system

Abstract

We provide the system. [Solution] A recording means that acquires user voice input and converts it into text data, A storage means for saving the aforementioned text data to the cloud, A tagging means that analyzes the aforementioned text data and automatically assigns relevant tags, A mapping means for generating a graphical relationship map based on the tagged data, A sharing means that enables the sharing of the aforementioned relationship map and text data on social media, etc. A recommendation system that suggests relevant books based on the user's preferences, A system that includes this.

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] There are problems that many pieces of information and ideas obtained during reading are likely to dissipate from memory unless recorded and cannot be effectively utilized. Also, there are problems that it takes time and effort to organize and manage ideas and impressions that occur during reading and further share them with others. Furthermore, in order to deepen the reading experience, appropriate recommendations for related books are required, but it is inefficient to perform this work manually.

Means for Solving the Problems

[0005] The interactive system of this invention includes a mechanism that acquires user voice input, converts it into text data in real time, and records it on the cloud. It then automatically assigns relevant tags to the acquired text data using natural language processing and generates a graphical relationship map, thereby visually and easily organizing the information. Furthermore, it has a function to make this data shareable on social media, supporting users in deepening their knowledge together. It also has a function to improve the reading experience by automatically recommending relevant books based on the user's past reading history and preferences.

[0006] "Voice input" is a method used to record information spoken by a user in a digital format.

[0007] "Text data" refers to data in string format obtained by analyzing voice input, and is the subject of recording and analysis.

[0008] A "recording device" is a mechanism for saving acquired data, and its role is to leave information in the cloud or local storage.

[0009] A "tagging method" is a process that automatically assigns keywords and categories related to data, making it easier to organize and search for information.

[0010] A "relationship map" is a structure that visually represents the relationships between data, providing information in an easy-to-understand way.

[0011] "Sharing methods" refer to functions or interfaces for sharing stored data with other users, and for distributing information.

[0012] A "recommendation method" is an algorithm that presents relevant information based on the user's preferences and history, delivering information tailored to the individual user's needs.

[0013] "Noise cancellation" is a technology that removes ambient noise during voice input, allowing for clear acquisition of the user's voice.

[0014] "Natural language processing" is a technique for analyzing text data and understanding its meaning and context, and is used for tagging and generating relevance maps. [Brief explanation of the drawing]

[0015] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the language used in the following description will be explained.

[0018] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] The 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.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is an interactive system that allows users to input ideas and impressions gained while reading via voice, effectively record, organize, and share that content, and further recommend related books. This system is operated primarily through the interaction of a terminal, a server, and the user.

[0037] First, the device utilizes speech recognition technology to receive user voice input. As the user reads the book, they input their thoughts and feelings in voice, for example, "The way this story unfolded was unexpected." The device then converts this voice into text data in real time.

[0038] The converted text data is automatically sent to a cloud database managed by the server. There, the server uses natural language processing technology to automatically assign relevant tags to the text data. For example, if the keyword "unexpected" is included, the tag "surprise" will be added. This tagged data is then useful for subsequent searching and classification.

[0039] Furthermore, the server generates a relationship map based on this data. When a user inputs information about multiple books, if there are common themes or keywords among them, these are displayed graphically, allowing the user to visually understand the relationships between the information.

[0040] The device also provides an interface for users to share this recorded data via social media or email, if they so desire. This can be used by users to spread knowledge or facilitate discussions.

[0041] Furthermore, the server analyzes the user's reading history and preferences to recommend relevant books. For example, if a user has recorded many thoughts related to psychology, new books in that genre will be automatically recommended.

[0042] In this way, by using this system, users can not only read books, but also organize their own knowledge, share it with others, and gain new intellectual horizons.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] Users input ideas and thoughts that come to mind while reading into the device via voice. For example, they might say, "The ending of this story was surprising."

[0046] Step 2:

[0047] The device converts the acquired audio into text data using a speech recognition engine. During this process, noise cancellation technology is used to remove ambient noise.

[0048] Step 3:

[0049] The device sends the converted text data to a database in the cloud. Security protocols are applied to this transmission, ensuring the data is stored securely.

[0050] Step 4:

[0051] The server retrieves text data stored in the database and analyzes it using natural language processing.

[0052] Step 5:

[0053] The server automatically assigns tags to each text based on the analysis results. For example, if the text contains the word "surprise," it will attach the tag "surprise."

[0054] Step 6:

[0055] The server generates a relationship map between data based on the tagged data, visually showing how different data are related.

[0056] Step 7:

[0057] The device provides an interface for sharing text data and relationship maps via social media or email, according to the user's preferences.

[0058] Step 8:

[0059] The server analyzes the user's historical data and, based on the results, selects and recommends relevant books to the user. This recommendation is based on the user's reading habits.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In modern times, it is difficult to efficiently record, organize, and share the insights and impressions gained from reading. Furthermore, the insufficient search capabilities for related information and the lack of personalized recommendations based on individual preferences limit users' ability to utilize information effectively.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes a processing unit that acquires user voice data and converts it into text data, a data storage unit that stores the text data in online storage, and a labeling unit that analyzes the text data and automatically assigns relevant characteristic words. This enables efficient data conversion and organization based on voice input.

[0065] "Audio data" refers to the digital format of information input by the user as voice.

[0066] "Text data" refers to information in text format that remains after audio data has been converted.

[0067] A "processing unit" is a component that has the function of converting audio data into text data.

[0068] "Online storage" refers to a service that provides space for storing and managing data on the internet.

[0069] The "data storage unit" is an element that implements the function of saving acquired text data to online storage.

[0070] The "labeling unit" is an element that analyzes character data and automatically adds labels that represent related features.

[0071] The "data sharing section" is an element that provides functionality for users to share text data with other platforms and users.

[0072] The "Information Recommendation Section" is a component that has the function of suggesting relevant information and books based on the user's preferences.

[0073] A "visual relationship diagram" is a graphical representation that shows the relationships between data based on labeled data.

[0074] This invention is an interactive information processing system that efficiently records, organizes, and shares user insights based on voice input. The entire system functions primarily through the cooperation of three entities: the terminal, the server, and the user.

[0075] The terminal is a hardware device that receives voice data from the user in real time. Specifically, it captures the user's speech as digital voice data via a microphone and converts this voice data into text data using speech recognition software such as Google Cloud Speech-to-Text. The terminal then sends this text data to the server. For example, if the user says, "I find this character's growth interesting," the terminal instantly converts the voice data into text.

[0076] The server manages the received text data in the cloud. To securely store the data, the server uses online storage services, such as Amazon Web Services (AWS®). The server also runs a process that automatically assigns relevant labels to this data using natural language processing technology. For example, if the word "growth" is present in the text, related labels such as "relationships" and "process" will be assigned. This improves the searchability and organization of the data.

[0077] Furthermore, the server organizes this labeled data into a visual relationship diagram. This diagram helps users visually understand the connections between various pieces of information, promoting personalized information comprehension. For example, if reviews of several books share a common theme such as "growth" or "challenge," the relationship between them is visually represented.

[0078] Finally, the device provides an interface for spreading this information according to the user's wishes. It can be easily shared via social media, email, etc., encouraging discussion. In addition, the server recommends new books and information based on the user's preferences. If a user has expressed many opinions on psychology, they can receive notifications of related new books.

[0079] A concrete example of a prompt message is one that instructs the user to "Please input any impressive ideas or thoughts you had while reading in voice. The system will analyze them and provide relevant information." Such prompt messages make using the system intuitive and easy.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user speaks into the device's microphone about their feelings and thoughts while reading. For example, the user might say, "This character's growth is interesting." The input here is audio data.

[0083] Step 2:

[0084] The device converts received audio data into text data in real time using speech recognition technology such as Google Cloud Speech-to-Text. Because the audio signal processing removes noise while converting speech to text, the output here is text data. This process quickly organizes the user's speech into text format.

[0085] Step 3:

[0086] The terminal sends the converted character data to an online server. A secure communication protocol is used to ensure the safe transfer of data. The input here is character data, and the output is stored in the server's database.

[0087] Step 4:

[0088] The server uses natural language processing techniques to automatically assign relevant labels to the received text data. This process involves text analysis, extracting highly relevant characteristic words, and labeling them with terms such as "growth" and "interesting." The input is text data, and the output is labeled text data.

[0089] Step 5:

[0090] The server analyzes data relationships based on labeled information and generates a visual relationship diagram. Data from multiple books and chapters are linked and graphically displayed so that common themes are immediately apparent. Input is labeled text data, and output is a visual relationship diagram.

[0091] Step 6:

[0092] The terminal displays the generated relationship diagrams and labeled data to the user, and provides an interface that allows for easy sharing via social media and email. Input here consists of visual relationship diagrams and labeled text data, while output allows the user to review and share the information.

[0093] Step 7:

[0094] The server analyzes the user's preferences based on their past input data and recommends new books. Using a machine learning model, it learns the user's preferred genres and tendencies, and suggests new books to read. The input is the user's past data, and the output is information about recommended books.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] The system needs to effectively record and organize individual ideas and impressions gained during reading, and recommend related books and content, but it must be provided in a way that is easy for users to use. Furthermore, a means of visualizing and sharing this related information with others is also necessary.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes a conversion means for acquiring user voice input and converting it into text information, an attribute assignment means for analyzing the text information and automatically assigning relevant attributes, and an adaptation means for providing an interface suitable for a portable information terminal and facilitating voice recording. This allows users to easily record and organize ideas and impressions while reading, and to efficiently discover related learning materials and other resources.

[0100] "Voice input" refers to the act of a technical device receiving and recognizing what a user speaks.

[0101] "Text information" refers to a data format in which non-textual data, such as audio, is converted into a string of characters.

[0102] "Remote data storage" refers to external data storage devices that can be accessed via the internet, such as cloud services.

[0103] "Attribute assignment" is the process of automatically adding labels such as specific keywords or sentiments to text information.

[0104] "Relational structure" refers to graphs and diagrams that visually represent the relationships between data points.

[0105] An "information sharing platform" is an online service that allows users to share content and information with others.

[0106] "Preferences" refer to the tendencies and hobbies that users are particularly interested in.

[0107] "Educational materials" is a general term for books and electronic content used for learning and education.

[0108] A "portable information terminal" refers to a device that is portable and possesses diverse information processing capabilities.

[0109] "Presentation" refers to the act of providing information or data to a user visually or audibly.

[0110] This invention is a system that allows users to use smart devices to input information via voice and effectively record, visualize, and share that information. In particular, it aims to improve the user's reading experience.

[0111] The system primarily consists of the following components: a terminal, a server, and a user-side interface. The terminal is assumed to be a smartphone, utilizing the Google Speech-to-Text API to receive voice input. Through this API, the user's speech is converted into text.

[0112] The server stores the converted text information in Firebase in the cloud. The server then analyzes the information using natural language processing techniques and automatically assigns relevant attributes using libraries such as spacy. Based on these attribute assignments, a graphical relationship structure is generated, allowing users to visually understand the relationships between the information.

[0113] Furthermore, the server recommends relevant educational materials and content based on the user's past usage frequency and preferences. This recommendation feature makes it easier for users to access new information according to their interests and learning motivation.

[0114] Furthermore, the device provides a function that allows users to share the aforementioned information with others via social media, email, etc. This makes it easy for users to communicate their thoughts and impressions to others.

[0115] For example, if a user reads a philosophy book and says, "This idea is very original," that comment will be assigned the attribute "original." Based on this, the server will recommend other books and articles related to philosophy, providing the user with new learning opportunities.

[0116] An example of a prompt message could be: "I've read a new philosophy book, and I'd like to record my thoughts on the ideas presented and be shown related articles."

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The user provides voice input to their smartphone. The voice data is captured through the smartphone's microphone. The device sends the voice data to the Google Speech-to-Text API and receives output as text information. In this process, the voice signal is analyzed and converted into a linguistic string.

[0120] Step 2:

[0121] The device's role is to transfer the acquired text information to a cloud database. The text information, as input, is stored in Firebase via the internet. Security is ensured because the data is transmitted in an encrypted format during this process.

[0122] Step 3:

[0123] The server retrieves text information from Firebase and analyzes the data using natural language processing techniques. Using spacy, it extracts specific keywords and sentiments from the input text information. The output is data with relevant attributes attached. This step involves contextual recognition and attribute tagging within the text.

