.g., important information, sensitive information, general information) contained in the data according to a processing method when executed individually or collectively by at least one processor (110).

[0308] In one embodiment, in operation 409, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to integrate at least one data that has been processed or modified according to the processing method.

[0309] In one embodiment, in the 411 operation, instructions stored in memory (120) can enable the electronic device (100) to acquire content based on at least one of integrated data or user input when executed individually or collectively by at least one processor (110).

[0310] In one embodiment, in the 411 operation, instructions stored in memory (120) can enable the electronic device (100) to obtain content based on at least one of integrated data or prompts when executed individually or collectively by at least one processor (110).

[0311] In one embodiment, in the 411 operation, instructions stored in memory (120) can cause the electronic device (100) to generate content based on at least one of integrated data or user input when executed individually or collectively by at least one processor (110).

[0312] In one embodiment, in the 411 operation, instructions stored in memory (120) can cause the electronic device (100) to generate content based on at least one of the integrated data or prompts when executed individually or collectively by at least one processor (110).

[0313] In one embodiment, the electronic device (100) can generate content based on at least one of an LLM AI engine (211), an MLLM AI engine (212), or an LVM AI engine (213).

[0314] In one embodiment, the electronic device (100) can generate content based on the data containing fake personal information and a prompt when the data contains fake personal information. For example, the fake personal information may include at least one of fake personal information, abstract information, or encrypted metadata.

[0315] In one embodiment, the electronic device (100) can generate content based on data and prompts from which personal information has been excluded, if the data does not contain personal information.

[0316] In one embodiment, the electronic device (100) can generate content based on the data containing actual personal information and the prompt, if the data contains actual personal information.

[0317] In one embodiment, in the 411 operation, instructions stored in memory (120) can cause the electronic device (100) to transmit integrated data and user input to an AI server (e.g., an external electronic device (300)) when executed individually or collectively by at least one processor (110).

[0318] In one embodiment, in the 411 operation, instructions stored in memory (120) can cause the electronic device (100) to transmit integrated data and prompts to an AI server (e.g., an external electronic device (300)) when executed individually or collectively by at least one processor (110).

[0319] In one embodiment, in the 411 operation, instructions stored in memory (120) can cause the electronic device (100) to transmit integrated data and prompts to an AI server (e.g., external electronic device (300)) based on a communication circuit (160) when executed individually or collectively by at least one processor (110).

[0320] In one embodiment, in operation 411, instructions stored in memory (120) can cause the electronic device (100) to receive content from an external electronic device (300) (e.g., an AI server) when executed individually or collectively by at least one processor (110).

[0321] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on integrated data and prompts from the electronic device (100).

[0322] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on at least one of an LLM AI engine (311), an MLLM AI engine (312), or an LVM AI engine (313).

[0323] In one embodiment, an external electronic device (300) (e.g., an AI server) may generate content based on data containing fake personal information and prompts when the data received from the electronic device (100) contains fake personal information. For example, the fake personal information may include at least one of fake personal information, abstract information, or encrypted metadata.

[0324] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on the data and prompts from which personal information has been excluded, if the data received from the electronic device (100) does not contain personal information.

[0325] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on the data containing actual personal information and a prompt when the data received from the electronic device (100) contains actual personal information.

[0326] In one embodiment, an external electronic device (300) (e.g., an AI server) can transmit the generated content to the electronic device (100) through a communication circuit.

[0327] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to process (or restore) the content based on actual personal information when executed individually or collectively by at least one processor (110).

[0328] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to process (or restore) content received from an external electronic device (300) (e.g., an AI server) based on actual personal information when executed individually or collectively by at least one processor (110).

[0329] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to process (or restore) content based on actual personal information based on the on-device AI engine (210) and / or screen AI (220) when executed individually or collectively by at least one processor (110).

[0330] In one embodiment, the content may include schema information for an area containing fake personal information, an area containing real personal information, or an area where personal information is excluded. The schema information may include coordinate information within the content for the area containing fake personal information, the area containing real personal information, or the area where personal information is excluded.

[0331] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to restore fake personal information contained in the content to real personal information based on metadata when executed individually or collectively by at least one processor (110).

[0332] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to restore fake personal information contained in content received from an external electronic device (300) to real personal information based on metadata when executed individually or collectively by at least one processor (110).

[0333] In one embodiment, the content generated from the electronic device (100) may include schema information for an area containing fake personal information, an area containing real personal information, or an area where personal information is excluded.

[0334] In one embodiment, the content obtained from an external electronic device (300) (e.g., an AI server) may include schema information regarding an area containing fake personal information, an area containing real personal information, or an area where personal information is excluded.

[0335] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to process content based on actual personal information based on schema information when executed individually or collectively by at least one processor (110).

[0336] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to process content based on actual personal information based on metadata when executed individually or collectively by at least one processor (110).

[0337] In one embodiment, in operation 413, instructions stored in memory (120) can cause the electronic device (100) to process content based on actual personal information based on coordinate information when executed individually or collectively by at least one processor (110).

[0338] For example, instructions stored in memory (120) can cause the electronic device (100) to convert fake personal information contained in the content into actual personal information based on coordinate information when executed individually or collectively by at least one processor (110).

[0339] For example, instructions stored in memory (120) can cause the electronic device (100) to convert fake personal information contained in the content into actual personal information based on coordinate information when executed individually or collectively by at least one processor (110).

[0340] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may convert an area of ​​content from which personal information has been excluded into actual personal information based on coordinate information.

[0341] In one embodiment, in operation 413, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to determine whether to process the received content based on actual personal information based on the user's choice.

[0342] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may display a user interface on a display (140) asking whether to convert fake personal information contained in the content into actual personal information.

[0343] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may display a user interface on the display (140) asking whether to convert an area of ​​the content from which personal information has been excluded into actual personal information.

[0344] In one embodiment, if the user chooses to convert the content based on actual personal information, in operation 413, the instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to process (or restore) the content based on actual personal information.

[0345] In one embodiment, if the user chooses not to convert the content based on actual personal information, in operation 413, the instructions stored in memory (120) may be executed individually or collectively by at least one processor (110), causing the electronic device (100) not to process the content based on actual personal information.

[0346] In one embodiment, in one embodiment, in operation 413, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to process content based on actual personal information based on personal information database (324) stored in a security area (330).

[0347] In one embodiment, in operation 415, instructions stored in memory (120) can cause the electronic device (100) to execute processed content when executed individually or collectively by at least one processor (110).

[0348] In one embodiment, in operation 415, instructions stored in memory (120) can cause the electronic device (100) to execute processed content based on a prompt when executed individually or collectively by at least one processor (110).

[0349] In one embodiment, in operation 415, instructions stored in memory (120) can cause the electronic device (100) to execute processed content based on user input when executed individually or collectively by at least one processor (110).

[0350] In one embodiment, in operation 415, instructions stored in memory (120) can cause the electronic device (100) to execute content containing actual personal information when executed individually or collectively by at least one processor (110).

[0351] For example, processed content may include content processed based on actual personal information in a 413 operation. Processed content may include fake personal information or areas where personal information is excluded.

[0352] In one embodiment, in operation 415, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to display the processed content through the display (140).

[0353] In one embodiment, in operation 415, instructions stored in memory (120) can cause the electronic device (100) to output processed content through a speaker when executed individually or collectively by at least one processor (110).

[0354] FIG. 5 is a flowchart illustrating a method for processing information for privacy protection of an electronic device (100) according to one embodiment of the present disclosure.

[0355] In describing FIG. 5, the description of the same content as FIG. 4 may be replaced with the description of FIG. 4. A method for processing information for the protection of personal information of the electronic device (100) of FIG. 5 may include a method of automatically processing personal information based on a screen context according to user input entered into the electronic device (100) and executing received content.

[0356] In one embodiment, in operation 501, instructions stored in memory (120) can enable the electronic device (100) to obtain user input when executed individually or collectively by at least one processor (110).

[0357] In one embodiment, in operation 501, instructions stored in memory (120) can enable the electronic device (100) to receive user input when executed individually or collectively by at least one processor (110).

[0358] In one embodiment, user input may include text input and voice input by the user, as well as touch input and gesture input.

[0359] In one embodiment, the electronic device (100) can execute an application or user interface capable of receiving user input and display the execution screen on a display (140).

[0360] For example, an application or user interface capable of receiving user input may include a chatbot, a virtual assistant, or a chat application that includes an interface for receiving user input.

[0361] In one embodiment, in operation 503, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to recognize a request from user input. The request may include, for example, at least one of a prompt, a command, a question, a message, or an input.

[0362] In one embodiment, in operation 503, instructions stored in memory (120) can cause the electronic device (100) to confirm a prompt in user input when executed individually or collectively by at least one processor (110).

[0363] In one embodiment, in operation 503, instructions stored in memory (120) can cause the electronic device (100) to check a prompt in user input based on an on-device prompt (222) when executed individually or collectively by at least one processor (110).

[0364] In one embodiment, in operation 505, instructions stored in memory (120) may cause the electronic device (100) to check information regarding the screen context of the screen being executed and / or information regarding a file when executed individually or collectively by at least one processor (110).

[0365] In one embodiment, in operation 505, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can check information regarding the screen context of the screen being executed based on the screen AI (220).

[0366] In one embodiment, the screen context may include information displayed on a screen on the display (140) and the environment and situation in which the information is used. The screen context may include not only the content displayed on the screen, but also information regarding interaction with the user, the state of the application, and the surrounding environment.

[0367] In one embodiment, the screen context may include various user interface elements displayed on the screen, such as buttons, menus, icons, and text fields.

[0368] In one embodiment, the screen context may include actions by which a user interacts with the screen, such as touching, clicking, swiping, or gestures on the display (140).

[0369] In one embodiment, the screen context may include the task currently being performed by the application, the state of the data, or the state of the network connection.

[0370] In one embodiment, the screen context may include physical environment information such as the user's location, time zone, ambient noise, or lighting conditions.

[0371] In one embodiment, the screen context may include information regarding various types of content displayed on the screen, such as text, images, videos, or animations.

[0372] In one embodiment, in operation 507, instructions stored in memory (120) can cause the electronic device (100) to reconstruct data based on analyzed information when executed individually or collectively by at least one processor (110).

[0373] In one embodiment, in operation 507, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to determine whether the data contains personal information.

[0374] In one embodiment, in operation 507, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), and the electronic device (100) can classify the sensitivity of the personal information contained in the data if the data contains personal information.

[0375] In one embodiment, in operation 507, instructions stored in memory (120) can cause the electronic device (100) to determine how to process personal information based on the sensitivity of the classified personal information when executed individually or collectively by at least one processor (110).

[0376] In one embodiment, in operation 507, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to determine fake personal information based on a prompt.

[0377] In one embodiment, in operation 507, instructions stored in memory (120) can cause the electronic device (100) to generate fake personal information containing information similar to personal information based on an analysis of actual personal information or a user profile when executed individually or collectively by at least one processor (110).

[0378] In one embodiment, in operation 507, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to generate metadata to maintain a relationship between real personal information and fake personal information.

[0379] In one embodiment, metadata is not transmitted to an external electronic device (300) or an externally generated AI service, and can be processed only in the electronic device (100).

