system

Abstract

We provide the system. [Solution] Information processing means for analyzing user preferences based on reading history, A means of using a generative model that recommends similar books based on the analysis results obtained by the aforementioned information processing means, A means of analyzing user reviews of recommended books and providing evaluations, 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 method for controlling a persona chatbot, which is 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 in 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] Currently, when choosing books, they are often selected based on simple rankings or sales information, and users tend to choose books that do not match their preferences. Also, since they tend to be biased towards the same genre, an effective method for leading to new genres is required. Furthermore, personalized recommendations considering individual preferences of users are insufficient, resulting in a problem that the reading experience is limited.

Means for Solving the Problems

[0005] This invention provides a system that analyzes a user's reading history and preferences in detail using information processing means. It also recommends similar books using a generative model based on the analysis results, and further provides book ratings by analyzing user reviews. In addition, by continuously updating the generative model based on user feedback, the system enhances the accuracy of personalized recommendations and supports users in exploring new genres, thereby broadening the reading experience.

[0006] "User reading history" refers to a record of information about books a user has read in the past, along with their ratings and comments.

[0007] "Information processing means" refers to a device or program that has the function of analyzing user data and identifying user preferences and tendencies based on that data.

[0008] A "generative model" is an algorithm that uses machine learning and artificial intelligence to generate new data or make recommendations based on existing data.

[0009] The "method for recommending similar books" is a function that selects and suggests books that have characteristics that match the user's preferences.

[0010] "Methods for analyzing reviews" refers to the process of analyzing comments and ratings left by users using methods such as text analysis to identify the evaluation and trends of a book.

[0011] "User feedback" refers to information collected to gather users' opinions and reactions to the proposed books.

[0012] "Methods for updating generative models" refer to the process of improving the accuracy and performance of a model using new data and feedback obtained from users. [Brief explanation of the drawing]

[0013] [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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered 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, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention relates to a system that provides customized book recommendations to users. The system aims to understand the user's individual preferences and enrich their reading experience.

[0035] The server first stores the user's past reading history, purchase history, ratings, and reviews in a database. When the user selects a new book, the history information is sent to the server, and the information processing system analyzes it. The results of the analysis are used to extract characteristics such as the user's preferred genres, authors, and themes.

[0036] Subsequently, the server utilizes a generative model to recommend similar books based on the extracted user preferences. This model is based on machine learning algorithms and considers not only the book's content and reviews, but also associated information (e.g., whether or not it has been adapted into a drama). This enables more accurate and personalized book recommendations for the user.

[0037] Users can view a list of recommended books from the server via their device. The list includes ratings and reasons for each book, which users can use to help them make informed decisions. For example, if a user has previously read many mystery novels, the server will recommend books by new authors or in different subgenres within the mystery genre.

[0038] Furthermore, the device collects user feedback and returns this information to the server. This feedback is used to train the generative model, and the algorithm is reflected in future recommendations. In this way, the system is continuously improved, enabling it to provide books that better match the user's interests.

[0039] This invention facilitates personalized book discovery for users, independent of conventional rankings and sales information, and supports them in exploring new genres.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] Users log in to the system using their devices and enter their past reading history and ratings. This includes books they have read, their ratings, reviews, and preferences for genres and themes they would like to read in the future.

[0043] Step 2:

[0044] The terminal sends the data entered by the user to the server. The server receives this data and stores it in a database. This allows for the accumulation of basic information about the user's preferences.

[0045] Step 3:

[0046] The server uses information processing tools to analyze user information in the database. Machine learning algorithms are used in the analysis to identify the user's preferred genres, themes, and authors.

[0047] Step 4:

[0048] The server activates a generative model based on the analysis results and selects similar books suitable for the user. The generative model analyzes books that have patterns matching the user's past preferences, including content and review information.

[0049] Step 5:

[0050] The server generates a list of recommended books and sends it to the terminal. The list includes detailed information such as reasons for the recommendation and book ratings.

[0051] Step 6:

[0052] Users can view a list of recommended books through their device and select books that interest them. They can also provide feedback on the recommendations.

[0053] Step 7:

[0054] The device collects user feedback information and sends it back to the server. The server receives this feedback, records it in its database, and incorporates it into the generative model. This improves the accuracy of future recommendations.

[0055] (Example 1)

[0056] 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."

[0057] Traditional recommendation systems often struggled to deeply understand individual user preferences, resulting in the provision of generalized recommendations. Consequently, discovering appealing products was difficult for users, hindering their exploration of new tastes. Furthermore, there was a lack of mechanisms to effectively utilize collected feedback to improve recommendation accuracy.

[0058] 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.

[0059] In this invention, the server includes a calculation means for analyzing individual preferences based on recorded information, a means for using a generative model that recommends similar items based on the analysis results obtained by the calculation means, and a means for collecting feedback from user input and using it to improve the generative model. This enables highly accurate recommendations based on the user's individual preferences and can support the discovery of new tastes.

[0060] "Information records" refer to a collection of data based on a user's activity history and evaluations.

[0061] "Individual preferences" refer to the tendency for each user to exhibit unique interests and tastes.

[0062] A "computational means" is a process within a system used to analyze information and extract specific patterns or trends.

[0063] A "generative model" is an algorithm that uses machine learning to generate new recommendations based on activity data.

[0064] "Similar items" refer to related items or information selected based on the user's past interests and preferences.

[0065] "User input" refers to information such as ratings, comments, and feedback provided by users through the system.

[0066] "Collecting feedback" refers to the act of gathering evaluations and opinions from users.

[0067] "Means used to improve the generative model" refers to the process of improving the recommendation accuracy of the model based on collected user feedback.

[0068] A description of embodiments for carrying out this invention will be given.

[0069] The server stores user activity history, ratings, and reviews based on information provided by users. This utilizes large-capacity storage and a high-speed database management system. Specific software includes database management systems (DBMS) and cloud storage services.

[0070] The server executes machine learning algorithms, including natural language processing (NLP), to analyze the accumulated information. This process extracts patterns and trends from the data to identify individual user preferences. This uses machine learning libraries implemented in programming languages ​​such as Python (e.g., Tensorflow®, PyTorch, etc.).

[0071] The server uses a generative AI model to recommend similar items based on the extracted user preferences. This model is pre-trained using a large amount of data and generates appropriate recommendations according to the user's interests. Specifically, it uses generative AI models such as BERT and GPT to provide books and information that match the user's interests.

[0072] Recommended items are sent to the terminal, through which the user can view details. The terminal also allows the user to enter feedback on the recommended items, and this input is then sent back to the server.

[0073] Using this feedback, the server strives to improve the accuracy of the generated AI model. This process is automated, and the model is updated each time new data is collected as feedback.

[0074] A concrete example is when a server prompts the user with a message like, "Please recommend books that match the user's preferences based on the latest data." This recommendation system, powered by a generative AI model, is highly accurate and helps users discover new interests.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects data such as the user's reading history, purchase history, ratings, and reviews as input. This information is stored in a database and used as foundational data for subsequent processing. Using this data, the server prepares to analyze the user's past activity trends.

[0078] Step 2:

[0079] The server analyzes the accumulated data to identify individual user preferences. At this stage, natural language processing (NLP) techniques are used to analyze text data and extract the user's preferred genres, authors, themes, etc. The input is a collection of user data, and the output generates features related to the user's main preferences.

[0080] Step 3:

[0081] The server uses a generative AI model to recommend similar books based on analyzed preference information. This model is pre-trained on a large dataset and makes predictions to recommend content that matches the user's preferences. It takes user preference features as input and generates a personalized list of books as output.

[0082] Step 4:

[0083] The device displays a list of recommended books sent from the server to the user. The user can browse this list and view details of books that interest them. At this stage, a user interface is provided that makes it easy for the user to refer to the recommendation results. The input is the recommendation list from the server, and the output is the presentation of visual information to the user.

[0084] Step 5:

[0085] Users input feedback on recommended books via a terminal. This feedback, including book ratings and comments, is sent to the server. The input is the user's feedback information, and the output is the data that is digitized and sent to the server.

[0086] Step 6:

[0087] The server uses the collected feedback to update the generated AI model, improving the accuracy of recommendations for future iterations. It analyzes the feedback data and adds new information as training data for the model. Based on the feedback information as input, an improved model is generated as output.

[0088] (Application Example 1)

[0089] 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."

[0090] In modern society, people are exposed to a vast amount of digital content, making it difficult to discover content that is best suited to each individual user. Existing technologies that provide personalized recommendations based on viewing history and reactions are not yet sufficiently accurate, often missing content that users might actually be interested in. Therefore, a system is needed that can analyze user preferences with greater precision and recommend more appropriate content.

[0091] 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.

[0092] In this invention, the server includes data processing means for analyzing user preferences based on the user's media consumption history, means for using a predictive model that recommends similar content based on the analysis results obtained by the data processing means, and means for analyzing the user's response to the recommended content and providing feedback. This makes it possible to recommend content that matches the individual user's preferences.

[0093] "User media consumption history" refers to a record of what kind of digital media content a user has watched and how much of it they have consumed.

[0094] A "data processing means for analyzing preferences" is an information processing system that identifies a user's preferred genres and themes based on their collected media consumption history.

[0095] A "predictive model that recommends similar content" is an algorithm that uses user preference data to select content that is likely to interest the user.

[0096] "Means of analyzing user reactions and providing feedback" refers to elements that analyze user evaluations and actions regarding recommended content and use the results to improve the recommendation algorithm.

[0097] To realize this invention, multiple components must work together in coordination. First, the server acquires the user's media consumption history and analyzes the user's preferences based on this data. The analysis uses a data processing algorithm implemented in Python, and a predictive model is trained using a machine learning framework such as TensorFlow.

[0098] The server then uses this user data to have a generative AI model recommend similar content. Here, Flask acts as the backend, sending and receiving data in response to user requests. Users can view the recommended content using applications built with React Native or other frontend technologies via their smartphones or computers.

[0099] After a user views recommended content, their reaction is sent to the server. This reaction data is analyzed as feedback and used to improve future recommendations. The server uses Scikit-learn to analyze user feedback and updates its AI model accordingly. This ensures the system is constantly optimized, allowing it to continuously provide content that matches the user's preferences.

[0100] For example, if a user's viewing history includes many "science fiction movies," the server will recommend new "science fiction series" or "space opera anime." An example of a prompt would be, "The user's viewing history includes many science fiction movies. What content would you recommend?" Based on this prompt, the generating AI model determines the most suitable content for the user and generates a list of recommended content.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The server retrieves the user's media consumption history from the database. The input is the user ID, and the output is that user's past viewing history. This history data mainly includes information such as the ID, genre, and viewing time of the content viewed. The server retrieves this data through database queries and prepares it for the next processing step.

[0104] Step 2:

[0105] The server uses a data processing algorithm to analyze the acquired viewing history data. The input is the viewing history, and the output is the user's preference profile. The preference profile shows the genres, themes, and specific content tendencies that the user likes. Python's NumPy and Pandas libraries are used for this analysis. This profile is necessary to recommend similar content.

[0106] Step 3:

[0107] The server applies a generated AI model to recommend similar content. The input is the user's preference profile, and the output is a list of recommended content based on that profile. The AI ​​model is primarily built using TensorFlow and makes predictions by combining historical data and new content data. This allows it to suggest new content that the user is likely to be interested in.

