system

Abstract

The system according to this embodiment aims to store memories as a digital archive, verify their reliability, and then output them in an appropriate format. [Solution] The system according to the embodiment comprises a language conversion unit, a categorization unit, a reliability verification unit, and a selection unit. The language conversion unit converts memories into language, such as voice or text, and converts them into data. The categorization unit categorizes the information converted into data by the language conversion unit. The reliability verification unit verifies the reliability of the information categorized by the categorization unit. The selection unit selects an output format based on the information verified by the reliability verification unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that memory is not sufficiently saved as a digital archive, and output in an appropriate format after confirming reliability.

[0005] The system according to the embodiment aims to save memory as a digital archive and output it in an appropriate format after confirming reliability.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a language conversion unit, a categorization unit, a reliability verification unit, and a selection unit. The language conversion unit converts memories into language, such as speech or text, and digitizes them. The categorization unit categorizes the information digitized by the language conversion unit. The reliability verification unit verifies the reliability of the information categorized by the categorization unit. The selection unit selects an output format based on the information verified by the reliability verification unit. [Effects of the Invention]

[0007] The system according to this embodiment can store memories as a digital archive and output them in an appropriate format after verifying their reliability. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The digital archiving system according to an embodiment of the present invention is a system that verbalizes memories into audio or text, categorizes them by event such as place, person, or object, and digitally archives them as data heritage. This digital archiving system verbalizes memories into audio or text and converts them into data. At this time, themes and keywords are extracted, and related information is also attached. Next, the listed information is compared with similar information and fake information, and the percentage of truth or falsehood is displayed. After that, the scrutinized data is categorized and digitally archived. Furthermore, the output format can be selected as a means of transmitting memory data. In addition, the intended target, story, genre / emotion, concept, etc. can be set, and the story and output format can be freely selected by combining memory data and settings. For example, the digital archiving system verbalizes memories into audio or text and converts them into data. For example, the digital archiving system extracts themes and keywords, and related information is also attached. Next, the digital archiving system compares the listed information with similar information and fake information, and the percentage of truth or falsehood is displayed. Next, the digital archiving system categorizes the scrutinized data and digitally archives it. Furthermore, digital archiving systems can select the output format as a means of transmitting memory data. For example, a digital archiving system can set the intended target, story, genre / emotion, concept, etc. For instance, a digital archiving system can freely select the story and output format by combining memory data and settings. This allows digital archiving systems to efficiently verbalize, categorize, verify the reliability of memories, and select the output format.

[0029] The digital archive system according to this embodiment comprises a language conversion unit, a categorization unit, a reliability verification unit, and a selection unit. The language conversion unit converts memories into language, such as speech or text, and digitizes them. The language conversion unit converts memories from speech to text using, for example, speech recognition technology. The language conversion unit can also convert memories into text using a text conversion algorithm. Furthermore, the language conversion unit can convert memories into text using a text conversion algorithm. The language conversion unit can also convert memories into speech or text using a generative AI. The categorization unit categorizes the digitized information by event, such as land, people, or objects. The categorization unit categorizes the digitized information by event, such as land, people, or objects, using, for example, a classification algorithm. For example, the categorization unit uses a classification algorithm to categorize the digitized information by event, such as land, people, or objects. The categorization unit can also categorize the digitized information based on category definitions. Furthermore, the categorization unit can use generative AI to categorize the digitized information by event, such as land, people, or objects. The reliability verification unit compares the listed information with similar and fake information and displays the percentage of truth or falsity. For example, the reliability verification unit verifies the source of the information to confirm its reliability. Furthermore, the reliability verification unit can perform reliability scoring to confirm the reliability of the listed information. Furthermore, the reliability verification unit can use generating AI to compare the listed information with similar or fake information and display the percentage of truthfulness.For example, the reliability verification unit uses a generation AI to compare the listed information with similar or fake information and displays the percentage of truth or falsity. The selection unit selects the output format from text, video, audio, etc. The selection unit selects the output format from text, video, audio, etc., based on, for example, the selection criteria for the output format. The selection unit can also select the output format from text, video, audio, etc., based on the user's preference. The selection unit can also select the output format from text, video, audio, etc., based on the user's preference. Furthermore, the selection unit can also select the output format from text, video, audio, etc., using a generation AI. The selection unit can also select the output format from text, video, audio, etc., using a generation AI. As a result, the digital archive system according to this embodiment can efficiently verbalize memories, categorize them, verify their reliability, and select the output format.

[0030] The language processing unit translates memories into speech, text, and other forms of data. Specifically, it uses speech recognition technology to convert memories from speech to text. Speech recognition technology is a process that analyzes speech signals and converts speech to text using a language model. For example, speech recognition technology extracts features from speech signals and maps them to phonemes and words to convert speech to text. The language processing unit can also convert memories to text using a text conversion algorithm. A text conversion algorithm is a technology that converts handwritten or printed characters into digital text, and often utilizes optical character recognition (OCR) technology. OCR technology is a process that recognizes characters from images acquired by a scanner or camera and converts them into digital text. Furthermore, the language processing unit can also use generative AI to translate memories into speech, text, and other forms of data. Generative AI utilizes natural language processing technology to analyze input information and convert it into appropriate linguistic expressions. For example, generative AI analyzes speech input and generates appropriate text according to the context. Generative AI also analyzes text input and generates natural linguistic expressions considering the appropriate use of grammar and vocabulary. This allows the language processing unit to handle diverse input formats and efficiently and accurately verbalize memories.

[0031] The categorization unit categorizes digitized information by event, such as land, people, or objects. Specifically, it uses classification algorithms to categorize digitized information by event, such as land, people, or objects. A classification algorithm is a technology that analyzes the characteristics of data and classifies it into predefined categories. For example, information about land is categorized based on geographical characteristics and location information, and information about people is categorized based on names and attribute information. Information about objects is categorized based on the characteristics and uses of the object. Furthermore, the categorization unit can also categorize digitized information based on category definitions. Category definitions can be flexibly set according to user needs and system requirements. For example, custom categories can be defined to categorize information related to a specific project or research. In addition, the categorization unit can also categorize digitized information by event, such as land, people, or objects, using generative AI. Generative AI analyzes the context and meaning of the data and classifies it into the appropriate category. For example, the generative AI analyzes the content of text data and automatically identifies the relevant categories. It can also analyze image and audio data and classify them into appropriate categories. This allows the categorization unit to handle diverse data formats and categorize information efficiently and accurately.

[0032] The reliability verification unit compares the listed information with similar and fake information and displays the percentage of truth or falsehood. Specifically, it verifies the source of the information to confirm its reliability. Source verification is the process of investigating the origin and citation of information and evaluating its reliability. For example, the reliability verification unit verifies whether the information source is from a reliable organization or expert. The reliability verification unit can also perform reliability scoring to confirm the reliability of the listed information. Reliability scoring is a technique that quantifies and evaluates the reliability of information. For example, the reliability verification unit evaluates the source of the information, the accuracy of the content, and the appropriateness of the citations to calculate a reliability score. Furthermore, the reliability verification unit can also use generative AI to compare the listed information with similar and fake information and display the percentage of truth or falsehood. Generative AI is a technique that analyzes large amounts of data and evaluates the truth or falsehood of information. For example, the generative AI collects information similar to the listed information from the internet and evaluates the degree of content similarity and reliability. Furthermore, the generating AI learns the characteristics of fake information and evaluates the likelihood that the listed information is fake. As a result, the reliability verification unit can evaluate the reliability of the information with high accuracy and provide users with reliable information.

[0033] The selection unit chooses the output format from options such as text, video, and audio. Specifically, it selects the output format from text, video, and audio based on selection criteria. The selection criteria are set according to the user's needs and the characteristics of the content. For example, text format is suitable for providing detailed information, video format is suitable for effectively conveying visual information, and audio format is suitable for providing auditory information. Furthermore, the selection unit can also select the output format from text, video, and audio based on the user's preferences. User preferences are collected through surveys and feedback and reflected in the system. For example, if the user prefers visual information, video format will be selected. If the user requests detailed information, text format will be selected. Furthermore, the selection unit can also use generative AI to select the output format from text, video, and audio. Generative AI analyzes the characteristics of the content and the user's needs and automatically selects the optimal output format. For example, the generative AI analyzes the content and the user's past selection history to suggest the optimal output format. Furthermore, the generation AI can collect user feedback in real time and continuously improve its output format selection. This allows the selection unit to provide the user with the optimal output format, maximizing the effectiveness of information transmission.