[0124] Step 4:

[0125] The server generates a graphical relationship structure based on attributed data. It takes attribute data as input and performs calculations to determine the relationships between the data. The output is a visualized relationship map, making it easier for users to understand the interrelationships between the information.

[0126] Step 5:

[0127] The server references the user's past preferences and recommends relevant educational materials and content. Based on the user's preference data as input, it uses an algorithm that evaluates similarity to output a recommendation list. This process utilizes machine learning models to achieve personalized recommendations.

[0128] Step 6:

[0129] The device displays the generated relationship structure and recommendation content in the user interface. The front-end framework handles the display of the outputted visualization information and recommendation data to the user. Users can visually review this information and share it as needed.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention is a system for recording and analyzing a user's daily reading experience and making the most of that knowledge and feedback, and is particularly characterized by its incorporation of an engine that recognizes the user's emotions. This system is realized through a series of interactions between a terminal, a server, and the user.

[0132] The device is designed to receive voice input from the user and also incorporates an emotion engine to enable emotion recognition. It receives voice recordings of emotional statements made by the user while reading, such as "This scene is very moving." This voice data is converted to text using noise cancellation and speech recognition technology, and then analyzed by the emotion engine. The emotion engine analyzes the tone of the voice and the content of the words to identify what emotions the user is experiencing, such as excitement, joy, or sadness.

[0133] Text data is stored in a cloud database and managed by a server. The server analyzes the text data, including user emotional information, using natural language processing technology and automatically assigns relevant tags. Emotional information is also considered in the tagging process; for example, if the emotion "emotional" is recognized, the tag "emotional" will be assigned.

[0134] Next, the server analyzes the relationships between the tagged text data and generates a relationship map that also takes sentiment data into account. This map visually shows which themes users are emotionally responding to, aiding in a deeper understanding.

[0135] Furthermore, the device has a function that recommends relevant books based on the user's past impressions and emotional tendencies. For example, if a user has recorded many instances of feeling "moved" in the past, books that may evoke similar emotions will be recommended. Also, if the user wishes to share this information with others, they can easily do so via social media or email.

[0136] Thus, this system goes beyond simple reading records, taking into account the user's emotions to provide personalized and profound insights into their individual reading experience. As a result, users can engage in more satisfying and meaningful reading activities.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] Users input their emotional thoughts and opinions into the device via voice while reading. For example, they might say, "The protagonist's growth was very moving."

[0140] Step 2:

[0141] The device uses a speech recognition engine to convert speech data into text data. Simultaneously, it uses an emotion engine to analyze the tone and content of the speech to identify the user's emotions. For example, a statement expressed as "moving" is recognized as the emotion "moved."

[0142] Step 3:

[0143] The device sends the converted text data and sentiment information to a database in the cloud. Encryption technology is applied during this process to protect privacy.

[0144] Step 4:

[0145] The server retrieves text data from a cloud database and analyzes its content using natural language processing technology. Simultaneously, it references emotional information and automatically assigns relevant tags. For example, content describing "the inspiring growth of the protagonist" would be tagged with "growth" and "emotion."

[0146] Step 5:

[0147] The server generates a relationship map between the tagged data. This map visually shows which themes and emotions users are responding to, allowing for a deeper understanding of the reading experience.

[0148] Step 6:

[0149] The device provides an interface that allows users to share generated data and relationship maps via social media or email, if they so desire. Users can easily share their reading experiences with others and exchange opinions.

[0150] Step 7:

[0151] The server analyzes and recommends relevant books based on the user's emotions and preferences. This recommendation process selects and presents books that evoke similar emotions, for example, if the user frequently expresses the emotion of being "emotional."

[0152] In this way, the system incorporates the emotions users feel while reading, aiming to improve knowledge management and the reading experience in a way that suits their individual needs and interests.

[0153] (Example 2)

[0154] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0155] Traditional reading log systems merely record book titles and impressions, failing to capture the nuances of emotions users felt while reading or recommend related information based on those emotions. Furthermore, they lack easy ways to visually express and share emotions. As a result, users are unable to fully utilize their reading experience and struggle to discover further reading options.

[0156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0157] In this invention, the server includes input means for acquiring user voice input and converting it into text data, information tagging means for analyzing the text data and automatically assigning relevant tags, and emotion recognition means for recognizing and evaluating emotions based on the user's expressions. This enables evaluation of the reading experience based on the user's emotions, and the recommendation and sharing of relevant information accordingly.

[0158] "Input means" refers to a device or method that acquires voice input from a user and converts it into text data.

[0159] "Data storage means" refers to a system or process for securely storing converted text data on the cloud.

[0160] An "information tagging method" is a technology or algorithm that analyzes text data and automatically assigns the appropriate tags.

[0161] A "mapping method" is a technique or method for generating a graphical relationship map based on tagged data.

[0162] "Sharing means" refers to a method or device for making relationship maps and text data shareable with others via a communication medium.

[0163] "Information recommendation methods" refer to technologies or algorithms that recommend relevant information sources based on the user's preferences and emotions.

[0164] "Emotion recognition means" refers to a technology or engine for recognizing emotions based on user expressions, and for evaluating and analyzing those emotions.

[0165] "Emotion mapping means" refers to a technology or method for generating a visual emotion map based on user emotion data.

[0166] The system for carrying out this invention aims to record, analyze, and provide relevant information about the user's reading experience. Details are provided below.

[0167] The device uses a built-in high-precision microphone to capture the user's voice. This device converts the speech to text using speech recognition software while performing noise cancellation. Specifically, it processes the audio data using speech services such as the Google Cloud Speech-to-Text API. For example, if a user says "This part is very interesting" while reading, that speech is converted to text.

[0168] The device also sends the converted text to an emotion recognition engine. This engine uses natural language processing techniques to analyze the user's emotions from the text content and tone of voice. The emotion recognition engine utilizes open-source natural language processing libraries (e.g., NLTK, TENSORFLOW®) to identify the user's emotions as "joy," "excitement," "surprise," etc.

[0169] The server securely stores and manages all text and sentiment data using a cloud database service (e.g., Amazon DynamoDB). User text data is tagged with informational tags, and a data analysis module calculates the relationships between the data. This generates a relationship map.

[0170] This system analyzes the user's past reading data and recommends relevant information sources, particularly based on content that resonated emotionally with them. The recommendation engine employs collaborative filtering to find and present books similar to those that moved the user.

[0171] Furthermore, the server generates a visual relationship map based on sentiment data, visualizing which themes users are emotionally responding to. This map helps to gain a deeper understanding of the user's reading habits.

[0172] For example, if a user says something like, "I was excited by this adventure scene," this emotion data is analyzed and assigned the emotion tag "excited." The subsequent generated relevance map includes books and content related to this emotion.

[0173] An example of a prompt for a generative AI model would be, "Please describe a system for recommending information based on user sentiment."

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The device acquires user speech using an audio input device. The input is voice data, which includes the user's emotions. This voice data is captured with a high-precision microphone, and ambient noise is minimized using noise cancellation technology. The acquired voice data is then sent to speech recognition software.

[0177] Step 2:

[0178] The device uses speech recognition software (e.g., Google Cloud Speech-to-Text API) to convert audio data into text data. The input is the audio data acquired in step 1, and the output is text data. The speech recognition process analyzes words and phrases within the audio data and accurately converts them into corresponding text.

[0179] Step 3:

[0180] The terminal transfers the converted text data to the emotion recognition engine. The input is text data, and the output is the emotion information contained in the text. The emotion recognition engine uses natural language processing techniques to evaluate emotions from the content of the text. For example, it can identify emotions such as joy, surprise, and emotion.

[0181] Step 4:

[0182] The terminal packages text data and identified sentiment information and sends it to the server. The input is text and sentiment information, and the output is data transmission to the server. This data is sent to the server using a stable communication protocol for subsequent analysis and storage processes.

[0183] Step 5:

[0184] The server manages text data and sentiment information using a cloud database. Input is data sent from the terminal, and output is storage in the database. The server stores data using a highly secure database service (e.g., Amazon DynamoDB). The stored data is made available for retrieval and analysis at any time.

[0185] Step 6:

[0186] The server uses a data analysis module to parse stored text data and automatically assigns relevant tags. The input is stored text data, and the output is tagged data. Natural language processing techniques are used to efficiently add appropriate tags based on the themes and content of different texts.

[0187] Step 7:

[0188] The server generates a graphical relationship map based on tagged data and sentiment information. The input is tagged data and sentiment information, and the output is a visual relationship map. This map shows the relationships between data and patterns of user sentiment, and is generated using visualization tools.

[0189] Step 8:

[0190] The user receives recommendation information from the server via their device based on sentiment data and relationship maps. The input is the information generated in the previous step, and the output is a list of books and related information presented to the user. These recommendations are provided based on the user's past sentiment patterns.

[0191] (Application Example 2)

[0192] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0193] Traditional reading record and recommendation systems do not adequately consider user emotions and opinions, making it difficult to provide a personalized experience based on individual preferences. Furthermore, a challenge remains in how to analyze the acquired data and return it to users as valuable information.

[0194] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0195] In this invention, the server includes an acquisition means for acquiring user voice input and converting it into text data, an assignment means for analyzing the text data and automatically assigning relevant attributes, and an emotion recognition means for recognizing the user's emotional state from the voice and utilizing it in recommending the literature. This enables effective literature recommendations based on the user's emotions and preferences.

[0196] "Acquisition means" refers to a device or method that has the function of collecting voice input from a user and converting it into text format.

[0197] "Storage means" refers to a device or method that has the function of securely storing text data on the cloud and making it accessible at a later date.

[0198] "Assignment means" refers to a device or method that has the function of analyzing text data and automatically adding related attributes thereto.

[0199] "Representation generation means" refers to a device or method that has the function of generating diagrams or maps that show visual relationships based on data to which attributes have been assigned.

[0200] "Sharing means" refers to a device or method that has the function of making generated relational expressions or text data shareable with other users on a network medium.

[0201] A "recommendation tool" is a device or method that has the function of selecting and suggesting relevant literature based on the user's preferences and emotions.

[0202] "Emotion recognition means" refers to a device or method that has the function of identifying emotions from a user's voice and applying that information to recommend literature, etc.

[0203] The system for implementing the present invention consists of a user, a terminal, and a server. The user expresses their thoughts on a book they are reading in voice, and the terminal acquires this voice, performs noise reduction, and converts it into text data. A terminal with emotion recognition capabilities analyzes the user's voice tone and the content of their words to identify their emotions. This emotion information is stored in the cloud along with the text data.

[0204] The server analyzes the stored text data using a natural language processing engine and assigns relevant attributes. This generates a visual relationship map to visualize the themes and emotions the user is responding to. Furthermore, based on this emotional information and preference history, the server recommends relevant literature to the user. The generated relationship representations and recommended books can also be shared via network media at the user's request.

[0205] For example, if a user voice-expresses their opinion, saying, "This part is really interesting!", the device recognizes this as "excitement." As a result, the server recommends new reading material based on related books that the user previously rated when they felt "excited." In this way, the system personalizes the reading experience according to the user's emotions and preferences.

[0206] Examples of prompts to input into a generative AI model include: "Describe a scene in which the user had an emotional reaction, and list other books that evoke similar emotions."

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The device acquires voice input from the user via a microphone. Noise reduction technology is used to clarify the acquired voice data, and a speech recognition engine converts it into text data. The input is voice data, and the output is the converted text data.

[0210] Step 2:

[0211] The device analyzes the converted text data using an emotion recognition engine to identify the user's emotions. The analysis targets voice tone and word content, and the output is the identified emotion information.

[0212] Step 3:

[0213] The server stores text data and sentiment information sent from the terminal in the cloud. The stored data is used for later analysis and recommendations. The input is text data and sentiment information, and the output is the data recorded in the cloud.

[0214] Step 4:

[0215] The server analyzes the stored data using natural language processing techniques and assigns relevant attributes to the data. This adds themes related to the text as tags. The input is the stored text data, and the output is the tagged data.

[0216] Step 5:

[0217] The server generates a visual relationship map based on tagged data using a generative AI model. By providing this prompt to the model, the relationships between data points are visualized. The input is tagged data, and the output is a relationship map.

[0218] Step 6:

[0219] The server recommends literature that may evoke similar emotions, based on the user's past emotional information and preference patterns. This recommendation information is likely to be of interest to the user. The input is the user's emotional information and preference patterns, and the output is the recommended literature information.

[0220] Step 7:

[0221] Users can share the generated relationship maps and recommended literature with friends and followers on network media. This step is performed through the sharing function. The input is the relationship map and literature information, and the output is the shared information.