[0108] Step 4:

[0109] The device displays a list of recommended content sent from the server to the user. The input is the recommendation list from the server, and the output is the content information displayed on the user's device. The screen displays the title, genre, and rating of the content. The user can then view the content details.

[0110] Step 5:

[0111] After a user views recommended content, they provide feedback to the server via their device, including their evaluation and reactions. The input is the user's evaluation information, and the output is newly updated preference data. This evaluation data is used to improve the recommendation algorithm for future sessions, and the server aggregates the data to prepare for the next learning step.

[0112] 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.

[0113] This invention relates to a book recommendation system that combines an emotion engine that recognizes user emotions. The system aims to enrich and personalize the reading experience by considering both the user's individual preferences and their emotional state.

[0114] The server receives past reading history, ratings, reviews, and related comments sent by users from their devices and manages them in a database. This information is analyzed by information processing tools and used to identify user preferences.

[0115] The emotion engine detects and analyzes the user's emotional state in real time based on their input and actions. The emotion engine identifies the user's emotions, such as "excited" or "calm." This emotional data then influences the server's book recommendations and the prioritization of those recommendations.

[0116] Specifically, if the system detects that a user is tired, books with relaxing content will be prioritized for recommendation. Conversely, if the user is excited, books with action or thrilling stories will be selected. Through these emotion-based recommendations, users can receive books that are perfectly suited to their current mood.

[0117] Furthermore, the sentiment engine also operates when users browse books and provide feedback. The sentiment information obtained through this feedback is used to update the generative model, resulting in improved quality of future recommendations.

[0118] For example, if a user feels moved while writing a review of a book, that emotional information is recorded as positive feedback, making it more likely that similar books will be recommended in the future, thus increasing user satisfaction.

[0119] Thus, the present invention combines emotion recognition technology to provide a more dynamic and personalized user experience that responds to the user's state.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] Users log in to the system by entering their reading history and preferred genres through their device. This sends the necessary data to the server for the initial login.

[0123] Step 2:

[0124] The device sends user input information to the emotion engine. The emotion engine analyzes the user's current emotional state based on their input speed and operation patterns, and sends the results to the server in real time.

[0125] Step 3:

[0126] The server uses information processing tools to analyze the user's past reading history and current emotional state data. This analysis identifies the user's preferences and provides guidance on what books would be most suitable.

[0127] Step 4:

[0128] The server activates a generative model to list books suitable for the user based on the analysis results. The model prioritizes books that match the user's emotional state, in addition to content, popularity, and review information.

[0129] Step 5:

[0130] The server sends book recommendations tailored to the user's emotional state to the device and displays them in a list that the user can view. This list includes a summary and rating of each book, along with the reasoning behind the recommendation based on the user's emotional state.

[0131] Step 6:

[0132] Users can select books of interest from a list of recommended books displayed on their device and view detailed information. They can also provide feedback on these selections (e.g., "interested" or "not interested").

[0133] Step 7:

[0134] The device re-analyzes user feedback using an emotion engine and sends the newly obtained emotion and response data to the server.

[0135] Step 8:

[0136] The server updates its generative model based on the feedback it receives, and uses this information to recommend books in the future. This process improves the accuracy of recommendations, reflecting user preferences and emotions.

[0137] (Example 2)

[0138] 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".

[0139] Traditional information recommendation systems rely solely on preference analysis based on user history data, making it difficult to consider the user's emotional state, which changes in real time. Therefore, they fail to provide information relevant to the user's current mood, resulting in an insufficient personalized experience. Consequently, there is a need for a system that recognizes user emotions in real time and uses that information to recommend and prioritize information.

[0140] 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.

[0141] In this invention, the server includes a device that analyzes user preferences based on user history data, a device that uses a generation engine to provide similar information based on the analysis results obtained by the device, a device that analyzes the user's reaction to the provided information and generates an evaluation, a device that recognizes the user's emotional state from user input and operations, and a device that prioritizes and provides information considering the emotional state. This makes it possible to provide personalized information that corresponds to the user's real-time emotional state.

[0142] "Historical data" refers to information that records a user's past activities and behaviors, and serves as the basis for analyzing user preferences and patterns.

[0143] "Preferences" refer to the tendencies regarding a user's specific interests and preferences, and serve as the basis for providing information and recommending products.

[0144] "Apparatus" refers to a mechanical or electronic tool or system designed to perform a specific process, and includes hardware and software for realizing the functions within this invention.

[0145] A "generative engine" is an algorithm or program that generates new information or results based on input data, and plays a role in analyzing data and producing valuable output.

[0146] "User response" refers to user feedback and actions regarding the information and recommendations provided, and serves as a criterion for measuring how information is received.

[0147] "Emotional state" refers to the psychological or emotional state a user experiences at a particular moment, and it influences how the user receives information.

[0148] Prioritization is the process of rearranging given options or tasks based on their importance and relevance, and it is essential for effective information delivery.

[0149] This invention provides a specific embodiment for providing an information recommendation system based on the user's emotional state.

[0150] Server Role

[0151] The server functions as a central processing unit for storing historical data collected from users and analyzing their preferences. The server uses machine learning algorithms to extract user preferences from the historical data and utilizes this information in the recommendation process driven by the generative engine. The software used is developed in, for example, Python, and utilizes libraries such as Pandas and Scikit-learn for data analysis.

[0152] Terminal role

[0153] The terminal collects user-provided data (ratings, reviews, operational behavior, etc.) and sends it to the server. The terminal is equipped with an emotion engine for recognizing emotional states in real time. The emotion engine analyzes emotions from user input information and operation logs and sends the emotional state to the server. This engine includes a natural language processing module and processes data useful for emotion analysis.

[0154] User roles

[0155] Users interact with the system via their devices, providing feedback through activities such as browsing, rating, and writing reviews of books. The user's emotional state (e.g., "I want to relax," "I'm looking for a new adventure story") is detected by the device and helps the server recommend the most suitable books.

[0156] Specific example

[0157] Suppose a user feels busy during the day and is looking for a book to help them relax. The device senses these needs from the user's keyboard input patterns and word choices, and reports this emotional state ("I want to relax") to the server. Based on this information, the server uses a generative AI model to generate a list of suitable books. In this process, the generative model is prompted with "Please recommend works that will help me relax," and appropriate candidates are listed.

[0158] In this way, dynamic and personalized information tailored to the user's emotional state is provided.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The server stores user history data, ratings, and reviews in a database. It receives user reading history and rating data sent from terminals as input, and organizes and stores this data in the database. Specifically, it uses database optimization algorithms to check for duplicate or missing data, ensuring accurate and efficient information storage.

[0162] Step 2:

[0163] The device detects the user's emotional state in real time based on their input behavior. It collects behavioral data such as the user's keyboard input speed, mouse operations, and scrolling actions as input. An emotion engine analyzes this data to identify the user's state, such as "excited" or "relaxed," and outputs the result. Specifically, it utilizes natural language processing technology to perform sentiment analysis on text.

[0164] Step 3:

[0165] The server uses emotional state data to provide prompts to a generative AI model, which then generates a list of book recommendations. It receives emotional state data and prompts reflecting the user's preferences from the terminal as input. The generative AI model uses these prompts to find relevant books and outputs candidates. Specifically, a natural language generation model operates to generate appropriate book candidates corresponding to the request, "Recommend books that will help me relax."

[0166] Step 4:

[0167] The server sends the generated list of recommended books to the terminal. It receives the book list output by the generating AI model as input and sends it to the terminal in a format optimized for the user. Specifically, it quickly applies the display format to the user interface, allowing the user to smoothly browse the book suggestions.

[0168] Step 5:

[0169] Users refer to a list of recommended books and select and rate books that interest them. They receive information from their device and input their own interests and ratings as feedback. Specifically, they fill out an evaluation form through the interface and freely write reviews and additional comments.

[0170] Step 6:

[0171] The device then sends user feedback back to the server. The input consists of ratings and reviews provided by the user to the device, which are then forwarded to the server. This feedback is stored and analyzed in a database to improve the accuracy of future recommendations. Specifically, a feedback collection module efficiently packages the data and securely transmits it using a communication protocol.

[0172] (Application Example 2)

[0173] 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".

[0174] In recent years, there has been a growing need to provide appropriate content based on individual users' preferences and emotional states. However, current content recommendation systems do not adequately reflect the individual emotional states of users, resulting in a limited user experience. This invention aims to solve this problem and enable personalized content recommendations based on user emotions.

[0175] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an information processing means for analyzing the user's preferences based on their usage history, a means for using a generative model that recommends similar content based on the analysis results obtained by the information processing means, a means for analyzing the user's opinion on the recommended content and providing an evaluation, an emotion recognition means for detecting the user's emotional state from their input and operation behavior and analyzing it in real time, and a means for providing appropriate content based on the user's emotional state. This enables dynamic and personalized content recommendations that are tailored to the user's emotional state and preferences.

[0176] "User history" refers to all information about content a user has accessed in the past and the feedback they have received on it.

[0177] "Information processing means" refers to a device or program for analyzing user data and extracting their preferences and trends.

[0178] "Methods using generative models" refer to algorithms or programs that automatically generate similar content based on acquired data.

[0179] "User opinions" refer to the evaluations and impressions that users express about the content.

[0180] "Emotion recognition means" refers to a device or program that identifies and analyzes a user's emotional state based on their input or actions.

[0181] "Content" refers to movies, music, books, or other entertainment or informational materials.

[0182] "Personalized content recommendations" refer to a method of suggesting content selected based on each user's individual emotional state and preferences.

[0183] To implement this invention, it is necessary to develop a system that provides personalized content recommendations based on the user's emotional state. The server analyzes usage history data obtained from the user and generates appropriate content based on the extracted preferences. Specifically, the server uses information processing means to analyze the user's past access history and feedback, and extracts the user's preferences from that data. This utilizes programming languages ​​such as Python and machine learning frameworks such as TensorFlow.

[0184] Next, similar content matching the extracted preferences is recommended through a generative model. This process uses an algorithm that searches content information in a database and selects content based on the user's interests. Furthermore, emotion recognition measures analyze the user's input and actions in real time to identify their emotional state at that moment. This makes it possible to dynamically adjust the recommended content according to the user's state, such as "tired" or "excited."

[0185] For example, if a user enters "I've had a long day and want to relax," the server will prioritize providing relaxing music and healing content. Similarly, if the user, via the emotion engine, indicates "I want to see fun and energetic content," action movies or energetic music might be recommended.

[0186] An example of a prompt sentence to input into a generative AI model would be, "What movies would you recommend to relieve stress?" In this way, content recommendations that take emotions into account can provide users with a more personalized entertainment experience.

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The user provides input, including their emotional state, via their device. This input is sent to the server as text data. For example, a request such as "I want to relax today" might be entered.

[0190] Step 2:

[0191] The server analyzes the received input data and identifies the user's emotional state using emotion recognition technology. The data processing performed here includes text analysis using natural language processing (NLP) techniques to extract emotional states such as "I want to relax" from the input data.

[0192] Step 3:

[0193] The server retrieves the user's past usage history data from a database and uses information processing tools to identify the user's preferences. Historical data is input, and a profile of the user's preferences is generated as output.

[0194] Step 4:

[0195] The server uses a generative model to select content that matches the identified emotional state and preferences. The algorithm compares similar content and outputs the one that best matches the emotion and preferences.

[0196] Step 5:

[0197] Recommended content information is sent to the device and displayed to the user. For example, if the user wants to "relax," healing music or relaxation videos will be presented.