[0380] In one embodiment, when an external electronic device (300) converts fake personal information into actual personal information in content generated based on fake personal information, the instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), thereby enabling the electronic device (100) to convert the fake personal information included in the externally generated content into actual personal information based on metadata.

[0381] In one embodiment, in operation 507, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to generate structured abstract information based on metadata.

[0382] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may transmit only structured abstract information to an external electronic device (300) or an external generative AI service.

[0383] However, it is not limited thereto, and the abstract information may be transmitted to an external electronic device (300) or an external generative AI service along with the fake personal information. The external electronic device (300) or the external generative AI service may generate content based on the structured abstract information and the fake personal information.

[0384] However, not limited to this, in operation 507, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to encrypt metadata.

[0385] In one embodiment, instructions stored in memory (120) can cause an electronic device (100) to transmit encrypted metadata and fake personal information to an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0386] However, not limited to this, in operation 507, instructions stored in memory (120) can cause the electronic device (100) to transmit fake personal information to an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0387] In one embodiment, an external electronic device (300) can generate content based on fake personal information. The electronic device (100) can restore the content generated based on the fake personal information to include actual personal data.

[0388] However, not limited thereto, in operation 507, instructions stored in memory (120) may cause the electronic device (100) to transmit fake personal information to an external electronic device (300) based on the sensitivity of the personal information when executed individually or collectively by at least one processor (110). When instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may cause personal information with low sensitivity to be converted into fake personal information and then transmitted to an external electronic device (300). When instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can generate content containing actual personal information based on an on-device AI engine (210) and / or screen AI (220) without transmitting personal information with high sensitivity to external electronic device (300).

[0389] In one embodiment, in operation 507, instructions stored in memory (120) can cause the electronic device (100) to process personal information according to a processing method when executed individually or collectively by at least one processor (110).

[0390] In one embodiment, the processing method may include at least one of the following: a method of processing data that does not contain personal information at an AI server (e.g., an external electronic device (300)); a method of processing personal information on an on-device (e.g., an electronic device (100)) and processing data excluding personal information at an AI server (e.g., an external electronic device (300)); a method of converting personal information into fake personal information and processing data containing fake personal information at an AI server (e.g., an external electronic device (300)); or a method of processing data containing personal information at an AI server (e.g., an external electronic device (300)) without processing personal information separately.

[0391] In one embodiment, in operation 507, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to integrate at least one of data that does not contain personal information, data that contains processed fake personal information, data that contains actual personal information, or data from which personal information is excluded.

[0392] In one embodiment, in operation 507, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to convert data containing personal information based on a processing method and integrate the converted data.

[0393] In one embodiment, in operation 509, instructions stored in memory (120) can enable the electronic device (100) to acquire content based on reconstructed data when executed individually or collectively by at least one processor (110).

[0394] In one embodiment, in operation 509, instructions stored in memory (120) can cause the electronic device (100) to generate content based on reconstructed data when executed individually or collectively by at least one processor (110).

[0395] In one embodiment, in operation 509, instructions stored in memory (120) can cause the electronic device (100) to obtain content based on at least one of reconstructed data or prompts when executed individually or collectively by at least one processor (110).

[0396] In one embodiment, the electronic device (100) can generate content based on at least one of an LLM AI engine (211), an MLLM AI engine (312), or an LVM AI engine (213).

[0397] In one embodiment, in operation 509, instructions stored in memory (120) can cause the electronic device (100) to transmit reconstructed data to an external electronic device (300) (e.g., an AI server) when executed individually or collectively by at least one processor (110).

[0398] In one embodiment, in operation 509, instructions stored in memory (120) can cause the electronic device (100) to transmit reconstructed data and prompts to an external electronic device (300) (e.g., AI server) when executed individually or collectively by at least one processor (110).

[0399] However, it is not limited to this, and the electronic device (100) may transmit only abstract information instead of fake personal information to an AI server (e.g., an external electronic device (300)).

[0400] In one embodiment, when transmitting fake personal information to an AI server (e.g., external electronic device (300)), the electronic device (100) may transmit only the fake personal information to the AI ​​server (e.g., external electronic device (300)).

[0401] In one embodiment, when transmitting fake personal information to an AI server (e.g., external electronic device (300)), the electronic device (100) can transmit fake personal information and abstract information to the AI ​​server (e.g., external electronic device (300)).

[0402] In one embodiment, when transmitting fake personal information to an AI server (e.g., external electronic device (300)), the electronic device (100) can transmit the fake personal information and encrypted metadata to the AI ​​server (e.g., external electronic device (300)).

[0403] For example, fake personal information may include at least one of fake personal information, abstract information, or encrypted metadata.

[0404] In one embodiment, in operation 509, instructions stored in memory (120) can cause the electronic device (100) to receive content from an external electronic device (300) (e.g., an AI server) when executed individually or collectively by at least one processor (110).

[0405] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on integrated data and prompts from the electronic device (100).

[0406] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on at least one of an LLM AI engine (311), an MLLM AI engine (312), or an LVM AI engine (313).

[0407] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on the data containing fake personal information and the prompts when the data received from the electronic device (100) contains fake personal information.

[0408] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on the data and prompts from which personal information has been excluded, if the data received from the electronic device (100) does not contain personal information.

[0409] In one embodiment, an external electronic device (300) (e.g., an AI server) can generate content based on the data containing actual personal information and a prompt when the data received from the electronic device (100) contains actual personal information.

[0410] In one embodiment, an external electronic device (300) (e.g., an AI server) can transmit the generated content to the electronic device (100) through a communication circuit.

[0411] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to process the acquired content based on actual personal information when executed individually or collectively by at least one processor (110).

[0412] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to process generated content based on actual personal information when executed individually or collectively by at least one processor (110).

[0413] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to process content based on actual personal information when executed individually or collectively by at least one processor (110).

[0414] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to process content based on actual personal information when executed individually or collectively by at least one processor (110).

[0415] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to process content received from an external electronic device (300) (e.g., an AI server) based on actual personal information when executed individually or collectively by at least one processor (110).

[0416] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to restore fake personal information contained in the content to real personal information based on metadata when executed individually or collectively by at least one processor (110).

[0417] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to restore fake personal information contained in content received from an external electronic device (300) to real personal information based on metadata when executed individually or collectively by at least one processor (110).

[0418] In one embodiment, in one embodiment, in operation 511, instructions stored in memory (120) can cause the electronic device (100) to process content based on actual personal information based on the on-device AI engine (210) and / or screen AI (220) when executed individually or collectively by at least one processor (110).

[0419] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to process content based on actual personal information based on metadata when executed individually or collectively by at least one processor (110).

[0420] In one embodiment, the content may include schema information for an area containing fake personal information, an area containing real personal information, or an area where personal information is excluded. The schema information may include coordinate information within the content for the area containing fake personal information, the area containing real personal information, or the area where personal information is excluded.

[0421] In one embodiment, the content obtained from the electronic device (100) may include schema information for an area containing fake personal information, an area containing real personal information, or an area where personal information is excluded.

[0422] In one embodiment, content received from an external electronic device (300) (e.g., an AI server) may include schema information regarding an area containing fake personal information, an area containing real personal information, or an area where personal information is excluded.

[0423] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to convert fake personal information included in the content into real personal information based on coordinate information when executed individually or collectively by at least one processor (110).

[0424] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to convert fake personal information included in the content into real personal information based on coordinate information when executed individually or collectively by at least one processor (110).

[0425] In one embodiment, in the 511 operation, instructions stored in memory (120) can cause the electronic device (100) to convert areas of content from which personal information has been excluded into actual personal information based on coordinate information when executed individually or collectively by at least one processor (110).

[0426] In one embodiment, in operation 513, instructions stored in memory (120) can cause the electronic device (100) to execute processed content when executed individually or collectively by at least one processor (110).

[0427] In one embodiment, in operation 513, instructions stored in memory (120) can cause the electronic device (100) to execute processed content based on a prompt when executed individually or collectively by at least one processor (110).

[0428] For example, processed content may include content processed based on actual personal information in a 513 operation. Processed content may include fake personal information or areas where personal information is excluded.

[0429] In one embodiment, in operation 513, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to display the processed content through the display (140).

[0430] In one embodiment, in operation 513, instructions stored in memory (120) can cause the electronic device (100) to output processed content through a speaker when executed individually or collectively by at least one processor (110).

[0431] FIGS. 6a, FIGS. 6b and FIGS. 6c are drawings illustrating the operation of receiving data and user input in an electronic device (100) according to one embodiment of the present disclosure.

[0432] Referring to FIG. 6a, the electronic device (100) can display a chat application execution screen (600) on a display (140).

[0433] In one embodiment, the chat application execution screen (600) may include conversation content between the user of the electronic device (100) and the other party. Reference numbers 601, 603, and 606 are conversation content of the other party, and reference numbers 602, 604, and 605 may include conversation content of the user of the electronic device (100).

[0434] Reference number 601 may include conversational content such as, 'S Broadcasting Station prefers a professional and calm tone of voice.'

[0435] In reference number 602, conversational content such as 'Really? There is no other information' may be included.

[0436] In reference number 603, conversation content such as ‘It seems that a neat hairstyle like an updo is important, and pronouncing it correctly is also important.’ may be included.

[0437] In reference number 604, image files such as updos can be included as incomplete content.

[0438] In reference number 605, conversational content such as 'You mean this kind of hair?' may be included.

[0439] In reference number 606, conversational content such as 'That's it' may be included.

[0440] Referring to FIGS. 6b and 6c, the user can execute an application or user interface (610) capable of receiving at least one of data or user input on a chat application execution screen (600).

[0441] For example, a user may input a physical key, touch key interaction, gesture, and / or wake word into the electronic device (100) to execute an application or user interface capable of receiving data and user input. The wake word may be input into the electronic device (100) as voice and / or text.

[0442] In one embodiment, upon receiving input to a physical key, touch key interaction, gesture, and / or wake word, the electronic device (100) may execute an application or user interface (610) capable of receiving data and user input.

[0443] In one embodiment, the electronic device (100) can receive user input (611) through a user interface (610).

[0444] For example, user input (611) may include content such as, ‘Please create a self-introduction video for applying to be a broadcast announcer using the current conversation content and attached materials, and make the background show the weather and time of the place where I am currently.’

[0445] In one embodiment, user input (611) may include text input and voice input by the user, as well as touch input and gesture input.

[0446] In one embodiment, instructions stored in memory (120) may cause the electronic device (100) to check a prompt from user input (611) when executed individually or collectively by at least one processor (110). For example, user input (611) may include a prompt.

[0447] In one embodiment, instructions stored in memory (120) can cause an electronic device (100) to receive at least one piece of data (612, 613, 614, 615, 617) through a user interface (610) when executed individually or collectively by at least one processor (110).

[0448] In one embodiment, at least one data (612, 613, 614, 615, 617) may include at least one of text (614, 615), an image (612, 613, 614), voice (617), and / or video. The data may be input in the form of a file.

[0449] For example, at least one piece of data may include an image file (612) containing the face of the user of the electronic device (100). At least one piece of data may include an image file (613) regarding an identification card (e.g., national ID card, driver's license) that can identify the user. At least one piece of data may include a job application (614) containing both text and images. The job application (613) may include an image file and a text file. At least one piece of data may include voice recording data (617) of the user. At least one piece of data may include a cover letter text file (615).

