Operation method of electronic device for providing new counseling on basis of card selection related to fortunetelling and user's mood journal

Abstract

An operation method of an electronic device is disclosed. The operation method comprises the steps of: setting, as a counseling topic, at least one mood journal including an event that has occurred to a user and the user's mood; selecting, according to a user input of the user, at least one target card for providing counseling regarding the mood journal set as the counseling topic from among a plurality of cards related to fortunetelling; generating counseling content for the user by inputting the mood journal and information on the selected target card into a generative model; and providing the generated counseling content to the user.

Description

Method of operation of an electronic device that provides new counseling based on the selection of cards related to fortune telling and the user's emotional journal

[0001] The present disclosure relates to a method of operation of an electronic device that provides counseling based on a user's emotion journal, and more specifically, to a solution that provides a new customized user experience by generating counseling content that combines the concepts of a target card and an emotion journal.

[0002] As mental illnesses among modern people exposed to various situations and interpersonal relationships increase, multifaceted efforts are underway to prevent or treat them.

[0003] The most common means of preventing or diagnosing mental illness is consultation with professionals such as counselors or psychiatrists; recently, in terms of technology, various platforms or software programs have emerged to search for or match optimal professionals for users, or to manage or monitor the consultation process.

[0004] However, this counseling matching has the disadvantage of being difficult for general users to easily initiate, as it amounts to a fragmentary solution that merely urges a meeting with a specialist regardless of the onset or severity of symptoms when it is difficult to accurately diagnose one's current condition. Additionally, there is a conditional limitation in that one must convey past experiences, current situations, and past / present emotions within the short consultation time with the specialist.

[0005] Therefore, in addition to the need for a service that allows users to easily record their emotions in their daily lives, there is a need to provide a practical, user-customized automated counseling service that is engaging, has low barriers to access, and offers genuine comfort.

[0006] The present disclosure provides a method of operation for an electronic device that supports interesting personalized counseling for a user by automatically generating counseling content based on card selections based on the contents of a user's personal emotion journal.

[0007] The purposes of the present disclosure are not limited to those mentioned above, and other purposes and advantages of the present disclosure not mentioned may be understood from the following description and will be more clearly understood from the embodiments of the present disclosure. Furthermore, it will be readily apparent that the purposes and advantages of the present disclosure can be realized by the means and combinations thereof set forth in the claims.

[0008] A method of operating an electronic device according to one embodiment of the present disclosure comprises: setting at least one emotion log, including an event that occurred to a user and the user's emotion, as a counseling subject; selecting at least one target card among a plurality of cards related to fortune telling to provide counseling regarding the emotion log set as the counseling subject, according to the user's input; inputting information regarding the emotion log and the selected target card into a generative model to generate counseling content for the user; and providing the generated counseling content to the user.

[0009] The method of operation of the electronic device may include the steps of sequentially selecting two or more target cards among the plurality of cards according to user input, inputting the emotion log and information about each target card into the generative model for each of the selected target cards to generate individual counseling content for each target card, and generating a counseling scenario that includes individual counseling content matching each target card in order according to the order in which the target cards were selected.

[0010] At this time, the method of operation of the electronic device may include a step of determining whether correction is required for at least one of the sequential individual consultation contents constituting the consultation scenario based on the flow of the consultation scenario, and, if correction is not required, a step of providing the individual consultation contents constituting the consultation scenario to the user in order.

[0011] However, the method of operation of the electronic device may include, when correction is required, a step of obtaining a corrected counseling scenario by modifying at least one of the sequential individual counseling contents constituting the counseling scenario through the generative model, and a step of providing the individual counseling contents constituting the corrected counseling scenario in order.

[0012] The step of determining whether the above correction is necessary can determine whether each individual counseling content is connected to an individual counseling content in a previous or subsequent order, based on contextual information between the sequential individual counseling contents constituting the above counseling scenario.

[0013] The step of determining whether the above correction is necessary may involve obtaining an emotional value related to the degree of positivity or negativity for each of the sequential individual counseling contents constituting the counseling scenario, and determining whether the sum or pattern of the emotional values ​​of each of the individual counseling contents satisfies a preset condition.

[0014] Meanwhile, the method of operating the electronic device may include the steps of: sequentially selecting a first target card, a second target card, a third target card, and a fourth target card among the plurality of cards according to user input; inputting information regarding the emotion log and the selected first target card into the generative model to generate a first counseling content for the user; inputting information regarding the emotion log and the selected second target card into the generative model to generate a second counseling content for the user; inputting information regarding the emotion log and the selected third target card into the generative model to generate a third counseling content for the user; and inputting information regarding the emotion log and the selected fourth target card into the generative model to generate a fourth counseling content for the user.

[0015] In this case, the step of generating the first counseling content generates the first counseling content by inputting information regarding the emotion log and the selected first target card into the generative model and requesting an interpretation of the cause of the emotion from the generative model; the step of generating the second counseling content generates the second counseling content for the user by inputting information regarding the emotion log and the selected second target card into the generative model and requesting an additional interpretation related to situational understanding from the generative model; the step of generating the third counseling content generates the third counseling content by inputting information regarding the emotion log and the selected third target card into the generative model and requesting advice for situational improvement from the generative model; and the step of generating the fourth counseling content generates the fourth counseling content for the user by inputting information regarding the emotion log and the selected fourth target card into the generative model and requesting a prediction of the result after situational improvement from the generative model. Meanwhile, the method of operation of the electronic device may generate counseling content related to at least one card based on learning data including keywords matching each of the plurality of cards. The method may include a step of training the generative model to generate. Here, the step of generating the counseling content may involve the trained generative model generating counseling content by combining the text constituting the emotion journal and keywords matching the selected target card.

[0016] At this time, the training data may include an intrinsic keyword and a derived keyword that match each of the plurality of cards, and may include expert interpretations related to each of the plurality of cards. Furthermore, the step of training the generative model may train the generative model to generate consultation content by setting the weight for the intrinsic keyword higher than the weight for the derived keyword.

[0017] Meanwhile, the method of operating the electronic device may include the steps of: identifying a group of emotion journals in which at least one element among a person, behavior, place, and emotion appears repeatedly within a certain period among a plurality of emotion journals; providing information about the repeating element within the group to the user; and recommending fortune counseling regarding the repeating element to the user.

[0018] In this case, the method of operation of the electronic device may include the steps of selecting one major emotion journal within the group and setting the major emotion journal as the subject of consultation when a fortune consultation regarding the repeating element is requested according to user input.

[0019] At this time, the step of selecting the main emotion log may also select one main emotion log within the group according to at least one of the date of each emotion log within the group and the depth of emotion included in each emotion log within the group.

[0020] The method of operation of an electronic device according to the present disclosure can provide not only highly useful customized counseling to the user by using the user's own emotional journal as the subject of counseling, but also immersive and interesting counseling based on a medium called a fortune card.

