System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting a user's reading and Internet browsing history; means for collecting and storing the user's reading and Internet browsing history in a database; means for analyzing the collected data and generating a recommendation algorithm based on the user's interests and concerns; means for presenting a list and summary of recommended books to the user; means for providing location and price information of the recommended books; and means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Many users often repurchase books that are similar to those they have read in the past or that are inappropriate for their interests. This results in a high risk of wasting time and money. Another problem is that it is difficult to find which book best suits their current interests and the problems they want to solve. Furthermore, there is a lack of a means to continuously incorporate feedback and improve the accuracy of recommendations. This invention aims to reduce resource waste by recommending optimal books to users based on their current interests, the problems they want to solve, and their past reading history. Furthermore, by providing feedback, the accuracy of recommendations can be continuously improved. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes the following means: a means for allowing a user to input their past reading history and internet browsing history, and a means for collecting and storing this history in a database; a means for analyzing the collected data and generating a recommendation algorithm based on the user's interests; a means for presenting a list of recommended books to the user and their summaries, and a means for providing information on where these books are available and their prices; and a means for allowing a user to input feedback after reading, and for collecting and storing this feedback to improve the accuracy of the recommendation algorithm. It is desirable that the system also include a means for inputting the problems or concerns the user wants to solve, and a means for collecting library collection information and online store inventory information.

[0006] "User" refers to an individual who uses the system to input their reading history and interests and receive appropriate book recommendations.

[0007] "Terminal" means an electronic device through which a user accesses the system and inputs and receives information.

[0008] "Server" refers to the central system that collects, stores, and analyzes information from users and generates appropriate recommendation algorithms.

[0009] "Reading history" refers to information about books a user has read in the past.

[0010] "Web browsing history" refers to information about the web pages a user has viewed on the Internet.

[0011] "Database" means the data storage system used to store and analyze collected User Data.

[0012] A "recommendation algorithm" refers to a calculation method that analyzes a user's reading history and internet browsing history to recommend appropriate books.

[0013] "Recommendation List" refers to a list of books suitable for a user, generated by a recommendation algorithm.

[0014] "Summary" refers to a short, concise description of the recommended book.

[0015] "Book information" refers to information such as book availability and prices at libraries and online stores.

[0016] "Feedback" refers to users' impressions and ratings of books they have read.

[0017] "Improved accuracy" refers to using collected feedback to improve the effectiveness of recommendation algorithms in future iterations.

[0018] "Challenges and concerns" refer to the problems and concerns that the user is currently trying to solve. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, 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), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a 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.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0033] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The system of the present invention analyzes a user's reading history and internet browsing history and recommends the most suitable books, effectively providing books that match the user's interests and challenges. This system mainly exchanges information between the user, the terminal, and the server, and is implemented in the following procedure.

[0041] 1. Enter your user information

[0042] Users can input their reading history, internet browsing history, current issues or concerns they want to resolve, etc. For example, if they want to learn a specific business skill, they can input that information.

[0043] 2. Information Collection and Storage

[0044] The terminal sends the input information to the server, which stores the received information in a database, thereby accumulating user history data.

[0045] 3. Data Analysis

[0046] The server analyzes the information stored in the database and generates algorithms that identify users' interests, such as the business books they have read or the web pages they have visited.

[0047] 4. Generating Recommendations

[0048] The server uses the generated algorithm to create a list of books suitable for the user, including a summary of each book, and also queries inventory information from libraries and online stores to provide information on where the book is available.

[0049] 5. Presentation of recommendation results

[0050] The server sends the recommendation list to the device, which displays the list to the user in an easy-to-understand format, allowing the user to easily decide which book to choose.

[0051] 6. Gathering Feedback

[0052] After reading a recommended book, users can enter feedback via their device, such as "It was very helpful" or "I would like to read another book by this author."

[0053] 7. Processing and storing feedback

[0054] The device sends the feedback information to the server, which then stores it in the database and uses it to improve the accuracy of the recommendation algorithm next time.

[0055] Specific examples

[0056] A specific usage scenario using the system of the present invention is shown below.

[0057] Scenario 1: Businessman's Case

[0058] Let's say a user is looking for a book to improve their business skills.

[0059] Through the terminal, users input tasks such as "improving business skills" and also enter a history of related books they have read in the past, such as "leadership" and "marketing."

[0060] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Marketing Fundamentals."

[0061] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[0062] After purchasing and reading "Essential Thinking," users enter feedback such as "It was very helpful."

[0063] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm next time.

[0064] Scenario 2: Student Case

[0065] Let's say a user is a student looking for books related to a particular course.

[0066] Assignments such as "Fundamentals of Statistics" are entered via the terminal.

[0067] The server also analyzes information about mathematics-related books that students have read in the past and educational websites that they have visited.

[0068] The server recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Introduction to Statistical Thinking" and presents them to users.

[0069] The device will present this list of recommendations along with links to check the library's holdings and purchase the book online.

[0070] The user finishes reading "Introduction to Statistics" and enters feedback such as "The content was easy to understand."

[0071] The server receives this feedback and uses it to improve its recommendation algorithm for future visits.

[0072] This allows users to find the books that best suit their interests and challenges, enriching their reading experience, and feedback allows the system to continually evolve and provide even more accurate recommendations.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] Users access the device's interface and enter their reading history, internet browsing history, problems they want to solve, and areas of interest.

[0076] Step 2:

[0077] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency.

[0078] Step 3:

[0079] The server receives the user data sent from the device and stores it in a database, which includes inserting it into the database using SQL queries.

[0080] Step 4:

[0081] The server analyzes the stored data periodically or as needed to generate a recommendation algorithm based on the user's interests, which involves applying machine learning models based on similar past data.

[0082] Step 5:

[0083] The server uses the generated recommendation algorithm to create a list of books that are most suitable for the user, along with associated summaries that are also generated and included in the list.

[0084] Step 6:

[0085] The server uses APIs from libraries and online stores to gather book availability and price information, which is then added to the recommendation list.

[0086] Step 7:

[0087] The server sends a recommendation list including detailed information to the terminal.

[0088] Step 8:

[0089] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[0090] Step 9:

[0091] After reading a recommended book, users can enter their feedback on the device, including their rating and impressions of the book.

[0092] Step 10:

[0093] The terminal converts the feedback data into an appropriate format and sends it to the server.

[0094] Step 11:

[0095] The server receives the feedback data sent from the terminal and stores it in a database.

[0096] Step 12:

[0097] The server analyzes the stored feedback data and makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[0098] This allows the system to continually improve and provide even more accurate recommendations to users.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] Current book recommendation systems struggle to recommend appropriate books that fully take into account a user's individual interests, past reading history, and internet browsing history. Furthermore, recommendations do not address the specific challenges or concerns of users, limiting the reading experience. Furthermore, improvements to the accuracy of recommendation algorithms using feedback information are insufficient.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes: a means for inputting a user's reading history and internet browsing history; a means for collecting the user's reading history and internet browsing history and storing it in a database; a means for analyzing the collected data and generating a recommendation algorithm based on the user's interests; a means for presenting a list of recommended books and summaries to the user; a means for providing information on where the recommended books are available and their prices; a means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm; a means for identifying the user's areas of interest using a machine learning algorithm; a means for generating a list of books that are best suited to the user using collaborative filtering or content-based filtering technology; and a means for saving the user's input information in a database in real time. This enables the server to recommend books that are best suited to the user's individual interests, specific challenges, and concerns. The accuracy of the recommendation algorithm is also improved based on the feedback.

[0104] "Reading history" is a record of information such as the title, summary, and date and time of books that a user has read in the past.

[0105] "Web browsing history" refers to the history of web pages and online materials that a user has viewed in the past.

[0106] An "input means" is a device or interface that allows users to input their reading history, internet browsing history, problems or concerns they want to solve, etc. into the system.

[0107] A "database" is a system for systematically storing collected information such as a user's reading history and internet browsing history.

[0108] A "recommendation algorithm" is a program and calculation method for recommending the most suitable books based on a user's interests and concerns.

[0109] A "machine learning algorithm" is a method for analyzing large amounts of data and finding patterns in it to make future predictions and classifications.

[0110] "Collaborative filtering" is a method of analyzing a user's interests and the behavior of other users to recommend items that are common to users with similar interests.

[0111] "Content-based filtering" is a method of recommending items with similar content based on a user's past behavior and preferences.

[0112] "Feedback" refers to the ratings and impressions that users enter after reading a recommended book.

[0113] "Real-time" means processing occurs immediately, without delay.

[0114] The system of the present invention analyzes a user's reading history and internet browsing history to recommend the most suitable books, providing books that match the user's interests and themes. This system is implemented by exchanging information mainly between the user, the terminal, and the server.

[0115] First, users input their reading and internet browsing history via the device, and then input information about the problems they currently want to solve and areas of interest, using prompts such as "improving business skills" or "basics of statistics."

[0116] The device then transmits the information entered by the user in real time to a server, which receives the information and stores it in a database that stores each user's reading history, internet browsing history, and input information about topics and interests.

[0117] The server analyzes the information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest. Specifically, it analyzes the content of books the user has read and web pages they have viewed to determine the user's interests.

[0118] The server then uses the analysis results to generate a list of books suitable for the user using collaborative or content-based filtering techniques, including each book's summary, author name, and availability information at libraries and online stores.

[0119] The generated recommendation list is sent from the server to the device, which then displays the list to the user in an easy-to-read format. The user can then decide which book to choose based on the list of recommended books. The list also includes a purchase link and library information, making it easy for the user to obtain the book.

[0120] After a user finishes reading a book, they can enter their feedback via their device. The feedback includes their rating and impressions of the book, such as "It was very helpful" or "I would like to read another book by this author."

[0121] The feedback information is sent from the device to the server, which stores it in a database. The server then analyzes the stored feedback data and uses it to improve the accuracy of the recommendation algorithm next time.

[0122] In this way, the system of the present invention can recommend books that are optimal for a user's individual interests, concerns, and specific problems and concerns. Furthermore, since the accuracy of the recommendation algorithm is improved based on feedback, high-quality recommendations that meet the user's needs are continuously provided.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] Users access the device's application or web interface and input their reading history, internet browsing history, current problems they want to solve, and areas of interest. For example, they input prompts such as "improve business skills" or "basics of statistics." The input data is sent to the system as user interest information (input: user information, output: user interest information).

[0126] Step 2:

[0127] The device sends the information entered by the user to the server in real time (input: user interest information, output: server-sent data). The server receives this information, associates it with the user ID, and stores it in a database (input: server-sent data, output: database-stored data). The database stores each user's reading history, internet browsing history, and entered assignments and interest information.

[0128] Step 3:

[0129] The server analyzes the user information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest (input: data stored in the database, output: user interest trends). Specifically, it analyzes the content of books the user has read in the past and web pages they have viewed to determine the user's interests. For example, it identifies trends in specific areas such as "marketing" or "leadership."

[0130] Step 4:

[0131] Based on the analysis results, the server uses collaborative filtering or content-based filtering techniques to generate a list of books that are best suited to the user (input: user's interest trends, output: recommended book list). This list includes each book's summary, author name, and availability information at libraries and online stores. The algorithm pulls out historical data of users with similar interests and books with related content from the past.

[0132] Step 5:

[0133] The server sends the generated recommended book list to the terminal (input: recommended book list, output: terminal-sent data). The terminal displays the list to the user in an easy-to-read format (input: terminal-sent data, output: user-displayed data). The recommended list includes the book title, summary, author name, and link to where the book is available. The user can decide which book to choose based on this list.

[0134] Step 6:

[0135] After reading a recommended book, the user inputs their evaluation and thoughts about the book into the device (input: thoughts after reading, output: feedback information). For example, they can input feedback such as "It was very helpful" or "I would like to read another book by the same author."

[0136] Step 7:

[0137] The device sends the input feedback information to the server (input: feedback information, output: server-sent feedback). The server stores this feedback in a database (input: server-sent feedback, output: database feedback storage). The server then analyzes the stored feedback data again and uses it to improve the accuracy of the next recommendation algorithm (input: database feedback storage, output: accuracy improvement data).

[0138] Through these steps, the system is able to recommend the most suitable books based on the user's individual interests, concerns, and specific problems and concerns. Furthermore, the accuracy of the recommendation algorithm is improved based on feedback, allowing the system to continuously provide high-quality recommendations that meet the user's needs.

[0139] (Application example 1)

[0140] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0141] Previously, there were systems that recommended books based on a user's reading and internet browsing history, reflecting their individual preferences. However, the accuracy and diversity of the recommendations were insufficient, and they were unable to sufficiently increase user satisfaction. Furthermore, existing systems did not provide sufficient information on where to obtain the recommended books and content, nor did they provide pricing information, and lacked a mechanism to enable users to easily obtain the content.