[0450] FIGS. 7a, FIGS. 7b and FIGS. 7c are drawings illustrating an operation for determining the sensitivity of personal information in an electronic device (100) according to one embodiment of the present disclosure.

[0451] Referring to FIGS. 7a, 7b, and 7c, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to determine whether personal information is included in conversation content (601, 602, 603, 604, 605, 606) and data (612, 614, 613, 614, 616) included in a chat application execution screen (600) being displayed through a display (140).

[0452] Referring to FIG. 7a, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can determine (711, 712, 713) that the conversation content (601, 602, 603, 604, 605, 606) does not contain personal information.

[0453] Referring to FIGS. 7b and 7c, instructions stored in memory (120) can cause an electronic device (100) to determine whether personal information is included in data (612, 614, 613, 614, 616) when executed individually or collectively by at least one processor (110).

[0454] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that an image file (612) containing the face of a user of the electronic device (100) contains personal information about the user's face and classify the sensitivity of the personal information.

[0455] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that the user's face is highly sensitive information (e.g., sensitive information) (714) as information that could have a significant impact on an individual's safety, health, financial status, and social reputation if leaked or misused.

[0456] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that an image file (613) regarding an identification card (e.g., national ID card, driver's license) that can identify an individual user contains personal information in the user's name (6131) and the user's birthday (6132), and classify the sensitivity of the personal information.

[0457] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that the user's name (6131) and the user's birthday (6132) are information that identifies an individual but does not pose a significant risk to the individual even if disclosed, and thus is low-sensitivity information (e.g., general information) (717).

[0458] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that an image file (613) regarding an identification card (e.g., national ID card, driver's license) that can identify a user contains personal information about a user's face (6133) and classify the sensitivity of the personal information.

[0459] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that the user face (6133) is highly sensitive information (e.g., sensitive information) (718) as information that could have a significant impact on an individual's safety, health, financial status, and social reputation if leaked or misused.

[0460] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that the user's voice recording data (617) contains personal information regarding the user's voice and classify the sensitivity of the personal information.

[0461] For example, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that the user voice is highly sensitive information (e.g., sensitive information) (715) as information that could have a significant impact on an individual's safety, health, financial status, and social reputation if leaked or misused.

[0462] In one embodiment, instructions stored in memory (120) can cause the electronic device (100) to determine that the cover letter text file (615) contains personal information such as the user's student number (6151) and academic information (6152) when executed individually or collectively by at least one processor (110).

[0463] In one embodiment, instructions stored in memory (120) can cause the electronic device (100) to classify the sensitivity of personal information regarding the user's student number (6151) and academic information (6152) when executed individually or collectively by at least one processor (110).

[0464] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that the student number (6151) is information (e.g., important information) (719) that can identify an individual and could cause serious damage if leaked.

[0465] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that the educational information (6152) is information that identifies an individual but does not pose a significant risk to the individual even if disclosed, and thus is information with low sensitivity (e.g., general information) (720).

[0466] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that location data (616) is information of normal sensitivity (e.g., important information) (716).

[0467] FIGS. 8a and FIGS. 8b are drawings illustrating the operation of processing personal information in an electronic device (100) according to one embodiment of the present disclosure.

[0468] Referring to FIGS. 8A and 8B, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can determine (711, 712, 713) that the conversation content (601, 602, 603, 604, 605, 606) does not contain personal information.

[0469] In one embodiment, when it is determined (711, 712, 713) that personal information is not included, the instructions stored in memory (120) can cause the electronic device (100) to process (811, 812, 813) conversation content (601, 602, 603, 604, 605, 606) without fake personal information conversion when executed individually or collectively by at least one processor (110).

[0470] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that a user face included in an image (612) is highly sensitive information (e.g., sensitive information) (714).

[0471] In one embodiment, when a user's face is determined to be highly sensitive information (e.g., sensitive information) (714), instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), causing the electronic device (100) to determine the processing method for the user's face as 'converting to fake personal information' (814).

[0472] In one embodiment, if the processing method for a user's face is determined to be 'converted into fake personal information' (814), the instructions stored in memory (120) can be executed individually or collectively by at least one processor (110) to cause the electronic device (100) to convert the user's face to include fake personal information. The converted user face (820) may include, for example, an image suggesting a face. However, it is not limited thereto, and the user face may be excluded from the data and processed by the settings of the electronic device (100).

[0473] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can determine that the user's voice included in voice recording data (617) is highly sensitive information (e.g., sensitive information) (715).

[0474] In one embodiment, if a user voice is determined to be highly sensitive information (e.g., sensitive information) (715), instructions stored in memory (120) may cause the electronic device (100) to convert and process the user voice into fake personal information when executed individually or collectively by at least one processor (110). The converted user voice (815) may include processed voice data that excludes the voice tone capable of personal identification while maintaining the speed of speech. When instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may cause the converted user voice (815) to be transmitted to an external electronic device (300) (e.g., an AI server). However, it is not limited thereto, and the user voice may be excluded from the data and processed by the configuration of the electronic device (100).

[0475] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may determine that location data (616) is information of normal sensitivity (e.g., important information) (716).

[0476] In one embodiment, if location data (616) is determined to be information of moderate sensitivity (e.g., important information) (716), instructions stored in memory (120) may cause the electronic device (100) to convert and process the processing method for the location data into fake personal information when executed individually or collectively by at least one processor (110). The converted location data (816) may include information about a location having an environment similar to the current location (a region with similar latitude and longitude). When instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may cause the converted location data (816) to be transmitted to an external electronic device (300) (e.g., an AI server). However, it is not limited thereto, and the location data may be excluded from the data and processed by the configuration of the electronic device (100).

[0477] FIGS. 9a and 9b are drawings illustrating the operation of an external electronic device (300) generating content according to one embodiment of the present disclosure.

[0478] Referring to FIG. 9a, an external electronic device (300) can receive user input (611) and integrated data (911, 912) from an electronic device (100) through a communication circuit.

[0479] In one embodiment, user input (611) may include content such as, "Please create a self-introduction video for a broadcast station announcer job application using the current conversation content and attached materials, and ensure the background accurately reflects the weather and time of my current location." User input (611) may include a prompt.

[0480] In one embodiment, the integrated data (911, 912) may include conversation content (601, 603, 604) determined to be necessary for content creation during conversation content, educational background information (6152) (e.g., self-introduction text information), user's name (6131), user's birthday (6132), user's face data (820) changed to fake personal information, voice data (815) changed to (or processed to) fake personal information, and location data (816) changed to (or processed to) fake personal information.

[0481] In one embodiment, an external electronic device (300) can generate content (900) based on user input (611) and integrated data (911, 912) using an LLM AI engine (311), an MLLM AI engine (312), and an LVM AI engine (313).

[0482] In one embodiment, the content (900) generated by the external electronic device (300) may include an image (910), voice data (911), and text (913).

[0483] In one embodiment, the image (910) may include a background image based on the user's face data (820) changed to fake personal information, an updo and posture based on conversation content, and changed location data (816).

[0484] In one embodiment, voice data (911) includes a professional and calm tone based on modified voice data (815) and conversation content, and may include content regarding educational background information (6152) (e.g., self-introduction text information).

[0485] In one embodiment, the text (913) may include content generated based on educational background information (6152) (e.g., self-introduction text information).

[0486] FIGS. 10a, FIGS. 10b and FIGS. 10c are drawings illustrating the operation of an electronic device (100) according to one embodiment of the present disclosure processing received content based on actual personal information.

[0487] Referring to FIGS. 10a, 10b, and 10c, the content (900) received from an external electronic device (300) may include an image (910), voice data (911), and location data (914).

[0488] In FIG. 10a, the image (910) may include the user's face data that has been changed to fake personal information. The voice data (911) may include the changed voice data. The location data (914) may include the changed location data.

[0489] In 1000 screens, instructions stored in memory (120) can cause the electronic device (100) to process the user's face data, which has been changed to fake personal information, into actual face data (1010) when executed individually or collectively by at least one processor (110).

[0490] In 1000 screens, instructions stored in memory (120) can cause the electronic device (100) to process voice data changed to fake personal information into actual voice data (1011) when executed individually or collectively by at least one processor (110).

[0491] In 1000 screens, instructions stored in memory (120) can cause the electronic device (100) to process location data changed to fake personal information into actual location data (1014) when executed individually or collectively by at least one processor (110).

[0492] In FIG. 10c, instructions stored in memory (120) can cause the electronic device (100) to generate content (1020) including an image (1021) processed based on actual face data and actual location data, voice data (1022) processed with voice pitch included in actual voice data, and text (913) when executed individually or collectively by at least one processor (110).

[0493] FIG. 11 is a drawing illustrating the operation of creating content through an electronic device (100) and an external electronic device (300) according to one embodiment of the present disclosure.

[0494] In one embodiment, in the 1111 operation, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to receive requests through the on-device AI engine (210).

[0495] In one embodiment, in the 1111 operation, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can receive prompt input through the on-device AI engine (210).

[0496] In one embodiment, the request may include, for example, at least one of a prompt, command, question, message, or input.

[0497] In one embodiment, in operation 1112, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) can determine whether personal information is included in image and text data through the on-device AI engine (210).

[0498] In one embodiment, if personal information is included within the image and text data, the electronic device (100) can branch from operation 1112 to operation 1113.

[0499] In one embodiment, if there is no personal information within the image and text data, the electronic device (100) can branch from operation 1112 to operation 1114.

[0500] In one embodiment, in operation 1113, instructions stored in memory (120) can cause the electronic device (100) to convert personal information into fake personal information through the on-device AI engine (210) when executed individually or collectively by at least one processor (110).

[0501] In one embodiment, in operation 1114, instructions stored in memory (120) can cause the electronic device (100) to transmit requests and data to an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0502] In one embodiment, in the 1114 operation, instructions stored in memory (120) can cause the electronic device (100) to transmit prompts and data to an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0503] In one embodiment, in operation 1115, instructions stored in memory (120) can cause the electronic device (100) to transmit converted personal information and data to an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0504] In one embodiment, in operation 1116, the external electronic device (300) can generate content based on data and requests received from the electronic device (100) by using an LLM AI engine (311), an MLLM AI engine (312), and an LVM AI engine (313).

[0505] In one embodiment, in operation 1116, the external electronic device (300) may use an LLM AI engine (311), an MLLM AI engine (312), and an LVM AI engine (313) to generate content based on data and prompts received from the electronic device (100).

[0506] In one embodiment, in operation 1117, instructions stored in memory (120) can cause the electronic device (100) to receive content from an external electronic device (300) when executed individually or collectively by at least one processor (110).

[0507] In one embodiment, in operation 1117, instructions stored in memory (120) can cause the electronic device (100) to verify personal information converted from received content when executed individually or collectively by at least one processor (110).

[0508] In one embodiment, in operation 1118, instructions stored in memory (120) can cause the electronic device (100) to convert personal information converted from received content into actual personal information when executed individually or collectively by at least one processor (110).

[0509] In one embodiment, in operation 1119, instructions stored in memory (120) can cause the electronic device (100) to generate and display content containing actual personal information when executed individually or collectively by at least one processor (110).