[0034] It includes a settings section for setting the target audience, story, genre / emotion, and concept. The settings section can, for example, set the target audience. It can also set the story. Furthermore, it can set the genre / emotion. Finally, it can set the concept. This allows users to freely select settings as a means of transmitting memory data.

[0035] The company has a business department that franchises and monetizes the accumulated data and templated output formats. For example, the business department can franchise the accumulated data. For example, the business department can franchise the accumulated data. The business department can also franchise the templated output formats. For example, the business department can franchise the templated output formats. Furthermore, the business department can monetize the accumulated data. For example, the business department can monetize the accumulated data. Furthermore, the business department can also monetize the templated output formats. For example, the business department can monetize the templated output formats. This allows the accumulated data and output formats to be used for business development.

[0036] The language processing unit verbalizes memories into audio, text, and other forms of data. For example, the language processing unit can use speech recognition technology to convert memories from audio to text. Furthermore, the language processing unit can also use a text conversion algorithm to convert memories into text. In addition, the language processing unit can use generative AI to verbalize memories into audio or text. This process of verbalizing memories into audio or text and digitizing them makes memory storage easier.

[0037] The categorization unit categorizes digitized information by event, such as land, people, or objects. For example, the categorization unit uses a classification algorithm to categorize digitized information by event, such as land, people, or objects. The categorization unit can also categorize digitized information based on category definitions. Furthermore, the categorization unit can use generative AI to categorize digitized information by event, such as land, people, or objects. This categorization of digitized information by event makes it easier to organize the information.

[0038] The reliability verification unit compares the listed information with similar and fake information and displays the percentage of truth or falsehood. For example, the reliability verification unit verifies the source of the information to confirm its reliability. The reliability verification unit can also perform reliability scoring to confirm the reliability of the listed information. Furthermore, the reliability verification unit can use generation AI to compare the listed information with similar and fake information and display the percentage of truth or falsehood. This verifies the reliability of the information and displays the percentage of truth or falsehood, thereby improving the accuracy of the information.

[0039] The selection unit selects the output format from options such as text, video, and audio. For example, the selection unit selects the output format from options such as text, video, and audio based on the selection criteria for the output format. The selection unit can also select the output format from options such as text, video, and audio based on the user's preference. Furthermore, the selection unit can use generative AI to select the output format from options such as text, video, and audio. This allows information to be transmitted in the format desired by the user by selecting the output format.

[0040] The verbalization unit adjusts the level of detail in verbalization based on the importance of the memory. For example, the verbalization unit verbalizes important memories in detail and records even the smallest details. For example, the verbalization unit verbalizes important memories in detail and records even the smallest details. The verbalization unit can also verbalize less important memories concisely and record only the main points. For example, the verbalization unit verbalizes less important memories concisely and records only the main points. Furthermore, the verbalization unit can add detailed explanations and background information depending on the importance of the memory. For example, the verbalization unit can add detailed explanations and background information depending on the importance of the memory. In this way, by adjusting the level of detail in verbalization according to the importance of the memory, important memories can be recorded in detail.

[0041] The verbalization unit applies different verbalization algorithms depending on the category of memory during the verbalization process. For example, when verbalizing memories about people, the verbalization unit emphasizes the characteristics and relationships of the people. For example, when verbalizing memories about people, the verbalization unit emphasizes the characteristics and relationships of the people. Furthermore, when verbalizing memories about objects, the verbalization unit can emphasize the details and usage of the objects. For example, when verbalizing memories about objects, the verbalization unit emphasizes the details and usage of the objects. In addition, when verbalizing memories about places, the verbalization unit can emphasize the geographical characteristics and historical background. For example, when verbalizing memories about places, the verbalization unit emphasizes the geographical characteristics and historical background. By applying different verbalization algorithms depending on the category of memory, more appropriate verbalization becomes possible.

[0042] The verbalization unit determines the priority of verbalization based on the timing of memory formation. For example, the verbalization unit prioritizes verbalizing recent memories and recording them while they are still vivid. The verbalization unit can also postpone older memories and verbalize them according to their importance. Furthermore, the verbalization unit can verbalize memories chronologically based on the timing of memory formation. This allows for the prioritization of verbalization based on the timing of memory formation, enabling the recording of vivid memories to be prioritized.

[0043] The verbalization unit adjusts the order of verbalization based on the relevance of memories. For example, the verbalization unit can verbalize related memories together to create continuity. For example, the verbalization unit can verbalize related memories together to create continuity. The verbalization unit can also verbalize less relevant memories individually, creating independent records. For example, the verbalization unit can verbalize less relevant memories individually, creating independent records. Furthermore, the verbalization unit can prioritize verbalizing important memories based on their relevance. For example, the verbalization unit prioritizes verbalizing important memories based on their relevance. This allows for a continuous record by adjusting the order of verbalization based on the relevance of memories.

[0044] The categorization unit improves the accuracy of categorization by considering the interrelationships of memories during the categorization process. For example, the categorization unit groups related memories and clarifies their interrelationships. The categorization unit can also subdivide categories based on the interrelationships of memories. For example, the categorization unit subdivides categories based on the interrelationships of memories. Furthermore, the categorization unit can categorize in a way that avoids duplication by considering the interrelationships of memories. For example, the categorization unit categorizes in a way that avoids duplication by considering the interrelationships of memories. As a result, categorizing while considering the interrelationships of memories leads to a more accurate organization of information.

[0045] The categorization unit considers the location where memories originate and the attribute information of individuals when categorizing. For example, the categorization unit sets geographical categories based on the location where memories originate. The categorization unit can also set person categories based on the attribute information of individuals. Furthermore, the categorization unit can combine the location where memories originate and the attribute information of individuals to set complex categories. By categorizing while considering the location where memories originate and the attribute information of individuals, the organization of information becomes more appropriate.

[0046] The categorization unit considers the geographical distribution of memories when categorizing. For example, the categorization unit categorizes by region based on the geographical distribution of memories. The categorization unit can also group related regions while considering geographical distribution. For example, the categorization unit groups related regions while considering geographical distribution. Furthermore, the categorization unit can subdivide categories based on geographical distribution. For example, the categorization unit subdivides categories based on geographical distribution. This makes it possible to organize information by region by categorizing while considering the geographical distribution of memories.

[0047] The categorization unit improves the accuracy of categorization by referring to related literature during the categorization process. For example, the categorization unit sets categories for memories by referring to related literature. For example, the categorization unit sets categories for memories by referring to related literature. The categorization unit can also clarify the interrelationships of memories based on related literature. For example, the categorization unit clarifies the interrelationships of memories based on related literature. Furthermore, the categorization unit can categorize in a way that avoids duplication by referring to related literature. For example, the categorization unit categorizes in a way that avoids duplication by referring to related literature. As a result, categorizing by referring to related literature for memories leads to a more accurate organization of information.

[0048] The reliability verification unit evaluates the reliability of memories by thoroughly analyzing the sources and information sources during reliability verification. For example, the reliability verification unit can thoroughly analyze the sources and evaluate their reliability. For example, the reliability verification unit can thoroughly analyze the sources and evaluate their reliability. The reliability verification unit can also evaluate the reliability of information sources and verify the reliability of memories. For example, the reliability verification unit can evaluate the reliability of information sources and verify the reliability of memories. Furthermore, the reliability verification unit can evaluate reliability based on a detailed analysis of sources and information sources. For example, the reliability verification unit evaluates reliability based on a detailed analysis of sources and information sources. In this way, by thoroughly analyzing the sources and information sources of memories, it is possible to provide highly reliable information.

[0049] The reliability verification unit improves reliability by incorporating third-party evaluations of the memory content during reliability verification. For example, the reliability verification unit verifies the reliability of the memory by incorporating third-party evaluations. For example, the reliability verification unit verifies the reliability of the memory by incorporating third-party evaluations. The reliability verification unit can also improve reliability based on third-party evaluations. For example, the reliability verification unit improves reliability based on third-party evaluations. Furthermore, the reliability verification unit can evaluate reliability by referring to third-party evaluations. For example, the reliability verification unit evaluates reliability by referring to third-party evaluations. In this way, by incorporating third-party evaluations, it is possible to provide highly reliable information.