[0198] Step 6:

[0199] Users view recommended content on their devices and provide feedback. This feedback is then sent back to the server as data to help improve the recommendation algorithm for the next time.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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".

[0216] This invention relates to a system that provides customized book recommendations to users. The system aims to understand the user's individual preferences and enrich their reading experience.

[0217] The server first stores the user's past reading history, purchase history, ratings, and reviews in a database. When the user selects a new book, the history information is sent to the server, and the information processing system analyzes it. The results of the analysis are used to extract characteristics such as the user's preferred genres, authors, and themes.

[0218] Subsequently, the server utilizes a generative model to recommend similar books based on the extracted user preferences. This model is based on machine learning algorithms and considers not only the book's content and reviews, but also associated information (e.g., whether or not it has been adapted into a drama). This enables more accurate and personalized book recommendations for the user.

[0219] Users can view a list of recommended books from the server via their device. The list includes ratings and reasons for each book, which users can use to help them make informed decisions. For example, if a user has previously read many mystery novels, the server will recommend books by new authors or in different subgenres within the mystery genre.

[0220] Furthermore, the device collects user feedback and returns this information to the server. This feedback is used to train the generative model, and the algorithm is reflected in future recommendations. In this way, the system is continuously improved, enabling it to provide books that better match the user's interests.

[0221] This invention facilitates personalized book discovery for users, independent of conventional rankings and sales information, and supports them in exploring new genres.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] Users log in to the system using their devices and enter their past reading history and ratings. This includes books they have read, their ratings, reviews, and preferences for genres and themes they would like to read in the future.

[0225] Step 2:

[0226] The terminal sends the data entered by the user to the server. The server receives this data and stores it in a database. This allows for the accumulation of basic information about the user's preferences.

[0227] Step 3:

[0228] The server uses information processing tools to analyze user information in the database. Machine learning algorithms are used in the analysis to identify the user's preferred genres, themes, and authors.

[0229] Step 4:

[0230] The server activates a generative model based on the analysis results and selects similar books suitable for the user. The generative model analyzes books that have patterns matching the user's past preferences, including content and review information.

[0231] Step 5:

[0232] The server generates a list of recommended books and sends it to the terminal. The list includes detailed information such as reasons for the recommendation and book ratings.

[0233] Step 6:

[0234] Users can view a list of recommended books through their device and select books that interest them. They can also provide feedback on the recommendations.

[0235] Step 7:

[0236] The device collects user feedback information and sends it back to the server. The server receives this feedback, records it in its database, and incorporates it into the generative model. This improves the accuracy of future recommendations.

[0237] (Example 1)

[0238] 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."

[0239] Traditional recommendation systems often struggled to deeply understand individual user preferences, resulting in the provision of generalized recommendations. Consequently, discovering appealing products was difficult for users, hindering their exploration of new tastes. Furthermore, there was a lack of mechanisms to effectively utilize collected feedback to improve recommendation accuracy.

[0240] 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.

[0241] In this invention, the server includes a calculation means for analyzing individual preferences based on recorded information, a means for using a generative model that recommends similar items based on the analysis results obtained by the calculation means, and a means for collecting feedback from user input and using it to improve the generative model. This enables highly accurate recommendations based on the user's individual preferences and can support the discovery of new tastes.

[0242] "Information records" refer to a collection of data based on a user's activity history and evaluations.

[0243] "Individual preferences" refer to the tendency for each user to exhibit unique interests and tastes.

[0244] A "computational means" is a process within a system used to analyze information and extract specific patterns or trends.

[0245] A "generative model" is an algorithm that uses machine learning to generate new recommendations based on activity data.

[0246] "Similar items" refer to related items or information selected based on the user's past interests and preferences.

[0247] "User input" refers to information such as ratings, comments, and feedback provided by users through the system.

[0248] "Collecting feedback" refers to the act of gathering evaluations and opinions from users.

[0249] "Means used to improve the generative model" refers to the process of improving the recommendation accuracy of the model based on collected user feedback.

[0250] A description of embodiments for carrying out this invention will be given.

[0251] The server stores user activity history, ratings, and reviews based on information provided by users. This utilizes large-capacity storage and a high-speed database management system. Specific software includes database management systems (DBMS) and cloud storage services.

[0252] The server executes machine learning algorithms, including natural language processing (NLP), to analyze the accumulated information. This process extracts patterns and trends from the data to identify individual user preferences. This uses machine learning libraries implemented in programming languages ​​such as Python (e.g., TensorFlow, PyTorch, etc.).

[0253] The server uses a generative AI model to recommend similar items based on the extracted user preferences. This model is pre-trained using a large amount of data and generates appropriate recommendations according to the user's interests. Specifically, it uses generative AI models such as BERT and GPT to provide books and information that match the user's interests.

[0254] Recommended items are sent to the terminal, through which the user can view details. The terminal also allows the user to enter feedback on the recommended items, and this input is then sent back to the server.

[0255] Using this feedback, the server strives to improve the accuracy of the generated AI model. This process is automated, and the model is updated each time new data is collected as feedback.

[0256] A concrete example is when a server prompts the user with a message like, "Please recommend books that match the user's preferences based on the latest data." This recommendation system, powered by a generative AI model, is highly accurate and helps users discover new interests.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server collects data such as the user's reading history, purchase history, ratings, and reviews as input. This information is stored in a database and used as foundational data for subsequent processing. Using this data, the server prepares to analyze the user's past activity trends.

[0260] Step 2:

[0261] The server analyzes the accumulated data to identify individual user preferences. At this stage, natural language processing (NLP) techniques are used to analyze text data and extract the user's preferred genres, authors, themes, etc. The input is a collection of user data, and the output generates features related to the user's main preferences.

[0262] Step 3:

[0263] The server uses a generative AI model to recommend similar books based on analyzed preference information. This model is pre-trained on a large dataset and makes predictions to recommend content that matches the user's preferences. It takes user preference features as input and generates a personalized list of books as output.

[0264] Step 4:

[0265] The device displays a list of recommended books sent from the server to the user. The user can browse this list and view details of books that interest them. At this stage, a user interface is provided that makes it easy for the user to refer to the recommendation results. The input is the recommendation list from the server, and the output is the presentation of visual information to the user.

[0266] Step 5:

[0267] Users input feedback on recommended books via a terminal. This feedback, including book ratings and comments, is sent to the server. The input is the user's feedback information, and the output is the data that is digitized and sent to the server.

[0268] Step 6:

[0269] The server uses the collected feedback to update the generated AI model, improving the accuracy of recommendations for future iterations. It analyzes the feedback data and adds new information as training data for the model. Based on the feedback information as input, an improved model is generated as output.

[0270] (Application Example 1)

[0271] 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."

[0272] In modern society, people are exposed to a vast amount of digital content, making it difficult to discover content that is best suited to each individual user. Existing technologies that provide personalized recommendations based on viewing history and reactions are not yet sufficiently accurate, often missing content that users might actually be interested in. Therefore, a system is needed that can analyze user preferences with greater precision and recommend more appropriate content.

[0273] 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.

[0274] In this invention, the server includes data processing means for analyzing user preferences based on the user's media consumption history, means for using a predictive model that recommends similar content based on the analysis results obtained by the data processing means, and means for analyzing the user's response to the recommended content and providing feedback. This makes it possible to recommend content that matches the individual user's preferences.

[0275] "User media consumption history" refers to a record of what kind of digital media content a user has watched and how much of it they have consumed.

[0276] A "data processing means for analyzing preferences" is an information processing system that identifies a user's preferred genres and themes based on their collected media consumption history.

[0277] A "predictive model that recommends similar content" is an algorithm that uses user preference data to select content that is likely to interest the user.

[0278] "Means of analyzing user reactions and providing feedback" refers to elements that analyze user evaluations and actions regarding recommended content and use the results to improve the recommendation algorithm.

[0279] To implement this invention, multiple components need to operate in cooperation with each other. First, the server acquires the user's media consumption history and analyzes the user's preferences based on this data. For the analysis, a data processing algorithm implemented using Python is used, and a prediction model is trained using a machine learning framework such as TensorFlow.

[0280] The server further uses this user data to have the generative AI model recommend similar content. Here, Flask functions as the backend, sending and receiving data in response to user requests. The user can view the recommended content through an application built using React Native and other frontend technologies via a smartphone or computer.

[0281] After the user watches the recommended content, their reaction is sent to the server. This reaction data is analyzed as feedback and reflected in the next recommendation. The server analyzes the user's evaluation using Scikit-learn and appropriately updates the generative AI model. As a result, the system can always be optimized and continue to provide content that matches the user's preferences.

[0282] As a specific example, if the user's viewing history contains many "science fiction movies", the server recommends new "science fiction series" or "space opera anime". An example of a prompt sentence is "The user's viewing history contains many science fiction movies. What content should be recommended?" Based on this prompt, the generative AI model determines the optimal content for the user and generates a list of recommended content.

[0283] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0284] Step 1:

[0285] The server retrieves the user's media consumption history from the database. The input is the user ID, and the output is the user's past viewing history. This history data mainly includes information such as the ID of the content viewed, genre, viewing time, etc. The server retrieves this through a database query and prepares it for the next process.

[0286] Step 2:

[0287] The server uses a data processing algorithm to analyze the retrieved viewing history data. The input is the viewing history, and the output is the user's preference profile. The preference profile indicates the genres, themes, and tendencies of specific content that the user likes. Python's NumPy and Pandas libraries are used for this analysis. This profile is necessary for recommending similar content.

[0288] Step 3:

[0289] The server applies a generative AI model to recommend similar content. The input is the user's preference profile, and the output is a list of recommended content based on that profile. The AI model is mainly built using TensorFlow and combines past data and new content data to make predictions. This enables the proposal of new content that the user is likely to be interested in.

[0290] Step 4:

[0291] The terminal displays the list of recommended content sent from the server to the user. The input is the recommendation list from the server, and the output is the content information displayed on the user's device. The title, genre, and rating of the content are displayed on the screen. The user can check the details of the content from here.

[0292] Step 5:

[0293] After a user views recommended content, they provide feedback to the server via their device, including their evaluation and reactions. The input is the user's evaluation information, and the output is newly updated preference data. This evaluation data is used to improve the recommendation algorithm for future sessions, and the server aggregates the data to prepare for the next learning step.

[0294] 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.

[0295] This invention relates to a book recommendation system that combines an emotion engine that recognizes user emotions. The system aims to enrich and personalize the reading experience by considering both the user's individual preferences and their emotional state.

[0296] The server receives past reading history, ratings, reviews, and related comments sent by users from their devices and manages them in a database. This information is analyzed by information processing tools and used to identify user preferences.

[0297] The emotion engine detects and analyzes the user's emotional state in real time based on their input and actions. The emotion engine identifies the user's emotions, such as "excited" or "calm." This emotional data then influences the server's book recommendations and the prioritization of those recommendations.

[0298] Specifically, if the system detects that a user is tired, books with relaxing content will be prioritized for recommendation. Conversely, if the user is excited, books with action or thrilling stories will be selected. Through these emotion-based recommendations, users can receive books that are perfectly suited to their current mood.

[0299] Furthermore, the emotion engine also operates when the user views a book and provides some feedback. The emotion information obtained through the feedback is used to update the generation model, and as a result, the quality of the recommendations made next time is improved.