[0142] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0143] In this invention, the server includes means for inputting a user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing it in a database, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests and concerns, means for presenting a list and summary of recommended content to the user, means for providing information on where the recommended content is available and its price, means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm, means for improving the recommendation algorithm based on the feedback, and means for making recommendations optimized to the user's interests and needs through prompt sentences using a generative AI model. This enables highly accurate content recommendations tailored to the user's needs and the provision of information on where and how to obtain the content.

[0144] "User reading history" is information about books and documents that a user has read in the past.

[0145] "Web browsing history" is information about the web pages and content a user has viewed on the Internet.

[0146] An "input means" is a device or interface through which a user provides information to a system, either manually or automatically.

[0147] "Means of collection" refers to the devices and methods used to properly acquire information entered by users and store it in a database.

[0148] A "database storage means" is a system or device that organizes collected information and stores it in a form that can be reused later.

[0149] "Analytical means" refers to the algorithms and programs used to process collected data and identify user interests.

[0150] A "recommendation algorithm" is a mathematical or programmatic method for selecting the most appropriate content based on a user's past behavioral data.

[0151] A "means for presenting lists and summaries" is an interface for displaying the recommendation results to the user in visual or text form.

[0152] "Means for providing" refers to a system or device that informs users where the recommended content is available and its price information.

[0153] "Means for collecting feedback" refers to devices or programs that obtain opinions and evaluations about the content used by users and reflect them in the system.

[0154] "Means for analyzing and storing feedback data" refers to a system or device that stores the feedback collected from users in a database and uses it to improve the recommendation algorithm for the next time.

[0155] "Means for improving recommendation algorithms" refers to techniques and methods for updating existing recommendation algorithms based on new feedback information and improving their accuracy.

[0156] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms for a specific task.

[0157] A "prompt sentence" is an input sentence given to a generative AI model, and is text data that serves as a trigger to obtain appropriate output from the model.

[0158] To put this invention into practice, it is necessary to build a system that analyzes a user's reading history and internet browsing history and recommends optimal content. Here, we will explain the various programs that make up this system and their processing.

[0159] 1. Collecting and entering user information

[0160] The device (e.g., a smartphone) provides an interface for users to input their reading history and internet browsing history. This information is collected by manual input or by syncing the browser history. The device then transmits this data to a cloud server. This transmission is secured using the HTTPS protocol.

[0161] 2. Data storage

[0162] The cloud server stores the received data in a database, where users' reading and browsing histories are accumulated and later used for analysis. This storage process is handled by a database management system such as MySQL or PostgreSQL.

[0163] 3. Data Analysis

[0164] The cloud server analyzes the information stored in the database and generates algorithms to identify user interests. This process uses data analysis tools such as Python and R and applies machine learning algorithms (e.g., collaborative filtering).

[0165] 4. Generating a recommendation list

[0166] The cloud server creates a list of content that is best suited to the user based on the analysis results. The recommendation list also includes a summary of each piece of content and available information (e.g., purchase links and stock information). This allows users to easily access the recommended content.

[0167] 5. Presentation of recommendation results

[0168] The device receives a list of recommendations from the cloud server and presents them to the user. The screen interface uses web technologies such as HTML and CSS to display information in a visually easy-to-understand format.

[0169] 6. Gathering Feedback

[0170] After using the recommended content, users can enter their ratings and feedback via their devices, which is then sent back to the cloud server and stored in a database.

[0171] 7. Algorithm Improvements

[0172] The cloud server analyzes the collected feedback data and improves the recommendation algorithm, which improves the accuracy of recommendations from the next time onwards and increases user satisfaction.

[0173] 8. Generative AI Model and Prompts

[0174] The system uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are inputs given to an artificial intelligence model trained using machine learning algorithms for a specific task, and are text data that triggers the model to produce an appropriate output.

[0175] As a concrete example, the following is an example of an input prompt for a generative AI model:

[0176] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[0177] Reading history: Leadership, Marketing

[0178] Browsing History: Digital Transformation

[0179] In this way, it is possible to recommend highly accurate content that meets the user's needs, and to provide information on where to obtain that content and its price, allowing users to select content that will give them greater satisfaction.

[0180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0181] Step 1:

[0182] The device provides an interface for users to input their reading history and internet browsing history. Users can manually input information about books they have read and web pages they have visited, or synchronize their browser history. This data is input into the device. The input data is the user's past reading materials and internet browsing records.

[0183] Step 2:

[0184] The device sends the user's reading and browsing history to the cloud server, using the HTTPS protocol to ensure data security. The output data is the user's reading and browsing history.

[0185] Step 3:

[0186] The server stores the received data in a database. The database management system used (e.g., MySQL or PostgreSQL) structures and stores the user's reading and browsing history. The input data is the user's history data, and the output is stored in the database.

[0187] Step 4:

[0188] The server analyzes the information stored in the database. In this process, it applies machine learning algorithms (e.g., collaborative filtering) using Python or R languages ​​to identify the user's interests. The input is the stored user history data, and the output is the analysis results based on the user's interests.

[0189] Step 5:

[0190] The server generates a list of optimal content based on the user's interests. This list includes a summary of each piece of content and acquisition information (purchase link and stock information). This allows the user to easily access the recommended content. The input is the analysis results, and the output is a list of several recommended contents.

[0191] Step 6:

[0192] The device presents the recommendation list received from the server to the user. The screen interface is constructed using HTML and CSS, and information is displayed in a visually easy-to-understand format. The input is the recommendation list data, and the output is the visual recommendation list presented to the user.

[0193] Step 7:

[0194] The user uses the recommended content and enters their rating and feedback through their device. This feedback is then sent back to the cloud server. The input is the user's feedback data, and the output is the sent feedback information.

[0195] Step 8:

[0196] The server analyzes the collected feedback data and improves the recommendation algorithm. It uses the new feedback information to update the existing recommendation algorithm and improve its accuracy, which will result in more accurate recommendations in the future. The input is the feedback data and the output is the improved recommendation algorithm.

[0197] Step 9:

[0198] The server uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are given to the generative AI model and act as triggers to obtain appropriate output. The input is the user's history data and feedback data, and the output is a highly accurate content recommendation prompt.

[0199] As a concrete example, the following is an example of an input prompt for a generative AI model:

[0200] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[0201] Reading history: Leadership, Marketing

[0202] Browsing History: Digital Transformation

[0203] In this way, by combining each step, a highly accurate content recommendation system that meets the user's needs is realized.

[0204] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0205] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotions to provide more personalized recommendations for the user. This system consists of four main components: the user, the device, the server, and the emotion engine.

[0206] 1. Enter your user information

[0207] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. Emotional information obtained through the user's input and actions is also recorded by the emotion engine.

[0208] 2. Information Collection and Storage

[0209] The device converts the input data into an appropriate format and sends it to the server, which stores the received information in a database, including the user's emotional state.

[0210] 3. Data Analysis

[0211] The server analyzes the saved reading history, browsing history, problems to be solved, and emotional information. The emotion engine analyzes the content entered by the user and the emotions expressed while browsing, and records them in a database. The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[0212] 4. Generating Recommendations

[0213] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[0214] 5. Presentation of recommendation results

[0215] The server sends a list of recommended books, along with summaries, pricing information, and inventory information from libraries and online stores, to the device, which then presents this information visually to the user.

[0216] 6. Gathering Feedback

[0217] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[0218] 7. Processing and storing feedback

[0219] The device sends the feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[0220] Specific examples

[0221] A specific usage scenario using the system of the present invention is shown below.

[0222] Scenario 1: Busy businessman

[0223] The user is looking for a book to help them improve their work efficiency, but is currently feeling stressed.

[0224] Users input tasks such as "How to improve work efficiency" via the device, as well as business-related books they have read in the past. The emotion engine then detects their current stress level.

[0225] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[0226] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[0227] After purchasing and reading "Stress Management," a user enters feedback saying, "I found it very relaxing."

[0228] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[0229] Scenario 2: A student studying for a test

[0230] A student user is looking for books related to a particular subject, but is currently experiencing low motivation.

[0231] A user inputs a topic such as "Basics of Statistics" via a terminal, and the emotion engine detects when the user's motivation is declining.

[0232] The server also analyzes information from academic books that have been read in the past and educational sites that have been visited, and recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Study Methods to Motivate You."

[0233] The device will present this list of recommendations along with library holdings information and online purchase links.

[0234] After reading "Study Methods to Motivate You," the user enters feedback such as "It was very encouraging."

[0235] The server and emotion engine receive this feedback information to help adjust the recommendation algorithm next time.

[0236] This allows users to receive recommendations for books that best fit their current emotional state, enhancing their reading experience, and feedback allows the system to continually evolve and improve its recommendations.

[0237] The processing flow will be explained below.

[0238] Step 1:

[0239] Users access the device's interface and input their reading history, internet browsing history, problems they want to solve, and areas of interest, such as "how to improve work efficiency" or "books on leadership."

[0240] Step 2:

[0241] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency and makes it easier for the server to parse.

[0242] Step 3:

[0243] The server receives the user data sent from the device and stores it in a database, including the user's emotional state.

[0244] Step 4:

[0245] The emotion engine analyzes user input and behavior (e.g., reading history, time spent on web pages, etc.) to identify the user's emotional state. For example, it can detect that the user's current stress level is high based on their writing and selections.

[0246] Step 5:

[0247] The server uses the stored data and the analysis results of the emotion engine to generate a recommendation algorithm based on the user's interests and concerns, which also takes into account the user's current emotional state.

[0248] Step 6:

[0249] The server then uses the generated recommendation algorithm to create a list of books that are best suited to the user. For example, it might recommend books that have a relaxing effect to a user who is feeling stressed, or books about efficiency to a user who wants to improve their work efficiency.

[0250] Step 7:

[0251] The server uses library collection information and online store APIs to collect book availability and price information, which is then added to the recommendation list.

[0252] Step 8:

[0253] The server sends a recommendation list including detailed information to the terminal.

[0254] Step 9:

[0255] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[0256] Step 10:

[0257] After reading the recommended book, users can input feedback via their device, including their emotional state after reading.

[0258] Step 11:

[0259] The terminal converts the feedback data into an appropriate format and sends it to the server, which ensures data consistency.

[0260] Step 12:

[0261] The server receives the feedback data sent from the terminal and stores it in a database.

[0262] Step 13:

[0263] Based on the stored feedback data and the analysis results of the emotion engine, the server makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[0264] This allows the system to continuously improve and provide users with more accurate recommendations, specifically recommendations that reflect the user's emotional state in real time, resulting in a more personalized reading experience.

[0265] Example 2

[0266] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0267] Recommendation systems that take into account a user's reading and internet browsing history are required to realize more personalized recommendations that reflect the user's current emotional state, rather than simply being based on past history. In particular, accurate recommendations that meet the specific needs of busy business people or students are heavily influenced by daily fluctuations in stress and motivation, so incorporating emotional information is important.

[0268] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0269] In this invention, the server includes means for collecting a user's reading history and internet browsing history and storing them in an information storage device, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, and means for recognizing and analyzing the user's emotional information to evaluate the user's current emotional state. This enables the server to recommend books that take into account the user's reading history and internet browsing history, as well as the user's current stress and motivation levels. This provides the user with an optimal reading experience, and by utilizing this feedback in subsequent recommendations, the accuracy of recommendations can be continuously improved.

[0270] "Reading history" is information about books a user has read in the past.

[0271] "Internet browsing history" is information about web pages and content that a user has viewed on the Internet in the past.

[0272] An "information storage device" is a device that stores and manages data collected by the server from users.

[0273] "Emotional information" is information about the emotional state a user expresses through their input or actions.

[0274] A "recommendation algorithm" is a set of calculation procedures and rules for recommending books and content suitable for a user based on collected user data.

[0275] An "emotion engine" is a system that analyzes a user's emotional state and reflects that data in the recommendation algorithm.

[0276] "Feedback" refers to information about ratings and impressions provided by users after using recommended books or content.

[0277] The "database" is a data storage system for centrally managing collected user reading history, internet browsing history, emotional information, etc.

[0278] "User" refers to an individual who uses this system to receive recommendations for books and content.

[0279] A "terminal" is an electronic device that a user uses to interface with the system.

[0280] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotional information to achieve more personalized recommendations for the user. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[0281] Entering user information

[0282] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. In addition, emotional information is also recorded through the emotion engine, which analyzes the user's input and actions.

[0283] Information Collection and Storage

[0284] The terminal converts the input data into an appropriate format (such as JSON format) and sends it to the server.