[0021] FIG. 1 is a block diagram for explaining the configuration of an electronic device according to one embodiment of the present disclosure,

[0022] FIG. 2a is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure providing a fortune-telling consultation function based on a generative model included in an external electronic device,

[0023] FIG. 2b is a drawing for explaining the operation of an electronic device according to one embodiment of the present disclosure providing a fortune-telling consultation function based on a self-equipped generative model.

[0024] FIG. 3 is a flowchart illustrating the operation of an electronic device according to one embodiment of the present disclosure providing fortune counseling based on the selection of a target card,

[0025] FIG. 4 is a diagram illustrating the process of an electronic device according to one embodiment of the present disclosure starting to activate a fortune counseling function in accordance with user input selecting at least one emotion log,

[0026] FIGS. 5a and 5b are drawings for explaining the operation of an electronic device according to an embodiment of the present disclosure providing sequential UI (User Interface) items to support the selection of a target card,

[0027] FIG. 6 is a flowchart illustrating the operation of an electronic device according to one embodiment of the present disclosure acquiring individual consultation content for each of a plurality of target cards and verifying a consultation scenario composed of the individual consultation contents.

[0028] FIGS. 7a and 7b are drawings for illustrating specific operational examples in which an electronic device according to one embodiment of the present disclosure provides sequential consultation content based on each of the first to fourth target cards,

[0029] FIG. 8 is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure generating and providing a "heart letter" comprising additional information based on a consultation result, and

[0030] FIG. 9 is a block diagram illustrating the configuration of an electronic device according to various embodiments of the present disclosure.

[0031] Before specifically describing the present disclosure, the method of description in the specification and drawings is described.

[0032] First, the terms used in this specification and claims have been selected based on general terms considering their functions in the various embodiments of this disclosure. However, these terms may vary depending on the intent of those skilled in the art, legal or technical interpretations, and the emergence of new technologies. Additionally, some terms have been arbitrarily selected by the applicant. Such terms may be interpreted according to the meanings defined in this specification; in the absence of specific definitions, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant field.

[0033] In addition, the same reference numbers or symbols described in each drawing attached to this specification represent parts or components that perform substantially the same function. For convenience of explanation and understanding, the same reference numbers or symbols are used to describe different embodiments. That is, even if components having the same reference number are all depicted in multiple drawings, the multiple drawings do not imply a single embodiment.

[0034] Additionally, in this specification and claims, terms including ordinal numbers, such as "first," "second," etc., may be used to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from one another, and the meaning of the terms should not be limited by the use of such ordinal numbers. For example, the order of use or arrangement of components combined with such ordinal numbers should not be restricted by the number. If necessary, each ordinal number may be used interchangeably.

[0035] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0036] In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or in a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except where each needs to be implemented in specific individual hardware.

[0037] Furthermore, in the embodiments of the present disclosure, when a part is described as being connected to another part, this includes not only a direct connection but also an indirect connection through another medium. Additionally, the meaning that a part includes a certain component implies that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0038] FIG. 1 is a block diagram for explaining the configuration of an electronic device according to one embodiment of the present disclosure.

[0039] The electronic device (100) is a device for providing counseling or fortune-telling based on the user's emotions according to various embodiments of the present disclosure to be described below. The electronic device (100) may be implemented as a server composed of at least one computer, or may be implemented as various terminal devices such as a smartphone, tablet PC, PDA, desktop PC, laptop PC, kiosk, set-top box, console device, VR / AR device, wearable device, etc.

[0040] Referring to FIG. 1, the electronic device (100) may include a memory (110), a communication interface (120), a processor (130), etc.

[0041] The memory (110) is configured to store at least one instruction or data related to an operating system (OS) for controlling the overall operation of the components of the electronic device (100) and the components of the electronic device (100).

[0042] The memory (110) may include non-volatile memory such as ROM or flash memory, and may include volatile memory such as DRAM. Additionally, the memory (120) may include an auxiliary storage device such as a hard disk or an SSD (Solid State Drive).

[0043] In one embodiment, the electronic device (100) may acquire an emotion log containing events that occurred to the user and the user’s emotions related thereto and store it in memory (110).

[0044] For example, multiple emotion logs containing various events that occurred to a user and the user's emotions resulting from individual events may be stored, and the date / time when each emotion log was written, keywords regarding the emotion representing each emotion log, and keywords corresponding to each item constituting the event included in each emotion log (e.g., with whom, what, how, why) may be stored.

[0045] In one embodiment, the electronic device (100) may store information regarding a plurality of cards related to fortune in memory (110). The information regarding the plurality of cards may include, but is not limited to, the name of each card, at least one keyword matching each card (e.g., essence keyword, derivative keyword), a description of each card, and an image of each card.

[0046] For example, in the case of the Universal Waite Tarot deck, the essential keywords are set to include rich, competent, and wealthy, while the derived keywords can be set to include supportive, compensated dating, and generous.

[0047] The communication interface (120) can be connected to an external server and / or terminal device through one or more networks, and can exchange data through various wired and wireless communication methods.

[0048] Depending on the area or scale, a network may be a Personal Area Network (PAN), Local Area Network (LAN), Wide Area Network (WAN), etc., and depending on the openness of the network, it may be an Intranet, Extranet, or Internet, etc.

[0049] Wireless communication may include at least one of the following communication methods: LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th Generation) mobile communication, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), Zigbee, etc.

[0050] Wired communication may include at least one of communication methods such as Ethernet, optical network, USB (Universal Serial Bus), and Thunderbolt.

[0051] Meanwhile, communication methods are not limited to the examples described above and may include new communication methods that emerge with technological advancements.

[0052] When the electronic device (100) is implemented as a server, the electronic device (100) can communicate with at least one user terminal (e.g., smartphone, tablet PC, laptop PC, etc.) through a web page or application, and can receive user input or provide various information for the user through the user terminal. For example, the electronic device (100) can provide at least one UI (User Interface) item for writing an emotion log to the user terminal, and can acquire and store at least one emotion log according to user input received through the user terminal. In addition, the electronic device (100) can sequentially provide the stored user emotion logs through the user terminal. Furthermore, in the process of performing the fortune telling consultation function described later, the electronic device (100) can provide UI items for starting the fortune telling consultation, selecting cards, etc. through the user terminal, and can generate content corresponding to the fortune telling consultation content according to user input received through the UI items and provide it through the user terminal.

[0053] When the electronic device (100) is implemented as a terminal device such as a smartphone or tablet PC, the electronic device (100) can provide functions such as recording an emotion journal and fortune telling by executing pre-stored software or applications. At this time, the electronic device (100) can provide various UI items, receive user input, and provide content through a user input interface or display equipped with itself.

[0054] The processor (130) is connected to the memory (110) and can control the electronic device (100) by executing at least one instruction stored in the memory (110).