[0050] The reliability verification unit weights reliability based on the timing of memory occurrence during the reliability verification process. For example, the reliability verification unit prioritizes verifying the reliability of recent memories and recording them while they are still fresh. The reliability verification unit can also postpone verifying the reliability of older memories and verifying their reliability according to their importance. Furthermore, the reliability verification unit can verify reliability chronologically based on the timing of memory occurrence. This allows for a more accurate reliability evaluation by weighting reliability based on the timing of memory occurrence.

[0051] The reliability verification unit evaluates the reliability of memories by referring to related literature during the reliability verification process. For example, the reliability verification unit evaluates the reliability of memories by referring to related literature. For example, the reliability verification unit evaluates the reliability of memories by referring to related literature. The reliability verification unit can also clarify the interrelationships of memories based on related literature. For example, the reliability verification unit clarifies the interrelationships of memories based on related literature. Furthermore, the reliability verification unit can evaluate reliability by referring to related literature to avoid duplication. For example, the reliability verification unit evaluates reliability by referring to related literature to avoid duplication. As a result, the accuracy of information is improved by evaluating reliability by referring to related literature for memories.

[0052] The selection unit, upon selection, proposes the most suitable output format according to the content of the memory. For example, the selection unit may output memories about people in audio format. For example, the selection unit may output memories about objects in video format. For example, the selection unit may output memories about objects in video format. Furthermore, the selection unit may output memories about places in text format. For example, the selection unit may output memories about places in text format. In this way, by proposing the most suitable output format according to the content of the memory, information can be transmitted in the format desired by the user.

[0053] The selection unit, when a selection is made, refers to the user's past selection history to suggest the optimal output format. For example, the selection unit suggests the optimal format based on the output formats the user has previously selected. The selection unit can also prioritize suggesting frequently used formats based on the user's past selection history. For example, the selection unit prioritizes suggesting frequently used formats based on the user's past selection history. Furthermore, the selection unit can analyze the user's past selection history and suggest the most suitable output format. For example, the selection unit analyzes the user's past selection history and suggests the most suitable output format. In this way, the optimal output format can be suggested by referring to the user's past selection history.

[0054] The selection unit proposes an output format when making a selection, taking into account the memory's origin and the person's attribute information. For example, the selection unit proposes an output format that includes geographical information based on the memory's origin. The selection unit can also propose an output format that includes information related to a person based on the person's attribute information. Furthermore, the selection unit can propose an optimal output format by combining the memory's origin and the person's attribute information. By proposing an output format that takes into account the memory's origin and the person's attribute information, information can be transmitted in a more appropriate format.

[0055] The selection unit, when making a selection, proposes an output format by referring to relevant literature related to memory. For example, the selection unit proposes the optimal output format for the content of the memory by referring to relevant literature. For example, the selection unit proposes the optimal output format for the content of the memory by referring to relevant literature. The selection unit can also propose an output format that clarifies the interrelationships of memories based on the relevant literature. For example, the selection unit proposes an output format that clarifies the interrelationships of memories based on the relevant literature. Furthermore, the selection unit can also propose an output format that avoids duplication by referring to relevant literature. For example, the selection unit proposes an output format that avoids duplication by referring to relevant literature. In this way, the accuracy of the information is improved by proposing an output format by referring to relevant literature related to memory.

[0056] The settings unit, during configuration, refers to the user's past configuration history to suggest the most suitable settings. For example, the settings unit suggests the most suitable settings based on the items the user has previously configured. The settings unit can also prioritize suggesting frequently used settings based on the user's past configuration history. Furthermore, the settings unit can analyze the user's past configuration history to suggest the most suitable settings. In this way, by referring to the user's past configuration history, the settings unit can suggest the most suitable settings.

[0057] The settings section, during setup, suggests optimal settings based on the user's device information. For example, if the user is using a smartphone, the settings section suggests settings that match the screen size. Furthermore, if the user is using a tablet, the settings section can suggest settings optimized for larger screens. Additionally, if the user is using a smartwatch, the settings section can suggest concise and highly visible settings. This allows for more appropriate settings by suggesting settings based on the user's device information.

[0058] The business department analyzes users' past purchasing behavior and proposes the optimal business model when developing a business. For example, the business department proposes the optimal business model based on users' past purchasing behavior. For example, the business department proposes the optimal business model based on users' past purchasing behavior. The business department can also prioritize proposing business models that users frequently use based on their past purchasing behavior. For example, the business department prioritizes proposing business models that users frequently use based on their past purchasing behavior. Furthermore, the business department can analyze users' past purchasing behavior and propose the most suitable business model. For example, the business department analyzes users' past purchasing behavior and proposes the most suitable business model. In this way, by analyzing users' past purchasing behavior, the optimal business model can be proposed.

[0059] The business department proposes the optimal business model when developing a business, taking into account the user's geographical location. For example, the business department proposes the optimal business model based on the user's geographical location. For example, the business department proposes the optimal business model based on the user's geographical location. The business department can also prioritize proposing business models that users frequently use based on their geographical location. For example, the business department prioritizes proposing business models that users frequently use based on their geographical location. Furthermore, the business department can analyze the user's geographical location and propose the most suitable business model. For example, the business department analyzes the user's geographical location and proposes the most suitable business model. In this way, the optimal business model can be proposed by considering the user's geographical location.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] Digital archiving systems can adjust the level of detail in verbalization based on the importance of the memory. For example, important memories can be verbalized in detail and recorded down to the smallest detail. Less important memories can be verbalized concisely, recording only the main points. Furthermore, detailed explanations and background information can be added depending on the importance of the memory. This allows important memories to be recorded in detail by adjusting the level of detail in verbalization according to their importance.

[0062] Digital archiving systems can apply different verbalization algorithms depending on the category of memory. For example, memories of people can be verbalized by emphasizing the person's characteristics and relationships. Memories of objects can be verbalized by emphasizing the details and usage of the object. Furthermore, memories of places can be verbalized by emphasizing geographical features and historical background. By applying different verbalization algorithms according to the category of memory, more appropriate verbalization becomes possible.

[0063] Digital archiving systems can prioritize the verbalization of memories based on when they originated. For example, recent memories can be prioritized for verbalization and recorded while they are still vivid. Older memories can be postponed and verbalized according to their importance. Furthermore, verbalization can be performed chronologically based on when the memories originated. This allows for the prioritization of verbalization based on the time of memory origin, ensuring that vivid memories are recorded first.

[0064] Digital archiving systems can adjust the order of verbalization based on the relevance of memories. For example, related memories can be grouped together and verbalized to create continuity. Less relevant memories can also be verbalized individually and kept as independent records. Furthermore, important memories can be prioritized and verbalized based on their relevance. This allows for a continuous record by adjusting the order of verbalization based on the relevance of memories.

[0065] Digital archiving systems can improve the accuracy of categorization by considering the interrelationships between memories. For example, related memories can be grouped together, clarifying their relationships. Categories can also be subdivided based on the interrelationships of memories. Furthermore, categorization can be done in a way that avoids duplication by considering the interrelationships of memories. As a result, categorizing while considering the interrelationships of memories leads to a more accurate organization of information.

[0066] Digital archiving systems can categorize information by considering the location where memories originated and the attributes of individuals. For example, geographical categories can be set based on the location where memories originated. Similarly, person categories can be set based on individual attributes. Furthermore, complex categories can be created by combining the location of memories and the attributes of individuals. This allows for more appropriate organization of information by categorizing it while considering the location of memories and the attributes of individuals.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The language processing unit converts memories into language, such as speech or text, and digitizes them. For example, it can use speech recognition technology to convert memories from speech to text, or use a text conversion algorithm to convert memories to text. It can also use generative AI to convert memories into language, such as speech or text. Step 2: The categorization unit categorizes the data generated by the language generation unit into categories such as land, people, and objects. For example, it categorizes the data generated based on classification algorithms or category definitions. It can also categorize the data generated using generative AI. Step 3: The reliability verification unit verifies the reliability of the information categorized by the categorization unit. For example, it verifies the source of the information and performs reliability scoring to confirm the reliability of the listed information. It can also use generation AI to compare the listed information with similar information and fake information and display the percentage of truth or falsehood. Step 4: The selection unit selects the output format based on the information verified by the reliability verification unit. For example, it selects the output format from text, video, audio, etc., based on the output format selection criteria and the user's preferences. It can also select the output format using a generation AI.