[0285] The server stores the received information in a database, including the user's emotional state.

[0286] Analyzing the data

[0287] The server analyzes saved reading history, internet browsing history, problems to be solved, and emotional information.

[0288] The emotion engine analyzes the content users enter and the emotions they express while browsing, and records them in a database.

[0289] The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[0290] Generating Recommendations

[0291] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[0292] Presentation of recommendation results

[0293] The server sends the device a list of recommended books, as well as summaries, pricing information, and inventory information from libraries and online stores.

[0294] The device visually presents this information to the user.

[0295] Gathering feedback

[0296] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[0297] Processing and storing feedback

[0298] The terminal transmits the feedback data to the server.

[0299] The server stores the received feedback information in a database and uses it to improve the recommendation algorithm in future.

[0300] The emotion engine reassess the user's emotional state from the feedback information and updates the recommendation algorithm based on this.

[0301] Specific examples

[0302] Scenario 1: Busy businessman

[0303] The user types "ways to improve work efficiency" into the device and also enters the business-related books they have read in the past.

[0304] The emotion engine detects the current stress state.

[0305] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[0306] The device will present the user with a list of recommended books, summaries, and a link to purchase from the online store.

[0307] After a user purchases and reads "Stress Management," they enter feedback saying, "I found it very relaxing."

[0308] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[0309] Prompt Sentence Examples

[0310] "I want to know how to improve my work efficiency. I've read books like 'The 7 Habits' and 'Essential Thinking' in the past. I've been feeling stressed lately."

[0311] "I want to learn the basics of statistics. The only book I've read on the subject is 'Introduction to Statistics.' I'm currently feeling unmotivated."

[0312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0313] Step 1: Enter your user information

[0314] Users use the device to input their reading history, internet browsing history, problems they want to solve, and areas of interest. The device converts the user's input into an appropriate data format, such as JSON. The emotion engine also analyzes the user's input and behavior and records the emotional information as an emotional status. The input data are raw text, qualitative comments, and rating scores. The output is formatted user information and emotional status.

[0315] Examples:

[0316] The user types in "How to improve work efficiency" and adds "essential thoughts" they have read in the past. The emotion engine detects stress from the user's input.

[0317] Step 2: Collecting and storing information

[0318] The device will format the data entered by the user, convert it into the appropriate data format, and then send it to the server. The server will store the received data in a database. This storage process includes the user's reading history, internet browsing history, and emotional information.

[0319] Input: Data entered by the user (reading history, internet browsing history, emotional information)

[0320] Output: Formatted data sent to the server

[0321] Examples:

[0322] The device sends the following data to the server:

[0323] json

[0324] {

[0325] "Reading history": ["Essential Thinking"],

[0326] "Web browsing history": ["How to improve work efficiency"],

[0327] "Emotional state": "Stress"

[0328] }

[0329] Step 3: Analyze the data

[0330] The server extracts stored user data and analyzes it based on reading history, internet browsing history, and emotional information. This analysis uses natural language processing algorithms and generative AI models to identify user interests and evaluate emotional information. The analysis results are then combined with the analysis data from the emotional engine to form a user profile.

[0331] Input: User data extracted from the database (reading history, internet browsing history, emotional information)

[0332] Output: User interest profile and emotional state

[0333] Examples:

[0334] The server analyzes the following information to create a profile of the user's attributes and emotional state:

[0335] Reading History: Essential Thinking

[0336] Web browsing history: How to improve your work efficiency

[0337] Emotional state: Stress

[0338] Step 4: Generate recommendations

[0339] The server then applies a recommendation algorithm based on the analysis results to generate a list of books that are best suited to the user, taking into account emotional information from the emotion engine. The algorithm reflects the user's current emotional state and selects books that fit that sentiment.

[0340] Input: User profile data (interests, concerns, emotional state)

[0341] Output: Recommended book list

[0342] Examples:

[0343] The server recommends the following book:

[0344] Essential Thinking

[0345] Mental Model

[0346] Stress management

[0347] Step 5: Presenting the Recommendations

[0348] The server sends the generated recommended book list, summaries, price information, and inventory information from libraries and online stores to the terminal, which visually displays this information to the user.

[0349] Input: Recommendation results provided by the server

[0350] Output: The list of recommendations and details displayed to the user

[0351] Examples:

[0352] The terminal will display the following list:

[0353] Essential Thinking (price, summary)

[0354] Mental model (price, summary)

[0355] Stress Management (Price, Summary)

[0356] Step 6: Gather feedback

[0357] After reading the recommended book, the user inputs feedback via the terminal, including their emotional state and specific impressions after reading. The terminal then sends the feedback data to the database.

[0358] Input: User feedback (emotional state, thoughts)

[0359] Output: Feedback data sent to the server

[0360] Examples:

[0361] A user finishes reading "Stress Management" and gives feedback that it was "very relaxing."

[0362] Step 7: Processing and storing feedback

[0363] The device sends the collected feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm.

[0364] Input: Feedback data

[0365] Output: Updated recommendation algorithm

[0366] Examples:

[0367] Your feedback information will be saved and used for future recommendations as follows:

[0368] json

[0369] {

[0370] "Books I've read": "Stress Management",

[0371] "Emotional state": "Very relaxed"

[0372] }

[0373] (Application example 2)

[0374] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0375] Conventional recommendation systems are based on a user's reading history and internet browsing history, and do not take into account the user's specific emotional state. This makes it difficult to recommend optimal books that vary depending on the user's current emotions, such as stress or lack of motivation. Furthermore, they lack the ability to effectively utilize user feedback to improve the accuracy of next recommendations. This has led to issues such as a decrease in user satisfaction and difficulty in promoting long-term use.

[0376] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing them in a database, and means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, concerns, and emotional state. This enables personalized recommendations that take the user's emotional state into consideration.

[0377] A "user" is an entity that uses this system and performs activities such as reading or browsing the Internet.

[0378] "Reading history" is a record of books a user has read in the past, including their content and impressions.

[0379] "Web browsing history" is a record of the web pages a user has accessed and articles they have read on the Internet.

[0380] "Emotional state" refers to the emotional state a user is feeling at a particular point in time, and can include stress, joy, motivation, etc.

[0381] A "recommendation algorithm" is a computational method for analyzing collected data and selecting the most suitable book for a user.

[0382] The "database" is a system that stores and centrally manages collected user information, emotional state, and feedback data.

[0383] A "recommended list" is a list of books presented to users based on analyzed data, including summaries and pricing information.

[0384] "Feedback" refers to the impressions and evaluations that users enter after reading a recommended book, and includes information about their emotional state.

[0385] "Server" means the central system that processes, stores and analyzes data received from Users.

[0386] "Data collection means" refers to interfaces or software used to collect information such as users' reading history and internet browsing history.

[0387] An "emotion engine" is a computer program that analyzes a user's emotional state and generates data based on that.

[0388] "Online store information" refers to inventory and price information on online book sales sites.

[0389] "Library information" refers to the stock status and lending information of books at libraries, etc.

[0390] "Terminal" refers to the device through which a user enters data and receives recommended book information, including smartphones and tablets.

[0391] The present invention is a book recommendation system that takes into account the emotional state of a user, and its main components are a user terminal, a server, and an emotion engine. This system is implemented using a user terminal such as a smartphone or tablet.

[0392] The user device is equipped with a means for collecting the user's reading history and internet browsing history and storing them in a database. Furthermore, the user device is equipped with an interface for inputting the user's current issues and concerns, and an interface for inputting feedback after reading. This allows the user to provide the system with their interests and emotional state.

[0393] The server analyzes data collected from the user's device and generates a recommendation algorithm based on the user's interests, concerns, and emotional state. An emotion analysis engine using libraries such as TextBlob determines the user's emotional state from the text they input. The analysis results are stored in a database and used to generate the recommendation algorithm.

[0394] Based on the generated recommendation algorithm, the server generates a list of books that are most suitable for the user. This list takes into account the user's emotional state, for example, recommending relaxing books to a user who is feeling stressed. The device then presents this recommendation list to the user, along with summaries, price information, and online store inventory information.

[0395] After the user finishes reading a recommended book, the device collects feedback from the user and sends it to the server. The server stores this feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future installments. The emotion engine reassess the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[0396] As a concrete example, User A is looking for books aimed at relieving work stress. Using this system, he searches for "stress management" and inputs his past reading history, and the sentiment analysis engine detects "stressed state." Based on this, the server recommends "books on mindfulness" as "books with a relaxing effect" and presents the list to the user.

[0397] An example prompt is, "I've been busy and stressed lately, so I'm looking for a book that will calm me down."

[0398] This system enables more personalized book recommendations that take into account the user's emotional state, thereby increasing user satisfaction.

[0399] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0400] Step 1:

[0401] The user uses the device to input text related to their reading history, internet browsing history, and their current emotional state. This input includes not only their reading history and internet browsing history, but also sentences that indicate their emotional state (e.g., "I've been feeling stressed lately.") This allows the user's areas of interest and current emotional state to be collected as initial data.

[0402] Step 2:

[0403] The device converts the collected data into an appropriate format and sends it to the server, using, for example, JSON format. The data includes the user's reading history, internet browsing history, and input emotional state text. The server receives this data and stores it in an initial database.

[0404] Step 3:

[0405] The server uses libraries such as TextBlob to analyze the input emotional state text. The emotion analysis engine performs the analysis and outputs the user's emotional state (e.g., positive, negative, neutral) as numerical data. This numerical emotional state data is also stored in the database.

[0406] Step 4:

[0407] The server generates a recommendation algorithm based on the collected reading history, internet browsing history, and emotional state data. A recommendation algorithm is a computational method for selecting the most suitable books for a user based on past data analysis. This algorithm generation process may use machine learning models (e.g., generative AI models).

[0408] Step 5:

[0409] The server then generates a list of books that best fit the user's emotional state based on the recommendation algorithm. Taking into account the analysis results of the emotion engine, the server lists books that have a "stress-relieving" or "relaxing" effect, for example. These recommended book lists also include summaries of each book, pricing information, and inventory information for online stores and libraries.

[0410] Step 6:

[0411] The server sends the generated recommended book list to the terminal, which visually presents the list to the user. The user can browse the recommended list and select books that interest them, allowing the user to easily find the books they currently need most.

[0412] Step 7:

[0413] After reading, users can use their devices to input feedback, including their emotional state after reading and their rating of the book. The feedback data provides users with an opportunity to specifically input their rating for the recommendation system.

[0414] Step 8:

[0415] The device sends the feedback data to the server. The server stores the received feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future. The emotion engine reanalyzes the feedback information, evaluates changes in the user's emotional state, and updates the recommendation algorithm based on this. This allows the system to continuously learn and make even more accurate recommendations.

[0416] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0417] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search<url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0419] [Second embodiment]

[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0421] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0422] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0424] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0426] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0427] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0428] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0429] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0430] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0431] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0432] The system of the present invention analyzes a user's reading history and internet browsing history and recommends the most suitable books, effectively providing books that match the user's interests and challenges. This system mainly exchanges information between the user, the terminal, and the server, and is implemented in the following procedure.

[0433] 1. Enter your user information

[0434] Users can input their reading history, internet browsing history, current issues or concerns they want to resolve, etc. For example, if they want to learn a specific business skill, they can input that information.

[0435] 2. Information Collection and Storage

[0436] The terminal sends the input information to the server, which stores the received information in a database, thereby accumulating user history data.

[0437] 3. Data Analysis

[0438] The server analyzes the information stored in the database and generates algorithms that identify users' interests, such as the business books they have read or the web pages they have visited.

[0439] 4. Generating Recommendations

[0440] The server uses the generated algorithm to create a list of books suitable for the user, including a summary of each book, and also queries inventory information from libraries and online stores to provide information on where the book is available.

[0441] 5. Presentation of recommendation results

[0442] The server sends the recommendation list to the device, which displays the list to the user in an easy-to-understand format, allowing the user to easily decide which book to choose.

[0443] 6. Gathering Feedback

[0444] After reading a recommended book, users can enter feedback via their device, such as "It was very helpful" or "I would like to read another book by this author."

[0445] 7. Processing and storing feedback

[0446] The device sends the feedback information to the server, which then stores it in the database and uses it to improve the accuracy of the recommendation algorithm next time.

[0447] Specific examples

[0448] A specific usage scenario using the system of the present invention is shown below.

[0449] Scenario 1: Businessman's Case

[0450] Let's say a user is looking for a book to improve their business skills.

[0451] Through the terminal, users input tasks such as "improving business skills" and also enter a history of related books they have read in the past, such as "leadership" and "marketing."

[0452] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Marketing Fundamentals."

[0453] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[0454] After purchasing and reading "Essential Thinking," users enter feedback such as "It was very helpful."