[0300] For example, when the user feels touched while writing a review of a certain book, the emotion information is recorded as positive feedback, and similar books are more likely to be recommended in the future, thus enhancing the user's satisfaction.

[0301] In this way, the present invention combines emotion recognition technology to provide a more dynamic and personalized user experience according to the user's state.

[0302] The processing flow will be described below.

[0303] Step 1:

[0304] The user inputs their reading history and interested genres through the terminal and logs in to the system. Thereby, the data required for the first time is sent to the server.

[0305] Step 2:

[0306] The terminal sends the user's input information to the emotion engine. The emotion engine analyzes the current emotional state from the user's input speed and operation pattern and sends the result to the server in real time.

[0307] Step 3:

[0308] The server uses information processing means to analyze the user's past reading history and current emotional state data. Through this analysis, the user's preferences are identified, and guidelines on what kind of books are optimal can be obtained.

[0309] Step 4:

[0310] The server activates a generative model to list books suitable for the user based on the analysis results. The model prioritizes books that match the user's emotional state, in addition to content, popularity, and review information.

[0311] Step 5:

[0312] The server sends book recommendations tailored to the user's emotional state to the device and displays them in a list that the user can view. This list includes a summary and rating of each book, along with the reasoning behind the recommendation based on the user's emotional state.

[0313] Step 6:

[0314] Users can select books of interest from a list of recommended books displayed on their device and view detailed information. They can also provide feedback on these selections (e.g., "interested" or "not interested").

[0315] Step 7:

[0316] The device re-analyzes user feedback using an emotion engine and sends the newly obtained emotion and response data to the server.

[0317] Step 8:

[0318] The server updates its generative model based on the feedback it receives, and uses this information to recommend books in the future. This process improves the accuracy of recommendations, reflecting user preferences and emotions.

[0319] (Example 2)

[0320] 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".

[0321] Traditional information recommendation systems rely solely on preference analysis based on user history data, making it difficult to consider the user's emotional state, which changes in real time. Therefore, they fail to provide information relevant to the user's current mood, resulting in an insufficient personalized experience. Consequently, there is a need for a system that recognizes user emotions in real time and uses that information to recommend and prioritize information.

[0322] 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.

[0323] In this invention, the server includes a device that analyzes user preferences based on user history data, a device that uses a generation engine to provide similar information based on the analysis results obtained by the device, a device that analyzes the user's reaction to the provided information and generates an evaluation, a device that recognizes the user's emotional state from user input and operations, and a device that prioritizes and provides information considering the emotional state. This makes it possible to provide personalized information that corresponds to the user's real-time emotional state.

[0324] "Historical data" refers to information that records a user's past activities and behaviors, and serves as the basis for analyzing user preferences and patterns.

[0325] "Preferences" refer to the tendencies regarding a user's specific interests and preferences, and serve as the basis for providing information and recommending products.

[0326] "Apparatus" refers to a mechanical or electronic tool or system designed to perform a specific process, and includes hardware and software for realizing the functions within this invention.

[0327] A "generative engine" is an algorithm or program that generates new information or results based on input data, and plays a role in analyzing data and producing valuable output.

[0328] "User response" refers to user feedback and actions regarding the information and recommendations provided, and serves as a criterion for measuring how information is received.

[0329] "Emotional state" refers to the psychological or emotional state a user experiences at a particular moment, and it influences how the user receives information.

[0330] Prioritization is the process of rearranging given options or tasks based on their importance and relevance, and it is essential for effective information delivery.

[0331] This invention provides a specific embodiment for providing an information recommendation system based on the user's emotional state.

[0332] Server Role

[0333] The server functions as a central processing unit for storing historical data collected from users and analyzing their preferences. The server uses machine learning algorithms to extract user preferences from the historical data and utilizes this information in the recommendation process driven by the generative engine. The software used is developed in, for example, Python, and utilizes libraries such as Pandas and Scikit-learn for data analysis.

[0334] Terminal role

[0335] The terminal collects user-provided data (ratings, reviews, operational behavior, etc.) and sends it to the server. The terminal is equipped with an emotion engine for recognizing emotional states in real time. The emotion engine analyzes emotions from user input information and operation logs and sends the emotional state to the server. This engine includes a natural language processing module and processes data useful for emotion analysis.

[0336] User roles

[0337] Users interact with the system via their devices, providing feedback through activities such as browsing, rating, and writing reviews of books. The user's emotional state (e.g., "I want to relax," "I'm looking for a new adventure story") is detected by the device and helps the server recommend the most suitable books.

[0338] Specific example

[0339] Suppose a user feels busy during the day and is looking for a book to help them relax. The device senses these needs from the user's keyboard input patterns and word choices, and reports this emotional state ("I want to relax") to the server. Based on this information, the server uses a generative AI model to generate a list of suitable books. In this process, the generative model is prompted with "Please recommend works that will help me relax," and appropriate candidates are listed.

[0340] In this way, dynamic and personalized information tailored to the user's emotional state is provided.

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] The server stores user history data, ratings, and reviews in a database. It receives user reading history and rating data sent from terminals as input, and organizes and stores this data in the database. Specifically, it uses database optimization algorithms to check for duplicate or missing data, ensuring accurate and efficient information storage.

[0344] Step 2:

[0345] The device detects the user's emotional state in real time based on their input behavior. It collects behavioral data such as the user's keyboard input speed, mouse operations, and scrolling actions as input. An emotion engine analyzes this data to identify the user's state, such as "excited" or "relaxed," and outputs the result. Specifically, it utilizes natural language processing technology to perform sentiment analysis on text.

[0346] Step 3:

[0347] The server uses emotional state data to provide prompts to a generative AI model, which then generates a list of book recommendations. It receives emotional state data and prompts reflecting the user's preferences from the terminal as input. The generative AI model uses these prompts to find relevant books and outputs candidates. Specifically, a natural language generation model operates to generate appropriate book candidates corresponding to the request, "Recommend books that will help me relax."

[0348] Step 4:

[0349] The server sends the generated list of recommended books to the terminal. It receives the book list output by the generating AI model as input and sends it to the terminal in a format optimized for the user. Specifically, it quickly applies the display format to the user interface, allowing the user to smoothly browse the book suggestions.

[0350] Step 5:

[0351] Users refer to a list of recommended books and select and rate books that interest them. They receive information from their device and input their own interests and ratings as feedback. Specifically, they fill out an evaluation form through the interface and freely write reviews and additional comments.

[0352] Step 6:

[0353] The device then sends user feedback back to the server. The input consists of ratings and reviews provided by the user to the device, which are then forwarded to the server. This feedback is stored and analyzed in a database to improve the accuracy of future recommendations. Specifically, a feedback collection module efficiently packages the data and securely transmits it using a communication protocol.

[0354] (Application Example 2)

[0355] 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."

[0356] In recent years, there has been a growing need to provide appropriate content based on individual users' preferences and emotional states. However, current content recommendation systems do not adequately reflect the individual emotional states of users, resulting in a limited user experience. This invention aims to solve this problem and enable personalized content recommendations based on user emotions.

[0357] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an information processing means for analyzing the user's preferences based on their usage history, a means for using a generative model that recommends similar content based on the analysis results obtained by the information processing means, a means for analyzing the user's opinion on the recommended content and providing an evaluation, an emotion recognition means for detecting the user's emotional state from their input and operation behavior and analyzing it in real time, and a means for providing appropriate content based on the user's emotional state. This enables dynamic and personalized content recommendations that are tailored to the user's emotional state and preferences.

[0358] "User history" refers to all information about content a user has accessed in the past and the feedback they have received on it.

[0359] "Information processing means" refers to a device or program for analyzing user data and extracting their preferences and trends.

[0360] "Methods using generative models" refer to algorithms or programs that automatically generate similar content based on acquired data.

[0361] "User opinions" refer to the evaluations and impressions that users express about the content.

[0362] "Emotion recognition means" refers to a device or program that identifies and analyzes a user's emotional state based on their input or actions.

[0363] "Content" refers to movies, music, books, or other entertainment or informational materials.

[0364] "Personalized content recommendations" refer to a method of suggesting content selected based on each user's individual emotional state and preferences.

[0365] To implement this invention, it is necessary to develop a system that provides personalized content recommendations based on the user's emotional state. The server analyzes usage history data obtained from the user and generates appropriate content based on the extracted preferences. Specifically, the server uses information processing means to analyze the user's past access history and feedback, and extracts the user's preferences from that data. This utilizes programming languages ​​such as Python and machine learning frameworks such as TensorFlow.

[0366] Next, similar content matching the extracted preferences is recommended through a generative model. This process uses an algorithm that searches content information in a database and selects content based on the user's interests. Furthermore, emotion recognition measures analyze the user's input and actions in real time to identify their emotional state at that moment. This makes it possible to dynamically adjust the recommended content according to the user's state, such as "tired" or "excited."

[0367] For example, if a user enters "I've had a long day and want to relax," the server will prioritize providing relaxing music and healing content. Similarly, if the user, via the emotion engine, indicates "I want to see fun and energetic content," action movies or energetic music might be recommended.

[0368] An example of a prompt sentence to input into a generative AI model would be, "What movies would you recommend to relieve stress?" In this way, content recommendations that take emotions into account can provide users with a more personalized entertainment experience.

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] The user provides input, including their emotional state, via their device. This input is sent to the server as text data. For example, a request such as "I want to relax today" might be entered.

[0372] Step 2:

[0373] The server analyzes the received input data and identifies the user's emotional state using emotion recognition technology. The data processing performed here includes text analysis using natural language processing (NLP) techniques to extract emotional states such as "I want to relax" from the input data.

[0374] Step 3:

[0375] The server retrieves the user's past usage history data from a database and uses information processing tools to identify the user's preferences. Historical data is input, and a profile of the user's preferences is generated as output.

[0376] Step 4:

[0377] The server uses a generative model to select content that matches the identified emotional state and preferences. The algorithm compares similar content and outputs the one that best matches the emotion and preferences.

[0378] Step 5:

[0379] Recommended content information is sent to the device and displayed to the user. For example, if the user wants to "relax," healing music or relaxation videos will be presented.

[0380] Step 6:

[0381] Users view recommended content on their devices and provide feedback. This feedback is then sent back to the server as data to help improve the recommendation algorithm for the next time.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] [Third Embodiment]

[0386] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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".

[0398] This invention relates to a system that provides customized book recommendations to users. The system aims to understand the user's individual preferences and enrich their reading experience.

[0399] The server first stores the user's past reading history, purchase history, ratings, and reviews in a database. When the user selects a new book, the history information is sent to the server, and the information processing system analyzes it. The results of the analysis are used to extract characteristics such as the user's preferred genres, authors, and themes.

[0400] Subsequently, the server utilizes a generative model to recommend similar books based on the extracted user preferences. This model is based on machine learning algorithms and considers not only the book's content and reviews, but also associated information (e.g., whether or not it has been adapted into a drama). This enables more accurate and personalized book recommendations for the user.

[0401] Users can view a list of recommended books from the server via their device. The list includes ratings and reasons for each book, which users can use to help them make informed decisions. For example, if a user has previously read many mystery novels, the server will recommend books by new authors or in different subgenres within the mystery genre.

[0402] Furthermore, the device collects user feedback and returns this information to the server. This feedback is used to train the generative model, and the algorithm is reflected in future recommendations. In this way, the system is continuously improved, enabling it to provide books that better match the user's interests.

[0403] This invention facilitates personalized book discovery for users, independent of conventional rankings and sales information, and supports them in exploring new genres.