[0069] (Example of form 2) The digital archiving system according to an embodiment of the present invention is a system that verbalizes memories into audio or text, categorizes them by event such as place, person, or object, and digitally archives them as data heritage. This digital archiving system verbalizes memories into audio or text and converts them into data. At this time, themes and keywords are extracted, and related information is also attached. Next, the listed information is compared with similar information and fake information, and the percentage of truth or falsehood is displayed. After that, the scrutinized data is categorized and digitally archived. Furthermore, the output format can be selected as a means of transmitting memory data. In addition, the intended target, story, genre / emotion, concept, etc. can be set, and the story and output format can be freely selected by combining memory data and settings. For example, the digital archiving system verbalizes memories into audio or text and converts them into data. For example, the digital archiving system extracts themes and keywords, and related information is also attached. Next, the digital archiving system compares the listed information with similar information and fake information, and the percentage of truth or falsehood is displayed. Next, the digital archiving system categorizes the scrutinized data and digitally archives it. Furthermore, digital archiving systems can select the output format as a means of transmitting memory data. For example, a digital archiving system can set the intended target, story, genre / emotion, concept, etc. For instance, a digital archiving system can freely select the story and output format by combining memory data and settings. This allows digital archiving systems to efficiently verbalize, categorize, verify the reliability of memories, and select the output format.

[0070] The digital archive system according to this embodiment comprises a language conversion unit, a categorization unit, a reliability verification unit, and a selection unit. The language conversion unit converts memories into language, such as speech or text, and digitizes them. The language conversion unit converts memories from speech to text using, for example, speech recognition technology. The language conversion unit can also convert memories into text using a text conversion algorithm. Furthermore, the language conversion unit can convert memories into text using a text conversion algorithm. The language conversion unit can also convert memories into speech or text using a generative AI. The categorization unit categorizes the digitized information by event, such as land, people, or objects. The categorization unit categorizes the digitized information by event, such as land, people, or objects, using, for example, a classification algorithm. For example, the categorization unit uses a classification algorithm to categorize the digitized information by event, such as land, people, or objects. The categorization unit can also categorize the digitized information based on category definitions. Furthermore, the categorization unit can use generative AI to categorize the digitized information by event, such as land, people, or objects. The reliability verification unit compares the listed information with similar and fake information and displays the percentage of truth or falsity. For example, the reliability verification unit verifies the source of the information to confirm its reliability. Furthermore, the reliability verification unit can perform reliability scoring to confirm the reliability of the listed information. Furthermore, the reliability verification unit can use generating AI to compare the listed information with similar or fake information and display the percentage of truthfulness.For example, the reliability verification unit uses a generation AI to compare the listed information with similar or fake information and displays the percentage of truth or falsity. The selection unit selects the output format from text, video, audio, etc. The selection unit selects the output format from text, video, audio, etc., based on, for example, the selection criteria for the output format. The selection unit can also select the output format from text, video, audio, etc., based on the user's preference. The selection unit can also select the output format from text, video, audio, etc., based on the user's preference. Furthermore, the selection unit can also select the output format from text, video, audio, etc., using a generation AI. The selection unit can also select the output format from text, video, audio, etc., using a generation AI. As a result, the digital archive system according to this embodiment can efficiently verbalize memories, categorize them, verify their reliability, and select the output format.

[0071] The language processing unit translates memories into speech, text, and other forms of data. Specifically, it uses speech recognition technology to convert memories from speech to text. Speech recognition technology is a process that analyzes speech signals and converts speech to text using a language model. For example, speech recognition technology extracts features from speech signals and maps them to phonemes and words to convert speech to text. The language processing unit can also convert memories to text using a text conversion algorithm. A text conversion algorithm is a technology that converts handwritten or printed characters into digital text, and often utilizes optical character recognition (OCR) technology. OCR technology is a process that recognizes characters from images acquired by a scanner or camera and converts them into digital text. Furthermore, the language processing unit can also use generative AI to translate memories into speech, text, and other forms of data. Generative AI utilizes natural language processing technology to analyze input information and convert it into appropriate linguistic expressions. For example, generative AI analyzes speech input and generates appropriate text according to the context. Generative AI also analyzes text input and generates natural linguistic expressions considering the appropriate use of grammar and vocabulary. This allows the language processing unit to handle diverse input formats and efficiently and accurately verbalize memories.

[0072] The categorization unit categorizes digitized information by event, such as land, people, or objects. Specifically, it uses classification algorithms to categorize digitized information by event, such as land, people, or objects. A classification algorithm is a technology that analyzes the characteristics of data and classifies it into predefined categories. For example, information about land is categorized based on geographical characteristics and location information, and information about people is categorized based on names and attribute information. Information about objects is categorized based on the characteristics and uses of the object. Furthermore, the categorization unit can also categorize digitized information based on category definitions. Category definitions can be flexibly set according to user needs and system requirements. For example, custom categories can be defined to categorize information related to a specific project or research. In addition, the categorization unit can also categorize digitized information by event, such as land, people, or objects, using generative AI. Generative AI analyzes the context and meaning of the data and classifies it into the appropriate category. For example, the generative AI analyzes the content of text data and automatically identifies the relevant categories. It can also analyze image and audio data and classify them into appropriate categories. This allows the categorization unit to handle diverse data formats and categorize information efficiently and accurately.

[0073] The reliability verification unit compares the listed information with similar and fake information and displays the percentage of truth or falsehood. Specifically, it verifies the source of the information to confirm its reliability. Source verification is the process of investigating the origin and citation of information and evaluating its reliability. For example, the reliability verification unit verifies whether the information source is from a reliable organization or expert. The reliability verification unit can also perform reliability scoring to confirm the reliability of the listed information. Reliability scoring is a technique that quantifies and evaluates the reliability of information. For example, the reliability verification unit evaluates the source of the information, the accuracy of the content, and the appropriateness of the citations to calculate a reliability score. Furthermore, the reliability verification unit can also use generative AI to compare the listed information with similar and fake information and display the percentage of truth or falsehood. Generative AI is a technique that analyzes large amounts of data and evaluates the truth or falsehood of information. For example, the generative AI collects information similar to the listed information from the internet and evaluates the degree of content similarity and reliability. Furthermore, the generating AI learns the characteristics of fake information and evaluates the likelihood that the listed information is fake. As a result, the reliability verification unit can evaluate the reliability of the information with high accuracy and provide users with reliable information.

[0074] The selection unit chooses the output format from options such as text, video, and audio. Specifically, it selects the output format from text, video, and audio based on selection criteria. The selection criteria are set according to the user's needs and the characteristics of the content. For example, text format is suitable for providing detailed information, video format is suitable for effectively conveying visual information, and audio format is suitable for providing auditory information. Furthermore, the selection unit can also select the output format from text, video, and audio based on the user's preferences. User preferences are collected through surveys and feedback and reflected in the system. For example, if the user prefers visual information, video format will be selected. If the user requests detailed information, text format will be selected. Furthermore, the selection unit can also use generative AI to select the output format from text, video, and audio. Generative AI analyzes the characteristics of the content and the user's needs and automatically selects the optimal output format. For example, the generative AI analyzes the content and the user's past selection history to suggest the optimal output format. Furthermore, the generation AI can collect user feedback in real time and continuously improve its output format selection. This allows the selection unit to provide the user with the optimal output format, maximizing the effectiveness of information transmission.

[0075] It includes a settings section for setting the target audience, story, genre / emotion, and concept. The settings section can, for example, set the target audience. It can also set the story. Furthermore, it can set the genre / emotion. Finally, it can set the concept. This allows users to freely select settings as a means of transmitting memory data.

[0076] The company has a business department that franchises and monetizes the accumulated data and templated output formats. For example, the business department can franchise the accumulated data. For example, the business department can franchise the accumulated data. The business department can also franchise the templated output formats. For example, the business department can franchise the templated output formats. Furthermore, the business department can monetize the accumulated data. For example, the business department can monetize the accumulated data. Furthermore, the business department can also monetize the templated output formats. For example, the business department can monetize the templated output formats. This allows the accumulated data and output formats to be used for business development.