[0222] 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.

[0223] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0224] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0229] 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.

[0230] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0231] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0232] 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.

[0233] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0234] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0235] The 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.

[0236] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0237] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0238] This invention is an interactive system that allows users to input ideas and impressions gained while reading via voice, effectively record, organize, and share that content, and further recommend related books. This system is operated primarily through the interaction of a terminal, a server, and the user.

[0239] First, the device utilizes speech recognition technology to receive user voice input. As the user reads the book, they input their thoughts and feelings in voice, for example, "The way this story unfolded was unexpected." The device then converts this voice into text data in real time.

[0240] The converted text data is automatically sent to a cloud database managed by the server. There, the server uses natural language processing technology to automatically assign relevant tags to the text data. For example, if the keyword "unexpected" is included, the tag "surprise" will be added. This tagged data is then useful for subsequent searching and classification.

[0241] Furthermore, the server generates a relationship map based on this data. When a user inputs information about multiple books, if there are common themes or keywords among them, these are displayed graphically, allowing the user to visually understand the relationships between the information.

[0242] The device also provides an interface for users to share this recorded data via social media or email, if they so desire. This can be used by users to spread knowledge or facilitate discussions.

[0243] Furthermore, the server analyzes the user's reading history and preferences to recommend relevant books. For example, if a user has recorded many thoughts related to psychology, new books in that genre will be automatically recommended.

[0244] In this way, by using this system, users can not only read books, but also organize their own knowledge, share it with others, and gain new intellectual horizons.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] Users input ideas and thoughts that come to mind while reading into the device via voice. For example, they might say, "The ending of this story was surprising."

[0248] Step 2:

[0249] The device converts the acquired audio into text data using a speech recognition engine. During this process, noise cancellation technology is used to remove ambient noise.

[0250] Step 3:

[0251] The device sends the converted text data to a database in the cloud. Security protocols are applied to this transmission, ensuring the data is stored securely.

[0252] Step 4:

[0253] The server retrieves text data stored in the database and analyzes it using natural language processing.

[0254] Step 5:

[0255] The server automatically assigns tags to each text based on the analysis results. For example, if the text contains the word "surprise," it will attach the tag "surprise."

[0256] Step 6:

[0257] The server generates a relationship map between data based on the tagged data, visually showing how different data are related.

[0258] Step 7:

[0259] The device provides an interface for sharing text data and relationship maps via social media or email, according to the user's preferences.

[0260] Step 8:

[0261] The server analyzes the user's historical data and, based on the results, selects and recommends relevant books to the user. This recommendation is based on the user's reading habits.

[0262] (Example 1)

[0263] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] In modern times, it is difficult to efficiently record, organize, and share the insights and impressions gained from reading. Furthermore, the insufficient search capabilities for related information and the lack of personalized recommendations based on individual preferences limit users' ability to utilize information effectively.

[0265] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0266] In this invention, the server includes a processing unit that acquires user voice data and converts it into text data, a data storage unit that stores the text data in online storage, and a labeling unit that analyzes the text data and automatically assigns relevant characteristic words. This enables efficient data conversion and organization based on voice input.

[0267] "Audio data" refers to the digital format of information input by the user as voice.

[0268] "Text data" refers to information in text format that remains after audio data has been converted.

[0269] A "processing unit" is a component that has the function of converting audio data into text data.

[0270] "Online storage" refers to a service that provides space for storing and managing data on the internet.

[0271] The "data storage unit" is an element that implements the function of saving acquired text data to online storage.

[0272] The "labeling unit" is an element that analyzes character data and automatically adds labels that represent related features.

[0273] The "data sharing section" is an element that provides functionality for users to share text data with other platforms and users.

[0274] The "Information Recommendation Section" is a component that has the function of suggesting relevant information and books based on the user's preferences.

[0275] A "visual relationship diagram" is a graphical representation that shows the relationships between data based on labeled data.

[0276] This invention is an interactive information processing system that efficiently records, organizes, and shares user insights based on voice input. The entire system functions primarily through the cooperation of three entities: the terminal, the server, and the user.

[0277] The terminal is a hardware device that receives voice data from the user in real time. Specifically, it captures the user's speech as digital voice data via a microphone and converts this voice data into text data using speech recognition software such as Google Cloud Speech-to-Text. The terminal then sends this text data to the server. For example, if the user says, "I find this character's growth interesting," the terminal instantly converts the voice data into text.

[0278] The server manages the received text data in the cloud. To securely store the data, the server uses online storage services, such as Amazon Web Services (AWS). The server also runs a process that automatically assigns relevant labels to this data using natural language processing techniques. For example, if the word "growth" is present in the text, related labels such as "relationships" and "process" will be assigned. This improves the searchability and organization of the data.

[0279] Furthermore, the server organizes this labeled data into a visual relationship diagram. This diagram helps users visually understand the connections between various pieces of information, promoting personalized information comprehension. For example, if reviews of several books share a common theme such as "growth" or "challenge," the relationship between them is visually represented.

[0280] Finally, the device provides an interface for spreading this information according to the user's wishes. It can be easily shared via social media, email, etc., encouraging discussion. In addition, the server recommends new books and information based on the user's preferences. If a user has expressed many opinions on psychology, they can receive notifications of related new books.

[0281] A concrete example of a prompt message is one that instructs the user to "Please input any impressive ideas or thoughts you had while reading in voice. The system will analyze them and provide relevant information." Such prompt messages make using the system intuitive and easy.

[0282] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0283] Step 1:

[0284] The user speaks into the microphone of the terminal about what they felt or thought while reading. As a specific action, the user says, "The growth of this character is interesting." The input here is voice data.

[0285] Step 2:

[0286] The terminal uses speech recognition technology such as Google Cloud Speech-to-Text to convert the received voice data into character data in real time. Through voice signal processing, while removing noise, the voice is converted into text, so the output here is character data. By this operation, the user's speech is quickly organized into text format.

[0287] Step 3:

[0288] The terminal sends the converted character data to an online server. At this time, secure data transfer is performed using a secure communication protocol. The input here is character data, and the output is in a state of being stored in the server's database.

[0289] Step 4:

[0290] The server utilizes natural language processing technology for the received character data and automatically assigns relevant labels. In this process, text analysis is performed, highly relevant characteristic words are extracted, and labels such as "growth" and "interesting" are attached. The input is character data, and the output is labeled character data.

[0291] Step 5:

[0292] The server analyzes the relationship of the data based on the labeled information and generates a visual relationship diagram. Data from multiple books or chapters are associated, and a common theme is visually presented in a graphic so that it can be understood at a glance. The input is labeled character data, and the output is a visual relationship diagram.

[0293] Step 6:

[0294] The terminal displays the generated relationship diagrams and labeled data to the user, and provides an interface that allows for easy sharing via social media and email. Input here consists of visual relationship diagrams and labeled text data, while output allows the user to review and share the information.

[0295] Step 7:

[0296] The server analyzes the user's preferences based on their past input data and recommends new books. Using a machine learning model, it learns the user's preferred genres and tendencies, and suggests new books to read. The input is the user's past data, and the output is information about recommended books.

[0297] (Application Example 1)

[0298] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0299] The system needs to effectively record and organize individual ideas and impressions gained during reading, and recommend related books and content, but it must be provided in a way that is easy for users to use. Furthermore, a means of visualizing and sharing this related information with others is also necessary.

[0300] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0301] In this invention, the server includes a conversion means for acquiring user voice input and converting it into text information, an attribute assignment means for analyzing the text information and automatically assigning relevant attributes, and an adaptation means for providing an interface suitable for a portable information terminal and facilitating voice recording. This allows users to easily record and organize ideas and impressions while reading, and to efficiently discover related learning materials and other resources.

[0302] "Voice input" refers to the act of a technical device receiving and recognizing the content uttered by a user.

[0303] "Text information" is a data format obtained by converting non-character data such as voice into a character string.

[0304] "Remote data storage" is an external data storage device accessible through the Internet such as the cloud.

[0305] "Attribute assignment" is a process of automatically adding labels such as specific keywords or emotions to text information.

[0306] "Relational structure" refers to a graph or diagram that visually represents the relationship between data.

[0307] "Information sharing platform" is an online service that allows users to share content and information with others.

[0308] "Preference" refers to a tendency or hobby that a user is particularly interested in.

[0309] "Educational materials" is a general term for books and electronic content used for learning and education.

[0310] "Portable information terminal" refers to a device with a portable form and various information processing functions.

[0311] "Presentation" is an act of visually or auditorily providing information and data to a user.

[0312] The present invention is a system for a user to perform voice input by utilizing a smart device and effectively record, visualize, and share the information. In particular, it aims to improve the reading experience of the user.

[0313] The system primarily consists of the following components: a terminal, a server, and a user-side interface. The terminal is assumed to be a smartphone, utilizing the Google Speech-to-Text API to receive voice input. Through this API, the user's speech is converted into text.

[0314] The server stores the converted text information in Firebase in the cloud. The server then analyzes the information using natural language processing techniques and automatically assigns relevant attributes using libraries such as spacy. Based on these attribute assignments, a graphical relationship structure is generated, allowing users to visually understand the relationships between the information.

[0315] Furthermore, the server recommends relevant educational materials and content based on the user's past usage frequency and preferences. This recommendation feature makes it easier for users to access new information according to their interests and learning motivation.

[0316] Furthermore, the device provides a function that allows users to share the aforementioned information with others via social media, email, etc. This makes it easy for users to communicate their thoughts and impressions to others.

[0317] For example, if a user reads a philosophy book and says, "This idea is very original," that comment will be assigned the attribute "original." Based on this, the server will recommend other books and articles related to philosophy, providing the user with new learning opportunities.

[0318] An example of a prompt message could be: "I've read a new philosophy book, and I'd like to record my thoughts on the ideas presented and be shown related articles."

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The user provides voice input to their smartphone. The voice data is captured through the smartphone's microphone. The device sends the voice data to the Google Speech-to-Text API and receives output as text information. In this process, the voice signal is analyzed and converted into a linguistic string.

[0322] Step 2:

[0323] The device's role is to transfer the acquired text information to a cloud database. The text information, as input, is stored in Firebase via the internet. Security is ensured because the data is transmitted in an encrypted format during this process.

[0324] Step 3:

[0325] The server retrieves text information from Firebase and analyzes the data using natural language processing techniques. Using spacy, it extracts specific keywords and sentiments from the input text information. The output is data with relevant attributes attached. This step involves contextual recognition and attribute tagging within the text.

[0326] Step 4:

[0327] The server generates a graphical relationship structure based on attributed data. It takes attribute data as input and performs calculations to determine the relationships between the data. The output is a visualized relationship map, making it easier for users to understand the interrelationships between the information.

[0328] Step 5:

[0329] The server references the user's past preferences and recommends relevant educational materials and content. Based on the user's preference data as input, it uses an algorithm that evaluates similarity to output a recommendation list. This process utilizes machine learning models to achieve personalized recommendations.

[0330] Step 6:

[0331] The device displays the generated relationship structure and recommendation content in the user interface. The front-end framework handles the display of the outputted visualization information and recommendation data to the user. Users can visually review this information and share it as needed.

[0332] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0333] This invention is a system for recording and analyzing a user's daily reading experience and making the most of that knowledge and feedback, and is particularly characterized by its incorporation of an engine that recognizes the user's emotions. This system is realized through a series of interactions between a terminal, a server, and the user.

[0334] The device is designed to receive voice input from the user and also incorporates an emotion engine to enable emotion recognition. It receives voice recordings of emotional statements made by the user while reading, such as "This scene is very moving." This voice data is converted to text using noise cancellation and speech recognition technology, and then analyzed by the emotion engine. The emotion engine analyzes the tone of the voice and the content of the words to identify what emotions the user is experiencing, such as excitement, joy, or sadness.

[0335] Text data is stored in a cloud database and managed by a server. The server analyzes the text data, including user emotional information, using natural language processing technology and automatically assigns relevant tags. Emotional information is also considered in the tagging process; for example, if the emotion "emotional" is recognized, the tag "emotional" will be assigned.

[0336] Next, the server analyzes the relationships between the tagged text data and generates a relationship map that also takes sentiment data into account. This map visually shows which themes users are emotionally responding to, aiding in a deeper understanding.