[0055] To this end, the processor (130) may be implemented as a general-purpose processor such as a CPU (Central Processing Unit) or AP (Application Processor), a graphics-dedicated processor such as a GPU (Graphic Processing Unit) or VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU (Neural Processing Unit). The processor (120) may include volatile memory such as SRAM.

[0056] In the case where the method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by a single processor (130) or by a plurality of processors (130) included in the electronic device (100). For example, when the first operation, the second operation, and the third operation are performed by the method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first processor, or the first operation and the second operation may be performed by a first processor (e.g., a general-purpose processor) and the third operation may be performed by a second processor (e.g., an artificial intelligence dedicated processor).

[0057] One or more processors (130) may be implemented as a single-core processor including one core, or as one or more multicore processors including multiple cores (e.g., homogeneous multicore or heterogeneous multicore). When one or more processors (120) are implemented as multicore processors, each of the multiple cores included in the multicore processor may include internal processor memory such as on-chip memory (110), and a common cache shared by the multiple cores may be included in the multicore processor (120). Additionally, each of the multiple cores included in the multicore processor (120) (or some of the multiple cores) may independently read and execute program instructions for implementing a method according to one embodiment of the present disclosure, or all (or some) of the multiple cores may be linked together to read and execute program instructions for implementing a method according to one embodiment of the present disclosure.

[0058] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one of the plurality of cores included in a multi-core processor, or may be performed by a plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first core included in a multi-core processor, or the first operation and the second operation may be performed by a first core included in a multi-core processor and the third operation may be performed by a second core included in a multi-core processor.

[0059] In embodiments of the present disclosure, the processor (130) may mean a system-on-chip (SoC) in which one or more processors and other electronic components are integrated, a single-core processor, a multi-core processor, or a core included in a single-core processor or a multi-core processor, wherein the core may be implemented as a CPU, GPU, APU, MIC, DSP, NPU, hardware accelerator or machine learning accelerator, etc., but the embodiments of the present disclosure are not limited thereto.

[0060] Referring to FIG. 1, the processor (130) can control an emotion log management module (131), a fortune counseling module (132), etc. These modules are functional unit modules implemented in software and / or hardware.

[0061] The emotion log management module (131) is a module for supporting the user's creation of an emotion log and for recording and analyzing the emotion log. To this end, the emotion log management module (131) may include a log UI module, a recording module, an analysis module, etc.

[0062] The journal UI module is a module for providing at least one UI item so that a user can write an emotion journal. For example, the electronic device (100) may provide, but is not limited to, a UI item corresponding to a note where the emotion journal is written, a UI item including at least one keypad for receiving text to be recorded in the note.

[0063] The recording module is a module for recording or managing emotion logs written by users. The recording module can classify and store emotion logs by user, and in this case, emotion logs can be registered and managed sequentially according to their date and time.

[0064] The analysis module is a module for identifying the user's psychological state or determining the main emotion by analyzing at least one emotion journal written by an individual user. To this end, the analysis module may include at least one natural language understanding module or natural language processing module for understanding the text constituting the emotion journal, and these modules can not only identify the user's emotional state contained in the text but also extract keywords corresponding to people, actions, places, times, emotions, etc. contained in the text. To this end, individual engines (e.g., BERT-based models, Transformer models, LSTM, parsing techniques, SVM, etc.) for performing intent recognition, entity extraction, sentence analysis, context understanding, and sentiment analysis, respectively, may be utilized, but are not limited thereto.

[0065] In one embodiment, the analysis module can identify the user's sequential emotional changes by analyzing multiple emotion logs sequentially written by the user, and may also numerically calculate the user's emotional fluctuations at regular intervals. For example, the greater and more frequent the emotional changes, the higher the numerical value of the emotional fluctuation may be calculated; to this end, vectors or emotional values ​​may be pre-set for each emotional state (e.g., joy, sadness, depression, anticipation). Here, the greater the difference between the vectors or emotional values ​​for an emotional change, the higher the numerical value of the emotional fluctuation may be. For example, the numerical value of the emotional fluctuation may be calculated higher for an emotional change corresponding to joy -> sadness than for an emotional change corresponding to joy -> anticipation.

[0066] Additionally, in one embodiment, the analysis module may identify a group of emotion journals in which at least one element among a person, behavior, place, and emotion appears repeatedly within a certain period. In this case, the analysis module may provide the user with information regarding the repeating element within the group. Additionally, the analysis module may recommend fortune telling consultation regarding the repeating element to the user.

[0067] For example, the analysis module can analyze multiple emotion logs sequentially written by a user to identify the user's dominant emotional state observed within a certain period. As a specific example, if the emotion logs written within a certain period contain the most entries corresponding to 'sadness,' the dominant emotional state can be identified as 'sadness.' In this case, the analysis module can recommend fortune telling consultations to the user regarding the group of emotion logs corresponding to 'sadness.'

[0068] The fortune consultation module (132) is a module for providing the fortune consultation or fortune consultation function described above. The consultation provided by the fortune consultation module (132) may correspond to consultation formats of various cultures for fortune telling based on card selection, such as Tarot cards, Oracle cards, Kamas cards, Len Normand cards, Gypsy cards, Ichaing cards, Kabbalah cards, Destiny cards, Zen cards, Love cards, etc. Alternatively, it may take the form of a new type of card-based fortune consultation in which at least one of the various consultation formats described above is modified or recombined. According to one embodiment of the present disclosure, the fortune consultation module (132) may provide a plurality of card-based consultations referred to as “Mind Tarot,” which are modified Tarot cards, but it is not necessary to be limited thereto.

[0069] The fortune telling consultation module (132) may include a card information management module, a model learning module, a consultation UI module, a consultation content generation module, etc.

[0070] The card information management module is designed to manage information regarding fortune cards that form the basis of fortune consultations. The module can manage the name, keywords, description, and images of each card; notably, the name or keywords of each card may be initially set by the administrator of the web page or application, or they may be updated or modified based on user input from the administrator.

[0071] The model training module is a module for training at least one generative model to generate fortune-telling consultation content. The generative module may be implemented as a Transformer-based model, an autoencoder model, etc., and may be a conversational model or a Large Language Model (LLM) for generating response text based on input text, but is not limited thereto.

[0072] The model training module can train a generative model to generate counseling content tailored to each card, based on information regarding multiple pre-stored cards. Specifically, the model training module can train the generative model to generate counseling content based on keywords matching each card and the emotional diaries of various users.

[0073] In one embodiment, training data for a generative model may include intrinsic keywords and derived keywords that match each of a plurality of cards. The intrinsic keywords are representative keywords representing the cards, and the derived keywords are keywords that are derived from the intrinsic keywords and are related to the cards.