[0077] The language processing unit verbalizes memories into audio, text, and other forms of data. For example, the language processing unit can use speech recognition technology to convert memories from audio to text. Furthermore, the language processing unit can also use a text conversion algorithm to convert memories into text. In addition, the language processing unit can use generative AI to verbalize memories into audio or text. This process of verbalizing memories into audio or text and digitizing them makes memory storage easier.

[0078] The categorization unit categorizes digitized information by event, such as land, people, or objects. For example, the categorization unit uses a classification algorithm to categorize digitized information by event, such as land, people, or objects. The categorization unit can also categorize digitized information based on category definitions. Furthermore, the categorization unit can use generative AI to categorize digitized information by event, such as land, people, or objects. This categorization of digitized information by event makes it easier to organize the information.

[0079] The reliability verification unit compares the listed information with similar and fake information and displays the percentage of truth or falsehood. For example, the reliability verification unit verifies the source of the information to confirm its reliability. The reliability verification unit can also perform reliability scoring to confirm the reliability of the listed information. Furthermore, the reliability verification unit can use generation AI to compare the listed information with similar and fake information and display the percentage of truth or falsehood. This verifies the reliability of the information and displays the percentage of truth or falsehood, thereby improving the accuracy of the information.

[0080] The selection unit selects the output format from options such as text, video, and audio. For example, the selection unit selects the output format from options such as text, video, and audio based on the selection criteria for the output format. The selection unit can also select the output format from options such as text, video, and audio based on the user's preference. Furthermore, the selection unit can use generative AI to select the output format from options such as text, video, and audio. This allows information to be transmitted in the format desired by the user by selecting the output format.

[0081] The verbalization unit estimates the user's emotions and adjusts the way memories are verbalized based on the estimated emotions. For example, if the user is sad, the verbalization unit verbalizes memories using gentle language. For example, if the user is sad, the verbalization unit verbalizes memories using gentle language. The verbalization unit can also verbalize memories in a cheerful tone if the user is happy. For example, if the user is happy, the verbalization unit verbalizes memories in a cheerful tone. Furthermore, if the user is angry, the verbalization unit can verbalize memories in a calm tone. For example, if the user is angry, the verbalization unit verbalizes memories in a calm tone. In this way, by adjusting the way memories are verbalized according to the user's emotions, more appropriate expression becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0082] The verbalization unit adjusts the level of detail in verbalization based on the importance of the memory. For example, the verbalization unit verbalizes important memories in detail and records even the smallest details. For example, the verbalization unit verbalizes important memories in detail and records even the smallest details. The verbalization unit can also verbalize less important memories concisely and record only the main points. For example, the verbalization unit verbalizes less important memories concisely and records only the main points. Furthermore, the verbalization unit can add detailed explanations and background information depending on the importance of the memory. For example, the verbalization unit can add detailed explanations and background information depending on the importance of the memory. In this way, by adjusting the level of detail in verbalization according to the importance of the memory, important memories can be recorded in detail.

[0083] The verbalization unit applies different verbalization algorithms depending on the category of memory during the verbalization process. For example, when verbalizing memories about people, the verbalization unit emphasizes the characteristics and relationships of the people. For example, when verbalizing memories about people, the verbalization unit emphasizes the characteristics and relationships of the people. Furthermore, when verbalizing memories about objects, the verbalization unit can emphasize the details and usage of the objects. For example, when verbalizing memories about objects, the verbalization unit emphasizes the details and usage of the objects. In addition, when verbalizing memories about places, the verbalization unit can emphasize the geographical characteristics and historical background. For example, when verbalizing memories about places, the verbalization unit emphasizes the geographical characteristics and historical background. By applying different verbalization algorithms depending on the category of memory, more appropriate verbalization becomes possible.

[0084] The verbalization unit estimates the user's emotions and adjusts the length of the verbalization based on the estimated emotions. For example, if the user is relaxed, the verbalization unit will produce a longer verbalization that includes detailed explanations. For example, if the user is relaxed, the verbalization unit will produce a longer verbalization that includes detailed explanations. For example, if the user is in a hurry, the verbalization unit will produce a shorter, more concise verbalization. For example, if the user is excited, the verbalization unit will produce a shorter, more concise verbalization. For example, if the user is excited, the verbalization unit will produce a longer, more concise verbalization. For example, if the user is excited, the verbalization unit will produce a shorter, more concise verbalization. This allows for the verbalization of memories at a more appropriate length by adjusting the length of the verbalization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The verbalization unit determines the priority of verbalization based on the timing of memory formation. For example, the verbalization unit prioritizes verbalizing recent memories and recording them while they are still vivid. The verbalization unit can also postpone older memories and verbalize them according to their importance. Furthermore, the verbalization unit can verbalize memories chronologically based on the timing of memory formation. This allows for the prioritization of verbalization based on the timing of memory formation, enabling the recording of vivid memories to be prioritized.

[0086] The verbalization unit adjusts the order of verbalization based on the relevance of memories. For example, the verbalization unit can verbalize related memories together to create continuity. For example, the verbalization unit can verbalize related memories together to create continuity. The verbalization unit can also verbalize less relevant memories individually, creating independent records. For example, the verbalization unit can verbalize less relevant memories individually, creating independent records. Furthermore, the verbalization unit can prioritize verbalizing important memories based on their relevance. For example, the verbalization unit prioritizes verbalizing important memories based on their relevance. This allows for a continuous record by adjusting the order of verbalization based on the relevance of memories.

[0087] The categorization unit estimates the user's emotions and adjusts the categorization criteria based on the estimated emotions. For example, if the user is sad, the categorization unit will categorize them using emotional criteria. The categorization unit can also categorize users using positive criteria if they are happy. For example, if the user is happy, the categorization unit will categorize them using positive criteria. Furthermore, if the user is angry, the categorization unit can also categorize them using calm criteria. For example, if the user is angry, the categorization unit will categorize them using calm criteria. By adjusting the categorization criteria according to the user's emotions, more appropriate categorization becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI.

[0088] The categorization unit improves the accuracy of categorization by considering the interrelationships of memories during the categorization process. For example, the categorization unit groups related memories and clarifies their interrelationships. The categorization unit can also subdivide categories based on the interrelationships of memories. For example, the categorization unit subdivides categories based on the interrelationships of memories. Furthermore, the categorization unit can categorize in a way that avoids duplication by considering the interrelationships of memories. For example, the categorization unit categorizes in a way that avoids duplication by considering the interrelationships of memories. As a result, categorizing while considering the interrelationships of memories leads to a more accurate organization of information.

[0089] The categorization unit considers the location where memories originate and the attribute information of individuals when categorizing. For example, the categorization unit sets geographical categories based on the location where memories originate. The categorization unit can also set person categories based on the attribute information of individuals. Furthermore, the categorization unit can combine the location where memories originate and the attribute information of individuals to set complex categories. By categorizing while considering the location where memories originate and the attribute information of individuals, the organization of information becomes more appropriate.

[0090] The categorization unit estimates the user's emotions and adjusts the order in which the categorization results are displayed based on the estimated emotions. For example, if the user is relaxed, the categorization unit will display a longer, more detailed explanation. For example, if the user is relaxed, the categorization unit will display a longer, more detailed explanation. For example, if the user is in a hurry, the categorization unit will display a shorter, more concise explanation. For example, if the user is excited, the categorization unit will display a shorter, more concise explanation. For example, if the user is excited, the categorization unit will display a shorter, more concise explanation. For example, if the user is excited, the categorization unit will display a shorter, more concise explanation. This allows for more appropriate display by adjusting the order in which the categorization results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The categorization unit considers the geographical distribution of memories when categorizing. For example, the categorization unit categorizes by region based on the geographical distribution of memories. The categorization unit can also group related regions while considering geographical distribution. For example, the categorization unit groups related regions while considering geographical distribution. Furthermore, the categorization unit can subdivide categories based on geographical distribution. For example, the categorization unit subdivides categories based on geographical distribution. This makes it possible to organize information by region by categorizing while considering the geographical distribution of memories.