[0510] FIGS. 12a and FIGS. 12b are drawings illustrating the operation of receiving data and user input in an electronic device (100) according to one embodiment of the present disclosure.

[0511] Referring to FIG. 12a, the electronic device (100) can display a chat application execution screen (1200) on a display (140).

[0512] In one embodiment, the chat application execution screen (1200) may include conversation content and data files between the user of the electronic device (100) and the other party.

[0513] In reference number 1201, the chat application execution screen (1200) may include a data file (e.g., a text file) such as 'S company job application'.

[0514] In reference number 1203, the chat application execution screen (1200) may include conversation content such as 'Send the S company job application file. Fill in the details here and apply.'

[0515] In reference number 1204, the chat application execution screen (1200) may include conversation content such as “Go for it.”

[0516] In reference number 1205, the chat application execution screen (1200) may include conversation content such as “thank you.”

[0517] In reference number 1206, the chat application execution screen (1200) may include a data file (e.g., an image file) such as an ‘ID card’. The ID card may include information such as facial information, name, gender, birthday, and address.

[0518] In reference number 1207, the chat application execution screen (1200) may include conversation content such as, ‘I don’t need to use an ID photo or take another one, right? Do you think the (photo) came out well?’

[0519] In reference number 1208, the chat application execution screen (1200) may include conversation content such as ‘write the address as is’.

[0520] In reference number 1209, the chat application execution screen (1200) may include conversation content such as ‘that should work.’

[0521] In reference number 1211, the chat application execution screen (1200) may include conversation content such as 'Will you recruit computer engineering majors too?'

[0522] Referring to FIG. 12b, the electronic device (100) can display a chat application execution screen (1200) on a display (140).

[0523] In FIG. 12b, a user can input a physical key, touch key interaction, gesture, and / or wake word into the electronic device (100) to execute an application or user interface capable of receiving data and user input. The wake word can be input into the electronic device (100) as voice and / or text.

[0524] In one embodiment, upon receiving input to a physical key, touch key interaction, gesture, and / or wake word, the electronic device (100) may execute an application or user interface (1222) capable of receiving data and user input.

[0525] In one embodiment, the electronic device (100) can receive user input through a user interface (1222).

[0526] For example, user input may include content such as 'Please draft my job application in a Word file according to the job application form.' User input may include at least one of voice input, such as natural language utterance, and text input.

[0527] In one embodiment, the electronic device (100) may display the content being analyzed through an interface (1221). For example, the interface (1221) may include information such as 'analysis of information within this screen'.

[0528] In one embodiment, instructions stored in memory (120) can cause the electronic device (100) to analyze the screen context of a screen (1200) being executed through the screen AI (220) when executed individually or collectively by at least one processor (110).

[0529] FIG. 13 is a diagram illustrating the operation of analyzing screen context in an electronic device (100) according to one embodiment of the present invention.

[0530] In one embodiment, the electronic device (100) may include an application / platform (1310) and a screen AI (220).

[0531] In one embodiment, the electronic device (100) can analyze and obtain context information of the screen currently being viewed by the user in an application / platform (1310) through the screen AI (220).

[0532] In one embodiment, when a user is viewing a chat application screen, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to collect and analyze attached files, images, and text on the chat application screen based on the screen context through the screen AI (220).

[0533] FIG. 14 is a diagram showing an operation for determining personal information of an electronic device (100) according to one embodiment of the present disclosure.

[0534] In one embodiment, the chat application execution screen (1200) may include conversation content and data files between the user of the electronic device (100) and the other party.

[0535] In reference number 1201, the chat application execution screen (1200) may include a data file (e.g., a text file) such as 'S company job application'.

[0536] In reference number 1203, the chat application execution screen (1200) may include conversation content such as 'Send the S company job application file. Fill in the details here and apply.'

[0537] In reference number 1204, the chat application execution screen (1200) may include conversation content such as “Go for it.”

[0538] In reference number 1205, the chat application execution screen (1200) may include conversation content such as “thank you.”

[0539] In reference number 1206, the chat application execution screen (1200) may include a data file (e.g., an image file) such as an ‘ID card’. The ID card may include information such as facial information, name, gender, birthday, and address.

[0540] In reference number 1207, the chat application execution screen (1200) may include conversation content such as, ‘I don’t need to use an ID photo or take another one, right? Do you think the (photo) came out well?’

[0541] In reference number 1208, the chat application execution screen (1200) may include conversation content such as ‘write the address as is’.

[0542] In reference number 1209, the chat application execution screen (1200) may include conversation content such as ‘that should work.’

[0543] In reference number 1211, the chat application execution screen (1200) may include conversation content such as 'Will you recruit computer engineering majors too?'

[0544] In one embodiment, the screen AI (220) may cause the MLLM AI engine (212) to send a prompt containing a request for analysis of the screen context. The MLLM AI engine (212) may analyze the current screen based on the prompt containing the request for analysis of the screen context and transmit information (1411, 1412) of the analysis of the current screen to the screen AI (220).

[0545] For example, the information (1411, 1412) analyzing the current screen may include information analyzing user input and data.

[0546] For example, the information (1411) analyzing the current screen may include analysis information regarding reference number 1201. The chat application execution screen (1200) may include a data file (e.g., a text file) such as 'S Company Job Application'. The information (1411) analyzing the current screen may include analysis information regarding the absence of personal information in the data file (e.g., a text file) such as 'S Company Job Application'.

[0547] For example, the information (1412) analyzing the current screen may include analysis information regarding reference number 1206. The chat application execution screen (1200) may include a data file (e.g., an image file) such as an 'ID card'. The ID card may include information such as facial information, name, gender, birthday, and address. The information (1412) analyzing the current screen may include analysis information regarding the inclusion of personal information in the data file (e.g., an image file) such as an 'ID card'.

[0548] FIG. 15 is a diagram showing the operation of an electronic device (100) according to one embodiment of the present disclosure converting personal information into fake personal information.

[0549] In one embodiment, the screen AI (220) may send a prompt containing a request to generate fake personal information based on personal information to the LVM AI engine (213). The LVM AI engine (213) may send data containing fake personal information to the screen AI (220).

[0550] For example, a data file (e.g., an image file) (1206), such as an ‘ID card’, may contain personal information (1511) such as facial information, name, gender, birthday, and address.

[0551] For example, the LVM AI engine (213) can convert personal information (1511) into fake personal information (1512) and generate an image (1513) containing the fake personal information.

[0552] In one embodiment, the electronic device (100) can transmit fake personal information (1512) and / or an image (1513) containing fake personal information to an external electronic device (300) including an external LLM AI.

[0553] FIG. 16 is a diagram showing the operation of an electronic device (100) according to one embodiment of the present disclosure converting personal information into fake personal information.

[0554] In one embodiment, when an electronic device (100) transmits data containing fake personal information (e.g., fake personal information (1512) of FIG. 15) through a screen AI (220) to an external electronic device (300), the external electronic device (300) can generate content (1610) containing fake personal information (e.g., fake personal information (1512) of FIG. 15).

[0555] In one embodiment, the electronic device (100) can receive content (1610) including fake personal information (e.g., fake personal information (1512) of FIG. 15) from an external electronic device (300) via a screen AI (220).

[0556] In one embodiment, the screen AI (220) may send a prompt to the LVM AI engine (213) requesting the creation of content (1610) containing real personal information for content (1610) containing fake personal information (e.g., fake personal information (1512) of FIG. 15).

[0557] In one embodiment, the LVM AI engine (213) can change fake personal information (e.g., fake personal information (1512) of FIG. 15) into real personal information to generate content (1620) and transmit it to the screen AI (220).

[0558] FIG. 17 is a diagram illustrating the operation of an electronic device (100) according to one embodiment of the present disclosure generating content based on a prompt.

[0559] In one embodiment, the screen AI (220) may send a prompt to the LVM AI engine (213) requesting the creation of content based on a personal information database (324) stored in a secure area (330). The personal information database (324) may include personal information, for example, a user's alma mater, language proficiency, and certifications.

[0560] In one embodiment, the LVM AI engine (213) can generate content based on the personal information database (324) and transmit the generated content to the screen AI (220).

[0561] FIG. 18 is a drawing showing a user interface (1800) that can set a processing method according to the sensitivity of personal information in an electronic device (100) according to one embodiment of the present disclosure.

[0562] In one embodiment, the user interface (1800) may include text (1801) indicating the type of interface (e.g., privacy processing settings by security level), and setting interfaces (1811, 1812, 1813) regarding privacy processing methods by sensitivity level.

[0563] In one embodiment, the setting interface (1811) for the first stage general personal information (e.g., general information) may include an interface in which the user selects one of the following: 'use on-device engine', 'use server engine (e.g., external electronic device (300)) after conversion to fake data', or 'use server engine (e.g., external electronic device (300)) (without conversion)'.

[0564] In one embodiment, the setting interface (1812) for two-stage sensitive personal information (e.g., important information) may include an interface in which the user selects one of 'use on-device engine', 'use server engine (e.g., external electronic device (300)) after conversion to fake data', or 'use server engine (e.g., external electronic device (300)) (without conversion)'.

[0565] In one embodiment, the setting interface (1813) for three-stage high-risk personal information (e.g., sensitive information) may include an interface in which the user selects one of 'use on-device engine' or 'use server engine (e.g., external electronic device (300)) after converting to fake data'.

[0566] FIGS. 19a, FIGS. 19b and FIGS. 19c are drawings illustrating an operation to request a modification to content (1900) generated in an electronic device (100) according to one embodiment of the present disclosure.

[0567] In FIG. 19a, the electronic device (100) can convert fake personal information into actual personal information on a display (140) and display content (1900) with input fields added based on the personal information. The electronic device (100) can display a user interface (1910) regarding personal information changes on at least a portion of the content (1900). It can receive touch input (1920) for the user interface (1910) regarding personal information changes.

[0568] In FIG. 19b and FIG. 19c, when a touch input (1920) is received for a user interface (1910) regarding a change in personal information, the electronic device (100) may display an interface (1901) regarding a change in the method of processing personal information through a display (140).

[0569] In one embodiment, an interface (1901) for changing the personal information processing method may include text (1911) indicating the type of interface (e.g., result of personal information processing settings), a setting interface (1912, 1913) for the personal information processing method, text (1914) explaining the effect of changing the personal information processing method, and an interface (1915) for re-executing content creation based on the settings.

[0570] In one embodiment, a setting interface (1912) for email, phone number, homepage, summary, period of enrollment, etc. (e.g., general information) may include an interface in which a user selects one of 'use on-device engine', 'use server engine (e.g., external electronic device (300)) after converting to fake data', or 'use server engine (e.g., external electronic device (300)) (without conversion)'. The electronic device (100) may change the personal information processing method from the current 'use server engine (e.g., external electronic device (300)) after converting to fake data' to 'use server engine (e.g., external electronic device (300)) (without conversion)' based on user input (1921).

[0571] In one embodiment, the setting interface (1913) for facial recognition information (e.g., sensitive information) may include an interface in which a user selects one of 'use on-device engine', 'use server engine (e.g., external electronic device (300)) after converting to fake data', or 'use server engine (e.g., external electronic device (300)) (without conversion)'. The electronic device (100) may change the personal information processing method from the current 'use server engine (e.g., external electronic device (300)) after converting to fake data' to 'use server engine (e.g., external electronic device (300)) (without conversion)' based on user input (1922).