[0337] Furthermore, the device has a function that recommends relevant books based on the user's past impressions and emotional tendencies. For example, if a user has recorded many instances of feeling "moved" in the past, books that may evoke similar emotions will be recommended. Also, if the user wishes to share this information with others, they can easily do so via social media or email.

[0338] Thus, this system goes beyond simple reading records, taking into account the user's emotions to provide personalized and profound insights into their individual reading experience. As a result, users can engage in more satisfying and meaningful reading activities.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] Users input their emotional thoughts and opinions into the device via voice while reading. For example, they might say, "The protagonist's growth was very moving."

[0342] Step 2:

[0343] The device uses a speech recognition engine to convert speech data into text data. Simultaneously, it uses an emotion engine to analyze the tone and content of the speech to identify the user's emotions. For example, a statement expressed as "moving" is recognized as the emotion "moved."

[0344] Step 3:

[0345] The device sends the converted text data and sentiment information to a database in the cloud. Encryption technology is applied during this process to protect privacy.

[0346] Step 4:

[0347] The server retrieves text data from a cloud database and analyzes its content using natural language processing technology. Simultaneously, it references emotional information and automatically assigns relevant tags. For example, content describing "the inspiring growth of the protagonist" would be tagged with "growth" and "emotion."

[0348] Step 5:

[0349] The server generates a relationship map between the tagged data. This map visually shows which themes and emotions users are responding to, allowing for a deeper understanding of the reading experience.

[0350] Step 6:

[0351] The device provides an interface that allows users to share generated data and relationship maps via social media or email, if they so desire. Users can easily share their reading experiences with others and exchange opinions.

[0352] Step 7:

[0353] The server analyzes and recommends relevant books based on the user's emotions and preferences. This recommendation process selects and presents books that evoke similar emotions, for example, if the user frequently expresses the emotion of being "emotional."

[0354] In this way, the system incorporates the emotions users feel while reading, aiming to improve knowledge management and the reading experience in a way that suits their individual needs and interests.

[0355] (Example 2)

[0356] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0357] Traditional reading log systems merely record book titles and impressions, failing to capture the nuances of emotions users felt while reading or recommend related information based on those emotions. Furthermore, they lack easy ways to visually express and share emotions. As a result, users are unable to fully utilize their reading experience and struggle to discover further reading options.

[0358] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0359] In this invention, the server includes input means for acquiring user voice input and converting it into text data, information tagging means for analyzing the text data and automatically assigning relevant tags, and emotion recognition means for recognizing and evaluating emotions based on the user's expressions. This enables evaluation of the reading experience based on the user's emotions, and the recommendation and sharing of relevant information accordingly.

[0360] "Input means" refers to a device or method that acquires voice input from a user and converts it into text data.

[0361] "Data storage means" refers to a system or process for securely storing converted text data on the cloud.

[0362] An "information tagging method" is a technology or algorithm that analyzes text data and automatically assigns the appropriate tags.

[0363] A "mapping method" is a technique or method for generating a graphical relationship map based on tagged data.

[0364] "Sharing means" refers to a method or device for making relationship maps and text data shareable with others via a communication medium.

[0365] "Information recommendation methods" refer to technologies or algorithms that recommend relevant information sources based on the user's preferences and emotions.

[0366] "Emotion recognition means" refers to a technology or engine for recognizing emotions based on user expressions, and for evaluating and analyzing those emotions.

[0367] "Emotion mapping means" refers to a technology or method for generating a visual emotion map based on user emotion data.

[0368] The system for carrying out this invention aims to record, analyze, and provide relevant information about the user's reading experience. Details are provided below.

[0369] The device uses a built-in high-precision microphone to capture the user's voice. This device converts the speech to text using speech recognition software while performing noise cancellation. Specifically, it processes the audio data using speech services such as the Google Cloud Speech-to-Text API. For example, if a user says "This part is very interesting" while reading, that speech is converted to text.

[0370] The device also sends the converted text to an emotion recognition engine. This engine uses natural language processing techniques to analyze the user's emotions from the text content and tone of voice. The emotion recognition engine utilizes open-source natural language processing libraries (e.g., NLTK, TensorFlow) to identify the user's emotions as "joy," "excitement," "surprise," etc.

[0371] The server securely stores and manages all text and sentiment data using a cloud database service (e.g., Amazon DynamoDB). User text data is tagged with informational tags, and a data analysis module calculates the relationships between the data. This generates a relationship map.

[0372] This system analyzes the user's past reading data and recommends relevant information sources, particularly based on content that resonated emotionally with them. The recommendation engine employs collaborative filtering to find and present books similar to those that moved the user.

[0373] Furthermore, the server generates a visual relationship map based on sentiment data, visualizing which themes users are emotionally responding to. This map helps to gain a deeper understanding of the user's reading habits.

[0374] For example, if a user says something like, "I was excited by this adventure scene," this emotion data is analyzed and assigned the emotion tag "excited." The subsequent generated relevance map includes books and content related to this emotion.

[0375] An example of a prompt for a generative AI model would be, "Please describe a system for recommending information based on user sentiment."

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The device acquires user speech using an audio input device. The input is voice data, which includes the user's emotions. This voice data is captured with a high-precision microphone, and ambient noise is minimized using noise cancellation technology. The acquired voice data is then sent to speech recognition software.

[0379] Step 2:

[0380] The device uses speech recognition software (e.g., Google Cloud Speech-to-Text API) to convert audio data into text data. The input is the audio data acquired in step 1, and the output is text data. The speech recognition process analyzes words and phrases within the audio data and accurately converts them into corresponding text.

[0381] Step 3:

[0382] The terminal transfers the converted text data to the emotion recognition engine. The input is text data, and the output is the emotion information contained in the text. The emotion recognition engine uses natural language processing techniques to evaluate emotions from the content of the text. For example, it can identify emotions such as joy, surprise, and emotion.

[0383] Step 4:

[0384] The terminal packages text data and identified sentiment information and sends it to the server. The input is text and sentiment information, and the output is data transmission to the server. This data is sent to the server using a stable communication protocol for subsequent analysis and storage processes.

[0385] Step 5:

[0386] The server manages text data and sentiment information using a cloud database. Input is data sent from the terminal, and output is storage in the database. The server stores data using a highly secure database service (e.g., Amazon DynamoDB). The stored data is made available for retrieval and analysis at any time.

[0387] Step 6:

[0388] The server uses a data analysis module to parse stored text data and automatically assigns relevant tags. The input is stored text data, and the output is tagged data. Natural language processing techniques are used to efficiently add appropriate tags based on the themes and content of different texts.

[0389] Step 7:

[0390] The server generates a graphical relationship map based on tagged data and sentiment information. The input is tagged data and sentiment information, and the output is a visual relationship map. This map shows the relationships between data and patterns of user sentiment, and is generated using visualization tools.

[0391] Step 8:

[0392] The user receives recommendation information from the server via their device based on sentiment data and relationship maps. The input is the information generated in the previous step, and the output is a list of books and related information presented to the user. These recommendations are provided based on the user's past sentiment patterns.

[0393] (Application Example 2)

[0394] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0395] Traditional reading record and recommendation systems do not adequately consider user emotions and opinions, making it difficult to provide a personalized experience based on individual preferences. Furthermore, a challenge remains in how to analyze the acquired data and return it to users as valuable information.

[0396] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0397] In this invention, the server includes an acquisition means for acquiring user voice input and converting it into text data, an assignment means for analyzing the text data and automatically assigning relevant attributes, and an emotion recognition means for recognizing the user's emotional state from the voice and utilizing it in recommending the literature. This enables effective literature recommendations based on the user's emotions and preferences.

[0398] "Acquisition means" refers to a device or method that has the function of collecting voice input from a user and converting it into text format.

[0399] "Storage means" refers to a device or method that has the function of securely storing text data on the cloud and making it accessible at a later date.

[0400] "Assignment means" refers to a device or method that has the function of analyzing text data and automatically adding related attributes thereto.

[0401] "Representation generation means" refers to a device or method that has the function of generating diagrams or maps that show visual relationships based on data to which attributes have been assigned.

[0402] "Sharing means" refers to a device or method that has the function of making generated relational expressions or text data shareable with other users on a network medium.

[0403] A "recommendation tool" is a device or method that has the function of selecting and suggesting relevant literature based on the user's preferences and emotions.

[0404] "Emotion recognition means" refers to a device or method that has the function of identifying emotions from a user's voice and applying that information to recommend literature, etc.

[0405] The system for implementing the present invention consists of a user, a terminal, and a server. The user expresses their thoughts on a book they are reading in voice, and the terminal acquires this voice, performs noise reduction, and converts it into text data. A terminal with emotion recognition capabilities analyzes the user's voice tone and the content of their words to identify their emotions. This emotion information is stored in the cloud along with the text data.

[0406] The server analyzes the stored text data using a natural language processing engine and assigns relevant attributes. This generates a visual relationship map to visualize the themes and emotions the user is responding to. Furthermore, based on this emotional information and preference history, the server recommends relevant literature to the user. The generated relationship representations and recommended books can also be shared via network media at the user's request.

[0407] For example, if a user voice-expresses their opinion, saying, "This part is really interesting!", the device recognizes this as "excitement." As a result, the server recommends new reading material based on related books that the user previously rated when they felt "excited." In this way, the system personalizes the reading experience according to the user's emotions and preferences.

[0408] Examples of prompts to input into a generative AI model include: "Describe a scene in which the user had an emotional reaction, and list other books that evoke similar emotions."

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The device acquires voice input from the user via a microphone. Noise reduction technology is used to clarify the acquired voice data, and a speech recognition engine converts it into text data. The input is voice data, and the output is the converted text data.

[0412] Step 2:

[0413] The device analyzes the converted text data using an emotion recognition engine to identify the user's emotions. The analysis targets voice tone and word content, and the output is the identified emotion information.

[0414] Step 3:

[0415] The server stores text data and sentiment information sent from the terminal in the cloud. The stored data is used for later analysis and recommendations. The input is text data and sentiment information, and the output is the data recorded in the cloud.

[0416] Step 4:

[0417] The server analyzes the stored data using natural language processing techniques and assigns relevant attributes to the data. This adds themes related to the text as tags. The input is the stored text data, and the output is the tagged data.

[0418] Step 5:

[0419] The server generates a visual relationship map based on tagged data using a generative AI model. By providing this prompt to the model, the relationships between data points are visualized. The input is tagged data, and the output is a relationship map.

[0420] Step 6:

[0421] The server recommends literature that may evoke similar emotions, based on the user's past emotional information and preference patterns. This recommendation information is likely to be of interest to the user. The input is the user's emotional information and preference patterns, and the output is the recommended literature information.

[0422] Step 7:

[0423] Users can share the generated relationship maps and recommended literature with friends and followers on network media. This step is performed through the sharing function. The input is the relationship map and literature information, and the output is the shared information.

[0424] 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.

[0425] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0426] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0431] 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.

[0432] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0433] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0434] 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.

[0435] 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.

[0436] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0437] The 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.

[0438] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0439] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0440] This invention is an interactive system that allows users to input ideas and impressions gained while reading via voice, effectively record, organize, and share that content, and further recommend related books. This system is operated primarily through the interaction of a terminal, a server, and the user.

[0441] First, the device utilizes speech recognition technology to receive user voice input. As the user reads the book, they input their thoughts and feelings in voice, for example, "The way this story unfolded was unexpected." The device then converts this voice into text data in real time.

[0442] The converted text data is automatically sent to a cloud database managed by the server. There, the server uses natural language processing technology to automatically assign relevant tags to the text data. For example, if the keyword "unexpected" is included, the tag "surprise" will be added. This tagged data is then useful for subsequent searching and classification.

[0443] Furthermore, the server generates a relationship map based on this data. When a user inputs information about multiple books, if there are common themes or keywords among them, these are displayed graphically, allowing the user to visually understand the relationships between the information.

[0444] The device also provides an interface for users to share this recorded data via social media or email, if they so desire. This can be used by users to spread knowledge or facilitate discussions.

[0445] Furthermore, the server analyzes the user's reading history and preferences to recommend relevant books. For example, if a user has recorded many thoughts related to psychology, new books in that genre will be automatically recommended.

[0446] In this way, by using this system, users can not only read books, but also organize their own knowledge, share it with others, and gain new intellectual horizons.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] Users input ideas and thoughts that come to mind while reading into the device via voice. For example, they might say, "The ending of this story was surprising."

[0450] Step 2:

[0451] The device converts the acquired audio into text data using a speech recognition engine. During this process, noise cancellation technology is used to remove ambient noise.