[0092] The categorization unit improves the accuracy of categorization by referring to related literature during the categorization process. For example, the categorization unit sets categories for memories by referring to related literature. For example, the categorization unit sets categories for memories by referring to related literature. The categorization unit can also clarify the interrelationships of memories based on related literature. For example, the categorization unit clarifies the interrelationships of memories based on related literature. Furthermore, the categorization unit can categorize in a way that avoids duplication by referring to related literature. For example, the categorization unit categorizes in a way that avoids duplication by referring to related literature. As a result, categorizing by referring to related literature for memories leads to a more accurate organization of information.

[0093] The reliability verification unit estimates the user's emotions and adjusts the reliability verification criteria based on the estimated user emotions. For example, if the user is sad, the reliability verification unit verifies reliability using emotional criteria. For example, if the user is sad, the reliability verification unit verifies reliability using emotional criteria. For example, if the user is happy, the reliability verification unit verifies reliability using positive criteria. For example, if the user is happy, the reliability verification unit verifies reliability using positive criteria. Furthermore, if the user is angry, the reliability verification unit verifies reliability using calm criteria. For example, if the user is angry, the reliability verification unit verifies reliability using calm criteria. In this way, by adjusting the reliability verification criteria according to the user's emotions, more appropriate reliability verification becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0094] The reliability verification unit evaluates the reliability of memories by thoroughly analyzing the sources and information sources during reliability verification. For example, the reliability verification unit can thoroughly analyze the sources and evaluate their reliability. For example, the reliability verification unit can thoroughly analyze the sources and evaluate their reliability. The reliability verification unit can also evaluate the reliability of information sources and verify the reliability of memories. For example, the reliability verification unit can evaluate the reliability of information sources and verify the reliability of memories. Furthermore, the reliability verification unit can evaluate reliability based on a detailed analysis of sources and information sources. For example, the reliability verification unit evaluates reliability based on a detailed analysis of sources and information sources. In this way, by thoroughly analyzing the sources and information sources of memories, it is possible to provide highly reliable information.

[0095] The reliability verification unit improves reliability by incorporating third-party evaluations of the memory content during reliability verification. For example, the reliability verification unit verifies the reliability of the memory by incorporating third-party evaluations. For example, the reliability verification unit verifies the reliability of the memory by incorporating third-party evaluations. The reliability verification unit can also improve reliability based on third-party evaluations. For example, the reliability verification unit improves reliability based on third-party evaluations. Furthermore, the reliability verification unit can evaluate reliability by referring to third-party evaluations. For example, the reliability verification unit evaluates reliability by referring to third-party evaluations. In this way, by incorporating third-party evaluations, it is possible to provide highly reliable information.

[0096] The reliability verification unit estimates the user's emotions and adjusts the order in which the reliability verification results are displayed based on the estimated emotions. For example, if the user is relaxed, the reliability verification unit will display a longer message including a detailed explanation. For example, if the user is relaxed, the reliability verification unit will display a longer message including a detailed explanation. For example, if the user is in a hurry, the reliability verification unit will display a shorter message to the point. For example, if the user is in a hurry, the reliability verification unit will display a shorter message to the point. For example, if the user is excited, the reliability verification unit will display a message with a visually stimulating effect. For example, if the user is excited, the reliability verification unit will display a message with a visually stimulating effect. In this way, by adjusting the order in which the reliability verification results are displayed according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0097] The reliability verification unit weights reliability based on the timing of memory occurrence during the reliability verification process. For example, the reliability verification unit prioritizes verifying the reliability of recent memories and recording them while they are still fresh. The reliability verification unit can also postpone verifying the reliability of older memories and verifying their reliability according to their importance. Furthermore, the reliability verification unit can verify reliability chronologically based on the timing of memory occurrence. This allows for a more accurate reliability evaluation by weighting reliability based on the timing of memory occurrence.

[0098] The reliability verification unit evaluates the reliability of memories by referring to related literature during the reliability verification process. For example, the reliability verification unit evaluates the reliability of memories by referring to related literature. For example, the reliability verification unit evaluates the reliability of memories by referring to related literature. The reliability verification unit can also clarify the interrelationships of memories based on related literature. For example, the reliability verification unit clarifies the interrelationships of memories based on related literature. Furthermore, the reliability verification unit can evaluate reliability by referring to related literature to avoid duplication. For example, the reliability verification unit evaluates reliability by referring to related literature to avoid duplication. As a result, the accuracy of information is improved by evaluating reliability by referring to related literature for memories.

[0099] The selection unit estimates the user's emotions and adjusts the criteria for selecting the output format based on the estimated emotions. For example, if the user is sad, the selection unit selects the output format based on emotional criteria. For example, if the user is sad, the selection unit selects the output format based on emotional criteria. The selection unit can also select the output format based on positive criteria if the user is happy. For example, if the user is happy, the selection unit selects the output format based on positive criteria. Furthermore, if the user is angry, the selection unit can select the output format based on calm criteria. For example, if the user is angry, the selection unit selects the output format based on calm criteria. In this way, by adjusting the criteria for selecting the output format according to the user's emotions, a more appropriate output format can be selected. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0100] The selection unit, upon selection, proposes the most suitable output format according to the content of the memory. For example, the selection unit may output memories about people in audio format. For example, the selection unit may output memories about objects in video format. For example, the selection unit may output memories about objects in video format. Furthermore, the selection unit may output memories about places in text format. For example, the selection unit may output memories about places in text format. In this way, by proposing the most suitable output format according to the content of the memory, information can be transmitted in the format desired by the user.

[0101] The selection unit, when a selection is made, refers to the user's past selection history to suggest the optimal output format. For example, the selection unit suggests the optimal format based on the output formats the user has previously selected. The selection unit can also prioritize suggesting frequently used formats based on the user's past selection history. For example, the selection unit prioritizes suggesting frequently used formats based on the user's past selection history. Furthermore, the selection unit can analyze the user's past selection history and suggest the most suitable output format. For example, the selection unit analyzes the user's past selection history and suggests the most suitable output format. In this way, the optimal output format can be suggested by referring to the user's past selection history.

[0102] The selection function estimates the user's emotions and adjusts the output format display method based on the estimated emotions. For example, if the user is relaxed, the selection function will display a longer version with a detailed explanation. If the user is in a hurry, the selection function can also display a shorter, more concise version. Furthermore, if the user is excited, the selection function can add visually stimulating effects to the display. This allows for more appropriate display by adjusting the output format display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0103] The selection unit proposes an output format when making a selection, taking into account the memory's origin and the person's attribute information. For example, the selection unit proposes an output format that includes geographical information based on the memory's origin. The selection unit can also propose an output format that includes information related to a person based on the person's attribute information. Furthermore, the selection unit can propose an optimal output format by combining the memory's origin and the person's attribute information. By proposing an output format that takes into account the memory's origin and the person's attribute information, information can be transmitted in a more appropriate format.

[0104] The selection unit, when making a selection, proposes an output format by referring to relevant literature related to memory. For example, the selection unit proposes the optimal output format for the content of the memory by referring to relevant literature. For example, the selection unit proposes the optimal output format for the content of the memory by referring to relevant literature. The selection unit can also propose an output format that clarifies the interrelationships of memories based on the relevant literature. For example, the selection unit proposes an output format that clarifies the interrelationships of memories based on the relevant literature. Furthermore, the selection unit can also propose an output format that avoids duplication by referring to relevant literature. For example, the selection unit proposes an output format that avoids duplication by referring to relevant literature. In this way, the accuracy of the information is improved by proposing an output format by referring to relevant literature related to memory.

[0105] The settings unit estimates the user's emotions and determines the priority of settings items based on the estimated emotions. For example, if the user is relaxed, the settings unit will prioritize displaying detailed settings items. For example, if the user is relaxed, the settings unit will prioritize displaying detailed settings items. For example, if the user is in a hurry, the settings unit will prioritize displaying important settings items. For example, if the user is excited, the settings unit will prioritize displaying visually stimulating settings items. For example, if the user is excited, the settings unit will prioritize displaying visually stimulating settings items. In this way, by determining the priority of settings items according to the user's emotions, more appropriate settings can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0106] The settings unit, during configuration, refers to the user's past configuration history to suggest the most suitable settings. For example, the settings unit suggests the most suitable settings based on the items the user has previously configured. The settings unit can also prioritize suggesting frequently used settings based on the user's past configuration history. Furthermore, the settings unit can analyze the user's past configuration history to suggest the most suitable settings. In this way, by referring to the user's past configuration history, the settings unit can suggest the most suitable settings.