[0074] In this case, the model training module can train the generative model to generate consultation content by setting the weight for intrinsic keywords (for each card) higher than the weight for derived keywords. In other words, the consultation content generated by the generative model is more likely to include content related to intrinsic keywords at a higher proportion than that related to derived keywords.

[0075] The consultation UI module is a module for providing various UI items for the user during the process of providing fortune telling consultation. Specifically, the consultation UI module can output various UI items, such as a UI item that supports selecting at least one emotion journal to be the subject of the fortune telling consultation, a UI item that supports selecting at least one target card among multiple fortune cards, a UI item that provides a description or image of the selected target card, and a UI item that provides generated consultation content.

[0076] The consultation content generation module is a module for generating the content of fortune telling consultations and may utilize the aforementioned generative model. Specifically, the consultation content generation module can generate consultation content by inputting the user's emotion journal and selected target card into the generative model trained by the aforementioned model learning module during the ongoing fortune telling consultation process.

[0077] Meanwhile, it is also possible for the generative model to be stored in an external electronic device rather than in the electronic device (100). In this case, the consultation content generation module of the electronic device (100) can communicate with the external electronic device to transmit input data for the generative model and receive consultation content generated by the generative model.

[0078] In this regard, FIGS. 2a and FIGS. 2b below are drawings illustrating cases where a generative model is provided on an external electronic device capable of communicating with the electronic device (100), and cases where a generative model is provided on the electronic device (100), respectively.

[0079] Referring to FIG. 2a, the fortune counseling module (132) communicates with an external electronic device (200) through a communication interface (120) and can generate counseling content through a generative model (201) stored in the external electronic device (200).

[0080] The external electronic device (200) may be a server of a separate platform that provides AI-based conversation or question-and-answer services. In this case, the electronic device (100) may access web pages, applications, etc. provided by the external electronic device (200) to use the generative model (201). Alternatively, the external electronic device (200) may correspond to a separate server operated by an administrator who manages platforms, software, applications, web pages, etc., for providing emotion journal recording or fortune-telling consultation functions provided through the electronic device (100).

[0081] In the case of FIG. 2a, the model learning module of the fortune counseling module (132) can request training of the generative model (201) by transmitting training data (e.g., information about each card, various emotion journal samples, counseling content written by a fortune counseling expert) to an external electronic device (200). Then, the counseling content generation module can generate counseling content through the trained generative model (201).

[0082] Meanwhile, as shown in FIG. 2b, it is also possible for the generating module (201) to be stored on the memory (110) of the electronic device (100).

[0083] The specific operation of an electronic device (100) capable of having the above-described configurations will be explained sequentially through the drawings below.

[0084] First, FIG. 3 is a flowchart illustrating the operation of an electronic device according to one embodiment of the present disclosure that provides fortune counseling based on the selection of a target card.

[0085] Referring to FIG. 3, the electronic device (100) can set at least one emotion log, including events that occurred to the user and the user's emotions, as a consultation topic (for fortune telling consultation) (S310).

[0086] For example, the electronic device (100) can set an emotion journal selected according to user input among a plurality of user emotion journals as a counseling topic.

[0087] In this regard, FIG. 4 is a diagram illustrating the process of an electronic device according to one embodiment of the present disclosure starting to activate a fortune counseling function in accordance with user input selecting at least one emotion log. Meanwhile, regarding the UI screens of the following drawings including FIG. 4 (e.g., FIG. 4, FIG. 5a to 5b, FIG. 7a to 7d, FIG. 8), when the electronic device (100) is implemented as a server, the UI screen of FIG. 4 is provided through a user terminal device capable of communicating with the electronic device (100), and when the electronic device (100) is implemented as a user terminal, it can be output on the display of the electronic device (100).

[0088] Referring to the UI screen (410) of FIG. 4, the electronic device (100) can provide summary information (411, 412) for the user's emotional journals. The summary information may include keywords related to people, actions, places, etc., in addition to emotional states (e.g., wronged, longing) representing the emotional journal.

[0089] Referring to the UI screen (420) of FIG. 4, if summary information (411) of a daily emotion log is selected on the UI screen (410), detailed information (411') containing the professional text of the corresponding emotion log may be provided. Here, a fortune telling consultation function may be activated according to user input (e.g., “Select”) of FIG. 4, which selects the corresponding emotion log as a consultation topic.

[0090] Meanwhile, the electronic device (100) may select at least one major emotional journal based on an analysis of multiple emotional journals and set it as a counseling topic. A major emotional journal is a concept that refers to an emotional journal that may be considered to require counseling from the perspective of a user or a professional. For example, a major emotional journal may correspond to an emotional journal containing situations (events) frequently faced by the user, emotions frequently experienced by the user, or pre-set types of emotions (e.g., negative emotions, depressed emotions, lonely emotions, angry emotions, etc.), but is not limited thereto.

[0091] In a related embodiment, an electronic device (100) can identify a group of emotion journals in which at least one element among a person, behavior, place, and emotion appears repeatedly within a certain period among a user's multiple emotion journals. Here, the electronic device (100) can provide the user with information about the repeating element within the group and can recommend fortune counseling regarding the repeating element to the user.

[0092] At this time, the electronic device (100) may identify a group of recurring emotion logs based on only one specific element (e.g., emotion, behavior, etc.), but may also identify a group of recurring emotion logs based on two or more elements including emotion. Specifically, the electronic device (100) may identify a group of emotion logs that include both a specific emotion and any other element (e.g., person, behavior, place, etc.). For example, if a specific emotion (e.g., tension) is identified whenever a specific person (e.g., Hong Gil-dong) appears, emotion logs containing 'Hong Gil-dong' and 'tension' may be identified as the same group, and fortune counseling may be recommended for a user who feels 'tension' when associated with 'Hong Gil-dong'.

[0093] Here, when a fortune telling consultation regarding the repeating element (or a specific emotional state related to the repeating element) is requested based on user input, the electronic device (100) can select one main emotional log within the group and set it as the consultation topic.

[0094] In the process of selecting a major emotion log, the electronic device (100) can select one major emotion log within a group according to at least one of the date of each emotion log within the group and the depth of emotion contained in each emotion log within the group.

[0095] For example, the electronic device (100) may select the most recent emotional log within the group as the main emotional log, or it may select the emotional log from the period when the frequency of emotional logs within the group was highest based on the dates / times of the emotional logs constituting the group as the main emotional log. As a specific example, assuming that within the group, sequentially, the first emotional log is May 1, the second emotional log is May 2, the third emotional log is May 3, and the fourth emotional log is May 7, the third emotional log, which has the most emotional logs confirmed within a certain period (e.g., 5 days) in the recent (past) based on the time of the individual emotional log, may be selected as the main emotional log.