[0452] Step 3:

[0453] The device sends the converted text data to a database in the cloud. Security protocols are applied to this transmission, ensuring the data is stored securely.

[0454] Step 4:

[0455] The server retrieves text data stored in the database and analyzes it using natural language processing.

[0456] Step 5:

[0457] The server automatically assigns tags to each text based on the analysis results. For example, if the text contains the word "surprise," it will attach the tag "surprise."

[0458] Step 6:

[0459] The server generates a relationship map between data based on the tagged data, visually showing how different data are related.

[0460] Step 7:

[0461] The device provides an interface for sharing text data and relationship maps via social media or email, according to the user's preferences.

[0462] Step 8:

[0463] The server analyzes the user's historical data and, based on the results, selects and recommends relevant books to the user. This recommendation is based on the user's reading habits.

[0464] (Example 1)

[0465] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0466] In modern times, it is difficult to efficiently record, organize, and share the insights and impressions gained from reading. Furthermore, the insufficient search capabilities for related information and the lack of personalized recommendations based on individual preferences limit users' ability to utilize information effectively.

[0467] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0468] In this invention, the server includes a processing unit that acquires user voice data and converts it into text data, a data storage unit that stores the text data in online storage, and a labeling unit that analyzes the text data and automatically assigns relevant characteristic words. This enables efficient data conversion and organization based on voice input.

[0469] "Audio data" refers to the digital format of information input by the user as voice.

[0470] "Text data" refers to information in text format that remains after audio data has been converted.

[0471] A "processing unit" is a component that has the function of converting audio data into text data.

[0472] "Online storage" refers to a service that provides space for storing and managing data on the internet.

[0473] The "data storage unit" is an element that implements the function of saving acquired text data to online storage.

[0474] The "labeling unit" is an element that analyzes character data and automatically adds labels that represent related features.

[0475] The "data sharing section" is an element that provides functionality for users to share text data with other platforms and users.

[0476] The "Information Recommendation Section" is a component that has the function of suggesting relevant information and books based on the user's preferences.

[0477] A "visual relationship diagram" is a graphical representation that shows the relationships between data based on labeled data.

[0478] This invention is an interactive information processing system that efficiently records, organizes, and shares user insights based on voice input. The entire system functions primarily through the cooperation of three entities: the terminal, the server, and the user.

[0479] The terminal is a hardware device that receives voice data from the user in real time. Specifically, it captures the user's speech as digital voice data via a microphone and converts this voice data into text data using speech recognition software such as Google Cloud Speech-to-Text. The terminal then sends this text data to the server. For example, if the user says, "I find this character's growth interesting," the terminal instantly converts the voice data into text.

[0480] The server manages the received text data in the cloud. To securely store the data, the server uses online storage services, such as Amazon Web Services (AWS). The server also runs a process that automatically assigns relevant labels to this data using natural language processing techniques. For example, if the word "growth" is present in the text, related labels such as "relationships" and "process" will be assigned. This improves the searchability and organization of the data.

[0481] Furthermore, the server organizes this labeled data into a visual relationship diagram. This diagram helps users visually understand the connections between various pieces of information, promoting personalized information comprehension. For example, if reviews of several books share a common theme such as "growth" or "challenge," the relationship between them is visually represented.

[0482] Finally, the device provides an interface for spreading this information according to the user's wishes. It can be easily shared via social media, email, etc., encouraging discussion. In addition, the server recommends new books and information based on the user's preferences. If a user has expressed many opinions on psychology, they can receive notifications of related new books.

[0483] A concrete example of a prompt message is one that instructs the user to "Please input any impressive ideas or thoughts you had while reading in voice. The system will analyze them and provide relevant information." Such prompt messages make using the system intuitive and easy.

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] The user speaks into the device's microphone about their feelings and thoughts while reading. For example, the user might say, "This character's growth is interesting." The input here is audio data.

[0487] Step 2:

[0488] The device converts received audio data into text data in real time using speech recognition technology such as Google Cloud Speech-to-Text. Because the audio signal processing removes noise while converting speech to text, the output here is text data. This process quickly organizes the user's speech into text format.

[0489] Step 3:

[0490] The terminal sends the converted character data to an online server. A secure communication protocol is used to ensure the safe transfer of data. The input here is character data, and the output is stored in the server's database.

[0491] Step 4:

[0492] The server uses natural language processing techniques to automatically assign relevant labels to the received text data. This process involves text analysis, extracting highly relevant characteristic words, and labeling them with terms such as "growth" and "interesting." The input is text data, and the output is labeled text data.

[0493] Step 5:

[0494] The server analyzes data relationships based on labeled information and generates a visual relationship diagram. Data from multiple books and chapters are linked and graphically displayed so that common themes are immediately apparent. Input is labeled text data, and output is a visual relationship diagram.

[0495] Step 6:

[0496] The terminal displays the generated relationship diagrams and labeled data to the user, and provides an interface that allows for easy sharing via social media and email. Input here consists of visual relationship diagrams and labeled text data, while output allows the user to review and share the information.

[0497] Step 7:

[0498] The server analyzes the user's preferences based on their past input data and recommends new books. Using a machine learning model, it learns the user's preferred genres and tendencies, and suggests new books to read. The input is the user's past data, and the output is information about recommended books.

[0499] (Application Example 1)

[0500] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0501] The system needs to effectively record and organize individual ideas and impressions gained during reading, and recommend related books and content, but it must be provided in a way that is easy for users to use. Furthermore, a means of visualizing and sharing this related information with others is also necessary.

[0502] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0503] In this invention, the server includes a conversion means for acquiring user voice input and converting it into text information, an attribute assignment means for analyzing the text information and automatically assigning relevant attributes, and an adaptation means for providing an interface suitable for a portable information terminal and facilitating voice recording. This allows users to easily record and organize ideas and impressions while reading, and to efficiently discover related learning materials and other resources.

[0504] "Voice input" refers to the act of a technical device receiving and recognizing what a user speaks.

[0505] "Text information" refers to a data format in which non-textual data, such as audio, is converted into a string of characters.

[0506] "Remote data storage" refers to external data storage devices that can be accessed via the internet, such as cloud services.

[0507] "Attribute assignment" is the process of automatically adding labels such as specific keywords or sentiments to text information.

[0508] "Relational structure" refers to graphs and diagrams that visually represent the relationships between data points.

[0509] An "information sharing platform" is an online service that allows users to share content and information with others.

[0510] "Preferences" refer to the tendencies and hobbies that users are particularly interested in.

[0511] "Educational materials" is a general term for books and electronic content used for learning and education.

[0512] A "portable information terminal" refers to a device that is portable and possesses diverse information processing capabilities.

[0513] "Presentation" refers to the act of providing information or data to a user visually or audibly.

[0514] This invention is a system that allows users to use smart devices to input information via voice and effectively record, visualize, and share that information. In particular, it aims to improve the user's reading experience.

[0515] The system primarily consists of the following components: a terminal, a server, and a user-side interface. The terminal is assumed to be a smartphone, utilizing the Google Speech-to-Text API to receive voice input. Through this API, the user's speech is converted into text.

[0516] The server stores the converted text information in Firebase in the cloud. The server then analyzes the information using natural language processing techniques and automatically assigns relevant attributes using libraries such as spacy. Based on these attribute assignments, a graphical relationship structure is generated, allowing users to visually understand the relationships between the information.

[0517] Furthermore, the server recommends relevant educational materials and content based on the user's past usage frequency and preferences. This recommendation feature makes it easier for users to access new information according to their interests and learning motivation.

[0518] Furthermore, the device provides a function that allows users to share the aforementioned information with others via social media, email, etc. This makes it easy for users to communicate their thoughts and impressions to others.

[0519] For example, if a user reads a philosophy book and says, "This idea is very original," that comment will be assigned the attribute "original." Based on this, the server will recommend other books and articles related to philosophy, providing the user with new learning opportunities.

[0520] An example of a prompt message could be: "I've read a new philosophy book, and I'd like to record my thoughts on the ideas presented and be shown related articles."

[0521] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0522] Step 1:

[0523] The user provides voice input to their smartphone. The voice data is captured through the smartphone's microphone. The device sends the voice data to the Google Speech-to-Text API and receives output as text information. In this process, the voice signal is analyzed and converted into a linguistic string.

[0524] Step 2:

[0525] The device's role is to transfer the acquired text information to a cloud database. The text information, as input, is stored in Firebase via the internet. Security is ensured because the data is transmitted in an encrypted format during this process.

[0526] Step 3:

[0527] The server retrieves text information from Firebase and analyzes the data using natural language processing techniques. Using spacy, it extracts specific keywords and sentiments from the input text information. The output is data with relevant attributes attached. This step involves contextual recognition and attribute tagging within the text.

[0528] Step 4:

[0529] The server generates a graphical relationship structure based on attributed data. It takes attribute data as input and performs calculations to determine the relationships between the data. The output is a visualized relationship map, making it easier for users to understand the interrelationships between the information.

[0530] Step 5:

[0531] The server references the user's past preferences and recommends relevant educational materials and content. Based on the user's preference data as input, it uses an algorithm that evaluates similarity to output a recommendation list. This process utilizes machine learning models to achieve personalized recommendations.

[0532] Step 6:

[0533] The device displays the generated relationship structure and recommendation content in the user interface. The front-end framework handles the display of the outputted visualization information and recommendation data to the user. Users can visually review this information and share it as needed.

[0534] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0535] This invention is a system for recording and analyzing a user's daily reading experience and making the most of that knowledge and feedback, and is particularly characterized by its incorporation of an engine that recognizes the user's emotions. This system is realized through a series of interactions between a terminal, a server, and the user.

[0536] The device is designed to receive voice input from the user and also incorporates an emotion engine to enable emotion recognition. It receives voice recordings of emotional statements made by the user while reading, such as "This scene is very moving." This voice data is converted to text using noise cancellation and speech recognition technology, and then analyzed by the emotion engine. The emotion engine analyzes the tone of the voice and the content of the words to identify what emotions the user is experiencing, such as excitement, joy, or sadness.

[0537] Text data is stored in a cloud database and managed by a server. The server analyzes the text data, including user emotional information, using natural language processing technology and automatically assigns relevant tags. Emotional information is also considered in the tagging process; for example, if the emotion "emotional" is recognized, the tag "emotional" will be assigned.

[0538] Next, the server analyzes the relationships between the tagged text data and generates a relationship map that also takes sentiment data into account. This map visually shows which themes users are emotionally responding to, aiding in a deeper understanding.

[0539] Furthermore, the device has a function that recommends relevant books based on the user's past impressions and emotional tendencies. For example, if a user has recorded many instances of feeling "moved" in the past, books that may evoke similar emotions will be recommended. Also, if the user wishes to share this information with others, they can easily do so via social media or email.

[0540] Thus, this system goes beyond simple reading records, taking into account the user's emotions to provide personalized and profound insights into their individual reading experience. As a result, users can engage in more satisfying and meaningful reading activities.

[0541] The following describes the processing flow.

[0542] Step 1:

[0543] Users input their emotional thoughts and opinions into the device via voice while reading. For example, they might say, "The protagonist's growth was very moving."

[0544] Step 2:

[0545] The device uses a speech recognition engine to convert speech data into text data. Simultaneously, it uses an emotion engine to analyze the tone and content of the speech to identify the user's emotions. For example, a statement expressed as "moving" is recognized as the emotion "moved."

[0546] Step 3:

[0547] The device sends the converted text data and sentiment information to a database in the cloud. Encryption technology is applied during this process to protect privacy.

[0548] Step 4:

[0549] The server retrieves text data from a cloud database and analyzes its content using natural language processing technology. Simultaneously, it references emotional information and automatically assigns relevant tags. For example, content describing "the inspiring growth of the protagonist" would be tagged with "growth" and "emotion."

[0550] Step 5:

[0551] The server generates a relationship map between the tagged data. This map visually shows which themes and emotions users are responding to, allowing for a deeper understanding of the reading experience.

[0552] Step 6:

[0553] The device provides an interface that allows users to share generated data and relationship maps via social media or email, if they so desire. Users can easily share their reading experiences with others and exchange opinions.

[0554] Step 7:

[0555] The server analyzes and recommends relevant books based on the user's emotions and preferences. This recommendation process selects and presents books that evoke similar emotions, for example, if the user frequently expresses the emotion of being "emotional."