[0107] The settings unit estimates the user's emotions and adjusts how the settings items are displayed based on the estimated emotions. For example, if the user is relaxed, the settings unit will display longer options with detailed explanations. If the user is in a hurry, the settings unit can also display shorter, more concise options. Furthermore, if the user is excited, the settings unit can add visually stimulating effects to the display. This allows for a more appropriate display by adjusting how the settings items are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The settings section, during setup, suggests optimal settings based on the user's device information. For example, if the user is using a smartphone, the settings section suggests settings that match the screen size. Furthermore, if the user is using a tablet, the settings section can suggest settings optimized for larger screens. Additionally, if the user is using a smartwatch, the settings section can suggest concise and highly visible settings. This allows for more appropriate settings by suggesting settings based on the user's device information.

[0109] The business department estimates the user's emotions and adjusts franchise and monetization methods based on those estimated emotions. For example, if the user is relaxed, the business department will suggest longer franchise and monetization methods that include detailed explanations. If the user is in a hurry, the business department can suggest shorter, more concise franchise and monetization methods. Furthermore, if the user is excited, the business department can suggest franchise and monetization methods that incorporate visually stimulating effects. By adjusting franchise and monetization methods according to the user's emotions, a more appropriate business development becomes possible. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0110] The business department analyzes users' past purchasing behavior and proposes the optimal business model when developing a business. For example, the business department proposes the optimal business model based on users' past purchasing behavior. For example, the business department proposes the optimal business model based on users' past purchasing behavior. The business department can also prioritize proposing business models that users frequently use based on their past purchasing behavior. For example, the business department prioritizes proposing business models that users frequently use based on their past purchasing behavior. Furthermore, the business department can analyze users' past purchasing behavior and propose the most suitable business model. For example, the business department analyzes users' past purchasing behavior and proposes the most suitable business model. In this way, by analyzing users' past purchasing behavior, the optimal business model can be proposed.

[0111] The business team estimates the user's emotions and prioritizes business development based on those emotions. For example, if the user is relaxed, the business team will deliver a longer business development presentation that includes detailed explanations. If the user is in a hurry, the business team can deliver a shorter, more concise presentation. Furthermore, if the user is excited, the business team can deliver a business development presentation with visually stimulating effects. This allows for more appropriate business development by prioritizing business development based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0112] The business department proposes the optimal business model when developing a business, taking into account the user's geographical location. For example, the business department proposes the optimal business model based on the user's geographical location. For example, the business department proposes the optimal business model based on the user's geographical location. The business department can also prioritize proposing business models that users frequently use based on their geographical location. For example, the business department prioritizes proposing business models that users frequently use based on their geographical location. Furthermore, the business department can analyze the user's geographical location and propose the most suitable business model. For example, the business department analyzes the user's geographical location and proposes the most suitable business model. In this way, the optimal business model can be proposed by considering the user's geographical location.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] Digital archiving systems can estimate a user's emotions and adjust the way memories are verbalized based on those estimated emotions. For example, if a user is sad, memories can be verbalized using gentle language. If a user is happy, memories can be verbalized in a cheerful tone. Furthermore, if a user is angry, memories can be verbalized in a calm tone. This allows for more appropriate expression by adjusting the way memories are verbalized according to the user's emotions.

[0115] Digital archiving systems can adjust the level of detail in verbalization based on the importance of the memory. For example, important memories can be verbalized in detail and recorded down to the smallest detail. Less important memories can be verbalized concisely, recording only the main points. Furthermore, detailed explanations and background information can be added depending on the importance of the memory. This allows important memories to be recorded in detail by adjusting the level of detail in verbalization according to their importance.

[0116] Digital archiving systems can apply different verbalization algorithms depending on the category of memory. For example, memories of people can be verbalized by emphasizing the person's characteristics and relationships. Memories of objects can be verbalized by emphasizing the details and usage of the object. Furthermore, memories of places can be verbalized by emphasizing geographical features and historical background. By applying different verbalization algorithms according to the category of memory, more appropriate verbalization becomes possible.

[0117] Digital archiving systems can estimate a user's emotions and adjust the length of verbalization based on those emotions. For example, if a user is relaxed, they can provide longer verbalizations with detailed explanations. If a user is in a hurry, they can provide shorter, more concise verbalizations. Furthermore, if a user is excited, they can provide verbalizations with visually stimulating effects. By adjusting the length of verbalization according to the user's emotions, memories can be verbalized at a more appropriate length.

[0118] Digital archiving systems can prioritize the verbalization of memories based on when they originated. For example, recent memories can be prioritized for verbalization and recorded while they are still vivid. Older memories can be postponed and verbalized according to their importance. Furthermore, verbalization can be performed chronologically based on when the memories originated. This allows for the prioritization of verbalization based on the time of memory origin, ensuring that vivid memories are recorded first.

[0119] Digital archiving systems can adjust the order of verbalization based on the relevance of memories. For example, related memories can be grouped together and verbalized to create continuity. Less relevant memories can also be verbalized individually and kept as independent records. Furthermore, important memories can be prioritized and verbalized based on their relevance. This allows for a continuous record by adjusting the order of verbalization based on the relevance of memories.

[0120] Digital archiving systems can estimate user emotions and adjust categorization criteria based on those estimated emotions. For example, if a user is sad, they can be categorized using emotional criteria. If a user is happy, they can be categorized using positive criteria. Furthermore, if a user is angry, they can be categorized using calm criteria. By adjusting categorization criteria according to user emotions, more appropriate categorization becomes possible.

[0121] Digital archiving systems can improve the accuracy of categorization by considering the interrelationships between memories. For example, related memories can be grouped together, clarifying their relationships. Categories can also be subdivided based on the interrelationships of memories. Furthermore, categorization can be done in a way that avoids duplication by considering the interrelationships of memories. As a result, categorizing while considering the interrelationships of memories leads to a more accurate organization of information.

[0122] Digital archiving systems can categorize information by considering the location where memories originated and the attributes of individuals. For example, geographical categories can be set based on the location where memories originated. Similarly, person categories can be set based on individual attributes. Furthermore, complex categories can be created by combining the location of memories and the attributes of individuals. This allows for more appropriate organization of information by categorizing it while considering the location of memories and the attributes of individuals.