[0096] Additionally, for example, an electronic device (100) can recognize the depth of emotion for each emotion journal within a group. To this end, the electronic device (100) can recognize the depth of emotion by using a table in which numerical values ​​regarding the degree to which each of the multiple words included in an individual emotion journal affects an individual emotion state (e.g., joy, sadness, depression, anticipation, tension, etc.) are pre-set, and summing the numerical values ​​regarding the degree to which each word in the emotion journal affects the corresponding emotion state. Alternatively, the electronic device (100) may use at least one artificial intelligence model (e.g., RNN, LSTM, Transformer-based model, etc.) trained to recognize text and recognize the depth of emotion (intensity of emotion). As a result, the electronic device (100) can select the emotion journal with the deepest emotional depth within the group as the primary emotion journal.

[0097] When a counseling topic is set according to at least one of the above-described embodiments, the electronic device (100) may select at least one target card among a plurality of cards related to fortune telling to provide counseling on the emotion journal set as the counseling topic, according to the user's input (S320). The selected target card may become an input to a generative model during the process of generating counseling content.

[0098] To this end, the electronic device (100) can provide UI items for explaining the concept of fortune telling, card selection, etc.

[0099] For example, referring to FIG. 5a, the electronic device (100) can provide an introduction to a character that serves as a medium for fortune counseling through a UI screen (510), provide a summary, keyword, or explanation of an emotion journal corresponding to the counseling topic through a UI screen (520), and guide the selection of a card through a UI screen (530).

[0100] And, referring to FIG. 5b, the electronic device (100) can support the selection of at least one by providing images of the backs of multiple cards that are not disclosed through a UI screen (540). As a result, an image of the selected card can be provided, such as on a UI screen (550). In FIG. 5b, four cards are recommended for selection, but this is not limited thereto, and it is obvious that only one card may be suggested or various other numbers may be suggested.

[0101] Referring to Fig. 5b, when multiple target cards are selected, the concept of the order in which the cards are selected can be recorded. That is, the order of the target cards can be performed sequentially one by one, and the selection order of each target card can be stored for consultation.

[0102] Meanwhile, in this selection process, the electronic device (100) may actually provide a back image (: card unidentifiable) that matches each of the multiple cards, thereby allowing the user to select a target card according to their selection. Alternatively, the screen images of FIGS. 5a and 5b, which show the selection of target cards one by one according to user input, may be provided, but it is also possible to simply randomly select a certain number (e.g., 4) of target cards sequentially from the multiple cards regardless of the screen images.

[0103] Alternatively, in one embodiment, the electronic device (100) may select a target card based on feedback regarding the counseling content of multiple similar users who have previously received counseling content according to the fortune-telling counseling function, based on a counseling topic corresponding to the same emotional state as the user. For example, the electronic device (100) may identify a first similar user who left the most positive review (e.g., highest rating or satisfaction for counseling) among multiple similar users. In this case, during the process of selecting a target card for counseling the user, the electronic device (100) may provide card candidates or perform automatic selection, including at least one of the target cards selected during the process of providing counseling to the first similar user. Alternatively, the electronic device (100) may identify a second similar user who left the most negative review (e.g., lowest rating or satisfaction for counseling) among multiple similar users. In this case, during the process of selecting a target card for the consultation of the above user, the electronic device (100) selects card candidates excluding all target cards that were selected during the process of providing consultation to a second similar user, and performs the selection of a target card based on user input or arbitrary selection according to the selected card candidates. Based on this selection, cases in which the consultation content of a generative model generated by combining the card's keywords and emotion log is inappropriately derived are prevented as much as possible, making it possible to maintain the service quality (consultation content) above a certain level.

[0104] Meanwhile, as described above, when a target card is selected, the electronic device (100) can input information about the emotional log corresponding to the counseling topic and the selected target card into a generative model to generate counseling content for the user (S330). Then, the electronic device (100) can provide the generated counseling content to the user (S340).

[0105] Specifically, the electronic device (100) can input text constituting an emotion journal and keywords matching a target card into a generative model, respectively. As a result, counseling content can be generated. As described above, the generative model may be a model trained based on learning data that includes keywords matching each of multiple cards, various users' emotion journals, and counseling content provided on a card basis to various users' emotion journals (e.g., an expert in fortune interpretation related to multiple cards).

[0106] Meanwhile, when multiple target cards are selected, the electronic device (100) can generate consultation content for each individual target card and configure it into a sequential scenario.

[0107] In this regard, FIG. 6 is a flowchart illustrating the operation of an electronic device according to one embodiment of the present disclosure acquiring individual consultation content for each of a plurality of target cards and verifying a consultation scenario composed of individual consultation content.

[0108] FIG. 6 is based on the premise that, according to user input, two or more target cards (e.g., first card, second card, third card, fourth card) among a plurality of cards are selected sequentially (S610).

[0109] In this case, the electronic device (100) can input information about the emotion log corresponding to the counseling topic and each selected target card into a generative model to generate individual counseling content for the user for each target card (S620).

[0110] The trained generative model can generate counseling content by combining text constituting an emotion log and keywords matching the selected target card. For example, when the keywords and emotion log of the first card are input into the generative model, a first counseling content matching the first card is generated; when the keywords and emotion log of the second card are input into the generative model, a second counseling content is generated; when the keywords and emotion log of the third card are input into the generative model, a third counseling content matching the third card is generated; and when the keywords and emotion log of the fourth card are input into the generative model, a fourth counseling content matching the fourth card is generated.

[0111] And, the electronic device (100) can generate a counseling scenario that includes individual counseling content that matches each target card in order according to the order in which the target cards are selected (S630). For example, if the first card, the second card, the third card, and the fourth card are selected in order, a counseling scenario that includes the first counseling content, the second counseling content, the third counseling content, and the fourth counseling content in order can be generated.

[0112] At this time, the electronic device (100) can determine whether correction is needed for the counseling scenario (S640). The electronic device (100) can determine whether correction is needed based on the context and / or emotional line between individual counseling contents.

[0113] If no correction is required (S640 - N), the electronic device (100) may provide individual counseling contents constituting a counseling scenario in order (S650). For example, as shown in FIGS. 7a to 7d described later, the first counseling contents, second counseling contents, third counseling contents, and fourth counseling contents may be provided in order.

[0114] On the other hand, if correction is required (S640 - Y), the electronic device (100) can obtain a corrected counseling scenario by modifying at least one of the sequential individual counseling contents that constitute the counseling scenario through a generative model (S660). Then, the electronic device (100) can provide the individual counseling contents that constitute the corrected counseling scenario in order.

[0115] Specific embodiments for determining whether correction is necessary for a consultation scenario and performing correction in relation to the above-described S640 to S660 are as follows.

[0116] First, in one embodiment, the electronic device (100) can determine whether each individual counseling content is connected to an individual counseling content in a previous or subsequent order based on context information between sequential individual counseling contents constituting a counseling scenario. If it is identified that the context is not connected, it is determined that correction is required.