[0556] In this way, the system incorporates the emotions users feel while reading, aiming to improve knowledge management and the reading experience in a way that suits their individual needs and interests.

[0557] (Example 2)

[0558] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0559] Traditional reading log systems merely record book titles and impressions, failing to capture the nuances of emotions users felt while reading or recommend related information based on those emotions. Furthermore, they lack easy ways to visually express and share emotions. As a result, users are unable to fully utilize their reading experience and struggle to discover further reading options.

[0560] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0561] In this invention, the server includes input means for acquiring user voice input and converting it into text data, information tagging means for analyzing the text data and automatically assigning relevant tags, and emotion recognition means for recognizing and evaluating emotions based on the user's expressions. This enables evaluation of the reading experience based on the user's emotions, and the recommendation and sharing of relevant information accordingly.

[0562] "Input means" refers to a device or method that acquires voice input from a user and converts it into text data.

[0563] "Data storage means" refers to a system or process for securely storing converted text data on the cloud.

[0564] An "information tagging method" is a technology or algorithm that analyzes text data and automatically assigns the appropriate tags.

[0565] A "mapping method" is a technique or method for generating a graphical relationship map based on tagged data.

[0566] "Sharing means" refers to a method or device for making relationship maps and text data shareable with others via a communication medium.

[0567] "Information recommendation methods" refer to technologies or algorithms that recommend relevant information sources based on the user's preferences and emotions.

[0568] "Emotion recognition means" refers to a technology or engine for recognizing emotions based on user expressions, and for evaluating and analyzing those emotions.

[0569] "Emotion mapping means" refers to a technology or method for generating a visual emotion map based on user emotion data.

[0570] The system for carrying out this invention aims to record, analyze, and provide relevant information about the user's reading experience. Details are provided below.

[0571] The device uses a built-in high-precision microphone to capture the user's voice. This device converts the speech to text using speech recognition software while performing noise cancellation. Specifically, it processes the audio data using speech services such as the Google Cloud Speech-to-Text API. For example, if a user says "This part is very interesting" while reading, that speech is converted to text.

[0572] The device also sends the converted text to an emotion recognition engine. This engine uses natural language processing techniques to analyze the user's emotions from the text content and tone of voice. The emotion recognition engine utilizes open-source natural language processing libraries (e.g., NLTK, TensorFlow) to identify the user's emotions as "joy," "excitement," "surprise," etc.

[0573] The server securely stores and manages all text and sentiment data using a cloud database service (e.g., Amazon DynamoDB). User text data is tagged with informational tags, and a data analysis module calculates the relationships between the data. This generates a relationship map.

[0574] This system analyzes the user's past reading data and recommends relevant information sources, particularly based on content that resonated emotionally with them. The recommendation engine employs collaborative filtering to find and present books similar to those that moved the user.

[0575] Furthermore, the server generates a visual relationship map based on sentiment data, visualizing which themes users are emotionally responding to. This map helps to gain a deeper understanding of the user's reading habits.

[0576] For example, if a user says something like, "I was excited by this adventure scene," this emotion data is analyzed and assigned the emotion tag "excited." The subsequent generated relevance map includes books and content related to this emotion.

[0577] An example of a prompt for a generative AI model would be, "Please describe a system for recommending information based on user sentiment."

[0578] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0579] Step 1:

[0580] The device acquires user speech using an audio input device. The input is voice data, which includes the user's emotions. This voice data is captured with a high-precision microphone, and ambient noise is minimized using noise cancellation technology. The acquired voice data is then sent to speech recognition software.

[0581] Step 2:

[0582] The device uses speech recognition software (e.g., Google Cloud Speech-to-Text API) to convert audio data into text data. The input is the audio data acquired in step 1, and the output is text data. The speech recognition process analyzes words and phrases within the audio data and accurately converts them into corresponding text.

[0583] Step 3:

[0584] The terminal transfers the converted text data to the emotion recognition engine. The input is text data, and the output is the emotion information contained in the text. The emotion recognition engine uses natural language processing techniques to evaluate emotions from the content of the text. For example, it can identify emotions such as joy, surprise, and emotion.

[0585] Step 4:

[0586] The terminal packages text data and identified sentiment information and sends it to the server. The input is text and sentiment information, and the output is data transmission to the server. This data is sent to the server using a stable communication protocol for subsequent analysis and storage processes.

[0587] Step 5:

[0588] The server manages text data and sentiment information using a cloud database. Input is data sent from the terminal, and output is storage in the database. The server stores data using a highly secure database service (e.g., Amazon DynamoDB). The stored data is made available for retrieval and analysis at any time.

[0589] Step 6:

[0590] The server uses a data analysis module to parse stored text data and automatically assigns relevant tags. The input is stored text data, and the output is tagged data. Natural language processing techniques are used to efficiently add appropriate tags based on the themes and content of different texts.

[0591] Step 7:

[0592] The server generates a graphical relationship map based on tagged data and sentiment information. The input is tagged data and sentiment information, and the output is a visual relationship map. This map shows the relationships between data and patterns of user sentiment, and is generated using visualization tools.

[0593] Step 8:

[0594] The user receives recommendation information from the server via their device based on sentiment data and relationship maps. The input is the information generated in the previous step, and the output is a list of books and related information presented to the user. These recommendations are provided based on the user's past sentiment patterns.

[0595] (Application Example 2)

[0596] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0597] Traditional reading record and recommendation systems do not adequately consider user emotions and opinions, making it difficult to provide a personalized experience based on individual preferences. Furthermore, a challenge remains in how to analyze the acquired data and return it to users as valuable information.

[0598] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0599] In this invention, the server includes an acquisition means for acquiring user voice input and converting it into text data, an assignment means for analyzing the text data and automatically assigning relevant attributes, and an emotion recognition means for recognizing the user's emotional state from the voice and utilizing it in recommending the literature. This enables effective literature recommendations based on the user's emotions and preferences.

[0600] "Acquisition means" refers to a device or method that has the function of collecting voice input from a user and converting it into text format.

[0601] "Storage means" refers to a device or method that has the function of securely storing text data on the cloud and making it accessible at a later date.

[0602] "Assignment means" refers to a device or method that has the function of analyzing text data and automatically adding related attributes thereto.

[0603] "Representation generation means" refers to a device or method that has the function of generating diagrams or maps that show visual relationships based on data to which attributes have been assigned.

[0604] "Sharing means" refers to a device or method that has the function of making generated relational expressions or text data shareable with other users on a network medium.

[0605] A "recommendation tool" is a device or method that has the function of selecting and suggesting relevant literature based on the user's preferences and emotions.

[0606] "Emotion recognition means" refers to a device or method that has the function of identifying emotions from a user's voice and applying that information to recommend literature, etc.

[0607] The system for implementing the present invention consists of a user, a terminal, and a server. The user expresses their thoughts on a book they are reading in voice, and the terminal acquires this voice, performs noise reduction, and converts it into text data. A terminal with emotion recognition capabilities analyzes the user's voice tone and the content of their words to identify their emotions. This emotion information is stored in the cloud along with the text data.

[0608] The server analyzes the stored text data using a natural language processing engine and assigns relevant attributes. This generates a visual relationship map to visualize the themes and emotions the user is responding to. Furthermore, based on this emotional information and preference history, the server recommends relevant literature to the user. The generated relationship representations and recommended books can also be shared via network media at the user's request.

[0609] For example, if a user voice-expresses their opinion, saying, "This part is really interesting!", the device recognizes this as "excitement." As a result, the server recommends new reading material based on related books that the user previously rated when they felt "excited." In this way, the system personalizes the reading experience according to the user's emotions and preferences.

[0610] Examples of prompts to input into a generative AI model include: "Describe a scene in which the user had an emotional reaction, and list other books that evoke similar emotions."

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] The device acquires voice input from the user via a microphone. Noise reduction technology is used to clarify the acquired voice data, and a speech recognition engine converts it into text data. The input is voice data, and the output is the converted text data.

[0614] Step 2:

[0615] The device analyzes the converted text data using an emotion recognition engine to identify the user's emotions. The analysis targets voice tone and word content, and the output is the identified emotion information.

[0616] Step 3:

[0617] The server stores text data and sentiment information sent from the terminal in the cloud. The stored data is used for later analysis and recommendations. The input is text data and sentiment information, and the output is the data recorded in the cloud.

[0618] Step 4:

[0619] The server analyzes the stored data using natural language processing techniques and assigns relevant attributes to the data. This adds themes related to the text as tags. The input is the stored text data, and the output is the tagged data.

[0620] Step 5:

[0621] The server generates a visual relationship map based on tagged data using a generative AI model. By providing this prompt to the model, the relationships between data points are visualized. The input is tagged data, and the output is a relationship map.

[0622] Step 6:

[0623] The server recommends literature that may evoke similar emotions, based on the user's past emotional information and preference patterns. This recommendation information is likely to be of interest to the user. The input is the user's emotional information and preference patterns, and the output is the recommended literature information.

[0624] Step 7:

[0625] Users can share the generated relationship maps and recommended literature with friends and followers on network media. This step is performed through the sharing function. The input is the relationship map and literature information, and the output is the shared information.

[0626] 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.

[0627] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] 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.

[0632] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0633] 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.

[0634] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0635] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0636] 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.

[0637] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0638] 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.

[0639] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The 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.

[0641] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0642] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] This invention is an interactive system that allows users to input ideas and impressions gained while reading via voice, effectively record, organize, and share that content, and further recommend related books. This system is operated primarily through the interaction of a terminal, a server, and the user.

[0644] First, the device utilizes speech recognition technology to receive user voice input. As the user reads the book, they input their thoughts and feelings in voice, for example, "The way this story unfolded was unexpected." The device then converts this voice into text data in real time.

[0645] The converted text data is automatically sent to a cloud database managed by the server. There, the server uses natural language processing technology to automatically assign relevant tags to the text data. For example, if the keyword "unexpected" is included, the tag "surprise" will be added. This tagged data is then useful for subsequent searching and classification.

[0646] Furthermore, the server generates a relationship map based on this data. When a user inputs information about multiple books, if there are common themes or keywords among them, these are displayed graphically, allowing the user to visually understand the relationships between the information.

[0647] The device also provides an interface for users to share this recorded data via social media or email, if they so desire. This can be used by users to spread knowledge or facilitate discussions.

[0648] Furthermore, the server analyzes the user's reading history and preferences to recommend relevant books. For example, if a user has recorded many thoughts related to psychology, new books in that genre will be automatically recommended.

[0649] In this way, by using this system, users can not only read books, but also organize their own knowledge, share it with others, and gain new intellectual horizons.

[0650] The following describes the processing flow.

[0651] Step 1:

[0652] Users input ideas and thoughts that come to mind while reading into the device via voice. For example, they might say, "The ending of this story was surprising."

[0653] Step 2:

[0654] The device converts the acquired audio into text data using a speech recognition engine. During this process, noise cancellation technology is used to remove ambient noise.

[0655] Step 3:

[0656] The device sends the converted text data to a database in the cloud. Security protocols are applied to this transmission, ensuring the data is stored securely.

[0657] Step 4:

[0658] The server retrieves text data stored in the database and analyzes it using natural language processing.

[0659] Step 5:

[0660] The server automatically assigns tags to each text based on the analysis results. For example, if the text contains the word "surprise," it will attach the tag "surprise."

[0661] Step 6:

[0662] The server generates a relationship map between data based on the tagged data, visually showing how different data are related.

[0663] Step 7:

[0664] The device provides an interface for sharing text data and relationship maps via social media or email, according to the user's preferences.

[0665] Step 8:

[0666] The server analyzes the user's historical data and, based on the results, selects and recommends relevant books to the user. This recommendation is based on the user's reading habits.

[0667] (Example 1)

[0668] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] In modern times, it is difficult to efficiently record, organize, and share the insights and impressions gained from reading. Furthermore, the insufficient search capabilities for related information and the lack of personalized recommendations based on individual preferences limit users' ability to utilize information effectively.

[0670] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0671] In this invention, the server includes a processing unit that acquires user voice data and converts it into text data, a data storage unit that stores the text data in online storage, and a labeling unit that analyzes the text data and automatically assigns relevant characteristic words. This enables efficient data conversion and organization based on voice input.

[0672] "Audio data" refers to the digital format of information input by the user as voice.

[0673] "Text data" refers to information in text format that remains after audio data has been converted.

[0674] A "processing unit" is a component that has the function of converting audio data into text data.