[0572] In one embodiment, the text (1914) describing the effect of changing the personal information processing method may include content such as, 'If processed after being converted into data, personal information is safely processed. If a server engine is used, data is processed online, but the performance of the result can be improved.'

[0573] In one embodiment, an interface (1915) that enables content creation based on settings can receive user input (1923). When user input (1923) is received for the interface (1915) that enables content creation based on settings, the electronic device (100) can create content based on settings.

[0574] FIGS. 20a, FIGS. 20b, FIGS. 20c and FIGS. 20d are drawings illustrating an operation of generating content based on text included in an application running in an electronic device (100) according to one embodiment of the present disclosure.

[0575] In FIG. 20a, the electronic device (100) may display a screen of a word application or note application (2000) running on a display (140). The word application or note application (2000) may include text (2010) regarding a job application.

[0576] In one embodiment, a word application or note application (2000) may receive user input (2020) for selecting text and / or images (2010) regarding a job application.

[0577] In one embodiment, when receiving an input (2020) for selecting text and / or an image (2010) regarding a job application, the electronic device (100) may highlight and display the selected area.

[0578] In FIG. 20b, in one embodiment, when receiving an input (2020) for selecting text and / or an image (2010) regarding a job application, the electronic device (100) may display an interface (2030) on a display (140) that performs an interaction regarding content creation.

[0579] In one embodiment, an interface (2030) for performing an interaction regarding content creation may include an interface (2031) capable of receiving user input, a user interface (2032) requesting confirmation, and an interface (2033) asking whether to process personal information on the device.

[0580] In one embodiment, the electronic device (100) may receive a prompt or user input on an interface (2031) that can receive user input through a display (140), and may display a user interface (2032) that requests confirmation when the prompt or user input is completed, and an interface (2033) that asks whether to process personal information on the device.

[0581] In one embodiment, a prompt or user input entered into an interface (2031) capable of receiving user input may include content such as, 'Change the sentence to a polite tone, correct grammar and typos, and fill in the face photo to fit the ID photo specifications so that the upper body is visible.'

[0582] In FIG. 20c, when input is received by a user interface (2032) that requests confirmation when a prompt or user input is completed, the electronic device (100) may create content and display a message (2034) that guides the content being processed based on the prompt and the settings of an interface (2033) that asks whether to process personal information on the device.

[0583] In one embodiment, a message (2034) indicating the content being processed may display a message such as 'Processing... Your personal information is locked and is safely processed within the terminal.'

[0584] In one embodiment, the electronic device (100) may display a personal information lock indicator (2040) on personal information processed at the electronic device (100) (e.g., on-device).

[0585] In FIG. 20d, the electronic device (100) may display content (2035) generated based on a prompt or user input on an interface (2030) that performs an interaction regarding content generation. The generated content (2035) may display (2050) by distinguishing between results processed by an external electronic device (300) and results processed by the electronic device (100).

[0586] FIGS. 21a, FIGS. 21b, FIGS. 21c, FIGS. 21d, FIGS. 21e and FIGS. 21f are drawings illustrating an operation to generate content when data containing personal information is found in an electronic device (100) according to one embodiment of the present disclosure.

[0587] In FIG. 21a, the electronic device (100) can display an execution screen of a chat application (2100) on a display (140). When data related to personal information is detected in the chat application (2100), the electronic device (100) can display an interface (2110) regarding personal information protection.

[0588] In reference number 2101, the chat application execution screen (2100) may include a data file (e.g., a text file) such as a ‘self-introduction’.

[0589] In reference number 2102, the chat application execution screen (2100) may include a data file (e.g., an image file) such as an ‘ID card’. The ID card may include information such as facial information, name, gender, birthday, and address.

[0590] In reference number 2103, the chat application execution screen (2100) may include financial information such as 'Samsung Bank 1234-56789-00'.

[0591] In FIG. 21b, the electronic device (100) may select a data file (e.g., an image file) (2102), such as an 'ID card', during a chat application execution screen (2100) based on input. When the image (2102) is selected based on input, the electronic device (100) may display an interface (2121, 2122, 2123, 2124) related to image editing on a display (140).

[0592] In FIG. 21c, when the interface (2110) for privacy protection is turned on, the electronic device (100) can exclude or delete (2130) parts corresponding to personal information in a data file (e.g., image file) (2102), such as an 'ID card'.

[0593] In FIG. 21d, when the interface (2110) for privacy protection is off, the electronic device (100) can maintain or display a portion corresponding to personal information in a data file (e.g., image file) (2102), such as an 'ID card'.

[0594] In FIG. 21e, when the electronic device (100) transmits an image file (2102) with the portion corresponding to the personal information in FIG. 21c excluded or deleted to an external electronic device (300), the external electronic device (300) can generate content based on the image file (2102) with the portion corresponding to the personal information excluded or deleted, and transmit the generated content to the electronic device (100). When the electronic device (100) receives content from the external electronic device (300), it can display a user interface (2151) asking whether to save it as is, a user interface (2152) asking whether to save it including personal information, and the content with the portion corresponding to the personal information excluded or deleted.

[0595] When receiving a user selection (2153) to store including personal information in FIG. 21e and FIG. 21f, the electronic device (100) may display an image containing actual personal information in content from which the portion corresponding to the personal information has been excluded or deleted.

[0596] In FIG. 21e, the electronic device (100) may display an exemplary image (e.g., a smiley face) that can be substituted for an image file (2102).

[0597] In FIG. 21f, the electronic device (100) can allow the user to directly draw an image that can be replaced in the image file (2102). When the user selects the image generation interface (2131) (example phrase: draw anything you want to generate in the image), the electronic device (100) displays the image generated according to the user input (e.g., drawing input), and the electronic device (100) can make the generated image replaceable in the image file (2102).

[0598] FIG. 22 is a drawing illustrating a method for processing an image containing personal information in an electronic device (100) according to one embodiment of the present disclosure.

[0599] In one embodiment, in operation 2201, instructions stored in memory (120) can be input to an electronic device (100) when executed individually or collectively by at least one processor (110).

[0600] In one embodiment, in operation 2203, instructions stored in memory (120) may cause the electronic device (100) to receive prompt input when executed individually or collectively by at least one processor (110). The prompt input may include content such as 'draw outside the photo area'.

[0601] In one embodiment, in operation 2204, instructions stored in memory (120) can cause the electronic device (100) to change face recognition information into fake information when executed individually or collectively by at least one processor (110). For example, faces (2210) included in an image file can be changed into fake faces or dummy faces (2211).

[0602] In one embodiment, in operation 2205, the external electronic device (300) can process data based on fake information and transmit the processed data to the electronic device (100).

[0603] In one embodiment, in operation 2206, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to convert fake information in processed data into actual personal information and integrate the data.

[0604] In one embodiment, in operation 2207, instructions stored in memory (120) may be executed individually or collectively by at least one processor (110), causing the electronic device (100) to display data that has been changed and integrated into actual personal information on the display (140). The electronic device (100) may display an interface (2212) indicating the part that has been changed and integrated into actual personal information on the display (140).

[0605] FIG. 23 is a flowchart illustrating a method for processing information for privacy protection of an electronic device (100) according to one embodiment of the present disclosure.

[0606] In one embodiment, in operation 2301, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to receive AI calls and commands from a user (101). If the user voice input includes an awake word, the electronic device (100) can execute an AI agent (201). For example, commands received from the user (101) may include voice and / or text input and may include requests for content creation based on personal information.

[0607] For example, the AI ​​call and command of the user (101) may include voice input. The AI ​​call may include user voice input regarding an awake word.

[0608] In one embodiment, when receiving AI calls and commands from a user (101), in operation 2303, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), and the electronic device (100) may request the screen AI (220) to analyze the screen running on the display (140) through the AI ​​agent (201). For example, the screen running may include a document file or screen context attached to or being displayed on the screen.

[0609] In one embodiment, the screen AI (220) can analyze the screen running on the display (140) or the current screen.

[0610] In one embodiment, the AI ​​agent (201) may include a program containing instructions. The AI ​​agent (201) may be stored in memory (120). The AI ​​agent (201) may perform voice assistant actions capable of performing natural language interaction with a user.

[0611] In one embodiment, in operation 2305, instructions stored in memory (120) can cause the electronic device (100) to request the screen AI (220) to collect personal information from the data collector (221) when executed individually or collectively by at least one processor (110).

[0612] In one embodiment, in operation 2307, instructions stored in memory (120) can cause the electronic device (100) to transmit collected personal information to the data collector (221) on-device prompt (222) and / or cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0613] In one embodiment, the data collector (221) can collect personal information based on the analyzed screen.

[0614] In one embodiment, in operation 2309, instructions stored in memory (120) can cause the electronic device (100), when executed individually or collectively by at least one processor (110), to cause the on-device prompt (222) and / or cloud prompt (223) to classify the sensitivity of personal information and to generate the personal information as fake personal information based on the classified sensitivity.

[0615] In one embodiment, the on-device prompt (222) and / or cloud prompt (223) may classify the sensitivity of personal information and generate the personal information as fake personal information based on the classified sensitivity.

[0616] In one embodiment, in operation 2311, instructions stored in memory (120) can cause the electronic device (100) to transmit fake personal information to the AI ​​agent (201) via an on-device prompt (222) and / or a cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0617] In one embodiment, in operation 2313, instructions stored in memory (120) may cause the electronic device (100) to request the AI ​​agent (201) to analyze and reconstruct on-screen visual content to the LVM AI engine (213) when executed individually or collectively by at least one processor (110). For example, the visual content may include images, photos, and / or videos.

[0618] In one embodiment, in operation 2315, instructions stored in memory (120) can cause the electronic device (100) to allow the LVM AI engine (213) to deliver visual content generated based on fake personal information to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0619] In one embodiment, the LVM AI engine (213) can generate visual content based on fake personal information.

[0620] In one embodiment, in operation 2317, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to request the AI ​​agent (201) to request the LLM AI engine (211) to process text data or text-based content. For example, the LLM AI engine (211) can textify content contained in a file (e.g., a document file).

[0621] In one embodiment, in operation 2319, instructions stored in memory (120) can cause the electronic device (100) to enable the LLM AI engine (211) to transmit the analysis and / or processing results of text data or text-based content to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0622] In one embodiment, in operation 2321, instructions stored in memory (120) can cause the electronic device (100) to request the AI ​​agent (201) to combine text data and generated visual content with the MLLM AI engine (212) when executed individually or collectively by at least one processor (110).

[0623] In one embodiment, the MLLM AI engine (212) can generate multimodal content that combines text data and generated visual content.

[0624] In one embodiment, in operation 2323, instructions stored in memory (120) can cause the electronic device (100) to enable the MLLM AI engine (212) to deliver multimodal content combining text data and generated visual content to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0625] In one embodiment, in operation 2325, instructions stored in memory (120) can cause the electronic device (100), when executed individually or collectively by at least one processor (110), to transmit text data based on fake personal information to the LLM AI engine (311) of an external electronic device (300) via a communication circuit (160) by an AI agent (201).