[0117] In this case, the electronic device (100) can check whether the context is connected between each consultation content through the aforementioned generative model or other artificial intelligence models (e.g., BERT, GPT, Transformer-based models, etc.). At this time, the electronic device (100) can obtain an embedding vector for each sentence by performing embedding on the sentences constituting the individual consultation content using the generative model or other artificial intelligence models, and based on the embedding vector of each sentence, calculate the similarity or coherence between connected sentences and check whether the context is connected according to the corresponding value.

[0118] Additionally, in one embodiment, the electronic device (100) may acquire an emotional value related to a positive or negative degree for each of the sequential individual counseling contents constituting a counseling scenario, and determine whether the sum or pattern of the emotional values ​​of each of the individual counseling contents satisfies a preset condition. If the preset condition is not satisfied, it is determined that correction is required.

[0119] Specifically, the electronic device (100) can obtain an emotional value for each individual counseling content constituting a counseling scenario. The emotional value can be set such that, for example, the higher the positive degree, the higher the emotional value, the lower the emotional value, and the median value (neutral emotion) is set to 50. In this case, the higher the positive degree, the closer the emotional value approaches 100, and the higher the negative degree, the closer the emotional value approaches 0.

[0120] As an example of calculating an emotional value, the electronic device (100) may identify a unit value related to the degree of positivity / negativity of each word constituting the individual counseling content, and obtain an emotional value related to the degree of positivity / negativity of the individual counseling content by summing the unit values ​​of each word or calculating the average thereof. To this end, at least one pre-stored emotional word dictionary in which unit values ​​are pre-set for each word may be utilized, but is not limited thereto.

[0121] As another example, the electronic device (100) can obtain the degree of positivity / negativity of individual counseling content by inputting individual counseling content into at least one artificial intelligence model (e.g., LSTM, BERT, etc.) for identifying emotional states. To this end, the artificial intelligence model may be an artificial intelligence model in which an output layer is designed to output an emotional value related to the degree of positivity / negativity.

[0122] When an emotional value of an individual counseling content is obtained according to at least one of the embodiments described above, the electronic device (100) can determine whether the sum or pattern of the emotional values ​​satisfies a preset condition.

[0123] The preset conditions may include, for example, at least one of the conditions in which the emotional values ​​of each individual counseling content do not exceed a first threshold range (e.g., 50 to 70) and the sum of the emotional values ​​does not exceed a second threshold range. The second threshold range may correspond to, for example, a range from the value obtained by multiplying the number of selected target cards (e.g., 4), the minimum value of the first threshold range (e.g., 50), and the preset coefficient (e.g., 0.8) to the value obtained by multiplying the number of selected target cards (e.g., 4), the maximum value of the first threshold range (e.g., 70), and the preset coefficient (e.g., 0.8) (e.g., 160 to 224), but is not limited thereto.

[0124] In this regard, if the above-mentioned preset conditions (first threshold range, second threshold range) are not satisfied as a result of excessively positive or negative emotional lines appearing in the overall counseling scenario as well as in the individual counseling content, the electronic device (100) may be determined to require correction.

[0125] At this time, the electronic device (100) can modify at least one individual counseling content to satisfy both the first threshold range and the second threshold range described above. Specifically, the electronic device (100) can select the individual counseling content that deviates most from the median value (e.g., 60) of the first threshold range and input the individual counseling content into a generative model so that the emotional value of the selected individual counseling content moves from the existing value toward the median value described above. For example, if the emotional value of the second counseling content that matches the second target card is 75, the electronic device (100) can input a request to the generative model to change the second counseling content so that the positive degree is lowered, and as a result, the modified second counseling content can be obtained.

[0126] In this case, the electronic device (100) can determine whether the pre-set conditions (first threshold range, second threshold range) are satisfied again for a counseling scenario in which the existing second counseling content is replaced with modified second counseling content. If it is not satisfied again, the electronic device (100) can select the individual counseling content that deviates the most from the median value of the first threshold range again and repeat the same process.

[0127] Meanwhile, a pre-set condition may be established for the difference in emotional values ​​between consecutive individual counseling contents. For example, a condition may be included in which the difference in emotional values ​​between consecutive individual counseling contents does not exceed a third threshold range (e.g., 5 to 15).

[0128] In this case, for example, if the emotional value of the first counseling content of the first target card is 50 and the emotional value of the second counseling content of the subsequent second target card is 67, it may be determined that correction is required because the pre-set conditions are not satisfied. For example, if the emotional value of the third counseling content of the third target card is 60 and the emotional value of the fourth counseling content of the subsequent fourth target card is 63, it may also be determined that correction is required because the pre-set conditions are not satisfied. As a result, not only are abrupt changes in the emotional line in the counseling scenario avoided, but overly monotonous patterns can also be prevented.

[0129] In cases where the preset condition (third threshold range) is not satisfied, the electronic device (100) can modify at least one individual counseling content so that the difference in emotional values ​​between consecutive individual counseling contents satisfies the condition. At this time, the electronic device (100) can select and modify at least one individual counseling content so that modifications are made only to a minimum number of individual counseling contents and a minimum change in emotional values ​​based on the initial counseling scenario. Then, modifications to the selected individual counseling content can be carried out in a direction to satisfy the preset condition (third threshold range) through the generative model described above.

[0130] As an additional example, the pre-set conditions may include a separate fourth threshold range for the emotional value of individual counseling content corresponding to a specific sequence. For instance, for the individual counseling content in the last sequence (e.g., the fourth counseling content of the fourth target card), a fourth threshold range of 65 to 70, which is relatively close to a positive value, may be set. Similarly, if the emotional value of the individual counseling content in that sequence falls outside the fourth threshold range, the individual counseling content may be modified. As a result, the conclusion of the counseling scenario can be provided in a relatively positive / hopeful manner.

[0131] Meanwhile, regarding the various pre-set conditions mentioned above related to emotional values ​​(e.g., first to fourth threshold ranges), only one of them may be utilized, or two or more conditions may be applied in parallel to proceed with modifications to satisfy the conditions.

[0132] Thus, the electronic device (100) according to the present disclosure can improve the quality of the overall counseling by providing counseling content corresponding to each of the sequentially selected target cards, thereby providing counseling content according to the characteristics (e.g., keywords) of each card without omission, while ensuring that the counseling content is linked to one another and emotionally naturally connected.

[0133] Meanwhile, FIGS. 7a to 7d are drawings for explaining specific operational examples in which an electronic device according to one embodiment of the present disclosure provides sequential consultation content based on each of the first to fourth target cards. With reference to these drawings, it was confirmed that when four target cards corresponding to the following four processes are selected sequentially to generate consultation content, very effective and interesting consultation results are derived by reflecting the knowledge of an actual fortune-telling (e.g., Tarot) expert and the actual utilization results of a generative model.

[0134] In other words, not only keywords from emotion logs and target cards, but also specific counseling items can be input into the generative model in sequential order as follows.