[0675] "Online storage" refers to a service that provides space for storing and managing data on the internet.

[0676] The "data storage unit" is an element that implements the function of saving acquired text data to online storage.

[0677] The "labeling unit" is an element that analyzes character data and automatically adds labels that represent related features.

[0678] The "data sharing section" is an element that provides functionality for users to share text data with other platforms and users.

[0679] The "Information Recommendation Section" is a component that has the function of suggesting relevant information and books based on the user's preferences.

[0680] A "visual relationship diagram" is a graphical representation that shows the relationships between data based on labeled data.

[0681] This invention is an interactive information processing system that efficiently records, organizes, and shares user insights based on voice input. The entire system functions primarily through the cooperation of three entities: the terminal, the server, and the user.

[0682] The terminal is a hardware device that receives voice data from the user in real time. Specifically, it captures the user's speech as digital voice data via a microphone and converts this voice data into text data using speech recognition software such as Google Cloud Speech-to-Text. The terminal then sends this text data to the server. For example, if the user says, "I find this character's growth interesting," the terminal instantly converts the voice data into text.

[0683] The server manages the received text data in the cloud. To securely store the data, the server uses online storage services, such as Amazon Web Services (AWS). The server also runs a process that automatically assigns relevant labels to this data using natural language processing techniques. For example, if the word "growth" is present in the text, related labels such as "relationships" and "process" will be assigned. This improves the searchability and organization of the data.

[0684] Furthermore, the server organizes this labeled data into a visual relationship diagram. This diagram helps users visually understand the connections between various pieces of information, promoting personalized information comprehension. For example, if reviews of several books share a common theme such as "growth" or "challenge," the relationship between them is visually represented.

[0685] Finally, the device provides an interface for spreading this information according to the user's wishes. It can be easily shared via social media, email, etc., encouraging discussion. In addition, the server recommends new books and information based on the user's preferences. If a user has expressed many opinions on psychology, they can receive notifications of related new books.

[0686] A concrete example of a prompt message is one that instructs the user to "Please input any impressive ideas or thoughts you had while reading in voice. The system will analyze them and provide relevant information." Such prompt messages make using the system intuitive and easy.

[0687] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0688] Step 1:

[0689] The user speaks into the device's microphone about their feelings and thoughts while reading. For example, the user might say, "This character's growth is interesting." The input here is audio data.

[0690] Step 2:

[0691] The device converts received audio data into text data in real time using speech recognition technology such as Google Cloud Speech-to-Text. Because the audio signal processing removes noise while converting speech to text, the output here is text data. This process quickly organizes the user's speech into text format.

[0692] Step 3:

[0693] The terminal sends the converted character data to an online server. A secure communication protocol is used to ensure the safe transfer of data. The input here is character data, and the output is stored in the server's database.

[0694] Step 4:

[0695] The server uses natural language processing techniques to automatically assign relevant labels to the received text data. This process involves text analysis, extracting highly relevant characteristic words, and labeling them with terms such as "growth" and "interesting." The input is text data, and the output is labeled text data.

[0696] Step 5:

[0697] The server analyzes data relationships based on labeled information and generates a visual relationship diagram. Data from multiple books and chapters are linked and graphically displayed so that common themes are immediately apparent. Input is labeled text data, and output is a visual relationship diagram.

[0698] Step 6:

[0699] The terminal displays the generated relationship diagrams and labeled data to the user, and provides an interface that allows for easy sharing via social media and email. Input here consists of visual relationship diagrams and labeled text data, while output allows the user to review and share the information.

[0700] Step 7:

[0701] The server analyzes the user's preferences based on their past input data and recommends new books. Using a machine learning model, it learns the user's preferred genres and tendencies, and suggests new books to read. The input is the user's past data, and the output is information about recommended books.

[0702] (Application Example 1)

[0703] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0704] The system needs to effectively record and organize individual ideas and impressions gained during reading, and recommend related books and content, but it must be provided in a way that is easy for users to use. Furthermore, a means of visualizing and sharing this related information with others is also necessary.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0706] In this invention, the server includes a conversion means for acquiring user voice input and converting it into text information, an attribute assignment means for analyzing the text information and automatically assigning relevant attributes, and an adaptation means for providing an interface suitable for a portable information terminal and facilitating voice recording. This allows users to easily record and organize ideas and impressions while reading, and to efficiently discover related learning materials and other resources.

[0707] "Voice input" refers to the act of a technical device receiving and recognizing what a user speaks.

[0708] "Text information" refers to a data format in which non-textual data, such as audio, is converted into a string of characters.

[0709] "Remote data storage" refers to external data storage devices that can be accessed via the internet, such as cloud services.

[0710] "Attribute assignment" is the process of automatically adding labels such as specific keywords or sentiments to text information.

[0711] "Relational structure" refers to graphs and diagrams that visually represent the relationships between data points.

[0712] An "information sharing platform" is an online service that allows users to share content and information with others.

[0713] "Preferences" refer to the tendencies and hobbies that users are particularly interested in.

[0714] "Educational materials" is a general term for books and electronic content used for learning and education.

[0715] A "portable information terminal" refers to a device that is portable and possesses diverse information processing capabilities.

[0716] "Presentation" refers to the act of providing information or data to a user visually or audibly.

[0717] This invention is a system that allows users to use smart devices to input information via voice and effectively record, visualize, and share that information. In particular, it aims to improve the user's reading experience.

[0718] The system primarily consists of the following components: a terminal, a server, and a user-side interface. The terminal is assumed to be a smartphone, utilizing the Google Speech-to-Text API to receive voice input. Through this API, the user's speech is converted into text.

[0719] The server stores the converted text information in Firebase in the cloud. The server then analyzes the information using natural language processing techniques and automatically assigns relevant attributes using libraries such as spacy. Based on these attribute assignments, a graphical relationship structure is generated, allowing users to visually understand the relationships between the information.

[0720] Furthermore, the server recommends relevant educational materials and content based on the user's past usage frequency and preferences. This recommendation feature makes it easier for users to access new information according to their interests and learning motivation.

[0721] Furthermore, the device provides a function that allows users to share the aforementioned information with others via social media, email, etc. This makes it easy for users to communicate their thoughts and impressions to others.

[0722] For example, if a user reads a philosophy book and says, "This idea is very original," that comment will be assigned the attribute "original." Based on this, the server will recommend other books and articles related to philosophy, providing the user with new learning opportunities.

[0723] An example of a prompt message could be: "I've read a new philosophy book, and I'd like to record my thoughts on the ideas presented and be shown related articles."

[0724] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0725] Step 1:

[0726] The user provides voice input to their smartphone. The voice data is captured through the smartphone's microphone. The device sends the voice data to the Google Speech-to-Text API and receives output as text information. In this process, the voice signal is analyzed and converted into a linguistic string.

[0727] Step 2:

[0728] The device's role is to transfer the acquired text information to a cloud database. The text information, as input, is stored in Firebase via the internet. Security is ensured because the data is transmitted in an encrypted format during this process.

[0729] Step 3:

[0730] The server retrieves text information from Firebase and analyzes the data using natural language processing techniques. Using spacy, it extracts specific keywords and sentiments from the input text information. The output is data with relevant attributes attached. This step involves contextual recognition and attribute tagging within the text.

[0731] Step 4:

[0732] The server generates a graphical relationship structure based on attributed data. It takes attribute data as input and performs calculations to determine the relationships between the data. The output is a visualized relationship map, making it easier for users to understand the interrelationships between the information.

[0733] Step 5:

[0734] The server references the user's past preferences and recommends relevant educational materials and content. Based on the user's preference data as input, it uses an algorithm that evaluates similarity to output a recommendation list. This process utilizes machine learning models to achieve personalized recommendations.

[0735] Step 6:

[0736] The device displays the generated relationship structure and recommendation content in the user interface. The front-end framework handles the display of the outputted visualization information and recommendation data to the user. Users can visually review this information and share it as needed.

[0737] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0738] This invention is a system for recording and analyzing a user's daily reading experience and making the most of that knowledge and feedback, and is particularly characterized by its incorporation of an engine that recognizes the user's emotions. This system is realized through a series of interactions between a terminal, a server, and the user.

[0739] The device is designed to receive voice input from the user and also incorporates an emotion engine to enable emotion recognition. It receives voice recordings of emotional statements made by the user while reading, such as "This scene is very moving." This voice data is converted to text using noise cancellation and speech recognition technology, and then analyzed by the emotion engine. The emotion engine analyzes the tone of the voice and the content of the words to identify what emotions the user is experiencing, such as excitement, joy, or sadness.

[0740] Text data is stored in a cloud database and managed by a server. The server analyzes the text data, including user emotional information, using natural language processing technology and automatically assigns relevant tags. Emotional information is also considered in the tagging process; for example, if the emotion "emotional" is recognized, the tag "emotional" will be assigned.

[0741] Next, the server analyzes the relationships between the tagged text data and generates a relationship map that also takes sentiment data into account. This map visually shows which themes users are emotionally responding to, aiding in a deeper understanding.

[0742] Furthermore, the device has a function that recommends relevant books based on the user's past impressions and emotional tendencies. For example, if a user has recorded many instances of feeling "moved" in the past, books that may evoke similar emotions will be recommended. Also, if the user wishes to share this information with others, they can easily do so via social media or email.

[0743] Thus, this system goes beyond simple reading records, taking into account the user's emotions to provide personalized and profound insights into their individual reading experience. As a result, users can engage in more satisfying and meaningful reading activities.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] Users input their emotional thoughts and opinions into the device via voice while reading. For example, they might say, "The protagonist's growth was very moving."

[0747] Step 2:

[0748] The device uses a speech recognition engine to convert speech data into text data. Simultaneously, it uses an emotion engine to analyze the tone and content of the speech to identify the user's emotions. For example, a statement expressed as "moving" is recognized as the emotion "moved."

[0749] Step 3:

[0750] The device sends the converted text data and sentiment information to a database in the cloud. Encryption technology is applied during this process to protect privacy.

[0751] Step 4:

[0752] The server retrieves text data from a cloud database and analyzes its content using natural language processing technology. Simultaneously, it references emotional information and automatically assigns relevant tags. For example, content describing "the inspiring growth of the protagonist" would be tagged with "growth" and "emotion."

[0753] Step 5:

[0754] The server generates a relationship map between the tagged data. This map visually shows which themes and emotions users are responding to, allowing for a deeper understanding of the reading experience.

[0755] Step 6:

[0756] The device provides an interface that allows users to share generated data and relationship maps via social media or email, if they so desire. Users can easily share their reading experiences with others and exchange opinions.

[0757] Step 7:

[0758] The server analyzes and recommends relevant books based on the user's emotions and preferences. This recommendation process selects and presents books that evoke similar emotions, for example, if the user frequently expresses the emotion of being "emotional."

[0759] In this way, the system incorporates the emotions users feel while reading, aiming to improve knowledge management and the reading experience in a way that suits their individual needs and interests.

[0760] (Example 2)

[0761] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] Traditional reading log systems merely record book titles and impressions, failing to capture the nuances of emotions users felt while reading or recommend related information based on those emotions. Furthermore, they lack easy ways to visually express and share emotions. As a result, users are unable to fully utilize their reading experience and struggle to discover further reading options.

[0763] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0764] In this invention, the server includes input means for acquiring user voice input and converting it into text data, information tagging means for analyzing the text data and automatically assigning relevant tags, and emotion recognition means for recognizing and evaluating emotions based on the user's expressions. This enables evaluation of the reading experience based on the user's emotions, and the recommendation and sharing of relevant information accordingly.

[0765] "Input means" refers to a device or method that acquires voice input from a user and converts it into text data.

[0766] "Data storage means" refers to a system or process for securely storing converted text data on the cloud.

[0767] An "information tagging method" is a technology or algorithm that analyzes text data and automatically assigns the appropriate tags.

[0768] A "mapping method" is a technique or method for generating a graphical relationship map based on tagged data.

[0769] "Sharing means" refers to a method or device for making relationship maps and text data shareable with others via a communication medium.

[0770] "Information recommendation methods" refer to technologies or algorithms that recommend relevant information sources based on the user's preferences and emotions.

[0771] "Emotion recognition means" refers to a technology or engine for recognizing emotions based on user expressions, and for evaluating and analyzing those emotions.

[0772] "Emotion mapping means" refers to a technology or method for generating a visual emotion map based on user emotion data.

[0773] The system for carrying out this invention aims to record, analyze, and provide relevant information about the user's reading experience. Details are provided below.