[0404] The following describes the processing flow.

[0405] Step 1:

[0406] Users log in to the system using their devices and enter their past reading history and ratings. This includes books they have read, their ratings, reviews, and preferences for genres and themes they would like to read in the future.

[0407] Step 2:

[0408] The terminal sends the data entered by the user to the server. The server receives this data and stores it in a database. This allows for the accumulation of basic information about the user's preferences.

[0409] Step 3:

[0410] The server uses information processing tools to analyze user information in the database. Machine learning algorithms are used in the analysis to identify the user's preferred genres, themes, and authors.

[0411] Step 4:

[0412] The server activates a generative model based on the analysis results and selects similar books suitable for the user. The generative model analyzes books that have patterns matching the user's past preferences, including content and review information.

[0413] Step 5:

[0414] The server generates a list of recommended books and sends it to the terminal. The list includes detailed information such as reasons for the recommendation and book ratings.

[0415] Step 6:

[0416] Users can view a list of recommended books through their device and select books that interest them. They can also provide feedback on the recommendations.

[0417] Step 7:

[0418] The device collects user feedback information and sends it back to the server. The server receives this feedback, records it in its database, and incorporates it into the generative model. This improves the accuracy of future recommendations.

[0419] (Example 1)

[0420] 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."

[0421] Traditional recommendation systems often struggled to deeply understand individual user preferences, resulting in the provision of generalized recommendations. Consequently, discovering appealing products was difficult for users, hindering their exploration of new tastes. Furthermore, there was a lack of mechanisms to effectively utilize collected feedback to improve recommendation accuracy.

[0422] 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.

[0423] In this invention, the server includes a calculation means for analyzing individual preferences based on recorded information, a means for using a generative model that recommends similar items based on the analysis results obtained by the calculation means, and a means for collecting feedback from user input and using it to improve the generative model. This enables highly accurate recommendations based on the user's individual preferences and can support the discovery of new tastes.

[0424] "Information records" refer to a collection of data based on a user's activity history and evaluations.

[0425] "Individual preferences" refer to the tendency for each user to exhibit unique interests and tastes.

[0426] A "computational means" is a process within a system used to analyze information and extract specific patterns or trends.

[0427] A "generative model" is an algorithm that uses machine learning to generate new recommendations based on activity data.

[0428] "Similar items" refer to related items or information selected based on the user's past interests and preferences.

[0429] "User input" refers to information such as ratings, comments, and feedback provided by users through the system.

[0430] "Collecting feedback" refers to the act of gathering evaluations and opinions from users.

[0431] "Means used to improve the generative model" refers to the process of improving the recommendation accuracy of the model based on collected user feedback.

[0432] A description of embodiments for carrying out this invention will be given.

[0433] The server stores user activity history, ratings, and reviews based on information provided by users. This utilizes large-capacity storage and a high-speed database management system. Specific software includes database management systems (DBMS) and cloud storage services.

[0434] The server executes machine learning algorithms, including natural language processing (NLP), to analyze the accumulated information. This process extracts patterns and trends from the data to identify individual user preferences. This uses machine learning libraries implemented in programming languages ​​such as Python (e.g., TensorFlow, PyTorch, etc.).

[0435] The server uses a generative AI model to recommend similar items based on the extracted user preferences. This model is pre-trained using a large amount of data and generates appropriate recommendations according to the user's interests. Specifically, it uses generative AI models such as BERT and GPT to provide books and information that match the user's interests.

[0436] Recommended items are sent to the terminal, through which the user can view details. The terminal also allows the user to enter feedback on the recommended items, and this input is then sent back to the server.

[0437] Using this feedback, the server strives to improve the accuracy of the generated AI model. This process is automated, and the model is updated each time new data is collected as feedback.

[0438] A concrete example is when a server prompts the user with a message like, "Please recommend books that match the user's preferences based on the latest data." This recommendation system, powered by a generative AI model, is highly accurate and helps users discover new interests.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1:

[0441] The server collects data such as the user's reading history, purchase history, ratings, and reviews as input. This information is stored in a database and used as foundational data for subsequent processing. Using this data, the server prepares to analyze the user's past activity trends.

[0442] Step 2:

[0443] The server analyzes the accumulated data to identify individual user preferences. At this stage, natural language processing (NLP) techniques are used to analyze text data and extract the user's preferred genres, authors, themes, etc. The input is a collection of user data, and the output generates features related to the user's main preferences.

[0444] Step 3:

[0445] The server uses a generative AI model to recommend similar books based on analyzed preference information. This model is pre-trained on a large dataset and makes predictions to recommend content that matches the user's preferences. It takes user preference features as input and generates a personalized list of books as output.

[0446] Step 4:

[0447] The device displays a list of recommended books sent from the server to the user. The user can browse this list and view details of books that interest them. At this stage, a user interface is provided that makes it easy for the user to refer to the recommendation results. The input is the recommendation list from the server, and the output is the presentation of visual information to the user.

[0448] Step 5:

[0449] Users input feedback on recommended books via a terminal. This feedback, including book ratings and comments, is sent to the server. The input is the user's feedback information, and the output is the data that is digitized and sent to the server.

[0450] Step 6:

[0451] The server uses the collected feedback to update the generated AI model, improving the accuracy of recommendations for future iterations. It analyzes the feedback data and adds new information as training data for the model. Based on the feedback information as input, an improved model is generated as output.

[0452] (Application Example 1)

[0453] 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."

[0454] In modern society, people are exposed to a vast amount of digital content, making it difficult to discover content that is best suited to each individual user. Existing technologies that provide personalized recommendations based on viewing history and reactions are not yet sufficiently accurate, often missing content that users might actually be interested in. Therefore, a system is needed that can analyze user preferences with greater precision and recommend more appropriate content.

[0455] 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.

[0456] In this invention, the server includes data processing means for analyzing user preferences based on the user's media consumption history, means for using a predictive model that recommends similar content based on the analysis results obtained by the data processing means, and means for analyzing the user's response to the recommended content and providing feedback. This makes it possible to recommend content that matches the individual user's preferences.

[0457] "User media consumption history" refers to a record of what kind of digital media content a user has watched and how much of it they have consumed.

[0458] A "data processing means for analyzing preferences" is an information processing system that identifies a user's preferred genres and themes based on their collected media consumption history.

[0459] A "predictive model that recommends similar content" is an algorithm that uses user preference data to select content that is likely to interest the user.

[0460] "Means of analyzing user reactions and providing feedback" refers to elements that analyze user evaluations and actions regarding recommended content and use the results to improve the recommendation algorithm.

[0461] To realize this invention, multiple components must work together in coordination. First, the server acquires the user's media consumption history and analyzes the user's preferences based on this data. The analysis uses a data processing algorithm implemented in Python, and a predictive model is trained using a machine learning framework such as TensorFlow.

[0462] The server then uses this user data to have a generative AI model recommend similar content. Here, Flask acts as the backend, sending and receiving data in response to user requests. Users can view the recommended content using applications built with React Native or other frontend technologies via their smartphones or computers.

[0463] After a user views recommended content, their reaction is sent to the server. This reaction data is analyzed as feedback and used to improve future recommendations. The server uses Scikit-learn to analyze user feedback and updates its AI model accordingly. This ensures the system is constantly optimized, allowing it to continuously provide content that matches the user's preferences.

[0464] For example, if a user's viewing history includes many "science fiction movies," the server will recommend new "science fiction series" or "space opera anime." An example of a prompt would be, "The user's viewing history includes many science fiction movies. What content would you recommend?" Based on this prompt, the generating AI model determines the most suitable content for the user and generates a list of recommended content.

[0465] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0466] Step 1:

[0467] The server retrieves the user's media consumption history from the database. The input is the user ID, and the output is that user's past viewing history. This history data mainly includes information such as the ID, genre, and viewing time of the content viewed. The server retrieves this data through database queries and prepares it for the next processing step.

[0468] Step 2:

[0469] The server uses a data processing algorithm to analyze the acquired viewing history data. The input is the viewing history, and the output is the user's preference profile. The preference profile shows the genres, themes, and specific content tendencies that the user likes. Python's NumPy and Pandas libraries are used for this analysis. This profile is necessary to recommend similar content.

[0470] Step 3:

[0471] The server applies a generated AI model to recommend similar content. The input is the user's preference profile, and the output is a list of recommended content based on that profile. The AI ​​model is primarily built using TensorFlow and makes predictions by combining historical data and new content data. This allows it to suggest new content that the user is likely to be interested in.

[0472] Step 4:

[0473] The device displays a list of recommended content sent from the server to the user. The input is the recommendation list from the server, and the output is the content information displayed on the user's device. The screen displays the title, genre, and rating of the content. The user can then view the content details.

[0474] Step 5:

[0475] After a user views recommended content, they provide feedback to the server via their device, including their evaluation and reactions. The input is the user's evaluation information, and the output is newly updated preference data. This evaluation data is used to improve the recommendation algorithm for future sessions, and the server aggregates the data to prepare for the next learning step.

[0476] 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.

[0477] This invention relates to a book recommendation system that combines an emotion engine that recognizes user emotions. The system aims to enrich and personalize the reading experience by considering both the user's individual preferences and their emotional state.

[0478] The server receives past reading history, ratings, reviews, and related comments sent by users from their devices and manages them in a database. This information is analyzed by information processing tools and used to identify user preferences.

[0479] The emotion engine detects and analyzes the user's emotional state in real time based on their input and actions. The emotion engine identifies the user's emotions, such as "excited" or "calm." This emotional data then influences the server's book recommendations and the prioritization of those recommendations.

[0480] Specifically, if the system detects that a user is tired, books with relaxing content will be prioritized for recommendation. Conversely, if the user is excited, books with action or thrilling stories will be selected. Through these emotion-based recommendations, users can receive books that are perfectly suited to their current mood.

[0481] Furthermore, the sentiment engine also operates when users browse books and provide feedback. The sentiment information obtained through this feedback is used to update the generative model, resulting in improved quality of future recommendations.

[0482] For example, if a user feels moved while writing a review of a book, that emotional information is recorded as positive feedback, making it more likely that similar books will be recommended in the future, thus increasing user satisfaction.

[0483] Thus, the present invention combines emotion recognition technology to provide a more dynamic and personalized user experience that responds to the user's state.

[0484] The following describes the processing flow.

[0485] Step 1:

[0486] Users log in to the system by entering their reading history and preferred genres through their device. This sends the necessary data to the server for the initial login.

[0487] Step 2:

[0488] The device sends user input information to the emotion engine. The emotion engine analyzes the user's current emotional state based on their input speed and operation patterns, and sends the results to the server in real time.

[0489] Step 3:

[0490] The server uses information processing tools to analyze the user's past reading history and current emotional state data. This analysis identifies the user's preferences and provides guidance on what books would be most suitable.

[0491] Step 4:

[0492] The server activates a generative model to list books suitable for the user based on the analysis results. The model prioritizes books that match the user's emotional state, in addition to content, popularity, and review information.

[0493] Step 5:

[0494] The server sends book recommendations tailored to the user's emotional state to the device and displays them in a list that the user can view. This list includes a summary and rating of each book, along with the reasoning behind the recommendation based on the user's emotional state.

[0495] Step 6:

[0496] Users can select books of interest from a list of recommended books displayed on their device and view detailed information. They can also provide feedback on these selections (e.g., "interested" or "not interested").