[0455] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm next time.

[0456] Scenario 2: Student Case

[0457] Let's say a user is a student looking for books related to a particular course.

[0458] Assignments such as "Fundamentals of Statistics" are entered via the terminal.

[0459] The server also analyzes information about mathematics-related books that students have read in the past and educational websites that they have visited.

[0460] The server recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Introduction to Statistical Thinking" and presents them to users.

[0461] The device will present this list of recommendations along with links to check the library's holdings and purchase the book online.

[0462] The user finishes reading "Introduction to Statistics" and enters feedback such as "The content was easy to understand."

[0463] The server receives this feedback and uses it to improve its recommendation algorithm for future visits.

[0464] This allows users to find the books that best suit their interests and challenges, enriching their reading experience, and feedback allows the system to continually evolve and provide even more accurate recommendations.

[0465] The processing flow will be explained below.

[0466] Step 1:

[0467] Users access the device's interface and enter their reading history, internet browsing history, problems they want to solve, and areas of interest.

[0468] Step 2:

[0469] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency.

[0470] Step 3:

[0471] The server receives the user data sent from the device and stores it in a database, which includes inserting it into the database using SQL queries.

[0472] Step 4:

[0473] The server analyzes the stored data periodically or as needed to generate a recommendation algorithm based on the user's interests, which involves applying machine learning models based on similar past data.

[0474] Step 5:

[0475] The server uses the generated recommendation algorithm to create a list of books that are most suitable for the user, along with associated summaries that are also generated and included in the list.

[0476] Step 6:

[0477] The server uses APIs from libraries and online stores to gather book availability and price information, which is then added to the recommendation list.

[0478] Step 7:

[0479] The server sends a recommendation list including detailed information to the terminal.

[0480] Step 8:

[0481] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[0482] Step 9:

[0483] After reading a recommended book, users can enter their feedback on the device, including their rating and impressions of the book.

[0484] Step 10:

[0485] The terminal converts the feedback data into an appropriate format and sends it to the server.

[0486] Step 11:

[0487] The server receives the feedback data sent from the terminal and stores it in a database.

[0488] Step 12:

[0489] The server analyzes the stored feedback data and makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[0490] This allows the system to continually improve and provide even more accurate recommendations to users.

[0491] Example 1

[0492] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0493] Current book recommendation systems struggle to recommend appropriate books that fully take into account a user's individual interests, past reading history, and internet browsing history. Furthermore, recommendations do not address the specific challenges or concerns of users, limiting the reading experience. Furthermore, improvements to the accuracy of recommendation algorithms using feedback information are insufficient.

[0494] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0495] In this invention, the server includes: a means for inputting a user's reading history and internet browsing history; a means for collecting the user's reading history and internet browsing history and storing it in a database; a means for analyzing the collected data and generating a recommendation algorithm based on the user's interests; a means for presenting a list of recommended books and summaries to the user; a means for providing information on where the recommended books are available and their prices; a means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm; a means for identifying the user's areas of interest using a machine learning algorithm; a means for generating a list of books that are best suited to the user using collaborative filtering or content-based filtering technology; and a means for saving the user's input information in a database in real time. This enables the server to recommend books that are best suited to the user's individual interests, specific challenges, and concerns. The accuracy of the recommendation algorithm is also improved based on the feedback.

[0496] "Reading history" is a record of information such as the title, summary, and date and time of books that a user has read in the past.

[0497] "Web browsing history" refers to the history of web pages and online materials that a user has viewed in the past.

[0498] An "input means" is a device or interface that allows users to input their reading history, internet browsing history, problems or concerns they want to solve, etc. into the system.

[0499] A "database" is a system for systematically storing collected information such as a user's reading history and internet browsing history.

[0500] A "recommendation algorithm" is a program and calculation method for recommending the most suitable books based on a user's interests and concerns.

[0501] A "machine learning algorithm" is a method for analyzing large amounts of data and finding patterns in it to make future predictions and classifications.

[0502] "Collaborative filtering" is a method of analyzing a user's interests and the behavior of other users to recommend items that are common to users with similar interests.

[0503] "Content-based filtering" is a method of recommending items with similar content based on a user's past behavior and preferences.

[0504] "Feedback" refers to the ratings and impressions that users enter after reading a recommended book.

[0505] "Real-time" means processing occurs immediately, without delay.

[0506] The system of the present invention analyzes a user's reading history and internet browsing history to recommend the most suitable books, providing books that match the user's interests and themes. This system is implemented by exchanging information mainly between the user, the terminal, and the server.

[0507] First, users input their reading and internet browsing history via the device, and then input information about the problems they currently want to solve and areas of interest, using prompts such as "improving business skills" or "basics of statistics."

[0508] The device then transmits the information entered by the user in real time to a server, which receives the information and stores it in a database that stores each user's reading history, internet browsing history, and input information about topics and interests.

[0509] The server analyzes the information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest. Specifically, it analyzes the content of books the user has read and web pages they have viewed to determine the user's interests.

[0510] The server then uses the analysis results to generate a list of books suitable for the user using collaborative or content-based filtering techniques, including each book's summary, author name, and availability information at libraries and online stores.

[0511] The generated recommendation list is sent from the server to the device, which then displays the list to the user in an easy-to-read format. The user can then decide which book to choose based on the list of recommended books. The list also includes a purchase link and library information, making it easy for the user to obtain the book.

[0512] After a user finishes reading a book, they can enter their feedback via their device. The feedback includes their rating and impressions of the book, such as "It was very helpful" or "I would like to read another book by this author."

[0513] The feedback information is sent from the device to the server, which stores it in a database. The server then analyzes the stored feedback data and uses it to improve the accuracy of the recommendation algorithm next time.

[0514] In this way, the system of the present invention can recommend books that are optimal for a user's individual interests, concerns, and specific problems and concerns. Furthermore, since the accuracy of the recommendation algorithm is improved based on feedback, high-quality recommendations that meet the user's needs are continuously provided.

[0515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0516] Step 1:

[0517] Users access the device's application or web interface and input their reading history, internet browsing history, current problems they want to solve, and areas of interest. For example, they input prompts such as "improve business skills" or "basics of statistics." The input data is sent to the system as user interest information (input: user information, output: user interest information).

[0518] Step 2:

[0519] The device sends the information entered by the user to the server in real time (input: user interest information, output: server-sent data). The server receives this information, associates it with the user ID, and stores it in a database (input: server-sent data, output: database-stored data). The database stores each user's reading history, internet browsing history, and entered assignments and interest information.

[0520] Step 3:

[0521] The server analyzes the user information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest (input: data stored in the database, output: user interest trends). Specifically, it analyzes the content of books the user has read in the past and web pages they have viewed to determine the user's interests. For example, it identifies trends in specific areas such as "marketing" or "leadership."

[0522] Step 4:

[0523] Based on the analysis results, the server uses collaborative filtering or content-based filtering techniques to generate a list of books that are best suited to the user (input: user's interest trends, output: recommended book list). This list includes each book's summary, author name, and availability information at libraries and online stores. The algorithm pulls out historical data of users with similar interests and books with related content from the past.

[0524] Step 5:

[0525] The server sends the generated recommended book list to the terminal (input: recommended book list, output: terminal-sent data). The terminal displays the list to the user in an easy-to-read format (input: terminal-sent data, output: user-displayed data). The recommended list includes the book title, summary, author name, and link to where the book is available. The user can decide which book to choose based on this list.

[0526] Step 6:

[0527] After reading a recommended book, the user inputs their evaluation and thoughts about the book into the device (input: thoughts after reading, output: feedback information). For example, they can input feedback such as "It was very helpful" or "I would like to read another book by the same author."

[0528] Step 7:

[0529] The device sends the input feedback information to the server (input: feedback information, output: server-sent feedback). The server stores this feedback in a database (input: server-sent feedback, output: database feedback storage). The server then analyzes the stored feedback data again and uses it to improve the accuracy of the next recommendation algorithm (input: database feedback storage, output: accuracy improvement data).

[0530] Through these steps, the system is able to recommend the most suitable books based on the user's individual interests, concerns, and specific problems and concerns. Furthermore, the accuracy of the recommendation algorithm is improved based on feedback, allowing the system to continuously provide high-quality recommendations that meet the user's needs.

[0531] (Application example 1)

[0532] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0533] Previously, there were systems that recommended books based on a user's reading and internet browsing history, reflecting their individual preferences. However, the accuracy and diversity of the recommendations were insufficient, and they were unable to sufficiently increase user satisfaction. Furthermore, existing systems did not provide sufficient information on where to obtain the recommended books and content, nor did they provide pricing information, and lacked a mechanism to enable users to easily obtain the content.

[0534] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0535] In this invention, the server includes means for inputting a user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing it in a database, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests and concerns, means for presenting a list and summary of recommended content to the user, means for providing information on where the recommended content is available and its price, means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm, means for improving the recommendation algorithm based on the feedback, and means for making recommendations optimized to the user's interests and needs through prompt sentences using a generative AI model. This enables highly accurate content recommendations tailored to the user's needs and the provision of information on where and how to obtain the content.

[0536] "User reading history" is information about books and documents that a user has read in the past.

[0537] "Web browsing history" is information about the web pages and content a user has viewed on the Internet.

[0538] An "input means" is a device or interface through which a user provides information to a system, either manually or automatically.

[0539] "Means of collection" refers to the devices and methods used to properly acquire information entered by users and store it in a database.

[0540] A "database storage means" is a system or device that organizes collected information and stores it in a form that can be reused later.

[0541] "Analytical means" refers to the algorithms and programs used to process collected data and identify user interests.

[0542] A "recommendation algorithm" is a mathematical or programmatic method for selecting the most appropriate content based on a user's past behavioral data.

[0543] A "means for presenting lists and summaries" is an interface for displaying the recommendation results to the user in visual or text form.

[0544] "Means for providing" refers to a system or device that informs users where the recommended content is available and its price information.

[0545] "Means for collecting feedback" refers to devices or programs that obtain opinions and evaluations about the content used by users and reflect them in the system.

[0546] "Means for analyzing and storing feedback data" refers to a system or device that stores the feedback collected from users in a database and uses it to improve the recommendation algorithm for the next time.

[0547] "Means for improving recommendation algorithms" refers to techniques and methods for updating existing recommendation algorithms based on new feedback information and improving their accuracy.

[0548] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms for a specific task.

[0549] A "prompt sentence" is an input sentence given to a generative AI model, and is text data that serves as a trigger to obtain appropriate output from the model.

[0550] To put this invention into practice, it is necessary to build a system that analyzes a user's reading history and internet browsing history and recommends optimal content. Here, we will explain the various programs that make up this system and their processing.

[0551] 1. Collecting and entering user information

[0552] The device (e.g., a smartphone) provides an interface for users to input their reading history and internet browsing history. This information is collected by manual input or by syncing the browser history. The device then transmits this data to a cloud server. This transmission is secured using the HTTPS protocol.

[0553] 2. Data storage

[0554] The cloud server stores the received data in a database, where users' reading and browsing histories are accumulated and later used for analysis. This storage process is handled by a database management system such as MySQL or PostgreSQL.

[0555] 3. Data Analysis

[0556] The cloud server analyzes the information stored in the database and generates algorithms to identify user interests. This process uses data analysis tools such as Python and R and applies machine learning algorithms (e.g., collaborative filtering).

[0557] 4. Generating a recommendation list

[0558] The cloud server creates a list of content that is best suited to the user based on the analysis results. The recommendation list also includes a summary of each piece of content and available information (e.g., purchase links and stock information). This allows users to easily access the recommended content.

[0559] 5. Presentation of recommendation results

[0560] The device receives a list of recommendations from the cloud server and presents them to the user. The screen interface uses web technologies such as HTML and CSS to display information in a visually easy-to-understand format.

[0561] 6. Gathering Feedback

[0562] After using the recommended content, users can enter their ratings and feedback via their devices, which is then sent back to the cloud server and stored in a database.

[0563] 7. Algorithm Improvements

[0564] The cloud server analyzes the collected feedback data and improves the recommendation algorithm, which improves the accuracy of recommendations from the next time onwards and increases user satisfaction.

[0565] 8. Generative AI Model and Prompts

[0566] The system uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are inputs given to an artificial intelligence model trained using machine learning algorithms for a specific task, and are text data that triggers the model to produce an appropriate output.

[0567] As a concrete example, the following is an example of an input prompt for a generative AI model:

[0568] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[0569] Reading history: Leadership, Marketing

[0570] Browsing History: Digital Transformation

[0571] In this way, it is possible to recommend highly accurate content that meets the user's needs, and to provide information on where to obtain that content and its price, allowing users to select content that will give them greater satisfaction.