[0774] The device uses a built-in high-precision microphone to capture the user's voice. This device converts the speech to text using speech recognition software while performing noise cancellation. Specifically, it processes the audio data using speech services such as the Google Cloud Speech-to-Text API. For example, if a user says "This part is very interesting" while reading, that speech is converted to text.

[0775] The device also sends the converted text to an emotion recognition engine. This engine uses natural language processing techniques to analyze the user's emotions from the text content and tone of voice. The emotion recognition engine utilizes open-source natural language processing libraries (e.g., NLTK, TensorFlow) to identify the user's emotions as "joy," "excitement," "surprise," etc.

[0776] The server securely stores and manages all text and sentiment data using a cloud database service (e.g., Amazon DynamoDB). User text data is tagged with informational tags, and a data analysis module calculates the relationships between the data. This generates a relationship map.

[0777] This system analyzes the user's past reading data and recommends relevant information sources, particularly based on content that resonated emotionally with them. The recommendation engine employs collaborative filtering to find and present books similar to those that moved the user.

[0778] Furthermore, the server generates a visual relationship map based on sentiment data, visualizing which themes users are emotionally responding to. This map helps to gain a deeper understanding of the user's reading habits.

[0779] For example, if a user says something like, "I was excited by this adventure scene," this emotion data is analyzed and assigned the emotion tag "excited." The subsequent generated relevance map includes books and content related to this emotion.

[0780] An example of a prompt for a generative AI model would be, "Please describe a system for recommending information based on user sentiment."

[0781] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0782] Step 1:

[0783] The device acquires user speech using an audio input device. The input is voice data, which includes the user's emotions. This voice data is captured with a high-precision microphone, and ambient noise is minimized using noise cancellation technology. The acquired voice data is then sent to speech recognition software.

[0784] Step 2:

[0785] The device uses speech recognition software (e.g., Google Cloud Speech-to-Text API) to convert audio data into text data. The input is the audio data acquired in step 1, and the output is text data. The speech recognition process analyzes words and phrases within the audio data and accurately converts them into corresponding text.

[0786] Step 3:

[0787] The terminal transfers the converted text data to the emotion recognition engine. The input is text data, and the output is the emotion information contained in the text. The emotion recognition engine uses natural language processing techniques to evaluate emotions from the content of the text. For example, it can identify emotions such as joy, surprise, and emotion.

[0788] Step 4:

[0789] The terminal packages text data and identified sentiment information and sends it to the server. The input is text and sentiment information, and the output is data transmission to the server. This data is sent to the server using a stable communication protocol for subsequent analysis and storage processes.

[0790] Step 5:

[0791] The server manages text data and sentiment information using a cloud database. Input is data sent from the terminal, and output is storage in the database. The server stores data using a highly secure database service (e.g., Amazon DynamoDB). The stored data is made available for retrieval and analysis at any time.

[0792] Step 6:

[0793] The server uses a data analysis module to parse stored text data and automatically assigns relevant tags. The input is stored text data, and the output is tagged data. Natural language processing techniques are used to efficiently add appropriate tags based on the themes and content of different texts.

[0794] Step 7:

[0795] The server generates a graphical relationship map based on tagged data and sentiment information. The input is tagged data and sentiment information, and the output is a visual relationship map. This map shows the relationships between data and patterns of user sentiment, and is generated using visualization tools.

[0796] Step 8:

[0797] The user receives recommendation information from the server via their device based on sentiment data and relationship maps. The input is the information generated in the previous step, and the output is a list of books and related information presented to the user. These recommendations are provided based on the user's past sentiment patterns.

[0798] (Application Example 2)

[0799] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0800] Traditional reading record and recommendation systems do not adequately consider user emotions and opinions, making it difficult to provide a personalized experience based on individual preferences. Furthermore, a challenge remains in how to analyze the acquired data and return it to users as valuable information.

[0801] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0802] In this invention, the server includes an acquisition means for acquiring user voice input and converting it into text data, an assignment means for analyzing the text data and automatically assigning relevant attributes, and an emotion recognition means for recognizing the user's emotional state from the voice and utilizing it in recommending the literature. This enables effective literature recommendations based on the user's emotions and preferences.

[0803] "Acquisition means" refers to a device or method that has the function of collecting voice input from a user and converting it into text format.

[0804] "Storage means" refers to a device or method that has the function of securely storing text data on the cloud and making it accessible at a later date.

[0805] "Assignment means" refers to a device or method that has the function of analyzing text data and automatically adding related attributes thereto.

[0806] "Representation generation means" refers to a device or method that has the function of generating diagrams or maps that show visual relationships based on data to which attributes have been assigned.

[0807] "Sharing means" refers to a device or method that has the function of making generated relational expressions or text data shareable with other users on a network medium.

[0808] A "recommendation tool" is a device or method that has the function of selecting and suggesting relevant literature based on the user's preferences and emotions.

[0809] "Emotion recognition means" refers to a device or method that has the function of identifying emotions from a user's voice and applying that information to recommend literature, etc.

[0810] The system for implementing the present invention consists of a user, a terminal, and a server. The user expresses their thoughts on a book they are reading in voice, and the terminal acquires this voice, performs noise reduction, and converts it into text data. A terminal with emotion recognition capabilities analyzes the user's voice tone and the content of their words to identify their emotions. This emotion information is stored in the cloud along with the text data.

[0811] The server analyzes the stored text data using a natural language processing engine and assigns relevant attributes. This generates a visual relationship map to visualize the themes and emotions the user is responding to. Furthermore, based on this emotional information and preference history, the server recommends relevant literature to the user. The generated relationship representations and recommended books can also be shared via network media at the user's request.

[0812] For example, if a user voice-expresses their opinion, saying, "This part is really interesting!", the device recognizes this as "excitement." As a result, the server recommends new reading material based on related books that the user previously rated when they felt "excited." In this way, the system personalizes the reading experience according to the user's emotions and preferences.

[0813] Examples of prompts to input into a generative AI model include: "Describe a scene in which the user had an emotional reaction, and list other books that evoke similar emotions."

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] The device acquires voice input from the user via a microphone. Noise reduction technology is used to clarify the acquired voice data, and a speech recognition engine converts it into text data. The input is voice data, and the output is the converted text data.

[0817] Step 2:

[0818] The device analyzes the converted text data using an emotion recognition engine to identify the user's emotions. The analysis targets voice tone and word content, and the output is the identified emotion information.

[0819] Step 3:

[0820] The server stores text data and sentiment information sent from the terminal in the cloud. The stored data is used for later analysis and recommendations. The input is text data and sentiment information, and the output is the data recorded in the cloud.

[0821] Step 4:

[0822] The server analyzes the stored data using natural language processing techniques and assigns relevant attributes to the data. This adds themes related to the text as tags. The input is the stored text data, and the output is the tagged data.

[0823] Step 5:

[0824] The server generates a visual relationship map based on tagged data using a generative AI model. By providing this prompt to the model, the relationships between data points are visualized. The input is tagged data, and the output is a relationship map.

[0825] Step 6:

[0826] The server recommends literature that may evoke similar emotions, based on the user's past emotional information and preference patterns. This recommendation information is likely to be of interest to the user. The input is the user's emotional information and preference patterns, and the output is the recommended literature information.

[0827] Step 7:

[0828] Users can share the generated relationship maps and recommended literature with friends and followers on network media. This step is performed through the sharing function. The input is the relationship map and literature information, and the output is the shared information.

[0829] 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.

[0830] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0831] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0832] 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.

[0833] Figure 9 shows an 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.

[0834] 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.

[0835] 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.

[0836] 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, motorcycles, etc., 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, for example, based 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.

[0837] 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."

[0838] 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.

[0839] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0840] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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 the like 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.

[0849] 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.

[0850] The following is further disclosed regarding the embodiments described above.

[0851] (Claim 1)

[0852] A recording means that acquires user voice input and converts it into text data,

[0853] A storage means for saving the aforementioned text data to the cloud,

[0854] A tagging means that analyzes the aforementioned text data and automatically assigns relevant tags,

[0855] A mapping means for generating a graphical relationship map based on the tagged data,

[0856] A sharing means that enables the sharing of the aforementioned relationship map and text data on social media, etc.

[0857] A recommendation system that suggests relevant books based on the user's preferences,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, which uses a speech recognition engine to convert speech into text data while performing noise cancellation.

[0861] (Claim 3)

[0862] The system according to claim 1, which uses natural language processing technology to assign relevant tags to text data.

[0863] "Example 1"

[0864] (Claim 1)

[0865] A processing unit that acquires user voice data and converts it into text data,

[0866] A data storage unit that stores the aforementioned character data in online storage,

[0867] A labeling unit that analyzes the aforementioned character data and automatically assigns related characteristic words,

[0868] Based on the labeled data, a diagram generation unit generates a visual relationship diagram.

[0869] A data sharing unit that enables the sharing of the aforementioned relationship diagram and text data on an information sharing platform,

[0870] A recommendation department that recommends relevant books based on user preferences,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, which uses speech recognition technology to convert speech into text data while performing noise reduction.

[0874] (Claim 3)

[0875] The system according to claim 1, which uses text analysis technology to assign relevant feature words to character data.

[0876] "Application Example 1"

[0877] (Claim 1)

[0878] A conversion means that acquires user voice input and converts it into text information,

[0879] Recording means for storing the aforementioned text information on remote data storage,

[0880] An attribute assignment means that analyzes the aforementioned text information and automatically assigns relevant attributes,

[0881] A structure generation means that generates a visual relationship structure based on the attributed information,

[0882] A sharing means that enables the sharing of the aforementioned relationship structure and text information on an information sharing platform,

[0883] A recommendation system that recommends relevant educational materials based on user preferences,

[0884] An interface suitable for portable information terminals, and a means for facilitating voice recording,

[0885] A presentation method that presents similar learning materials and articles based on the aforementioned information,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, which uses a speech processing function to convert speech into text information while removing noise.

[0889] (Claim 3)

[0890] The system according to claim 1, which uses natural language processing technology to assign relevant attributes to text information.

[0891] "Example 2 of combining an emotion engine"

[0892] (Claim 1)

[0893] An input means that acquires user voice input and converts it into text data,

[0894] A data storage means for storing the aforementioned text data on the cloud,

[0895] Information tagging means that analyzes the aforementioned text data and automatically assigns relevant tags,

[0896] A mapping means for generating a graphical relationship map based on the tagged data,

[0897] A sharing means that enables the sharing of the aforementioned relationship map and text data via a communication medium,

[0898] An information recommendation system that recommends relevant information sources based on user preferences,

[0899] An emotion recognition means that recognizes and evaluates emotions based on user expressions,

[0900] An emotion mapping means for generating a visual emotion map based on user emotion data,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, which uses speech recognition technology to convert speech into text data while suppressing noise.

[0904] (Claim 3)

[0905] The system according to claim 1, which uses natural language processing technology to assign relevant tags and sentiment information to text data.

[0906] "Application example 2 when combining with an emotional engine"

[0907] (Claim 1)

[0908] A means for acquiring user voice input and converting it into text data,

[0909] A storage means for saving the aforementioned text data to the cloud,

[0910] The aforementioned text data is analyzed and an assignment means automatically assigns relevant attributes,

[0911] A representation generation means that generates a visual representation of relationships based on data to which the aforementioned attributes have been assigned,

[0912] A sharing means that enables the sharing of the aforementioned relationship expressions and text data over network media,

[0913] A recommendation system that recommends relevant literature based on user preferences,

[0914] An emotion recognition means that recognizes the user's emotional state from their voice and utilizes it for recommending the aforementioned literature,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, which uses a speech recognition engine to convert data into text data while performing noise reduction.

[0918] (Claim 3)

[0919] The system according to claim 1, which uses natural language processing technology to assign relevant attributes to text data. [Explanation of Symbols]

[0920] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A recording means that acquires user voice input and converts it into text data, A storage means for saving the aforementioned text data to the cloud, A tagging means that analyzes the aforementioned text data and automatically assigns relevant tags, A mapping means for generating a graphical relationship map based on the tagged data, A sharing means that enables the sharing of the aforementioned relationship map and text data on social media, etc. A recommendation system that suggests relevant books based on the user's preferences, A system that includes this.

2. The system according to claim 1, which uses a speech recognition engine to convert speech into text data while performing noise cancellation.

3. The system according to claim 1, which uses natural language processing technology to assign relevant tags to text data.

Images