[0497] Step 7:

[0498] The device re-analyzes user feedback using an emotion engine and sends the newly obtained emotion and response data to the server.

[0499] Step 8:

[0500] The server updates its generative model based on the feedback it receives, and uses this information to recommend books in the future. This process improves the accuracy of recommendations, reflecting user preferences and emotions.

[0501] (Example 2)

[0502] 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."

[0503] Traditional information recommendation systems rely solely on preference analysis based on user history data, making it difficult to consider the user's emotional state, which changes in real time. Therefore, they fail to provide information relevant to the user's current mood, resulting in an insufficient personalized experience. Consequently, there is a need for a system that recognizes user emotions in real time and uses that information to recommend and prioritize information.

[0504] 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.

[0505] In this invention, the server includes a device that analyzes user preferences based on user history data, a device that uses a generation engine to provide similar information based on the analysis results obtained by the device, a device that analyzes the user's reaction to the provided information and generates an evaluation, a device that recognizes the user's emotional state from user input and operations, and a device that prioritizes and provides information considering the emotional state. This makes it possible to provide personalized information that corresponds to the user's real-time emotional state.

[0506] "Historical data" refers to information that records a user's past activities and behaviors, and serves as the basis for analyzing user preferences and patterns.

[0507] "Preferences" refer to the tendencies regarding a user's specific interests and preferences, and serve as the basis for providing information and recommending products.

[0508] "Apparatus" refers to a mechanical or electronic tool or system designed to perform a specific process, and includes hardware and software for realizing the functions within this invention.

[0509] A "generative engine" is an algorithm or program that generates new information or results based on input data, and plays a role in analyzing data and producing valuable output.

[0510] "User response" refers to user feedback and actions regarding the information and recommendations provided, and serves as a criterion for measuring how information is received.

[0511] "Emotional state" refers to the psychological or emotional state a user experiences at a particular moment, and it influences how the user receives information.

[0512] Prioritization is the process of rearranging given options or tasks based on their importance and relevance, and it is essential for effective information delivery.

[0513] This invention provides a specific embodiment for providing an information recommendation system based on the user's emotional state.

[0514] Server Role

[0515] The server functions as a central processing unit for storing historical data collected from users and analyzing their preferences. The server uses machine learning algorithms to extract user preferences from the historical data and utilizes this information in the recommendation process driven by the generative engine. The software used is developed in, for example, Python, and utilizes libraries such as Pandas and Scikit-learn for data analysis.

[0516] Terminal role

[0517] The terminal collects user-provided data (ratings, reviews, operational behavior, etc.) and sends it to the server. The terminal is equipped with an emotion engine for recognizing emotional states in real time. The emotion engine analyzes emotions from user input information and operation logs and sends the emotional state to the server. This engine includes a natural language processing module and processes data useful for emotion analysis.

[0518] User roles

[0519] Users interact with the system via their devices, providing feedback through activities such as browsing, rating, and writing reviews of books. The user's emotional state (e.g., "I want to relax," "I'm looking for a new adventure story") is detected by the device and helps the server recommend the most suitable books.

[0520] Specific example

[0521] Suppose a user feels busy during the day and is looking for a book to help them relax. The device senses these needs from the user's keyboard input patterns and word choices, and reports this emotional state ("I want to relax") to the server. Based on this information, the server uses a generative AI model to generate a list of suitable books. In this process, the generative model is prompted with "Please recommend works that will help me relax," and appropriate candidates are listed.

[0522] In this way, dynamic and personalized information tailored to the user's emotional state is provided.

[0523] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0524] Step 1:

[0525] The server stores user history data, ratings, and reviews in a database. It receives user reading history and rating data sent from terminals as input, and organizes and stores this data in the database. Specifically, it uses database optimization algorithms to check for duplicate or missing data, ensuring accurate and efficient information storage.

[0526] Step 2:

[0527] The device detects the user's emotional state in real time based on their input behavior. It collects behavioral data such as the user's keyboard input speed, mouse operations, and scrolling actions as input. An emotion engine analyzes this data to identify the user's state, such as "excited" or "relaxed," and outputs the result. Specifically, it utilizes natural language processing technology to perform sentiment analysis on text.

[0528] Step 3:

[0529] The server uses emotional state data to provide prompts to a generative AI model, which then generates a list of book recommendations. It receives emotional state data and prompts reflecting the user's preferences from the terminal as input. The generative AI model uses these prompts to find relevant books and outputs candidates. Specifically, a natural language generation model operates to generate appropriate book candidates corresponding to the request, "Recommend books that will help me relax."

[0530] Step 4:

[0531] The server sends the generated list of recommended books to the terminal. It receives the book list output by the generating AI model as input and sends it to the terminal in a format optimized for the user. Specifically, it quickly applies the display format to the user interface, allowing the user to smoothly browse the book suggestions.

[0532] Step 5:

[0533] Users refer to a list of recommended books and select and rate books that interest them. They receive information from their device and input their own interests and ratings as feedback. Specifically, they fill out an evaluation form through the interface and freely write reviews and additional comments.

[0534] Step 6:

[0535] The device then sends user feedback back to the server. The input consists of ratings and reviews provided by the user to the device, which are then forwarded to the server. This feedback is stored and analyzed in a database to improve the accuracy of future recommendations. Specifically, a feedback collection module efficiently packages the data and securely transmits it using a communication protocol.

[0536] (Application Example 2)

[0537] 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."

[0538] In recent years, there has been a growing need to provide appropriate content based on individual users' preferences and emotional states. However, current content recommendation systems do not adequately reflect the individual emotional states of users, resulting in a limited user experience. This invention aims to solve this problem and enable personalized content recommendations based on user emotions.

[0539] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an information processing means for analyzing the user's preferences based on their usage history, a means for using a generative model that recommends similar content based on the analysis results obtained by the information processing means, a means for analyzing the user's opinion on the recommended content and providing an evaluation, an emotion recognition means for detecting the user's emotional state from their input and operation behavior and analyzing it in real time, and a means for providing appropriate content based on the user's emotional state. This enables dynamic and personalized content recommendations that are tailored to the user's emotional state and preferences.

[0540] "User history" refers to all information about content a user has accessed in the past and the feedback they have received on it.

[0541] "Information processing means" refers to a device or program for analyzing user data and extracting their preferences and trends.

[0542] "Methods using generative models" refer to algorithms or programs that automatically generate similar content based on acquired data.

[0543] "User opinions" refer to the evaluations and impressions that users express about the content.

[0544] "Emotion recognition means" refers to a device or program that identifies and analyzes a user's emotional state based on their input or actions.

[0545] "Content" refers to movies, music, books, or other entertainment or informational materials.

[0546] "Personalized content recommendations" refer to a method of suggesting content selected based on each user's individual emotional state and preferences.

[0547] To implement this invention, it is necessary to develop a system that provides personalized content recommendations based on the user's emotional state. The server analyzes usage history data obtained from the user and generates appropriate content based on the extracted preferences. Specifically, the server uses information processing means to analyze the user's past access history and feedback, and extracts the user's preferences from that data. This utilizes programming languages ​​such as Python and machine learning frameworks such as TensorFlow.

[0548] Next, similar content matching the extracted preferences is recommended through a generative model. This process uses an algorithm that searches content information in a database and selects content based on the user's interests. Furthermore, emotion recognition measures analyze the user's input and actions in real time to identify their emotional state at that moment. This makes it possible to dynamically adjust the recommended content according to the user's state, such as "tired" or "excited."

[0549] For example, if a user enters "I've had a long day and want to relax," the server will prioritize providing relaxing music and healing content. Similarly, if the user, via the emotion engine, indicates "I want to see fun and energetic content," action movies or energetic music might be recommended.

[0550] An example of a prompt sentence to input into a generative AI model would be, "What movies would you recommend to relieve stress?" In this way, content recommendations that take emotions into account can provide users with a more personalized entertainment experience.

[0551] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0552] Step 1:

[0553] The user provides input, including their emotional state, via their device. This input is sent to the server as text data. For example, a request such as "I want to relax today" might be entered.

[0554] Step 2:

[0555] The server analyzes the received input data and identifies the user's emotional state using emotion recognition technology. The data processing performed here includes text analysis using natural language processing (NLP) techniques to extract emotional states such as "I want to relax" from the input data.

[0556] Step 3:

[0557] The server retrieves the user's past usage history data from a database and uses information processing tools to identify the user's preferences. Historical data is input, and a profile of the user's preferences is generated as output.

[0558] Step 4:

[0559] The server uses a generative model to select content that matches the identified emotional state and preferences. The algorithm compares similar content and outputs the one that best matches the emotion and preferences.

[0560] Step 5:

[0561] Recommended content information is sent to the device and displayed to the user. For example, if the user wants to "relax," healing music or relaxation videos will be presented.

[0562] Step 6:

[0563] Users view recommended content on their devices and provide feedback. This feedback is then sent back to the server as data to help improve the recommendation algorithm for the next time.

[0564] 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.

[0565] 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.

[0566] 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.

[0567] [Fourth Embodiment]

[0568] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0569] 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.

[0570] 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).

[0571] 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.

[0572] 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.

[0573] 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).

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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".

[0581] This invention relates to a system that provides customized book recommendations to users. The system aims to understand the user's individual preferences and enrich their reading experience.

[0582] The server first stores the user's past reading history, purchase history, ratings, and reviews in a database. When the user selects a new book, the history information is sent to the server, and the information processing system analyzes it. The results of the analysis are used to extract characteristics such as the user's preferred genres, authors, and themes.

[0583] Subsequently, the server utilizes a generative model to recommend similar books based on the extracted user preferences. This model is based on machine learning algorithms and considers not only the book's content and reviews, but also associated information (e.g., whether or not it has been adapted into a drama). This enables more accurate and personalized book recommendations for the user.

[0584] Users can view a list of recommended books from the server via their device. The list includes ratings and reasons for each book, which users can use to help them make informed decisions. For example, if a user has previously read many mystery novels, the server will recommend books by new authors or in different subgenres within the mystery genre.

[0585] Furthermore, the device collects user feedback and returns this information to the server. This feedback is used to train the generative model, and the algorithm is reflected in future recommendations. In this way, the system is continuously improved, enabling it to provide books that better match the user's interests.

[0586] This invention facilitates personalized book discovery for users, independent of conventional rankings and sales information, and supports them in exploring new genres.

[0587] The following describes the processing flow.

[0588] Step 1:

[0589] Users log in to the system using their devices and enter their past reading history and ratings. This includes books they have read, their ratings, reviews, and preferences for genres and themes they would like to read in the future.

[0590] Step 2:

[0591] The terminal sends the data entered by the user to the server. The server receives this data and stores it in a database. This allows for the accumulation of basic information about the user's preferences.

[0592] Step 3:

[0593] The server uses information processing tools to analyze user information in the database. Machine learning algorithms are used in the analysis to identify the user's preferred genres, themes, and authors.

[0594] Step 4:

[0595] The server activates a generative model based on the analysis results and selects similar books suitable for the user. The generative model analyzes books that have patterns matching the user's past preferences, including content and review information.

[0596] Step 5:

[0597] The server generates a list of recommended books and sends it to the terminal. The list includes detailed information such as reasons for the recommendation and book ratings.

[0598] Step 6:

[0599] Users can view a list of recommended books through their device and select books that interest them. They can also provide feedback on the recommendations.