[0626] In one embodiment, in operation 2327, the LLM AI engine (311) of the external electronic device (300) can transmit text data generated based on fake personal information to the electronic device (100) through a communication circuit under the control of the processor.

[0627] In one embodiment, in operation 2329, instructions stored in memory (120) can cause the electronic device (100) to request the AI ​​agent (201) to generate visual content to the LVM AI engine (313) of the external electronic device (300) through the communication circuit (160) when executed individually or collectively by at least one processor (110).

[0628] In one embodiment, the electronic device (100) may transmit visual content based on multimodal content and / or fake personal information coupled to the LVM AI engine (313) of the external electronic device (300) through the communication circuit (160).

[0629] In one embodiment, the LVM AI engine (313) of the external electronic device (300) can generate visual content based on combined multimodal content and / or fake personal information.

[0630] In one embodiment, in operation 2331, the LVM AI engine (313) of the external electronic device (300) can transmit visual content generated through a communication circuit to the electronic device (100) under the control of the processor.

[0631] In one embodiment, in operation 2333, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to request, through a communication circuit (160), that the AI ​​agent (201) generate multimodal content combined with text data generated based on visual content and fake personal information generated by the MLLM AI engine (312) of the external electronic device (300).

[0632] In one embodiment, the MLLM AI engine (312) of the external electronic device (300) can generate multimodal content that combines generated visual content and text data generated based on fake personal information.

[0633] In one embodiment, in operation 2335, the MLLM AI engine (312) of the external electronic device (300) can transmit combined multimodal content to the electronic device (100) through a communication circuit under the control of the processor.

[0634] In one embodiment, in operation 2337, instructions stored in memory (120), when executed individually or collectively by at least one processor (110), may cause the electronic device (100) to request that the AI ​​agent (201) change fake personal information contained in multimodal content combined with the MLLM AI engine (212) into actual personal information. The combined multimodal content may include content generated by the MLLM AI engine (212) of the electronic device (100) and / or the MLLM AI engine (312) of an external electronic device (300).

[0635] In one embodiment, in operation 2339, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), causing the electronic device (100) to allow the MLLM AI engine (212) to deliver the processed content to the AI ​​agent (201) as final content, so that the fake personal information is changed into actual personal information.

[0636] In one embodiment, in operation 2340, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to provide the AI ​​agent (201) processed content or final content to the user (101).

[0637] In one embodiment, in operation 2340, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to display processed content or final content to the user (101) on the display (140).

[0638] FIG. 24 is a flowchart illustrating a method for processing information for privacy protection of an electronic device (100) according to one embodiment of the present disclosure.

[0639] In one embodiment, in operation 2401, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to receive AI calls and commands from the user (101).

[0640] For example, the AI ​​call and command of the user (101) may include voice input. The AI ​​call may include user voice input regarding an awake word. If the user voice input includes an awake word, the electronic device (100) may execute the AI ​​agent (201). For example, the command received from the user (101) may include voice and / or text input and may include a request to create content based on personal information.

[0641] In one embodiment, when receiving AI calls and commands from a user (101), in operation 2403, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), and the electronic device (100) may request the screen AI (220) to analyze the screen running on the display (140) through the AI ​​agent (201). For example, the screen running may include a document file or screen context attached to or displayed on the screen.

[0642] In one embodiment, the AI ​​agent (201) may include a program containing instructions. The AI ​​agent (201) may be stored in memory (120). The AI ​​agent (201) may perform voice assistant actions capable of performing natural language interaction with a user.

[0643] In one embodiment, in operation 2405, instructions stored in memory (120) can cause the electronic device (100) to request the screen AI (220) to collect personal information from the data collector (221) when executed individually or collectively by at least one processor (110).

[0644] In one embodiment, the data collector (221) can collect personal information based on the analyzed screen.

[0645] In one embodiment, in operation 2407, instructions stored in memory (120) can cause the electronic device (100) to transmit collected personal information to the data collector (221) on-device prompt (222) and / or cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0646] In one embodiment, in operation 2407, instructions stored in memory (120) may be executed individually or collectively by at least one processor (110), causing the electronic device (100) to request the data collector (221) to classify the personal information collected at the on-device prompt (222) and / or cloud prompt (223) based on sensitivity and to generate fake personal information.

[0647] In one embodiment, in operation 2409, instructions stored in memory (120) can cause the electronic device (100), when executed individually or collectively by at least one processor (110), to cause the on-device prompt (222) and / or cloud prompt (223) to classify the sensitivity of personal information and to generate the personal information as fake personal information based on the classified sensitivity.

[0648] In one embodiment, in operation 2409, instructions stored in memory (120) can cause the electronic device (100) to transmit fake personal information to the AI ​​agent (201) via an on-device prompt (222) and / or a cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0649] In one embodiment, in operation 2411, instructions stored in memory (120) can cause the electronic device (100) to request the AI ​​agent (201) to generate visual content based on fake personal information to the on-device AI engine (210) when executed individually or collectively by at least one processor (110).

[0650] In one embodiment, in operation 2413, instructions stored in memory (120) can cause the electronic device (100) to allow the on-device AI engine (210) to deliver visual content generated based on fake personal information to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0651] In one embodiment, the on-device AI engine (210) can generate visual content based on fake personal information.

[0652] In one embodiment, in operation 2415, instructions stored in memory (120) can cause the electronic device (100) to transmit fake personal information-based text data to an external electronic device (300) via a communication circuit (160) when executed individually or collectively by at least one processor (110).

[0653] In one embodiment, in operation 2417, the LLM AI engine (311) of the external electronic device (300) can generate text data based on fake personal information through a communication circuit under the control of a processor and transmit the generated text data to the electronic device (100).

[0654] In one embodiment, in operation 2419, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to request the AI ​​agent (201) to change fake personal information contained in content transmitted from an external electronic device (300) to real personal information.

[0655] In one embodiment, in operation 2421, instructions stored in memory (120) can cause the electronic device (100), when executed individually or collectively by at least one processor (110), to cause the on-device AI engine (210) to deliver the content processed to change fake personal information into actual personal information to the AI ​​agent (201) as final content. The on-device AI engine (210) can generate the content processed to change fake personal information into actual personal information as final content.

[0656] In one embodiment, in operation 2423, instructions stored in memory (120) can cause the electronic device (100) to provide the AI ​​agent (201) processed content or final content to the user (101) when executed individually or collectively by at least one processor (110).

[0657] In one embodiment, in operation 2425, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to receive a modification request from a user (101) through an AI agent (201).

[0658] In one embodiment, when a modification request is received from a user (101), in operation 2427, instructions stored in memory (120) may be executed individually or collectively by at least one processor (110), causing the electronic device (100) to request that the AI ​​agent (201) modify the content or final content processed by the on-device AI engine (210).

[0659] In one embodiment, when a modification request is received from a user (101), in operation 2429, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), causing the electronic device (100) to enable the on-device AI engine (210) to provide modified content to the AI ​​agent (201) based on the user's modification request.

[0660] In one embodiment, the on-device AI engine (210) can modify the processed content or the final content based on the user's modification request.

[0661] In one embodiment, in operation 2431, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to display modified processed content or final content to the user (101) on the display (140).

[0662] FIG. 25 is a flowchart illustrating a method for processing information for privacy protection of an electronic device (100) according to one embodiment of the present disclosure.

[0663] In one embodiment, in operation 2501, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to receive AI calls and commands from a user (101).

[0664] For example, the AI ​​call and command of the user (101) may include voice input. The AI ​​call may include user voice input regarding an awake word. When the user voice input includes an awake word, the electronic device (100) may execute or activate the AI ​​agent (201) through the operating system (202).

[0665] In one embodiment, in operation 2503, instructions stored in memory (120) can enable the electronic device (100) to execute or activate an AI agent (201) through an operating system (202) when executed individually or collectively by at least one processor (110).

[0666] In one embodiment, when the AI ​​agent (201) is activated, in operation 2505, the instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), causing the electronic device (100) to cause the AI ​​agent (201) to enter an input waiting state and / or a waiting state.

[0667] In one embodiment, in operation 2507, instructions stored in memory (120) can cause the electronic device (100) to allow the AI ​​agent (201) to receive commands from the user (101) when executed individually or collectively by at least one processor (110). For example, commands received from the user (101) may include voice and / or text input and may include requests for content creation based on personal information.

[0668] In one embodiment, when a request for content creation based on personal information is received, in operation 2509, instructions stored in memory (120) may be executed individually or collectively by at least one processor (110), causing the electronic device (100) to request the screen AI (220) to analyze the screen running on the display (140) through the AI ​​agent (201). For example, the screen running may include a document file or screen context attached to or being displayed on the screen.

[0669] In one embodiment, the AI ​​agent (201) may include a program containing instructions. The AI ​​agent (201) may be stored in memory (120). The AI ​​agent (201) may perform voice assistant actions capable of performing natural language interaction with a user.

[0670] In one embodiment, the screen AI (220) can analyze the screen running on the display (140) or the current screen.

[0671] In one embodiment, in operation 2511, instructions stored in memory (120) can cause the electronic device (100) to transmit screen information or current screen information that the screen AI (220) is executing to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0672] In one embodiment, when running screen information or current screen information is transmitted to the AI ​​agent (201), in operation 2513, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to enable the AI ​​agent (201) to provide a confirmation message to the user (101).

[0673] For example, a confirmation message may be displayed through the display (140), and for example, the confirmation message may include guidance such as “Would you like to start the task?”

[0674] In one embodiment, in operation 2515, instructions stored in memory (120) can cause the electronic device (100) to allow the AI ​​agent (201) to receive a command regarding the performance of a task from the user (101) when executed individually or collectively by at least one processor (110).

[0675] In one embodiment, in operation 2517, instructions stored in memory (120) can cause the electronic device (100) to enable the AI ​​agent (201) to provide messages regarding the work process to the user (101) when executed individually or collectively by at least one processor (110).

[0676] For example, a message regarding the work process can be displayed through the display (140), and, for example, the message regarding the work process may include guidance such as “Data is being analyzed.”

[0677] FIG. 26 is a flowchart illustrating a method for processing information for privacy protection of an electronic device (100) according to one embodiment of the present disclosure.

[0678] In one embodiment, in operation 2601, instructions stored in memory (120) can cause the electronic device (100) to allow the AI ​​agent (201) to receive commands from the user (101) when executed individually or collectively by at least one processor (110). For example, commands received from the user (101) may include voice and / or text input and may include requests for content creation based on personal information.

[0679] In one embodiment, when a request for content creation based on personal information is received, in operation 2603, instructions stored in memory (120) may be executed individually or collectively by at least one processor (110), causing the electronic device (100) to request the screen AI (220) to analyze the screen running on the display (140) through the AI ​​agent (201). For example, the screen running may include a document file or screen context attached to or being displayed on the screen.

[0680] In one embodiment, the screen AI (220) can analyze the screen running on the display (140) or the current screen.

[0681] In one embodiment, in operation 2605, instructions stored in memory (120) can cause the electronic device (100) to transmit screen information or current screen information that the screen AI (220) is executing to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0682] In one embodiment, in operation 2607, instructions stored in memory (120) can cause the electronic device (100) to request the AI ​​agent (201) to collect personal information from the data collector (221) when executed individually or collectively by at least one processor (110).

[0683] In one embodiment, the data collector (221) can collect personal information based on the analyzed screen.