[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0573] Step 1:

[0574] The device provides an interface for users to input their reading history and internet browsing history. Users can manually input information about books they have read and web pages they have visited, or synchronize their browser history. This data is input into the device. The input data is the user's past reading materials and internet browsing records.

[0575] Step 2:

[0576] The device sends the user's reading and browsing history to the cloud server, using the HTTPS protocol to ensure data security. The output data is the user's reading and browsing history.

[0577] Step 3:

[0578] The server stores the received data in a database. The database management system used (e.g., MySQL or PostgreSQL) structures and stores the user's reading and browsing history. The input data is the user's history data, and the output is stored in the database.

[0579] Step 4:

[0580] The server analyzes the information stored in the database. In this process, it applies machine learning algorithms (e.g., collaborative filtering) using Python or R languages ​​to identify the user's interests. The input is the stored user history data, and the output is the analysis results based on the user's interests.

[0581] Step 5:

[0582] The server generates a list of optimal content based on the user's interests. This list includes a summary of each piece of content and acquisition information (purchase link and stock information). This allows the user to easily access the recommended content. The input is the analysis results, and the output is a list of several recommended contents.

[0583] Step 6:

[0584] The device presents the recommendation list received from the server to the user. The screen interface is constructed using HTML and CSS, and information is displayed in a visually easy-to-understand format. The input is the recommendation list data, and the output is the visual recommendation list presented to the user.

[0585] Step 7:

[0586] The user uses the recommended content and enters their rating and feedback through their device. This feedback is then sent back to the cloud server. The input is the user's feedback data, and the output is the sent feedback information.

[0587] Step 8:

[0588] The server analyzes the collected feedback data and improves the recommendation algorithm. It uses the new feedback information to update the existing recommendation algorithm and improve its accuracy, which will result in more accurate recommendations in the future. The input is the feedback data and the output is the improved recommendation algorithm.

[0589] Step 9:

[0590] The server uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are given to the generative AI model and act as triggers to obtain appropriate output. The input is the user's history data and feedback data, and the output is a highly accurate content recommendation prompt.

[0591] As a concrete example, the following is an example of an input prompt for a generative AI model:

[0592] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[0593] Reading history: Leadership, Marketing

[0594] Browsing History: Digital Transformation

[0595] In this way, by combining each step, a highly accurate content recommendation system that meets the user's needs is realized.

[0596] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0597] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotions to provide more personalized recommendations for the user. This system consists of four main components: the user, the device, the server, and the emotion engine.

[0598] 1. Enter your user information

[0599] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. Emotional information obtained through the user's input and actions is also recorded by the emotion engine.

[0600] 2. Information Collection and Storage

[0601] The device converts the input data into an appropriate format and sends it to the server, which stores the received information in a database, including the user's emotional state.

[0602] 3. Data Analysis

[0603] The server analyzes the saved reading history, browsing history, problems to be solved, and emotional information. The emotion engine analyzes the content entered by the user and the emotions expressed while browsing, and records them in a database. The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[0604] 4. Generating Recommendations

[0605] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[0606] 5. Presentation of recommendation results

[0607] The server sends a list of recommended books, along with summaries, pricing information, and inventory information from libraries and online stores, to the device, which then presents this information visually to the user.

[0608] 6. Gathering Feedback

[0609] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[0610] 7. Processing and storing feedback

[0611] The device sends the feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[0612] Specific examples

[0613] A specific usage scenario using the system of the present invention is shown below.

[0614] Scenario 1: Busy businessman

[0615] The user is looking for a book to help them improve their work efficiency, but is currently feeling stressed.

[0616] Users input tasks such as "How to improve work efficiency" via the device, as well as business-related books they have read in the past. The emotion engine then detects their current stress level.

[0617] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[0618] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[0619] After purchasing and reading "Stress Management," a user enters feedback saying, "I found it very relaxing."

[0620] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[0621] Scenario 2: A student studying for a test

[0622] A student user is looking for books related to a particular subject, but is currently experiencing low motivation.

[0623] A user inputs a topic such as "Basics of Statistics" via a terminal, and the emotion engine detects when the user's motivation is declining.

[0624] The server also analyzes information from academic books that have been read in the past and educational sites that have been visited, and recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Study Methods to Motivate You."

[0625] The device will present this list of recommendations along with library holdings information and online purchase links.

[0626] After reading "Study Methods to Motivate You," the user enters feedback such as "It was very encouraging."

[0627] The server and emotion engine receive this feedback information to help adjust the recommendation algorithm next time.

[0628] This allows users to receive recommendations for books that best fit their current emotional state, enhancing their reading experience, and feedback allows the system to continually evolve and improve its recommendations.

[0629] The processing flow will be explained below.

[0630] Step 1:

[0631] Users access the device's interface and input their reading history, internet browsing history, problems they want to solve, and areas of interest, such as "how to improve work efficiency" or "books on leadership."

[0632] Step 2:

[0633] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency and makes it easier for the server to parse.

[0634] Step 3:

[0635] The server receives the user data sent from the device and stores it in a database, including the user's emotional state.

[0636] Step 4:

[0637] The emotion engine analyzes user input and behavior (e.g., reading history, time spent on web pages, etc.) to identify the user's emotional state. For example, it can detect that the user's current stress level is high based on their writing and selections.

[0638] Step 5:

[0639] The server uses the stored data and the analysis results of the emotion engine to generate a recommendation algorithm based on the user's interests and concerns, which also takes into account the user's current emotional state.

[0640] Step 6:

[0641] The server then uses the generated recommendation algorithm to create a list of books that are best suited to the user. For example, it might recommend books that have a relaxing effect to a user who is feeling stressed, or books about efficiency to a user who wants to improve their work efficiency.

[0642] Step 7:

[0643] The server uses library collection information and online store APIs to collect book availability and price information, which is then added to the recommendation list.

[0644] Step 8:

[0645] The server sends a recommendation list including detailed information to the terminal.

[0646] Step 9:

[0647] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[0648] Step 10:

[0649] After reading the recommended book, users can input feedback via their device, including their emotional state after reading.

[0650] Step 11:

[0651] The terminal converts the feedback data into an appropriate format and sends it to the server, which ensures data consistency.

[0652] Step 12:

[0653] The server receives the feedback data sent from the terminal and stores it in a database.

[0654] Step 13:

[0655] Based on the stored feedback data and the analysis results of the emotion engine, the server makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[0656] This allows the system to continuously improve and provide users with more accurate recommendations, specifically recommendations that reflect the user's emotional state in real time, resulting in a more personalized reading experience.

[0657] Example 2

[0658] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0659] Recommendation systems that take into account a user's reading and internet browsing history are required to realize more personalized recommendations that reflect the user's current emotional state, rather than simply being based on past history. In particular, accurate recommendations that meet the specific needs of busy business people or students are heavily influenced by daily fluctuations in stress and motivation, so incorporating emotional information is important.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0661] In this invention, the server includes means for collecting a user's reading history and internet browsing history and storing them in an information storage device, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, and means for recognizing and analyzing the user's emotional information to evaluate the user's current emotional state. This enables the server to recommend books that take into account the user's reading history and internet browsing history, as well as the user's current stress and motivation levels. This provides the user with an optimal reading experience, and by utilizing this feedback in subsequent recommendations, the accuracy of recommendations can be continuously improved.

[0662] "Reading history" is information about books a user has read in the past.

[0663] "Internet browsing history" is information about web pages and content that a user has viewed on the Internet in the past.

[0664] An "information storage device" is a device that stores and manages data collected by the server from users.

[0665] "Emotional information" is information about the emotional state a user expresses through their input or actions.

[0666] A "recommendation algorithm" is a set of calculation procedures and rules for recommending books and content suitable for a user based on collected user data.

[0667] An "emotion engine" is a system that analyzes a user's emotional state and reflects that data in the recommendation algorithm.

[0668] "Feedback" refers to information about ratings and impressions provided by users after using recommended books or content.

[0669] The "database" is a data storage system for centrally managing collected user reading history, internet browsing history, emotional information, etc.

[0670] "User" refers to an individual who uses this system to receive recommendations for books and content.

[0671] A "terminal" is an electronic device that a user uses to interface with the system.

[0672] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotional information to achieve more personalized recommendations for the user. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[0673] Entering user information

[0674] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. In addition, emotional information is also recorded through the emotion engine, which analyzes the user's input and actions.

[0675] Information Collection and Storage

[0676] The terminal converts the input data into an appropriate format (such as JSON format) and sends it to the server.

[0677] The server stores the received information in a database, including the user's emotional state.

[0678] Analyzing the data

[0679] The server analyzes saved reading history, internet browsing history, problems to be solved, and emotional information.

[0680] The emotion engine analyzes the content users enter and the emotions they express while browsing, and records them in a database.

[0681] The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[0682] Generating Recommendations

[0683] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[0684] Presentation of recommendation results

[0685] The server sends the device a list of recommended books, as well as summaries, pricing information, and inventory information from libraries and online stores.

[0686] The device visually presents this information to the user.

[0687] Gathering feedback

[0688] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[0689] Processing and storing feedback

[0690] The terminal transmits the feedback data to the server.

[0691] The server stores the received feedback information in a database and uses it to improve the recommendation algorithm in future.

[0692] The emotion engine reassess the user's emotional state from the feedback information and updates the recommendation algorithm based on this.

[0693] Specific examples

[0694] Scenario 1: Busy businessman

[0695] The user types "ways to improve work efficiency" into the device and also enters the business-related books they have read in the past.

[0696] The emotion engine detects the current stress state.

[0697] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[0698] The device will present the user with a list of recommended books, summaries, and a link to purchase from the online store.

[0699] After a user purchases and reads "Stress Management," they enter feedback saying, "I found it very relaxing."

[0700] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[0701] Prompt Sentence Examples

[0702] "I want to know how to improve my work efficiency. I've read books like 'The 7 Habits' and 'Essential Thinking' in the past. I've been feeling stressed lately."

[0703] "I want to learn the basics of statistics. The only book I've read on the subject is 'Introduction to Statistics.' I'm currently feeling unmotivated."

[0704] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0705] Step 1: Enter your user information

[0706] Users use the device to input their reading history, internet browsing history, problems they want to solve, and areas of interest. The device converts the user's input into an appropriate data format, such as JSON. The emotion engine also analyzes the user's input and behavior and records the emotional information as an emotional status. The input data are raw text, qualitative comments, and rating scores. The output is formatted user information and emotional status.

[0707] Examples:

[0708] The user types in "How to improve work efficiency" and adds "essential thoughts" they have read in the past. The emotion engine detects stress from the user's input.

[0709] Step 2: Collecting and storing information

[0710] The device will format the data entered by the user, convert it into the appropriate data format, and then send it to the server. The server will store the received data in a database. This storage process includes the user's reading history, internet browsing history, and emotional information.

[0711] Input: Data entered by the user (reading history, internet browsing history, emotional information)

[0712] Output: Formatted data sent to the server

[0713] Examples:

[0714] The device sends the following data to the server:

[0715] json

[0716] {

[0717] "Reading history": ["Essential Thinking"],

[0718] "Web browsing history": ["How to improve work efficiency"],

[0719] "Emotional state": "Stress"

[0720] }

[0721] Step 3: Analyze the data

[0722] The server extracts stored user data and analyzes it based on reading history, internet browsing history, and emotional information. This analysis uses natural language processing algorithms and generative AI models to identify user interests and evaluate emotional information. The analysis results are then combined with the analysis data from the emotional engine to form a user profile.

[0723] Input: User data extracted from the database (reading history, internet browsing history, emotional information)

[0724] Output: User interest profile and emotional state

[0725] Examples:

[0726] The server analyzes the following information to create a profile of the user's attributes and emotional state:

[0727] Reading History: Essential Thinking

[0728] Web browsing history: How to improve your work efficiency

[0729] Emotional state: Stress

[0730] Step 4: Generate recommendations

[0731] The server then applies a recommendation algorithm based on the analysis results to generate a list of books that are best suited to the user, taking into account emotional information from the emotion engine. The algorithm reflects the user's current emotional state and selects books that fit that sentiment.

[0732] Input: User profile data (interests, concerns, emotional state)

[0733] Output: Recommended book list

[0734] Examples:

[0735] The server recommends the following book:

[0736] Essential Thinking

[0737] Mental Model

[0738] Stress management

[0739] Step 5: Presenting the Recommendations

[0740] The server sends the generated recommended book list, summaries, price information, and inventory information from libraries and online stores to the terminal, which visually displays this information to the user.