[0600] Step 7:

[0601] The device collects user feedback information and sends it back to the server. The server receives this feedback, records it in its database, and incorporates it into the generative model. This improves the accuracy of future recommendations.

[0602] (Example 1)

[0603] 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".

[0604] Traditional recommendation systems often struggled to deeply understand individual user preferences, resulting in the provision of generalized recommendations. Consequently, discovering appealing products was difficult for users, hindering their exploration of new tastes. Furthermore, there was a lack of mechanisms to effectively utilize collected feedback to improve recommendation accuracy.

[0605] 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.

[0606] In this invention, the server includes a calculation means for analyzing individual preferences based on recorded information, a means for using a generative model that recommends similar items based on the analysis results obtained by the calculation means, and a means for collecting feedback from user input and using it to improve the generative model. This enables highly accurate recommendations based on the user's individual preferences and can support the discovery of new tastes.

[0607] "Information records" refer to a collection of data based on a user's activity history and evaluations.

[0608] "Individual preferences" refer to the tendency for each user to exhibit unique interests and tastes.

[0609] A "computational means" is a process within a system used to analyze information and extract specific patterns or trends.

[0610] A "generative model" is an algorithm that uses machine learning to generate new recommendations based on activity data.

[0611] "Similar items" refer to related items or information selected based on the user's past interests and preferences.

[0612] "User input" refers to information such as ratings, comments, and feedback provided by users through the system.

[0613] "Collecting feedback" refers to the act of gathering evaluations and opinions from users.

[0614] "Means used to improve the generative model" refers to the process of improving the recommendation accuracy of the model based on collected user feedback.

[0615] A description of embodiments for carrying out this invention will be given.

[0616] The server stores user activity history, ratings, and reviews based on information provided by users. This utilizes large-capacity storage and a high-speed database management system. Specific software includes database management systems (DBMS) and cloud storage services.

[0617] The server executes machine learning algorithms, including natural language processing (NLP), to analyze the accumulated information. This process extracts patterns and trends from the data to identify individual user preferences. This uses machine learning libraries implemented in programming languages ​​such as Python (e.g., TensorFlow, PyTorch, etc.).

[0618] The server uses a generative AI model to recommend similar items based on the extracted user preferences. This model is pre-trained using a large amount of data and generates appropriate recommendations according to the user's interests. Specifically, it uses generative AI models such as BERT and GPT to provide books and information that match the user's interests.

[0619] Recommended items are sent to the terminal, through which the user can view details. The terminal also allows the user to enter feedback on the recommended items, and this input is then sent back to the server.

[0620] Using this feedback, the server strives to improve the accuracy of the generated AI model. This process is automated, and the model is updated each time new data is collected as feedback.

[0621] A concrete example is when a server prompts the user with a message like, "Please recommend books that match the user's preferences based on the latest data." This recommendation system, powered by a generative AI model, is highly accurate and helps users discover new interests.

[0622] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0623] Step 1:

[0624] The server collects data such as the user's reading history, purchase history, ratings, and reviews as input. This information is stored in a database and used as foundational data for subsequent processing. Using this data, the server prepares to analyze the user's past activity trends.

[0625] Step 2:

[0626] The server analyzes the accumulated data to identify individual user preferences. At this stage, natural language processing (NLP) techniques are used to analyze text data and extract the user's preferred genres, authors, themes, etc. The input is a collection of user data, and the output generates features related to the user's main preferences.

[0627] Step 3:

[0628] The server uses a generative AI model to recommend similar books based on analyzed preference information. This model is pre-trained on a large dataset and makes predictions to recommend content that matches the user's preferences. It takes user preference features as input and generates a personalized list of books as output.

[0629] Step 4:

[0630] The device displays a list of recommended books sent from the server to the user. The user can browse this list and view details of books that interest them. At this stage, a user interface is provided that makes it easy for the user to refer to the recommendation results. The input is the recommendation list from the server, and the output is the presentation of visual information to the user.

[0631] Step 5:

[0632] Users input feedback on recommended books via a terminal. This feedback, including book ratings and comments, is sent to the server. The input is the user's feedback information, and the output is the data that is digitized and sent to the server.

[0633] Step 6:

[0634] The server uses the collected feedback to update the generated AI model, improving the accuracy of recommendations for future iterations. It analyzes the feedback data and adds new information as training data for the model. Based on the feedback information as input, an improved model is generated as output.

[0635] (Application Example 1)

[0636] 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".

[0637] In modern society, people are exposed to a vast amount of digital content, making it difficult to discover content that is best suited to each individual user. Existing technologies that provide personalized recommendations based on viewing history and reactions are not yet sufficiently accurate, often missing content that users might actually be interested in. Therefore, a system is needed that can analyze user preferences with greater precision and recommend more appropriate content.

[0638] 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.

[0639] In this invention, the server includes data processing means for analyzing user preferences based on the user's media consumption history, means for using a predictive model that recommends similar content based on the analysis results obtained by the data processing means, and means for analyzing the user's response to the recommended content and providing feedback. This makes it possible to recommend content that matches the individual user's preferences.

[0640] "User media consumption history" refers to a record of what kind of digital media content a user has watched and how much of it they have consumed.

[0641] A "data processing means for analyzing preferences" is an information processing system that identifies a user's preferred genres and themes based on their collected media consumption history.

[0642] A "predictive model that recommends similar content" is an algorithm that uses user preference data to select content that is likely to interest the user.

[0643] "Means of analyzing user reactions and providing feedback" refers to elements that analyze user evaluations and actions regarding recommended content and use the results to improve the recommendation algorithm.

[0644] To realize this invention, multiple components must work together in coordination. First, the server acquires the user's media consumption history and analyzes the user's preferences based on this data. The analysis uses a data processing algorithm implemented in Python, and a predictive model is trained using a machine learning framework such as TensorFlow.

[0645] The server then uses this user data to have a generative AI model recommend similar content. Here, Flask acts as the backend, sending and receiving data in response to user requests. Users can view the recommended content using applications built with React Native or other frontend technologies via their smartphones or computers.

[0646] After a user views recommended content, their reaction is sent to the server. This reaction data is analyzed as feedback and used to improve future recommendations. The server uses Scikit-learn to analyze user feedback and updates its AI model accordingly. This ensures the system is constantly optimized, allowing it to continuously provide content that matches the user's preferences.

[0647] For example, if a user's viewing history includes many "science fiction movies," the server will recommend new "science fiction series" or "space opera anime." An example of a prompt would be, "The user's viewing history includes many science fiction movies. What content would you recommend?" Based on this prompt, the generating AI model determines the most suitable content for the user and generates a list of recommended content.

[0648] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0649] Step 1:

[0650] The server retrieves the user's media consumption history from the database. The input is the user ID, and the output is that user's past viewing history. This history data mainly includes information such as the ID, genre, and viewing time of the content viewed. The server retrieves this data through database queries and prepares it for the next processing step.

[0651] Step 2:

[0652] The server uses a data processing algorithm to analyze the acquired viewing history data. The input is the viewing history, and the output is the user's preference profile. The preference profile shows the genres, themes, and specific content tendencies that the user likes. Python's NumPy and Pandas libraries are used for this analysis. This profile is necessary to recommend similar content.

[0653] Step 3:

[0654] The server applies a generated AI model to recommend similar content. The input is the user's preference profile, and the output is a list of recommended content based on that profile. The AI ​​model is primarily built using TensorFlow and makes predictions by combining historical data and new content data. This allows it to suggest new content that the user is likely to be interested in.

[0655] Step 4:

[0656] The device displays a list of recommended content sent from the server to the user. The input is the recommendation list from the server, and the output is the content information displayed on the user's device. The screen displays the title, genre, and rating of the content. The user can then view the content details.

[0657] Step 5:

[0658] After a user views recommended content, they provide feedback to the server via their device, including their evaluation and reactions. The input is the user's evaluation information, and the output is newly updated preference data. This evaluation data is used to improve the recommendation algorithm for future sessions, and the server aggregates the data to prepare for the next learning step.

[0659] 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.

[0660] This invention relates to a book recommendation system that combines an emotion engine that recognizes user emotions. The system aims to enrich and personalize the reading experience by considering both the user's individual preferences and their emotional state.

[0661] The server receives past reading history, ratings, reviews, and related comments sent by users from their devices and manages them in a database. This information is analyzed by information processing tools and used to identify user preferences.

[0662] The emotion engine detects and analyzes the user's emotional state in real time based on their input and actions. The emotion engine identifies the user's emotions, such as "excited" or "calm." This emotional data then influences the server's book recommendations and the prioritization of those recommendations.

[0663] Specifically, if the system detects that a user is tired, books with relaxing content will be prioritized for recommendation. Conversely, if the user is excited, books with action or thrilling stories will be selected. Through these emotion-based recommendations, users can receive books that are perfectly suited to their current mood.

[0664] Furthermore, the sentiment engine also operates when users browse books and provide feedback. The sentiment information obtained through this feedback is used to update the generative model, resulting in improved quality of future recommendations.

[0665] For example, if a user feels moved while writing a review of a book, that emotional information is recorded as positive feedback, making it more likely that similar books will be recommended in the future, thus increasing user satisfaction.

[0666] Thus, the present invention combines emotion recognition technology to provide a more dynamic and personalized user experience that responds to the user's state.

[0667] The following describes the processing flow.

[0668] Step 1:

[0669] Users log in to the system by entering their reading history and preferred genres through their device. This sends the necessary data to the server for the initial login.

[0670] Step 2:

[0671] The device sends user input information to the emotion engine. The emotion engine analyzes the user's current emotional state based on their input speed and operation patterns, and sends the results to the server in real time.

[0672] Step 3:

[0673] The server uses information processing tools to analyze the user's past reading history and current emotional state data. This analysis identifies the user's preferences and provides guidance on what books would be most suitable.

[0674] Step 4:

[0675] The server activates a generative model to list books suitable for the user based on the analysis results. The model prioritizes books that match the user's emotional state, in addition to content, popularity, and review information.

[0676] Step 5:

[0677] The server sends book recommendations tailored to the user's emotional state to the device and displays them in a list that the user can view. This list includes a summary and rating of each book, along with the reasoning behind the recommendation based on the user's emotional state.

[0678] Step 6:

[0679] Users can select books of interest from a list of recommended books displayed on their device and view detailed information. They can also provide feedback on these selections (e.g., "interested" or "not interested").

[0680] Step 7:

[0681] The device re-analyzes user feedback using an emotion engine and sends the newly obtained emotion and response data to the server.

[0682] Step 8:

[0683] The server updates its generative model based on the feedback it receives, and uses this information to recommend books in the future. This process improves the accuracy of recommendations, reflecting user preferences and emotions.

[0684] (Example 2)

[0685] 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".

[0686] Traditional information recommendation systems rely solely on preference analysis based on user history data, making it difficult to consider the user's emotional state, which changes in real time. Therefore, they fail to provide information relevant to the user's current mood, resulting in an insufficient personalized experience. Consequently, there is a need for a system that recognizes user emotions in real time and uses that information to recommend and prioritize information.

[0687] 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.

[0688] In this invention, the server includes a device that analyzes user preferences based on user history data, a device that uses a generation engine to provide similar information based on the analysis results obtained by the device, a device that analyzes the user's reaction to the provided information and generates an evaluation, a device that recognizes the user's emotional state from user input and operations, and a device that prioritizes and provides information considering the emotional state. This makes it possible to provide personalized information that corresponds to the user's real-time emotional state.