[0123] The digital archiving system can estimate the user's emotions and adjust the order in which categorization results are displayed based on those emotions. For example, if the user is relaxed, a longer display with detailed explanations can be shown. If the user is in a hurry, a shorter, more concise display can be shown. Furthermore, if the user is excited, a display with visually stimulating effects can be added. By adjusting the order in which categorization results are displayed according to the user's emotions, a more appropriate display becomes possible.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The language processing unit converts memories into language, such as speech or text, and digitizes them. For example, it can use speech recognition technology to convert memories from speech to text, or use a text conversion algorithm to convert memories to text. It can also use generative AI to convert memories into language, such as speech or text. Step 2: The categorization unit categorizes the data generated by the language generation unit into categories such as land, people, and objects. For example, it categorizes the data generated based on classification algorithms or category definitions. It can also categorize the data generated using generative AI. Step 3: The reliability verification unit verifies the reliability of the information categorized by the categorization unit. For example, it verifies the source of the information and performs reliability scoring to confirm the reliability of the listed information. It can also use generation AI to compare the listed information with similar information and fake information and display the percentage of truth or falsehood. Step 4: The selection unit selects the output format based on the information verified by the reliability verification unit. For example, it selects the output format from text, video, audio, etc., based on the output format selection criteria and the user's preferences. It can also select the output format using a generation AI.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0127] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0128] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the language processing unit, categorization unit, reliability verification unit, selection unit, setting unit, and business unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the language processing unit is implemented by the processor 46 of the smart device 14 and uses speech recognition technology and generative AI to translate memories into speech or text. The categorization unit is implemented by the identification processing unit 290 of the data processing unit 12 and uses classification algorithms and generative AI to categorize the data. The reliability verification unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs source verification and reliability scoring of information. The selection unit is implemented by the control unit 46A of the smart device 14 and selects the output format. The setting unit is implemented by the identification processing unit 290 of the data processing unit 12 and sets the expected target and story. The business unit is implemented by the identification processing unit 290 of the data processing unit 12 and franchises or monetizes the accumulated data and output format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0134] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the language processing unit, categorization unit, reliability verification unit, selection unit, setting unit, and business unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the language processing unit is implemented by the processor 46 of the smart glasses 214 and uses speech recognition technology and generative AI to translate memories into speech or text. The categorization unit is implemented by the identification processing unit 290 of the data processing unit 12 and uses classification algorithms and generative AI to categorize the data. The reliability verification unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs source verification and reliability scoring of information. The selection unit is implemented by the control unit 46A of the smart glasses 214 and selects the output format. The setting unit is implemented by the identification processing unit 290 of the data processing unit 12 and sets the expected target and story. The business unit is implemented by the identification processing unit 290 of the data processing unit 12 and franchises or monetizes the accumulated data and output format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0150] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0158] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0159] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0160] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0161] Each of the multiple elements described above, including the language processing unit, categorization unit, reliability verification unit, selection unit, setting unit, and business unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the language processing unit is implemented by the processor 46 of the headset terminal 314 and uses speech recognition technology and generative AI to translate memories into speech or text. The categorization unit is implemented by the identification processing unit 290 of the data processing unit 12 and uses classification algorithms and generative AI to categorize the data. The reliability verification unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs source verification and reliability scoring of information. The selection unit is implemented by the control unit 46A of the headset terminal 314 and selects the output format. The setting unit is implemented by the identification processing unit 290 of the data processing unit 12 and sets the expected target and story. The business unit is implemented by the identification processing unit 290 of the data processing unit 12 and franchises or monetizes the accumulated data and output format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0164] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0165] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0166] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0167] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0168] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0169] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0170] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0171] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0172] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0173] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0174] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0175] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0176] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0177] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0178] Each of the multiple elements described above, including the language processing unit, categorization unit, reliability verification unit, selection unit, setting unit, and business unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the language processing unit is implemented by the processor 46 of the robot 414 and uses speech recognition technology and generative AI to translate memories into speech or text. The categorization unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and categorizes the digitized information using classification algorithms and generative AI. The reliability verification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and performs source verification and reliability scoring of information. The selection unit is implemented by, for example, the control unit 46A of the robot 414 and selects the output format. The setting unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and sets assumed targets, stories, etc. The business unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and franchises or monetizes the accumulated data and output format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0179] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0180] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0181] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0182] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0183] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0184] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0185] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0186] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0187] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0188] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0189] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0190] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0191] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0192] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0193] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0194] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0195] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0196] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0197] (Note 1) A language processing unit that converts memories into language such as audio or text and digitizes them, A categorization unit that categorizes the information converted into data by the language conversion unit, A reliability verification unit that verifies the reliability of the information categorized by the categorization unit, A selection unit that selects the output format based on the information confirmed by the reliability verification unit, Equipped with A system characterized by the following features. (Note 2) It includes a setting section for defining the target audience, story, genre / emotion, and concept. The system described in Appendix 1, characterized by the features described herein. (Note 3) The company has a business division that franchises and monetizes the accumulated data and templated output formats. The system described in Appendix 1, characterized by the features described herein. (Note 4) The language processing unit, Memories are verbalized into audio, text, and other forms of data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The categorization section is, The digitized information is categorized by event, such as land, people, or objects. The system described in Appendix 1, characterized by the features described herein. (Note 6) The reliability verification unit is, The listed information is compared with similar and fake information, and the percentage of truthfulness is displayed. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned selection unit is Select the output format from text, video, audio, etc. The system described in Appendix 1, characterized by the features described herein. (Note 8) The language processing unit, It estimates the user's emotions and adjusts the way memories are verbalized based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The language processing unit, When verbalizing, adjust the level of detail based on the importance of the memory. The system described in Appendix 1, characterized by the features described herein. (Note 10) The language processing unit, When verbalizing, different verbalization algorithms are applied depending on the category of the memory. The system described in Appendix 1, characterized by the features described herein. (Note 11) The language processing unit, It estimates the user's emotions and adjusts the length of the verbalization based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The language processing unit, When verbalizing information, the priority of verbalization is determined based on when the memory was formed. The system described in Appendix 1, characterized by the features described herein. (Note 13) The language processing unit, When verbalizing, adjust the order of verbalization based on the relevance of memories. The system described in Appendix 1, characterized by the features described herein. (Note 14) The categorization section is, It estimates user sentiment and adjusts categorization criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The categorization section is, When categorizing, consider the interrelationships between memories to improve the accuracy of categorization. The system described in Appendix 1, characterized by the features described herein. (Note 16) The categorization section is, When categorizing, the location where the memory originated and the attribute information of the person involved are taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 17) The categorization section is, It estimates the user's emotions and adjusts the order in which the categorization results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The categorization section is, When categorizing, consider the geographical distribution of memories. The system described in Appendix 1, characterized by the features described herein. (Note 19) The categorization section is, When categorizing, referencing relevant literature improves the accuracy of the categorization. The system described in Appendix 1, characterized by the features described herein. (Note 20) The reliability verification unit is, We estimate user sentiment and adjust the reliability verification criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The reliability verification unit is, During reliability verification, the source and information of the memory are analyzed in detail to assess its reliability. The system described in Appendix 1, characterized by the features described herein. (Note 22) The reliability verification unit is, When verifying reliability, incorporate third-party evaluations of the memory content to improve reliability. The system described in Appendix 1, characterized by the features described herein. (Note 23) The reliability verification unit is, It estimates the user's sentiment and adjusts the order in which the reliability check results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The reliability verification unit is, During reliability testing, reliability is weighted based on when the memory was created. The system described in Appendix 1, characterized by the features described herein. (Note 25) The reliability verification unit is, During reliability verification, the reliability of the memory is evaluated by referring to relevant literature. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned selection unit is It estimates the user's emotions and adjusts the selection criteria for the output format based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned selection unit is When you make a selection, we will suggest the most suitable output format based on the content of your memory. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned selection unit is When a selection is made, the system will refer to the user's past selection history to suggest the most suitable output format. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned selection unit is It estimates the user's emotions and adjusts the display method of the output format based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned selection unit is When selecting, the system will suggest an output format that takes into account the location where the memory originated and the attribute information of the person. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned selection unit is When making a selection, we will suggest an output format by referring to relevant literature on memory. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned setting unit is, It estimates the user's emotions and determines the priority of settings based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned setting unit is, During setup, the system will refer to the user's past configuration history to suggest the most suitable settings. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned setting unit is, It estimates the user's emotions and adjusts how settings items are displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned setting unit is, During setup, the system will suggest the most suitable settings based on the user's device information. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned business department, We estimate user sentiment and adjust franchise and monetization methods based on that estimated sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned business department, When developing a business, we analyze users' past consumer behavior and propose the optimal business model. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned business department, We estimate user emotions and prioritize business developments based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned business department, When developing a business, we propose the optimal business model by taking into account the user's geographical location. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0198] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A language processing unit that converts memories into language such as audio or text and digitizes them, A categorization unit that categorizes the information converted into data by the language conversion unit, A reliability verification unit that verifies the reliability of the information categorized by the categorization unit, A selection unit that selects the output format based on the information confirmed by the reliability verification unit, Equipped with A system characterized by the following features.

2. It includes a setting section for defining the target audience, story, genre / emotion, and concept. The system according to feature 1.

3. The company has a business division that franchises and monetizes the accumulated data and templated output formats. The system according to feature 1.

4. The language processing unit, Memories are verbalized into audio, text, and other forms of data. The system according to feature 1.

5. The categorization section is, The digitized information is categorized by event, such as land, people, or objects. The system according to feature 1.

6. The reliability verification unit is, The listed information is compared with similar and fake information, and the percentage of truthfulness is displayed. The system according to feature 1.

7. The aforementioned selection unit is Select the output format from text, video, audio, etc. The system according to feature 1.

8. The language processing unit, It estimates the user's emotions and adjusts the way memories are verbalized based on the estimated user emotions. The system according to feature 1.

9. The language processing unit, When verbalizing, adjust the level of detail based on the importance of the memory. The system according to feature 1.

10. The language processing unit, When verbalizing, different verbalization algorithms are applied depending on the category of the memory. The system according to feature 1.

Images