[0741] Input: Recommendation results provided by the server

[0742] Output: The list of recommendations and details displayed to the user

[0743] Examples:

[0744] The terminal will display the following list:

[0745] Essential Thinking (price, summary)

[0746] Mental model (price, summary)

[0747] Stress Management (Price, Summary)

[0748] Step 6: Gather feedback

[0749] After reading the recommended book, the user inputs feedback via the terminal, including their emotional state and specific impressions after reading. The terminal then sends the feedback data to the database.

[0750] Input: User feedback (emotional state, thoughts)

[0751] Output: Feedback data sent to the server

[0752] Examples:

[0753] A user finishes reading "Stress Management" and gives feedback that it was "very relaxing."

[0754] Step 7: Processing and storing feedback

[0755] The device sends the collected feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm.

[0756] Input: Feedback data

[0757] Output: Updated recommendation algorithm

[0758] Examples:

[0759] Your feedback information will be saved and used for future recommendations as follows:

[0760] json

[0761] {

[0762] "Books I've read": "Stress Management",

[0763] "Emotional state": "Very relaxed"

[0764] }

[0765] (Application example 2)

[0766] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0767] Conventional recommendation systems are based on a user's reading history and internet browsing history, and do not take into account the user's specific emotional state. This makes it difficult to recommend optimal books that vary depending on the user's current emotions, such as stress or lack of motivation. Furthermore, they lack the ability to effectively utilize user feedback to improve the accuracy of next recommendations. This has led to issues such as a decrease in user satisfaction and difficulty in promoting long-term use.

[0768] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing them in a database, and means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, concerns, and emotional state. This enables personalized recommendations that take the user's emotional state into consideration.

[0769] A "user" is an entity that uses this system and performs activities such as reading or browsing the Internet.

[0770] "Reading history" is a record of books a user has read in the past, including their content and impressions.

[0771] "Web browsing history" is a record of the web pages a user has accessed and articles they have read on the Internet.

[0772] "Emotional state" refers to the emotional state a user is feeling at a particular point in time, and can include stress, joy, motivation, etc.

[0773] A "recommendation algorithm" is a computational method for analyzing collected data and selecting the most suitable book for a user.

[0774] The "database" is a system that stores and centrally manages collected user information, emotional state, and feedback data.

[0775] A "recommended list" is a list of books presented to users based on analyzed data, including summaries and pricing information.

[0776] "Feedback" refers to the impressions and evaluations that users enter after reading a recommended book, and includes information about their emotional state.

[0777] "Server" means the central system that processes, stores and analyzes data received from Users.

[0778] "Data collection means" refers to interfaces or software used to collect information such as users' reading history and internet browsing history.

[0779] An "emotion engine" is a computer program that analyzes a user's emotional state and generates data based on that.

[0780] "Online store information" refers to inventory and price information on online book sales sites.

[0781] "Library information" refers to the stock status and lending information of books at libraries, etc.

[0782] "Terminal" refers to the device through which a user enters data and receives recommended book information, including smartphones and tablets.

[0783] The present invention is a book recommendation system that takes into account the emotional state of a user, and its main components are a user terminal, a server, and an emotion engine. This system is implemented using a user terminal such as a smartphone or tablet.

[0784] The user device is equipped with a means for collecting the user's reading history and internet browsing history and storing them in a database. Furthermore, the user device is equipped with an interface for inputting the user's current issues and concerns, and an interface for inputting feedback after reading. This allows the user to provide the system with their interests and emotional state.

[0785] The server analyzes data collected from the user's device and generates a recommendation algorithm based on the user's interests, concerns, and emotional state. An emotion analysis engine using libraries such as TextBlob determines the user's emotional state from the text they input. The analysis results are stored in a database and used to generate the recommendation algorithm.

[0786] Based on the generated recommendation algorithm, the server generates a list of books that are most suitable for the user. This list takes into account the user's emotional state, for example, recommending relaxing books to a user who is feeling stressed. The device then presents this recommendation list to the user, along with summaries, price information, and online store inventory information.

[0787] After the user finishes reading a recommended book, the device collects feedback from the user and sends it to the server. The server stores this feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future installments. The emotion engine reassess the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[0788] As a concrete example, User A is looking for books aimed at relieving work stress. Using this system, he searches for "stress management" and inputs his past reading history, and the sentiment analysis engine detects "stressed state." Based on this, the server recommends "books on mindfulness" as "books with a relaxing effect" and presents the list to the user.

[0789] An example prompt is, "I've been busy and stressed lately, so I'm looking for a book that will calm me down."

[0790] This system enables more personalized book recommendations that take into account the user's emotional state, thereby increasing user satisfaction.

[0791] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0792] Step 1:

[0793] The user uses the device to input text related to their reading history, internet browsing history, and their current emotional state. This input includes not only their reading history and internet browsing history, but also sentences that indicate their emotional state (e.g., "I've been feeling stressed lately.") This allows the user's areas of interest and current emotional state to be collected as initial data.

[0794] Step 2:

[0795] The device converts the collected data into an appropriate format and sends it to the server, using, for example, JSON format. The data includes the user's reading history, internet browsing history, and input emotional state text. The server receives this data and stores it in an initial database.

[0796] Step 3:

[0797] The server uses libraries such as TextBlob to analyze the input emotional state text. The emotion analysis engine performs the analysis and outputs the user's emotional state (e.g., positive, negative, neutral) as numerical data. This numerical emotional state data is also stored in the database.

[0798] Step 4:

[0799] The server generates a recommendation algorithm based on the collected reading history, internet browsing history, and emotional state data. A recommendation algorithm is a computational method for selecting the most suitable books for a user based on past data analysis. This algorithm generation process may use machine learning models (e.g., generative AI models).

[0800] Step 5:

[0801] The server then generates a list of books that best fit the user's emotional state based on the recommendation algorithm. Taking into account the analysis results of the emotion engine, the server lists books that have a "stress-relieving" or "relaxing" effect, for example. These recommended book lists also include summaries of each book, pricing information, and inventory information for online stores and libraries.

[0802] Step 6:

[0803] The server sends the generated recommended book list to the terminal, which visually presents the list to the user. The user can browse the recommended list and select books that interest them, allowing the user to easily find the books they currently need most.

[0804] Step 7:

[0805] After reading, users can use their devices to input feedback, including their emotional state after reading and their rating of the book. The feedback data provides users with an opportunity to specifically input their rating for the recommendation system.

[0806] Step 8:

[0807] The device sends the feedback data to the server. The server stores the received feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future. The emotion engine reanalyzes the feedback information, evaluates changes in the user's emotional state, and updates the recommendation algorithm based on this. This allows the system to continuously learn and make even more accurate recommendations.

[0808] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0809] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0810] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0811] [Third embodiment]

[0812] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0813] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0814] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0815] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0816] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0817] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0818] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0819] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0820] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0821] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0822] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0823] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0824] The system of the present invention analyzes a user's reading history and internet browsing history and recommends the most suitable books, effectively providing books that match the user's interests and challenges. This system mainly exchanges information between the user, the terminal, and the server, and is implemented in the following procedure.

[0825] 1. Enter your user information

[0826] Users can input their reading history, internet browsing history, current issues or concerns they want to resolve, etc. For example, if they want to learn a specific business skill, they can input that information.

[0827] 2. Information Collection and Storage

[0828] The terminal sends the input information to the server, which stores the received information in a database, thereby accumulating user history data.

[0829] 3. Data Analysis

[0830] The server analyzes the information stored in the database and generates algorithms that identify users' interests, such as the business books they have read or the web pages they have visited.

[0831] 4. Generating Recommendations

[0832] The server uses the generated algorithm to create a list of books suitable for the user, including a summary of each book, and also queries inventory information from libraries and online stores to provide information on where the book is available.

[0833] 5. Presentation of recommendation results

[0834] The server sends the recommendation list to the device, which displays the list to the user in an easy-to-understand format, allowing the user to easily decide which book to choose.

[0835] 6. Gathering Feedback

[0836] After reading a recommended book, users can enter feedback via their device, such as "It was very helpful" or "I would like to read another book by this author."

[0837] 7. Processing and storing feedback

[0838] The device sends the feedback information to the server, which then stores it in the database and uses it to improve the accuracy of the recommendation algorithm next time.

[0839] Specific examples

[0840] A specific usage scenario using the system of the present invention is shown below.

[0841] Scenario 1: Businessman's Case

[0842] Let's say a user is looking for a book to improve their business skills.

[0843] Through the terminal, users input tasks such as "improving business skills" and also enter a history of related books they have read in the past, such as "leadership" and "marketing."

[0844] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Marketing Fundamentals."

[0845] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[0846] After purchasing and reading "Essential Thinking," users enter feedback such as "It was very helpful."

[0847] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm next time.

[0848] Scenario 2: Student Case

[0849] Let's say a user is a student looking for books related to a particular course.

[0850] Assignments such as "Fundamentals of Statistics" are entered via the terminal.

[0851] The server also analyzes information about mathematics-related books that students have read in the past and educational websites that they have visited.

[0852] The server recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Introduction to Statistical Thinking" and presents them to users.

[0853] The device will present this list of recommendations along with links to check the library's holdings and purchase the book online.

[0854] The user finishes reading "Introduction to Statistics" and enters feedback such as "The content was easy to understand."

[0855] The server receives this feedback and uses it to improve its recommendation algorithm for future visits.

[0856] This allows users to find the books that best suit their interests and challenges, enriching their reading experience, and feedback allows the system to continually evolve and provide even more accurate recommendations.

[0857] The processing flow will be explained below.

[0858] Step 1:

[0859] Users access the device's interface and enter their reading history, internet browsing history, problems they want to solve, and areas of interest.

[0860] Step 2:

[0861] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency.

[0862] Step 3:

[0863] The server receives the user data sent from the device and stores it in a database, which includes inserting it into the database using SQL queries.

[0864] Step 4:

[0865] The server analyzes the stored data periodically or as needed to generate a recommendation algorithm based on the user's interests, which involves applying machine learning models based on similar past data.

[0866] Step 5:

[0867] The server uses the generated recommendation algorithm to create a list of books that are most suitable for the user, along with associated summaries that are also generated and included in the list.

[0868] Step 6:

[0869] The server uses APIs from libraries and online stores to gather book availability and price information, which is then added to the recommendation list.

[0870] Step 7:

[0871] The server sends a recommendation list including detailed information to the terminal.

[0872] Step 8:

[0873] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[0874] Step 9:

[0875] After reading a recommended book, users can enter their feedback on the device, including their rating and impressions of the book.

[0876] Step 10:

[0877] The terminal converts the feedback data into an appropriate format and sends it to the server.

[0878] Step 11:

[0879] The server receives the feedback data sent from the terminal and stores it in a database.

[0880] Step 12:

[0881] The server analyzes the stored feedback data and makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[0882] This allows the system to continually improve and provide even more accurate recommendations to users.

[0883] Example 1

[0884] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0885] Current book recommendation systems struggle to recommend appropriate books that fully take into account a user's individual interests, past reading history, and internet browsing history. Furthermore, recommendations do not address the specific challenges or concerns of users, limiting the reading experience. Furthermore, improvements to the accuracy of recommendation algorithms using feedback information are insufficient.

[0886] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0887] In this invention, the server includes: means for inputting a user's reading history and internet browsing history; means for collecting the user's reading history and internet browsing history and storing it in a database; means for analyzing the collected data and generating a recommendation algorithm based on the user's interests; means for presenting a list of recommended books and summaries to the user; means for providing information on where the recommended books are available and their prices; means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm; means for identifying the user's areas of interest using a machine learning algorithm; means for generating a list of books that are best suited to the user using collaborative filtering or content-based filtering technology; and means for saving the user's input information in the database in real time. This enables the server to recommend books that are best suited to the user's individual interests, specific challenges, and concerns. The accuracy of the recommendation algorithm is also improved based on the feedback.

[0888] "Reading history" is a record of information such as the title, summary, and date and time of books that a user has read in the past.

[0889] "Web browsing history" refers to the history of web pages and online materials that a user has viewed in the past.

[0890] An "input means" is a device or interface that allows users to input their reading history, internet browsing history, problems or concerns they want to solve, etc. into the system.

[0891] A "database" is a system for systematically storing collected information such as a user's reading history and internet browsing history.

[0892] A "recommendation algorithm" is a program and calculation method for recommending the most suitable books based on a user's interests and concerns.

[0893] A "machine learning algorithm" is a method for analyzing large amounts of data and finding patterns in it to make future predictions and classifications.

[0894] "Collaborative filtering" is a method of analyzing a user's interests and the behavior of other users to recommend items that are common to users with similar interests.

[0895] "Content-based filtering" is a method of recommending items with similar content based on a user's past behavior and preferences.