[0684] In one embodiment, in operation 2609, instructions stored in memory (120) can cause the electronic device (100) to transmit personal information collected by the data collector (221) to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0685] In one embodiment, in operation 2611, instructions stored in memory (120) may be executed individually or collectively by at least one processor (110), causing the electronic device (100) to request the AI ​​agent (201) to transmit collected personal information and data to an on-device prompt (222) and / or a cloud prompt (223) and to classify the sensitivity of the personal information to the on-device prompt (222) and / or the cloud prompt (223).

[0686] In one embodiment, the on-device prompt (222) and / or cloud prompt (223) classify the sensitivity of personal information and can generate the personal information as fake personal information based on the classified sensitivity.

[0687] In one embodiment, in operation 2613, instructions stored in memory (120) can cause the electronic device (100) to classify the sensitivity of personal information on an on-device prompt (222) and / or a cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0688] In one embodiment, in operation 2615, instructions stored in memory (120) can cause the electronic device (100) to transmit the results of classifying the sensitivity of personal information to the AI ​​agent (201) via an on-device prompt (222) and / or a cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0689] FIG. 27 is a flowchart illustrating a method for processing information for personal information protection of an electronic device (100) according to one embodiment of the present disclosure.

[0690] In one embodiment, in operation 2701, instructions stored in memory (120) can cause the electronic device (100) to request the AI ​​agent (201) to convert personal information classified according to sensitivity into fake personal information at the on-device prompt (222) and / or cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0691] In one embodiment, the on-device prompt (222) and / or cloud prompt (223) can generate personal information as fake personal information based on classified sensitivity.

[0692] In one embodiment, in operation 2703, instructions stored in memory (120) can cause the electronic device (100) to generate personal information as fake personal information based on the sensitivity classified by the on-device prompt (222) and / or cloud prompt (223) when executed individually or collectively by at least one processor (110).

[0693] In one embodiment, in operation 2705, instructions stored in memory (120) can cause the electronic device (100) to transmit fake personal information generated by an on-device prompt (222) and / or a cloud prompt (223) to an AI agent (201) when executed individually or collectively by at least one processor (110).

[0694] In one embodiment, in operation 2707, instructions stored in memory (120) can cause the electronic device (100) to request the AI ​​agent (201) to generate visual content based on fake personal information in the LVM AI engine (213) when executed individually or collectively by at least one processor (110).

[0695] In one embodiment, in operation 2709, the LVM AI engine (213) can generate visual content based on fake personal information. For example, the visual content may include images, photos, and / or videos.

[0696] In one embodiment, in operation 2711, instructions stored in memory (120) can cause the electronic device (100) to transmit visual content generated by the LVM AI engine (213) based on fake personal information to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0697] In one embodiment, in operation 2713, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to request the LLM AI engine (211) to process text data or text-based content based on fake personal information by the AI ​​agent (201). For example, the LLM AI engine (211) can textify content contained in a file (e.g., a document file).

[0698] In one embodiment, in operation 2715, instructions stored in memory (120) can cause the electronic device (100) to enable the LLM AI engine (211) to process or generate text data or text-based content based on fake personal information when executed individually or collectively by at least one processor (110).

[0699] In one embodiment, in operation 2717, instructions stored in memory (120) can cause the electronic device (100) to transmit text-based content generated by the LLM AI engine (211) based on fake personal information to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0700] In one embodiment, in operation 2719, instructions stored in memory (120) may cause the electronic device (100) to request the AI ​​agent (201) to process text-based content generated based on fake personal information and visual content generated based on fake personal information to the MLLM AI engine (212) when executed individually or collectively by at least one processor (110).

[0701] In one embodiment, in operation 2719, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to request the AI ​​agent (201) to process text-based content generated based on fake personal information and visual content generated based on fake personal information to the MLLM AI engine (212) to generate multimodal content.

[0702] In one embodiment, in operation 2719, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to request the AI ​​agent (201) to combine text-based content generated based on fake personal information and visual content generated based on fake personal information with the MLLM AI engine (212) to generate multimodal content.

[0703] In one embodiment, the MLLM AI engine (212) can generate multimodal content that combines text-based content generated based on fake personal information and visual content generated based on fake personal information.

[0704] In one embodiment, in operation 2721, instructions stored in memory (120) can cause the electronic device (100) to generate multimodal content in which text-based content generated based on fake personal information and visual content generated based on fake personal information are combined by the MLLM AI engine (212) when executed individually or collectively by at least one processor (110).

[0705] In one embodiment, in operation 2723, instructions stored in memory (120) can cause the electronic device (100) to transmit multimodal content generated by the MLLM AI engine (212) to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0706] FIG. 28 is a flowchart illustrating a method for processing information for personal information protection of an electronic device (100) according to one embodiment of the present disclosure.

[0707] In one embodiment, in operation 2801, instructions stored in memory (120) may, when executed individually or collectively by at least one processor (110), cause the electronic device (100) to request the AI ​​agent (201) to change fake personal information contained in content received from an external electronic device (300) to real personal information.

[0708] In one embodiment, in operation 2803, instructions stored in memory (120) can cause the electronic device (100) to change fake personal information contained in content received from an external electronic device (300) into real personal information when executed individually or collectively by at least one processor (110).

[0709] In one embodiment, in operation 2805, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may cause the MLLM AI engine (212) to deliver the content processed to change fake personal information into actual personal information to the AI ​​agent (201) as final content.

[0710] In one embodiment, in operation 2807, instructions stored in memory (120) can cause the electronic device (100) to request the LVM AI engine (213) to modify visual content generated by the AI ​​agent (201) based on fake personal information into visual content containing real personal information when executed individually or collectively by at least one processor (110).

[0711] In one embodiment, in operation 2809, instructions stored in memory (120) can cause the electronic device (100) to modify visual content generated by the LVM AI engine (213) based on fake personal information into visual content containing real personal information when executed individually or collectively by at least one processor (110).

[0712] In one embodiment, in operation 2811, instructions stored in memory (120) can cause the electronic device (100) to allow the LVM AI engine (213) to deliver visual content modified to include actual personal information to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0713] In one embodiment, in operation 2813, instructions stored in memory (120) can cause the electronic device (100) to request the LLM AI engine (211) to modify text-based content generated by the AI ​​agent (201) based on fake personal information into text-based content containing real personal information when executed individually or collectively by at least one processor (110).

[0714] In one embodiment, in operation 2815, instructions stored in memory (120) can cause the electronic device (100) to modify text-based content generated by the LLM AI engine (211) based on fake personal information into text-based content containing real personal information when executed individually or collectively by at least one processor (110).

[0715] In one embodiment, in operation 2817, instructions stored in memory (120) can cause the electronic device (100) to allow the LLM AI engine (211) to deliver text-based content modified to include actual personal information to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0716] In one embodiment, in operation 2819, instructions stored in memory (120) can cause the electronic device (100) to enable the AI ​​agent (201) to provide the final content or processed content containing actual personal information to the user (101) when executed individually or collectively by at least one processor (110).

[0717] FIG. 29 is a flowchart illustrating a method for processing information for personal information protection of an electronic device (100) according to one embodiment of the present disclosure.

[0718] In one embodiment, in operation 2901, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to enable the AI ​​agent (201) to receive input from the user (101) regarding an error report for the final content or processed content.

[0719] In one embodiment, in operation 2903, instructions stored in memory (120) can cause the electronic device (100) to request the AI ​​agent (201) to request the MLLM AI engine (212) to perform error analysis on the final content or processed content when executed individually or collectively by at least one processor (110).

[0720] In one embodiment, in operation 2905, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to enable the MLLM AI engine (212) to analyze errors in the final content or processed content.

[0721] In one embodiment, in operation 2905, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), allowing the electronic device (100) to enable the MLLM AI engine (212) to compare fake personal information with real personal information and analyze errors in the final content or processed content.

[0722] In one embodiment, in operation 2907, instructions stored in memory (120) can cause the electronic device (100) to allow the MLLM AI engine (212) to transmit error analysis results to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0723] In one embodiment, in operation 2909, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), causing the electronic device (100) to request the LLM AI engine (211) for the AI ​​agent (201) to modify text data based on the error analysis results.

[0724] In one embodiment, in operation 2911, instructions stored in memory (120) can cause the electronic device (100) to allow the LLM AI engine (211) to modify text data based on error analysis results when executed individually or collectively by at least one processor (110).

[0725] In one embodiment, in operation 2911, instructions stored in memory (120) can cause the electronic device (100) to modify text data so that actual personal information is included based on the error analysis results of the LLM AI engine (211) when executed individually or collectively by at least one processor (110).

[0726] In one embodiment, in operation 2913, instructions stored in memory (120) can cause the electronic device (100) to allow the LLM AI engine (211) to transmit modified text data to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0727] In one embodiment, in operation 2915, instructions stored in memory (120) can be executed individually or collectively by at least one processor (110), causing the electronic device (100) to request the LVM AI engine (213) for the AI ​​agent (201) to modify visual content based on the error analysis results.

[0728] In one embodiment, in operation 2917, instructions stored in memory (120) can cause the electronic device (100) to allow the LVM AI engine (213) to modify visual content based on error analysis results when executed individually or collectively by at least one processor (110).

[0729] In one embodiment, in operation 2917, instructions stored in memory (120) can cause the electronic device (100) to allow the LVM AI engine (213) to modify visual content to include actual personal information based on the error analysis results when executed individually or collectively by at least one processor (110).

[0730] In one embodiment, in operation 2919, instructions stored in memory (120) can cause the electronic device (100) to allow the LVM AI engine (213) to deliver modified visual content to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0731] In one embodiment, in operation 2921, instructions stored in memory (120) may cause the electronic device (100) to request the MLLM AI engine (212) to combine or integrate the modified visual content and modified text data when executed individually or collectively by at least one processor (110).

[0732] In one embodiment, in operation 2923, instructions stored in memory (120) can cause the electronic device (100) to enable the MLLM AI engine (212) to combine or integrate modified visual content and modified text data when executed individually or collectively by at least one processor (110).

[0733] In one embodiment, in operation 2925, instructions stored in memory (120) can cause the electronic device (100) to transmit the modified final content or modified multimodal content to the AI ​​agent (201) when executed individually or collectively by at least one processor (110).

[0734] In one embodiment, in operation 2927, instructions stored in memory (120) can cause the electronic device (100) to provide the AI ​​agent (201) modified final content or modified multimodal content to the user (101) when executed individually or collectively by at least one processor (110).

[0735] FIG. 30 is a drawing illustrating an operation to request modification for generated content (3007) according to one embodiment of the present disclosure.

[0736] Screen 3001 displays actual personal information. For example, actual personal information may include Address: Resides in Gangnam-gu, Seoul, Occupation: Office worker, Major: Visual design, Age: 35, and Name: Kim Sam-seong.

[0737] Screen 3003 displays fake personal information. Fake personal information may include data generated based on actual personal information. For example, fake personal information may include Address: Resides in Yongin-si, Gyeonggi-do, Occupation: Freelancer, Major: Fine Arts, Age: 29, and Name: Hong Gil-dong.