[0135] Counseling Item 1. Interpretation of the Cause of Emotions

[0136] Consultation Item 2. Interpretation of Additional Information to Understand the Situation

[0137] Consultation Item 3. Advice for Improving the Situation

[0138] Consultation Item 4. Results after situation improvement

[0139] FIGS. 7a to 7d below are based on the premise that first to fourth counseling contents are generated according to each of the four counseling items described above based on the first to fourth target cards, and that a counseling scenario containing the first to fourth counseling contents generated in this way satisfies the pre-set conditions described above (with or without modification).

[0140] First, referring to FIG. 7a, the electronic device (100) can provide UI screens (711, 712) for the process of verifying the first target card, which is the first card. Then, the electronic device (100) can provide first consultation content included in the consultation scenario (713, 714).

[0141] The first counseling content provided here corresponds to the result of the electronic device (100) inputting information about the emotion log and the first target card into the generative model and requesting an interpretation of the cause of the emotion from the generative model, and may have been modified depending on whether the initial counseling scenario (first to fourth counseling content) satisfies the pre-set conditions.

[0142] Next, referring to FIG. 7b, the electronic device (100) can provide UI screens (721, 722) for the process of verifying the second target card, which is the second card. And, the electronic device (100) can provide second counseling content included in the counseling scenario (723).

[0143] The second counseling content provided here corresponds to the result of the electronic device (100) requesting additional interpretation related to situational understanding from the generative model while inputting information about the emotion log and the second target card into the generative model, and may have been modified depending on whether the initial counseling scenario (first to fourth counseling content) satisfies pre-set conditions.

[0144] Next, referring to FIG. 7c, the electronic device (100) can provide UI screens (731, 732) for the process of verifying the third target card, which is the third card. And, the electronic device (100) can provide third counseling content included in the counseling scenario (733, 734).

[0145] The third counseling content provided here corresponds to the result of the electronic device (100) inputting information about the emotion log and the third target card into the generative model and requesting advice for situation improvement from the generative model, and may have been modified depending on whether the initial counseling scenario (first to fourth counseling content) satisfies the pre-set conditions.

[0146] Finally, referring to FIG. 7d, the electronic device (100) can provide UI screens (741, 742) for the process of verifying the fourth target card, which is the fourth card. Also, the electronic device (100) can provide fourth counseling content included in the counseling scenario (743, 745, 746).

[0147] The fourth counseling content provided here corresponds to the result of the electronic device (100) inputting information about the emotion log and the fourth target card into the generative model and requesting a prediction of the result after the situation improvement from the generative model, and may have been modified depending on whether the initial counseling scenario (first to fourth counseling content) satisfies the pre-set conditions.

[0148] Thus, the electronic device (100) according to the present disclosure can construct a consultation scenario by configuring consultation content corresponding to sequentially designed consultation items according to the keywords of each target card in a natural flow, and can provide a consultation scenario as if explaining the solution of sequential target cards based on a visual UI composed of familiar characters as shown in FIGS. 7a to 7d. This user experience is attributed to the method of operation of the electronic device (100) according to the present disclosure, which corresponds to technical content that did not exist in the prior art.

[0149] Meanwhile, the electronic device (100) according to one embodiment of the present disclosure may provide at least one additional function even after providing individual counseling content according to a counseling scenario as described above. The additional function may include, but is not limited to, recording counseling content, generating a heart letter according to counseling content, providing a summary of advice according to counseling content, and providing information on the emotional state to be induced through counseling.

[0150] In this regard, the electronic device (100) may generate a heart letter containing counseling content according to the fortune-telling counseling function described above (e.g., at least one of the first to fourth counseling content). At this time, the heart letter may include the entire counseling scenario, or may include content summarizing the counseling scenario or individual counseling content. To this end, the electronic device (100) may utilize at least one natural language processing module for summarizing text, but is not limited thereto.

[0151] The heart letter generated in this way can be provided to the user at a time desired by the user, depending on user input.

[0152] In this regard, FIG. 8 is a diagram illustrating the operation of an electronic device according to one embodiment of the present disclosure to generate and provide a heart letter comprising additional information based on the consultation result.

[0153] The UI screen (810) of FIG. 8 corresponds to a screen containing a plurality of emotion stones (811, 812, 813) to interestingly display the results of the electronic device (100) recording the user's emotion journal. Each of the plurality of emotion stones stacked sequentially from the bottom visualizes the shape of emotions accumulating according to the emotion journal written sequentially, and the shape of each emotion stone may change depending on the emotion state matched to each emotion journal.

[0154] Here, when the fortune-telling consultation function described above is performed on the emotional log that matches the emotional stone (813), the electronic device (100) may generate a heart letter according to the consultation scenario or individual consultation content derived from the fortune-telling consultation, and may provide a UI item (813') for checking the heart letter on the UI screen (810). At this time, the UI item (813') may be displayed in a form pointing to the emotional stone (813) that was the consultation topic that matched the heart letter.

[0155] Here, when the corresponding UI item (813') is selected according to user input, the electronic device (100) may provide a UI screen (820) containing the entire content of the heart letter. Additionally, the electronic device (100) may provide a UI screen (830) for providing only the advice content regarding future actions from the content of the heart letter.

[0156] Meanwhile, the electronic device (100) may also identify a positive target emotional state recommended according to the fortune telling consultation (: mind tarot). To do this, the electronic device (100) may analyze text of ‘advice to improve the situation’ or ‘prediction of results after improving the situation’ among the consultation contents to identify at least one target emotional state related thereto. For example, if consultation contents such as ‘take it easy’ or ‘you will be able to reach a relaxed state’ are provided, the target emotional state may be identified as ‘relaxation’.

[0157] At this time, the electronic device (100) can select at least one emotion journal that matches the target emotion state (e.g., comfort) among the user's multiple emotion journals, and can provide a UI item for viewing the emotion journal that matches the target emotion state, as in the UI screen (830) described above. As a result, the user can come closer to a positive target emotion state that matches the counseling content by looking back on past positive emotion journals or events that placed them in the target emotion state.

[0158] Meanwhile, FIG. 9 is a block diagram for explaining the configuration of an electronic device according to various embodiments of the present disclosure.

[0159] Referring to FIG. 9, the electronic device (100) may further include a display (140), a user input interface (150), etc. in addition to a memory (110), a communication interface (120), and a processor (130).

[0160] For example, if the electronic device (100) is implemented as a user terminal such as a smartphone, tablet PC, or laptop PC, the electronic device (100) may further include a display (140), a user input interface (150), etc.

[0161] The display (140) is configured to visually provide various information and may be composed of LED, OLED, LCD, etc., but is not limited thereto. The electronic device (100) can visually output the various UI screens or UI items described above through the display (140).