[0896] "Feedback" refers to the ratings and impressions that users enter after reading a recommended book.

[0897] "Real-time" means that the processing occurs immediately, without delay.

[0898] The system of the present invention analyzes a user's reading history and internet browsing history to recommend the most suitable books, providing books that match the user's interests and themes. This system is implemented by exchanging information mainly between the user, the terminal, and the server.

[0899] First, users input their reading and internet browsing history via the device, and then input information about the problems they currently want to solve and areas of interest, using prompts such as "improving business skills" or "basics of statistics."

[0900] The device then transmits the information entered by the user in real time to a server, which receives the information and stores it in a database that stores each user's reading history, internet browsing history, and input information about topics and interests.

[0901] The server analyzes the information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest. Specifically, it analyzes the content of books the user has read and web pages they have viewed to determine the user's interests.

[0902] The server then uses the analysis results to generate a list of books suitable for the user using collaborative or content-based filtering techniques, including each book's summary, author name, and availability information at libraries and online stores.

[0903] The generated recommendation list is sent from the server to the device, which then displays the list to the user in an easy-to-read format. The user can then decide which book to choose based on the list of recommended books. The list also includes a purchase link and library information, making it easy for the user to obtain the book.

[0904] After a user finishes reading a book, they can enter their feedback via their device. The feedback includes their rating and impressions of the book, such as "It was very helpful" or "I would like to read another book by this author."

[0905] The feedback information is sent from the device to the server, which stores it in a database. The server then analyzes the stored feedback data and uses it to improve the accuracy of the recommendation algorithm next time.

[0906] In this way, the system of the present invention can recommend books that are optimal for a user's individual interests, concerns, and specific problems and concerns. Furthermore, since the accuracy of the recommendation algorithm is improved based on feedback, high-quality recommendations that meet the user's needs are continuously provided.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Step 1:

[0909] Users access the device's application or web interface and input their reading history, internet browsing history, current problems they want to solve, and areas of interest. For example, they input prompts such as "improve business skills" or "basics of statistics." The input data is sent to the system as user interest information (input: user information, output: user interest information).

[0910] Step 2:

[0911] The device sends the information entered by the user to the server in real time (input: user interest information, output: server-sent data). The server receives this information, associates it with the user ID, and stores it in a database (input: server-sent data, output: database-stored data). The database stores each user's reading history, internet browsing history, and entered assignments and interest information.

[0912] Step 3:

[0913] The server analyzes the user information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest (input: data stored in the database, output: user interest trends). Specifically, it analyzes the content of books the user has read in the past and web pages they have viewed to determine the user's interests. For example, it identifies trends in specific areas such as "marketing" or "leadership."

[0914] Step 4:

[0915] Based on the analysis results, the server uses collaborative filtering or content-based filtering techniques to generate a list of books that are best suited to the user (input: user's interest trends, output: recommended book list). This list includes each book's summary, author name, and availability information at libraries and online stores. The algorithm pulls out historical data of users with similar interests and books with related content from the past.

[0916] Step 5:

[0917] The server sends the generated recommended book list to the terminal (input: recommended book list, output: terminal-sent data). The terminal displays the list to the user in an easy-to-read format (input: terminal-sent data, output: user-displayed data). The recommended list includes the book title, summary, author name, and link to where the book is available. The user can decide which book to choose based on this list.

[0918] Step 6:

[0919] After reading a recommended book, the user inputs their evaluation and thoughts about the book into the device (input: thoughts after reading, output: feedback information). For example, they can input feedback such as "It was very helpful" or "I would like to read another book by the same author."

[0920] Step 7:

[0921] The device sends the input feedback information to the server (input: feedback information, output: server-sent feedback). The server stores this feedback in a database (input: server-sent feedback, output: database feedback storage). The server then analyzes the stored feedback data again and uses it to improve the accuracy of the next recommendation algorithm (input: database feedback storage, output: accuracy improvement data).

[0922] Through these steps, the system is able to recommend the most suitable books based on the user's individual interests, concerns, and specific problems and concerns. Furthermore, the accuracy of the recommendation algorithm is improved based on feedback, allowing the system to continuously provide high-quality recommendations that meet the user's needs.

[0923] (Application example 1)

[0924] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0925] Previously, there were systems that recommended books based on a user's reading and internet browsing history, reflecting their individual preferences. However, the accuracy and diversity of the recommendations were insufficient, and they were unable to sufficiently increase user satisfaction. Furthermore, existing systems did not provide sufficient information on where to obtain the recommended books and content, nor did they provide pricing information, and lacked a mechanism to enable users to easily obtain the content.

[0926] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0927] In this invention, the server includes means for inputting a user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing it in a database, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests and concerns, means for presenting a list and summary of recommended content to the user, means for providing information on where the recommended content is available and its price, means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm, means for improving the recommendation algorithm based on the feedback, and means for making recommendations optimized to the user's interests and needs through prompt sentences using a generative AI model. This enables highly accurate content recommendations tailored to the user's needs and the provision of information on where and how to obtain the content.

[0928] "User reading history" is information about books and documents that a user has read in the past.

[0929] "Web browsing history" is information about the web pages and content a user has viewed on the Internet.

[0930] An "input means" is a device or interface through which a user provides information to a system, either manually or automatically.

[0931] "Means of collection" refers to the devices and methods used to properly acquire information entered by users and store it in a database.

[0932] A "database storage means" is a system or device that organizes collected information and stores it in a form that can be reused later.

[0933] "Analytical means" refers to the algorithms and programs used to process collected data and identify user interests.

[0934] A "recommendation algorithm" is a mathematical or programmatic method for selecting the most appropriate content based on a user's past behavioral data.

[0935] A "means for presenting lists and summaries" is an interface for displaying the recommendation results to the user in visual or text form.

[0936] "Means for providing" refers to a system or device that informs users where the recommended content is available and its price information.

[0937] "Means for collecting feedback" refers to devices or programs that obtain opinions and evaluations about the content used by users and reflect them in the system.

[0938] "Means for analyzing and storing feedback data" refers to a system or device that stores the feedback collected from users in a database and uses it to improve the recommendation algorithm for the next time.

[0939] "Means for improving recommendation algorithms" refers to techniques and methods for updating existing recommendation algorithms based on new feedback information and improving their accuracy.

[0940] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms for a specific task.

[0941] A "prompt sentence" is an input sentence given to a generative AI model, and is text data that serves as a trigger to obtain appropriate output from the model.

[0942] In order to put this invention into practice, it is necessary to build a system that analyzes a user's reading history and internet browsing history and recommends optimal content. Here, we will explain the various programs that make up this system and their processing.

[0943] 1. Collecting and entering user information

[0944] The device (e.g., a smartphone) provides an interface for users to input their reading history and internet browsing history. This information is collected by manual input or by syncing the browser history. The device then transmits this data to a cloud server. This transmission is secured using the HTTPS protocol.

[0945] 2. Data storage

[0946] The cloud server stores the received data in a database, where users' reading and browsing histories are accumulated and later used for analysis. This storage process is handled by a database management system such as MySQL or PostgreSQL.

[0947] 3. Data Analysis

[0948] The cloud server analyzes the information stored in the database and generates algorithms to identify user interests. This process uses data analysis tools such as Python and R and applies machine learning algorithms (e.g., collaborative filtering).

[0949] 4. Generating a recommendation list

[0950] The cloud server creates a list of content that is best suited to the user based on the analysis results. The recommendation list also includes a summary of each piece of content and available information (e.g., purchase links and stock information). This allows users to easily access the recommended content.

[0951] 5. Presentation of recommendation results

[0952] The device receives a list of recommendations from the cloud server and presents them to the user. The screen interface uses web technologies such as HTML and CSS to display information in a visually easy-to-understand format.

[0953] 6. Gathering Feedback

[0954] After using the recommended content, users can enter their ratings and feedback via their devices, which is then sent back to the cloud server and stored in a database.

[0955] 7. Algorithm Improvements

[0956] The cloud server analyzes the collected feedback data and improves the recommendation algorithm, which improves the accuracy of recommendations from the next time onwards and increases user satisfaction.

[0957] 8. Generative AI Model and Prompts

[0958] The system uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are inputs given to an artificial intelligence model trained using machine learning algorithms for a specific task, and are text data that triggers the model to produce an appropriate output.

[0959] As a concrete example, the following is an example of an input prompt for a generative AI model:

[0960] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[0961] Reading history: Leadership, Marketing

[0962] Browsing History: Digital Transformation

[0963] In this way, it is possible to recommend highly accurate content that meets the user's needs, and to provide information on where to obtain that content and its price, allowing users to select content that will give them greater satisfaction.

[0964] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0965] Step 1:

[0966] The device provides an interface for users to input their reading history and internet browsing history. Users can manually input information about books they have read and web pages they have visited, or synchronize their browser history. This data is input into the device. The input data is the user's past reading materials and internet browsing records.

[0967] Step 2:

[0968] The device sends the user's reading and browsing history to the cloud server, using the HTTPS protocol to ensure data security. The output data is the user's reading and browsing history.

[0969] Step 3:

[0970] The server stores the received data in a database. The database management system used (e.g., MySQL or PostgreSQL) structures and stores the user's reading and browsing history. The input data is the user's history data, and the output is stored in the database.

[0971] Step 4:

[0972] The server analyzes the information stored in the database. In this process, it applies machine learning algorithms (e.g., collaborative filtering) using Python or R languages ​​to identify the user's interests. The input is the stored user history data, and the output is the analysis results based on the user's interests.

[0973] Step 5:

[0974] The server generates a list of optimal content based on the user's interests. This list includes a summary of each piece of content and acquisition information (purchase link and stock information). This allows the user to easily access the recommended content. The input is the analysis results, and the output is a list of several recommended contents.

[0975] Step 6:

[0976] The device presents the recommendation list received from the server to the user. The screen interface is constructed using HTML and CSS, and information is displayed in a visually easy-to-understand format. The input is the recommendation list data, and the output is the visual recommendation list presented to the user.

[0977] Step 7:

[0978] The user uses the recommended content and enters their rating and feedback through their device. This feedback is then sent back to the cloud server. The input is the user's feedback data, and the output is the sent feedback information.

[0979] Step 8:

[0980] The server analyzes the collected feedback data and improves the recommendation algorithm. It uses the new feedback information to update the existing recommendation algorithm and improve its accuracy, which will result in more accurate recommendations in the future. The input is the feedback data and the output is the improved recommendation algorithm.

[0981] Step 9:

[0982] The server uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are given to the generative AI model and act as triggers to obtain appropriate output. The input is the user's history data and feedback data, and the output is a highly accurate content recommendation prompt.

[0983] As a concrete example, the following is an example of an input prompt for a generative AI model:

[0984] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[0985] Reading history: Leadership, Marketing

[0986] Browsing History: Digital Transformation

[0987] In this way, by combining each step, a highly accurate content recommendation system that meets the user's needs is realized.

[0988] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0989] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotions to provide more personalized recommendations for the user. This system consists of four main components: the user, the device, the server, and the emotion engine.

[0990] 1. Enter your user information

[0991] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. Emotional information obtained through the user's input and actions is also recorded by the emotion engine.

[0992] 2. Information Collection and Storage

[0993] The device converts the input data into an appropriate format and sends it to the server, which stores the received information in a database, including the user's emotional state.

[0994] 3. Data Analysis

[0995] The server analyzes the saved reading history, browsing history, problems to be solved, and emotional information. The emotion engine analyzes the content entered by the user and the emotions expressed while browsing, and records them in a database. The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[0996] 4. Generating Recommendations

[0997] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[0998] 5. Presentation of recommendation results

[0999] The server sends a list of recommended books, along with summaries, pricing information, and inventory information from libraries and online stores, to the device, which then presents this information visually to the user.

[1000] 6. Gathering Feedback

[1001] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[1002] 7. Processing and storing feedback

[1003] The device sends the feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[1004] Specific examples

[1005] A specific usage scenario using the system of the present invention is shown below.

[1006] Scenario 1: Busy businessman

[1007] The user is looking for a book to help them improve their work efficiency, but is currently feeling stressed.

[1008] Users input tasks such as "How to improve work efficiency" via the device, as well as business-related books they have read in the past. The emotion engine then detects their current stress level.

[1009] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[1010] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[1011] After purchasing and reading "Stress Management," a user enters feedback saying, "I found it very relaxing."

[1012] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[1013] Scenario 2: A student studying for a test

[1014] A student user is looking for books related to a particular subject, but is currently experiencing low motivation.

[1015] A user inputs a topic such as "Basics of Statistics" via a terminal, and the emotion engine detects when the user's motivation is declining.

[1016] The server also analyzes information from academic books that have been read in the past and educational sites that have been visited, and recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Study Methods to Motivate You."