[0738] Screen 3005 displays content generated based on fake personal information. For example, content generated based on fake personal information may include “Hello, I am Hong Gil-dong. I live in Jung-gu, Seoul and work as a freelance artist. I am 30 years old and have a creative and free personality.”

[0739] Screen 3007 displays content in which fake personal information is converted into actual personal information. The content converted into actual personal information may include “Hello, I am Kim Sam-seong. I am a 35-year-old office worker residing in Gangnam-gu, Seoul. I work at a design company and have a highly independent, creative, and free-spirited personality.” The content converted into actual personal information may contain contextual errors. The electronic device (100) may display an affordance interface (e.g., “?”) for correcting errors in the content converted into actual personal information on the display (140) along with the content converted into actual personal information.

[0740] In one embodiment, if the user determines that there is an error in the content converted into actual personal information, the user may select an affordance interface (e.g., “?”) for error correction.

[0741] Screen 3008 may include items converted into actual personal information (3011, 3013, 3015, 3017, 3019) and items converted into fake personal information (3012, 3014, 3016, 3018, 3020) and a re-execution interface (3021).

[0742] Referring to screens 3008 and 3009, if the user, for example, selects or deselects the employee item (3017) and selects the re-execution interface (3021), the electronic device (100) can regenerate content in which fake personal information in the content is converted into actual personal information based on the selected or deselected item.

[0743] The screen of the electronic device (100) displays content that has been regenerated from fake personal information into actual personal information based on the selected or deselected item. The regenerated content may include “Hello, I am Kim Sam-seong. I am a 35-year-old office worker residing in Gangnam-gu, Seoul. I work at a design company and have the strengths of being responsible for my work and diligent in all tasks.”

[0744] In one embodiment, when comparing the regenerated content with the previous content, it can be seen that the part regarding work attitude and personality has been rewritten.

[0745] FIG. 31 is a drawing illustrating an operation to request modification to generated content according to one embodiment of the present disclosure.

[0746] While FIG. 30 initiates an operation to regenerate content in which fake personal information is converted into actual personal information based on an item selected or deselected by the user, FIG. 31 may provide an interface (3111) for selecting not only the selection / deselection of an item but also the conversion intensity (e.g., high conversion level, medium conversion level, or low conversion level). FIG. 31 may include content branching from screen 3007 of FIG. 30.

[0747] In one embodiment, if the user determines that there is an error in the content converted into actual personal information, the user may select an affordance interface (e.g., “?”) for error correction.

[0748] The 3101 screen may include items converted into actual personal information (3011, 3013, 3015, 3017, 3019) and items converted into fake personal information (3012, 3014, 3016, 3018, 3020) and a re-execution interface (3021).

[0749] Referring to screens 3103 and 3105, if the user selects or deselects, for example, the employee item (3017) and changes the conversion intensity (changes from high conversion level to medium conversion level) and selects the re-execution interface (3021), the electronic device (100) can regenerate content in which fake personal information in the content has been converted into actual personal information based on the changed conversion intensity.

[0750] 3107 The electronic device (100) displays content that has been regenerated from fake personal information into actual personal information based on the selected or deselected item. The regenerated content may include “Hello, I am Kim Sam-seong. I am a 35-year-old office worker residing in Gangnam-gu, Seoul. I work at a design company, and I have the strengths of having a free and creative perspective on work, a strong sense of responsibility, and being diligent in all tasks.”

[0751] In one embodiment, when comparing the regenerated content with the previous content, it can be seen that the part regarding work attitude and personality has been rewritten.

[0752] In one embodiment, the electronic device (100) may include a communication circuit (160); a display (140); an audio device; a camera (e.g., an image sensor (150)); at least one processor (110); and a memory (120).

[0753] In one embodiment, when instructions stored in memory (120) are executed individually or collectively by at least one processor (110), the electronic device (100) may acquire data, acquire user input, determine whether the data contains personal information, and if the data contains personal information, convert the personal information into fake personal information, integrate at least one of data that does not contain personal information, data containing fake personal information, data containing actual personal information, data from which personal information is excluded, abstract information, encrypted metadata, or personal information, acquire content based on at least one of the integrated data and user input, process the content based on actual personal information, and execute the processed content.

[0754] In one embodiment, when the instructions are executed individually or collectively by at least one processor (110), the electronic device (100) may classify the sensitivity of personal information if personal information is included in the data, and based on the classified sensitivity of personal information, may not process the personal information, process the personal information as fake personal data, or exclude the personal information from the data.

[0755] In one embodiment, fake personal information can be determined based on a prompt.

[0756] In one embodiment, fake personal information may be generated to resemble actual personal information based on an analysis of actual personal information or a user's profile.

[0757] In one embodiment, the user profile may include at least one piece of information regarding the user's characteristics, tendencies, tastes, behaviors, personality, preferences, or social relationships.

[0758] In one embodiment, the content may include processed schema data.

[0759] In one embodiment, when the instructions are executed individually or collectively by at least one processor (110), the electronic device (100) may convert an area corresponding to personal information processed in the content into actual personal information based on schema data.

[0760] In one embodiment, when instructions are executed individually or collectively by at least one processor (110), the electronic device (100) may display the processed content on a display (140) or output it through a sound device when executing the processed content based on a prompt.

[0761] In one embodiment, user input may include text input and / or voice input.

[0762] In one embodiment, when the instructions are executed individually or collectively by at least one processor (110), the electronic device (100) may be able to identify information and / or information regarding files in the screen context of the screen being executed, analyze data and personal information based on the identified information, reconstruct data based on the analyzed information, and obtain content based on the reconstructed data.

[0763] In one embodiment, a method for processing information for the protection of personal information of an electronic device (100) may include: an operation of acquiring data; an operation of acquiring user input; an operation of determining whether the data contains personal information; an operation of converting the personal information into fake personal information if the data contains personal information; an operation of integrating at least one of data that does not contain personal information, data containing fake personal information, data containing actual personal information, data from which personal information is excluded, abstract information, encrypted metadata, or personal information; an operation of acquiring content based on at least one of the integrated data and user input; an operation of processing the content based on actual personal information; and an operation of executing the processed content.

[0764] In one embodiment, a method for processing information for the protection of personal information of an electronic device (100) may include: an operation of classifying the sensitivity of personal information if personal information is included in the data; and an operation of not processing personal information, treating personal information as fake personal data, or excluding personal information from the data based on the classified sensitivity of personal information.

[0765] In one embodiment, a method for processing information for the protection of personal information of an electronic device (100) may include an operation of converting an area corresponding to the personal information processed in the content into actual personal information based on schema data.

[0766] In one embodiment, a method for processing information for privacy protection of an electronic device (100) may include an operation of displaying the processed content on a display (140) or outputting it through a sound device when the processed content is executed based on a prompt.

[0767] In one embodiment, a method for processing information for the protection of personal information of an electronic device (100) may include: an action of checking information regarding information and / or files in the screen context of a running screen; an action of analyzing data and personal information based on the checked information; an action of reconstructing data based on the analyzed information; and an action of obtaining content based on the reconstructed data.

[0768] An electronic device according to one embodiment disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiment of this document is not limited to the aforementioned devices.

[0769] The embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said 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 said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "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" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as “coupled” or “connected” to another (e.g., 2nd) component, with or without the terms “functionally” or “communicationly,” it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0770] As used in one embodiment of this document, the term “module” may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0771] One embodiment of the present document may be implemented as software (e.g., a program) comprising one or more instructions stored in a storage medium (e.g., internal memory) or external memory that is readable by a machine (e.g., an electronic device (100)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (100)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to be operated 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 that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0772] According to one embodiment, the method according to one embodiment disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer 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 an application store (e.g., Play Store). TM It can be distributed online (e.g., downloaded or uploaded) through ) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0773] According to one embodiment, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to one embodiment, one or more of the components or operations among the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to one embodiment, operations performed by the module, program, or other components 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.

[0774]

Claims

1. In an electronic device, Communication circuit; display; Sound device; camera; At least one processor; and When the instructions stored in memory are executed individually or collectively by the at least one processor, the electronic device, To acquire data, It determines whether the above data contains personal information, and If the above data contains the above personal information, convert the above personal information into fake personal information, and Integrating at least one of data that does not contain personal information, data containing the fake personal information, data containing actual personal information, data from which personal information is excluded, abstract information, encrypted metadata, or the personal information, and Content is obtained based on at least one of integrated data and user input, and To process the above content based on actual personal information, and An electronic device that executes processed content.

2. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, It obtains user input, If the above data contains personal information, classify the sensitivity of the said personal information, and An electronic device that, based on the sensitivity of the classified personal information, causes the personal information to be unprocessed, the personal information to be treated as fake personal data, or the personal information to be excluded from the data.

3. In Paragraph 2, The above fake personal information An electronic device determined based on the above user input.

4. In Paragraph 2, The above fake personal information An electronic device that is generated similarly to the actual personal information based on an analysis of the actual personal information or a user profile.

5. In Paragraph 4, The above user profile is An electronic device comprising at least one piece of information regarding the characteristics, tendencies, tastes, behaviors, personality, preferences, or social relationships of the user.

6. In Paragraph 1, The above content is An electronic device containing the above-mentioned processed schema data.

7. In Paragraph 6, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that converts an area corresponding to the processed personal information in the content into the actual personal information based on the schema data.

8. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that, when executing the processed content based on the user input, displays the processed content on the display or outputs it through the sound device.

9. In Paragraph 1, The above user input is An electronic device including text input and / or voice input.

10. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Check information and / or file information in the screen context of the running screen, and Based on verified information, the above data and the above personal information are analyzed, and Reconstruct the above data based on the above analyzed information, and An electronic device that enables the acquisition of content based on the above-mentioned reconstructed data.

11. In a method for processing information for the protection of personal information of an electronic device, Operation of acquiring data; An action to determine whether the above data contains personal information; If the above data contains the above personal information, the operation of converting the above personal information into fake personal information; An operation that integrates at least one of data that does not contain personal information, data that includes the fake personal information, data that includes actual personal information, data from which personal information is excluded, abstract information, encrypted metadata, or personal information; An action of acquiring content based on at least one of integrated data and user input; The operation of processing the above content based on actual personal information; and A method including an action to execute processed content.

12. In Paragraph 11, Action of obtaining user input; If the above data contains personal information, an operation to classify the sensitivity of the said personal information; and A method comprising, based on the sensitivity of the classified personal information, an action of not processing the personal information, treating the personal information as fake personal data, or excluding the personal information from the data.

13. In Paragraph 12, The above fake personal information It is determined based on the above user input, The above fake personal information Based on an analysis of the actual personal information or the user's profile, it is generated similarly to the actual personal information, and The above user profile is including at least one piece of information regarding the characteristics, tendencies, tastes, behaviors, personality, preferences, or social relationships of the above-mentioned user The above content is A method including the above-mentioned processed schema data.

14. In Paragraph 13, A method comprising the operation of converting an area corresponding to the processed personal information in the content into the actual personal information based on the schema data.

15. In Paragraph 11, When executing the processed content based on the user input, the operation of displaying the processed content on a display or outputting it through the sound device; An action of checking information and / or file information in the screen context of the running screen; An operation to analyze the above data and the above personal information based on verified information; An operation to reconstruct the data based on the analyzed information above; A method including an operation to acquire content based on the above-mentioned reconstructed data.

Images