[0162] The user input interface (150) is configured to receive various commands or information from a user and may include, but is not limited to, at least one button, keypad, microphone, camera, touch panel, various sensors, etc. However, the electronic device (100) may also receive user input from an external user input device (e.g., keyboard, mouse, controller, etc.) connected through a communication interface (120).

[0163] Specifically, the electronic device (100) may create an emotion journal or select at least one emotion journal as a counseling topic for the fortune counseling function based on user input received through the user input interface (150). Additionally, the electronic device (100) may obtain user input through the user input interface (150) to proceed with various step-by-step procedures, such as selecting a card, checking a card, or viewing counseling content, during the process of the fortune counseling function (Mind Tarot).

[0164] Meanwhile, the various embodiments described above may be implemented by combining two or more embodiments, provided that they do not conflict or contradict each other.

[0165] Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

[0166] According to hardware implementation, the embodiments described in this disclosure may be implemented using at least one of ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, and other electrical units for performing functions.

[0167] In some cases, the embodiments described herein may be implemented as the processor itself. In a software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software modules. Each of the aforementioned software modules may perform one or more functions and operations described herein.

[0168] Meanwhile, computer instructions or computer programs for performing processing operations in an electronic device (100), etc., according to various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. When such computer instructions or computer programs stored in the non-transitory computer-readable medium are executed by a processor of a specific device, the specific device described above performs processing operations in an electronic device (100), etc., according to various embodiments described above.

[0169] A non-transient computer-readable medium refers to a medium that stores data semi-permanently and can be read by a device, unlike media that store data for a short period of time such as registers, caches, and memory. Specific examples of non-transient computer-readable media include CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, and ROMs.

[0170] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure.

Claims

1. In a method of operating an electronic device, A step of setting at least one emotion journal, including events that occurred to the user and the user's emotions, as a counseling topic; A step of selecting at least one target card among a plurality of cards related to fortune telling to provide counseling regarding the emotion journal set as the counseling topic, according to the user input of the above user; A step of inputting information regarding the above emotion log and the above selected target card into a generative model to generate counseling content for the user; and A method of operating an electronic device comprising the step of providing the generated consultation content to the user.

2. In Paragraph 1, The method of operation of the above electronic device is, A step of sequentially selecting two or more target cards among the plurality of cards according to user input; For each of the selected target cards, a step of inputting the emotion log and information regarding each target card into the generative model to generate individual counseling content for each target card; and A method of operating an electronic device comprising the step of generating a counseling scenario that includes, in order, individual counseling contents that match each target card according to the order in which the target cards are selected.

3. In Paragraph 2, The method of operation of the above electronic device is, A step of determining whether correction is required for at least one of the sequential individual counseling contents constituting the counseling scenario based on the flow of the counseling scenario; and A method of operating an electronic device comprising the step of providing the user with individual consultation contents constituting the consultation scenario in sequence when the above correction is not required.

4. In Paragraph 3, The method of operation of the above electronic device is, If the above correction is necessary, a step of obtaining a corrected counseling scenario by modifying at least one of the sequential individual counseling contents constituting the counseling scenario through the generative model; and A method of operating an electronic device comprising the step of providing individual counseling contents constituting the above-mentioned corrected counseling scenario in sequence.

5. In Paragraph 3, The step of determining whether the above correction is necessary is, A method of operation of an electronic device for determining whether each individual consultation content is connected to an individual consultation content in a previous or subsequent order, based on context information between sequential individual consultation contents constituting the above consultation scenario.

6. In Paragraph 3, The step of determining whether the above correction is necessary is, For each of the sequential individual counseling contents constituting the above counseling scenario, an emotional value related to the degree of positivity or negativity is obtained, and A method of operation of an electronic device for determining whether the sum or pattern of emotional values ​​of each of the above individual counseling contents satisfies a preset condition.

7. In Paragraph 2, A step of sequentially selecting a first target card, a second target card, a third target card, and a fourth target card among the plurality of cards according to user input; A step of inputting information regarding the above emotion log and the above selected first target card into the above generative model to generate first counseling content for the user; A step of inputting information regarding the above emotion log and the above selected second target card into the above generative model to generate second counseling content for the user; A step of inputting information regarding the above emotion log and the above selected third target card into the above generative model to generate third counseling content for the user; and A method of operating an electronic device comprising the step of inputting information regarding the above-mentioned emotion log and the above-mentioned selected fourth target card into the above-mentioned generative model to generate a fourth counseling content for the user.

8. In Paragraph 7, The step of generating the above-mentioned first consultation content is, While inputting information regarding the above emotion log and the above-selected first target card into the generative model, requesting an interpretation of the cause of the emotion from the generative model to generate the first counseling content, The step of generating the above second consultation content is, While inputting information regarding the above emotion log and the above selected second target card into the generative model, requesting additional interpretation related to situational understanding from the generative model to generate second counseling content for the user, The step of generating the above third consultation content is, While inputting information regarding the above emotion log and the above selected third target card into the above generative model, requesting advice for situation improvement from the above generative model to generate third counseling content, and The step of generating the above-mentioned fourth consultation content is, A method of operation of an electronic device, wherein information regarding the above-mentioned emotion log and the above-mentioned selected fourth target card is input into the above-mentioned generative model, and a prediction of the result after situation improvement is requested from the above-mentioned generative model to generate a fourth counseling content for the user.

9. In Paragraph 1, The method of operation of the above electronic device is, The method includes the step of training the generative model to generate counseling content related to at least one card based on training data containing keywords matching each of the plurality of cards; The step of generating the above consultation content is, A method of operation of an electronic device in which the above-mentioned trained generative model generates counseling content by combining text constituting the above-mentioned emotion journal and keywords matching the above-mentioned selected target card.

10. In Paragraph 9, The above training data is, Includes an essential keyword and a derived keyword that match each of the aforementioned plurality of cards, It includes expert interpretations related to each of the aforementioned plurality of cards, The step of training the above generative model is, A method of operation of an electronic device for training a generative model to generate consultation content by setting the weight for intrinsic keywords higher than the weight for derived keywords.

11. In Paragraph 1, The method of operation of the above electronic device is, A step of identifying a group of emotion diaries in which at least one element among person, behavior, place, and emotion appears repeatedly within a certain period among a plurality of emotion diaries; A step of providing the user with information about repeating elements within the group; and A method of operating an electronic device comprising the step of recommending fortune counseling regarding the repeating elements to the user.

12. In Paragraph 11, The method of operation of the above electronic device is, When a fortune consultation regarding the above-mentioned repeating elements is requested based on user input, the step of selecting one major emotion journal within the above group; and A method of operating an electronic device comprising the step of setting the above-mentioned main emotion log as a counseling topic.

13. In Paragraph 12, The step of selecting the above main emotion log is, A method of operation of an electronic device for selecting one main emotion log within a group according to at least one of the date of each emotion log within the group and the depth of emotion contained in each emotion log within the group.

Images