[0689] "Historical data" refers to information that records a user's past activities and behaviors, and serves as the basis for analyzing user preferences and patterns.

[0690] "Preferences" refer to the tendencies regarding a user's specific interests and preferences, and serve as the basis for providing information and recommending products.

[0691] "Apparatus" refers to a mechanical or electronic tool or system designed to perform a specific process, and includes hardware and software for realizing the functions within this invention.

[0692] A "generative engine" is an algorithm or program that generates new information or results based on input data, and plays a role in analyzing data and producing valuable output.

[0693] "User response" refers to user feedback and actions regarding the information and recommendations provided, and serves as a criterion for measuring how information is received.

[0694] "Emotional state" refers to the psychological or emotional state a user experiences at a particular moment, and it influences how the user receives information.

[0695] Prioritization is the process of rearranging given options or tasks based on their importance and relevance, and it is essential for effective information delivery.

[0696] This invention provides a specific embodiment for providing an information recommendation system based on the user's emotional state.

[0697] Server Role

[0698] The server functions as a central processing unit for storing historical data collected from users and analyzing their preferences. The server uses machine learning algorithms to extract user preferences from the historical data and utilizes this information in the recommendation process driven by the generative engine. The software used is developed in, for example, Python, and utilizes libraries such as Pandas and Scikit-learn for data analysis.

[0699] Terminal role

[0700] The terminal collects user-provided data (ratings, reviews, operational behavior, etc.) and sends it to the server. The terminal is equipped with an emotion engine for recognizing emotional states in real time. The emotion engine analyzes emotions from user input information and operation logs and sends the emotional state to the server. This engine includes a natural language processing module and processes data useful for emotion analysis.

[0701] User roles

[0702] Users interact with the system via their devices, providing feedback through activities such as browsing, rating, and writing reviews of books. The user's emotional state (e.g., "I want to relax," "I'm looking for a new adventure story") is detected by the device and helps the server recommend the most suitable books.

[0703] Specific example

[0704] Suppose a user feels busy during the day and is looking for a book to help them relax. The device senses these needs from the user's keyboard input patterns and word choices, and reports this emotional state ("I want to relax") to the server. Based on this information, the server uses a generative AI model to generate a list of suitable books. In this process, the generative model is prompted with "Please recommend works that will help me relax," and appropriate candidates are listed.

[0705] In this way, dynamic and personalized information tailored to the user's emotional state is provided.

[0706] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0707] Step 1:

[0708] The server stores user history data, ratings, and reviews in a database. It receives user reading history and rating data sent from terminals as input, and organizes and stores this data in the database. Specifically, it uses database optimization algorithms to check for duplicate or missing data, ensuring accurate and efficient information storage.

[0709] Step 2:

[0710] The device detects the user's emotional state in real time based on their input behavior. It collects behavioral data such as the user's keyboard input speed, mouse operations, and scrolling actions as input. An emotion engine analyzes this data to identify the user's state, such as "excited" or "relaxed," and outputs the result. Specifically, it utilizes natural language processing technology to perform sentiment analysis on text.

[0711] Step 3:

[0712] The server uses emotional state data to provide prompts to a generative AI model, which then generates a list of book recommendations. It receives emotional state data and prompts reflecting the user's preferences from the terminal as input. The generative AI model uses these prompts to find relevant books and outputs candidates. Specifically, a natural language generation model operates to generate appropriate book candidates corresponding to the request, "Recommend books that will help me relax."

[0713] Step 4:

[0714] The server sends the generated list of recommended books to the terminal. It receives the book list output by the generating AI model as input and sends it to the terminal in a format optimized for the user. Specifically, it quickly applies the display format to the user interface, allowing the user to smoothly browse the book suggestions.

[0715] Step 5:

[0716] Users refer to a list of recommended books and select and rate books that interest them. They receive information from their device and input their own interests and ratings as feedback. Specifically, they fill out an evaluation form through the interface and freely write reviews and additional comments.

[0717] Step 6:

[0718] The device then sends user feedback back to the server. The input consists of ratings and reviews provided by the user to the device, which are then forwarded to the server. This feedback is stored and analyzed in a database to improve the accuracy of future recommendations. Specifically, a feedback collection module efficiently packages the data and securely transmits it using a communication protocol.

[0719] (Application Example 2)

[0720] 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".

[0721] In recent years, there has been a growing need to provide appropriate content based on individual users' preferences and emotional states. However, current content recommendation systems do not adequately reflect the individual emotional states of users, resulting in a limited user experience. This invention aims to solve this problem and enable personalized content recommendations based on user emotions.

[0722] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an information processing means for analyzing the user's preferences based on their usage history, a means for using a generative model that recommends similar content based on the analysis results obtained by the information processing means, a means for analyzing the user's opinion on the recommended content and providing an evaluation, an emotion recognition means for detecting the user's emotional state from their input and operation behavior and analyzing it in real time, and a means for providing appropriate content based on the user's emotional state. This enables dynamic and personalized content recommendations that are tailored to the user's emotional state and preferences.

[0723] "User history" refers to all information about content a user has accessed in the past and the feedback they have received on it.

[0724] "Information processing means" refers to a device or program for analyzing user data and extracting their preferences and trends.

[0725] "Methods using generative models" refer to algorithms or programs that automatically generate similar content based on acquired data.

[0726] "User opinions" refer to the evaluations and impressions that users express about the content.

[0727] "Emotion recognition means" refers to a device or program that identifies and analyzes a user's emotional state based on their input or actions.

[0728] "Content" refers to movies, music, books, or other entertainment or informational materials.

[0729] "Personalized content recommendations" refer to a method of suggesting content selected based on each user's individual emotional state and preferences.

[0730] To implement this invention, it is necessary to develop a system that provides personalized content recommendations based on the user's emotional state. The server analyzes usage history data obtained from the user and generates appropriate content based on the extracted preferences. Specifically, the server uses information processing means to analyze the user's past access history and feedback, and extracts the user's preferences from that data. This utilizes programming languages ​​such as Python and machine learning frameworks such as TensorFlow.

[0731] Next, similar content matching the extracted preferences is recommended through a generative model. This process uses an algorithm that searches content information in a database and selects content based on the user's interests. Furthermore, emotion recognition measures analyze the user's input and actions in real time to identify their emotional state at that moment. This makes it possible to dynamically adjust the recommended content according to the user's state, such as "tired" or "excited."

[0732] For example, if a user enters "I've had a long day and want to relax," the server will prioritize providing relaxing music and healing content. Similarly, if the user, via the emotion engine, indicates "I want to see fun and energetic content," action movies or energetic music might be recommended.

[0733] An example of a prompt sentence to input into a generative AI model would be, "What movies would you recommend to relieve stress?" In this way, content recommendations that take emotions into account can provide users with a more personalized entertainment experience.

[0734] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0735] Step 1:

[0736] The user provides input, including their emotional state, via their device. This input is sent to the server as text data. For example, a request such as "I want to relax today" might be entered.

[0737] Step 2:

[0738] The server analyzes the received input data and identifies the user's emotional state using emotion recognition technology. The data processing performed here includes text analysis using natural language processing (NLP) techniques to extract emotional states such as "I want to relax" from the input data.

[0739] Step 3:

[0740] The server retrieves the user's past usage history data from a database and uses information processing tools to identify the user's preferences. Historical data is input, and a profile of the user's preferences is generated as output.

[0741] Step 4:

[0742] The server uses a generative model to select content that matches the identified emotional state and preferences. The algorithm compares similar content and outputs the one that best matches the emotion and preferences.

[0743] Step 5:

[0744] Recommended content information is sent to the device and displayed to the user. For example, if the user wants to "relax," healing music or relaxation videos will be presented.

[0745] Step 6:

[0746] Users view recommended content on their devices and provide feedback. This feedback is then sent back to the server as data to help improve the recommendation algorithm for the next time.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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."

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] The following is further disclosed regarding the embodiments described above.

[0769] (Claim 1)

[0770] Information processing means for analyzing user preferences based on reading history,

[0771] A means of using a generative model that recommends similar books based on the analysis results obtained by the aforementioned information processing means,

[0772] A means of analyzing user reviews of recommended books and providing evaluations,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, which includes means for performing sentiment analysis when analyzing user reviews and reflecting the results in the evaluation of the book.

[0776] (Claim 3)

[0777] The system according to claim 1, further comprising means for collecting user feedback and updating the generative model based thereon.

[0778] "Example 1"

[0779] (Claim 1)

[0780] A computational means for analyzing individual preferences based on information records,

[0781] A means for using a generative model that recommends similar items based on the analysis results obtained by the calculation means,

[0782] A means of providing users with the reasons for the recommendation when selecting recommended items,

[0783] A means of collecting feedback from user input and using it to improve the generative model,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, comprising means for performing emotion recognition when analyzing user input and integrating it into the evaluation of the item.

[0787] (Claim 3)

[0788] The system according to claim 1, comprising means for a user to view recommended items through an operating terminal.

[0789] "Application Example 1"

[0790] (Claim 1)

[0791] A data processing means for analyzing user preferences based on their media consumption history,

[0792] A means of using a predictive model that recommends similar content based on the analysis results obtained by the data processing means,

[0793] A means of analyzing user reactions to recommended content and providing feedback,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, which includes means for performing emotional determination when analyzing user reactions and reflecting this in the evaluation of content.

[0797] (Claim 3)

[0798] The system according to claim 1, comprising means for collecting user feedback and improving a predictive model based on that feedback.

[0799] "Example 2 of combining an emotion engine"

[0800] (Claim 1)

[0801] A device that analyzes user preferences based on historical data,

[0802] A device that uses a generation engine to provide similar information based on the analysis results obtained by the aforementioned device,

[0803] A device that analyzes user reactions to provided information and generates evaluations,

[0804] A device that recognizes the emotional state from the user's input and actions,

[0805] A device that prioritizes and provides information taking into account the aforementioned emotional state,

[0806] A system that includes this.

[0807] (Claim 2)

[0808] The system according to claim 1, comprising a device that performs emotion recognition when analyzing user responses and reflects this in the quality of information.

[0809] (Claim 3)

[0810] The system according to claim 1, further comprising a device for collecting user feedback and updating the generation engine based on that feedback.

[0811] "Application example 2 when combining with an emotional engine"

[0812] (Claim 1)

[0813] Information processing means for analyzing user preferences based on usage history,

[0814] A means of using a generative model that recommends similar content based on the analysis results obtained from the aforementioned information processing means,

[0815] A means of analyzing and providing evaluations of user opinions on recommended content,

[0816] An emotion recognition means that detects the emotional state from the user's input and actions and analyzes it in real time,

[0817] A means of providing appropriate content based on the user's emotional state,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, which includes means for performing sentiment analysis when analyzing user opinions and reflecting the results in the evaluation of content.

[0821] (Claim 3)

[0822] The system according to claim 1, further comprising means for collecting user feedback and updating the generative model based thereon. [Explanation of Symbols]

[0823] 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. Information processing means for analyzing user preferences based on reading history, A means of using a generative model that recommends similar books based on the analysis results obtained by the aforementioned information processing means, A means of analyzing user reviews of recommended books and providing evaluations, A system that includes this.

2. The system according to claim 1, which includes means for performing sentiment analysis when analyzing user reviews and reflecting the results in the evaluation of the book.

3. The system according to claim 1, further comprising means for collecting user feedback and updating the generative model based thereon.

Images