[1017] The device will present this list of recommendations along with library holdings information and online purchase links.

[1018] After reading "Study Methods to Motivate You," the user enters feedback such as "It was very encouraging."

[1019] The server and emotion engine receive this feedback information to help adjust the recommendation algorithm next time.

[1020] This allows users to receive recommendations for books that best fit their current emotional state, enhancing their reading experience, and feedback allows the system to continually evolve and improve its recommendations.

[1021] The processing flow will be explained below.

[1022] Step 1:

[1023] Users access the device's interface and input their reading history, internet browsing history, problems they want to solve, and areas of interest, such as "how to improve work efficiency" or "books on leadership."

[1024] Step 2:

[1025] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency and makes it easier for the server to parse.

[1026] Step 3:

[1027] The server receives the user data sent from the device and stores it in a database, including the user's emotional state.

[1028] Step 4:

[1029] The emotion engine analyzes user input and behavior (e.g., reading history, time spent on web pages, etc.) to identify the user's emotional state. For example, it can detect that the user's current stress level is high based on their writing and selections.

[1030] Step 5:

[1031] The server uses the stored data and the analysis results of the emotion engine to generate a recommendation algorithm based on the user's interests, which also takes into account the user's current emotional state.

[1032] Step 6:

[1033] The server then uses the generated recommendation algorithm to create a list of books that are best suited to the user. For example, it might recommend books that have a relaxing effect to a user who is feeling stressed, or books about efficiency to a user who wants to improve their work efficiency.

[1034] Step 7:

[1035] The server uses library collection information and online store APIs to collect book availability and price information, which is then added to the recommendation list.

[1036] Step 8:

[1037] The server sends a recommendation list including detailed information to the terminal.

[1038] Step 9:

[1039] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[1040] Step 10:

[1041] After reading the recommended book, users can input feedback via their device, including their emotional state after reading.

[1042] Step 11:

[1043] The terminal converts the feedback data into an appropriate format and sends it to the server, which ensures data consistency.

[1044] Step 12:

[1045] The server receives the feedback data sent from the terminal and stores it in a database.

[1046] Step 13:

[1047] Based on the stored feedback data and the analysis results of the emotion engine, the server makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[1048] This allows the system to continuously improve and provide users with more accurate recommendations, specifically those that reflect the user's emotional state in real time, resulting in a more personalized reading experience.

[1049] Example 2

[1050] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1051] Recommendation systems that take into account a user's reading and internet browsing history are required to realize more personalized recommendations that reflect the user's current emotional state, rather than simply being based on past history. In particular, accurate recommendations that meet the specific needs of busy business people or students are heavily influenced by daily fluctuations in stress and motivation, so incorporating emotional information is important.

[1052] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1053] In this invention, the server includes means for collecting a user's reading history and internet browsing history and storing them in an information storage device, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, and means for recognizing and analyzing the user's emotional information to evaluate the user's current emotional state. This enables the server to recommend books that take into account the user's reading history and internet browsing history, as well as the user's current stress and motivation levels. This provides the user with an optimal reading experience, and by utilizing this feedback in subsequent recommendations, the accuracy of recommendations can be continuously improved.

[1054] "Reading history" is information about books a user has read in the past.

[1055] "Internet browsing history" is information about web pages and content that a user has viewed on the Internet in the past.

[1056] An "information storage device" is a device that stores and manages data collected by the server from users.

[1057] "Emotional information" is information about the emotional state a user expresses through their input and actions.

[1058] A "recommendation algorithm" is a set of calculation procedures and rules for recommending books and content suitable for a user based on collected user data.

[1059] An "emotion engine" is a system that analyzes a user's emotional state and reflects that data in the recommendation algorithm.

[1060] "Feedback" refers to information about ratings and impressions provided by users after using recommended books or content.

[1061] The "database" is a data storage system for centrally managing collected user reading history, internet browsing history, emotional information, etc.

[1062] "User" refers to an individual who uses this system to receive recommendations for books and content.

[1063] A "terminal" is an electronic device that a user uses to interface with the system.

[1064] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotional information to achieve more personalized recommendations for the user. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[1065] Entering user information

[1066] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. In addition, emotional information is also recorded through the emotion engine, which analyzes the user's input and actions.

[1067] Information Collection and Storage

[1068] The terminal converts the input data into an appropriate format (such as JSON format) and sends it to the server.

[1069] The server stores the received information in a database, including the user's emotional state.

[1070] Analyzing the data

[1071] The server analyzes saved reading history, internet browsing history, problems to be solved, and emotional information.

[1072] The emotion engine analyzes the content users enter and the emotions they express while browsing, and records them in a database.

[1073] The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[1074] Generating Recommendations

[1075] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[1076] Presentation of recommendation results

[1077] The server sends the device a list of recommended books, as well as summaries, pricing information, and inventory information from libraries and online stores.

[1078] The device visually presents this information to the user.

[1079] Collecting feedback

[1080] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[1081] Processing and storing feedback

[1082] The terminal transmits the feedback data to the server.

[1083] The server stores the received feedback information in a database and uses it to improve the recommendation algorithm in future.

[1084] The emotion engine reassess the user's emotional state from the feedback information and updates the recommendation algorithm based on this.

[1085] Specific examples

[1086] Scenario 1: Busy businessman

[1087] The user types "ways to improve work efficiency" into the device and also enters the business-related books they have read in the past.

[1088] The emotion engine detects the current stress state.

[1089] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[1090] The device will present the user with a list of recommended books, summaries, and a link to purchase from the online store.

[1091] After a user purchases and reads "Stress Management," they enter feedback saying, "I found it very relaxing."

[1092] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[1093] Prompt Sentence Examples

[1094] "I want to know how to improve my work efficiency. I've read books like 'The 7 Habits' and 'Essential Thinking' in the past. I've been feeling stressed lately."

[1095] "I want to learn the basics of statistics. The only book I've read on the subject is 'Introduction to Statistics.' I'm currently feeling unmotivated."

[1096] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1097] Step 1: Enter your user information

[1098] Users use the device to input their reading history, internet browsing history, problems they want to solve, and areas of interest. The device converts the user's input into an appropriate data format, such as JSON. The emotion engine also analyzes the user's input and behavior and records the emotional information as an emotional status. The input data are raw text, qualitative comments, and rating scores. The output is formatted user information and emotional status.

[1099] Examples:

[1100] The user types in "How to improve work efficiency" and adds "essential thoughts" they have read in the past. The emotion engine detects stress from the user's input.

[1101] Step 2: Collecting and storing information

[1102] The device will format the data entered by the user, convert it into the appropriate data format, and then send it to the server. The server will store the received data in a database. This storage process includes the user's reading history, internet browsing history, and emotional information.

[1103] Input: Data entered by the user (reading history, internet browsing history, emotional information)

[1104] Output: Formatted data sent to the server

[1105] Examples:

[1106] The device sends the following data to the server:

[1107] json

[1108] {

[1109] "Reading history": ["Essential Thinking"],

[1110] "Web browsing history": ["How to improve work efficiency"],

[1111] "Emotional state": "Stress"

[1112] }

[1113] Step 3: Analyze the data

[1114] The server extracts stored user data and analyzes it based on reading history, internet browsing history, and emotional information. This analysis uses natural language processing algorithms and generative AI models to identify user interests and evaluate emotional information. The analysis results are then combined with the analysis data from the emotional engine to form a user profile.

[1115] Input: User data extracted from the database (reading history, internet browsing history, emotional information)

[1116] Output: User interest profile and emotional state

[1117] Examples:

[1118] The server analyzes the following information to create a profile of the user's attributes and emotional state:

[1119] Reading History: Essential Thinking

[1120] Web browsing history: How to improve your work efficiency

[1121] Emotional state: Stress

[1122] Step 4: Generate recommendations

[1123] The server then applies a recommendation algorithm based on the analysis results to generate a list of books that are best suited to the user, taking into account emotional information from the emotion engine. The algorithm reflects the user's current emotional state and selects books that fit that sentiment.

[1124] Input: User profile data (interests, concerns, emotional state)

[1125] Output: Recommended book list

[1126] Examples:

[1127] The server recommends the following book:

[1128] Essential Thinking

[1129] Mental Model

[1130] Stress management

[1131] Step 5: Presenting the Recommendations

[1132] The server sends the generated recommended book list, summaries, price information, and inventory information from libraries and online stores to the terminal, which visually displays this information to the user.

[1133] Input: Recommendation results provided by the server

[1134] Output: The list of recommendations and details displayed to the user

[1135] Examples:

[1136] The terminal will display the following list:

[1137] Essential Thinking (price, summary)

[1138] Mental model (price, summary)

[1139] Stress Management (Price, Summary)

[1140] Step 6: Gather feedback

[1141] After reading the recommended book, the user inputs feedback via the terminal, including their emotional state and specific impressions after reading. The terminal then sends the feedback data to the database.

[1142] Input: User feedback (emotional state, thoughts)

[1143] Output: Feedback data sent to the server

[1144] Examples:

[1145] A user finishes reading "Stress Management" and gives feedback that it was "very relaxing."

[1146] Step 7: Processing and storing feedback

[1147] The device sends the collected feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm.

[1148] Input: Feedback data

[1149] Output: Updated recommendation algorithm

[1150] Examples:

[1151] Your feedback information will be saved and used for future recommendations as follows:

[1152] json

[1153] {

[1154] "Books I've read": "Stress Management",

[1155] "Emotional state": "Very relaxed"

[1156] }

[1157] (Application example 2)

[1158] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1159] Conventional recommendation systems are based on a user's reading history and internet browsing history, and do not take into account the user's specific emotional state. This makes it difficult to recommend optimal books that vary depending on the user's current emotions, such as stress or lack of motivation. Furthermore, they lack the ability to effectively utilize user feedback to improve the accuracy of next recommendations. This has led to issues such as a decrease in user satisfaction and difficulty in promoting long-term use.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing them in a database, and means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, concerns, and emotional state. This enables personalized recommendations that take the user's emotional state into consideration.

[1161] A "user" is an entity that uses this system and performs activities such as reading or browsing the Internet.

[1162] "Reading history" is a record of books a user has read in the past, including their content and impressions.

[1163] "Web browsing history" is a record of the web pages a user has accessed and articles they have read on the Internet.

[1164] "Emotional state" refers to the emotional state a user is feeling at a particular point in time, and can include stress, joy, motivation, etc.

[1165] A "recommendation algorithm" is a computational method for analyzing collected data and selecting the most suitable book for a user.

[1166] The "database" is a system that stores and centrally manages collected user information, emotional state, and feedback data.

[1167] A "recommended list" is a list of books presented to users based on analyzed data, including summaries and pricing information.

[1168] "Feedback" refers to the impressions and evaluations that users enter after reading a recommended book, and includes information about their emotional state.

[1169] "Server" means the central system that processes, stores and analyzes data received from Users.

[1170] "Data collection means" refers to interfaces or software used to collect information such as users' reading history and internet browsing history.

[1171] An "emotion engine" is a computer program that analyzes a user's emotional state and generates data based on that.

[1172] "Online store information" refers to inventory and price information on online book sales sites.

[1173] "Library information" refers to the stock status and lending information of books at libraries, etc.

[1174] "Terminal" refers to the device through which a user enters data and receives recommended book information, including smartphones and tablets.

[1175] The present invention is a book recommendation system that takes into account the emotional state of a user, and its main components are a user terminal, a server, and an emotion engine. This system is implemented using a user terminal such as a smartphone or tablet.

[1176] The user device is equipped with a means for collecting the user's reading history and internet browsing history and storing them in a database. Furthermore, the user device is equipped with an interface for inputting the user's current issues and concerns, and an interface for inputting feedback after reading. This allows the user to provide the system with their interests and emotional state.

[1177] The server analyzes data collected from the user's device and generates a recommendation algorithm based on the user's interests, concerns, and emotional state. An emotion analysis engine using libraries such as TextBlob determines the user's emotional state from the text they input. The analysis results are stored in a database and used to generate the recommendation algorithm.

[1178] Based on the generated recommendation algorithm, the server generates a list of books that are most suitable for the user. This list takes into account the user's emotional state, for example, recommending relaxing books to a user who is feeling stressed. The device then presents this recommendation list to the user, along with summaries, price information, and online store inventory information.

[1179] After the user finishes reading a recommended book, the device collects feedback from the user and sends it to the server. The server stores this feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future installments. The emotion engine reassess the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[1180] As a concrete example, User A is looking for books aimed at relieving work stress. Using this system, he searches for "stress management" and inputs his past reading history, and the sentiment analysis engine detects "stressed state." Based on this, the server recommends "books on mindfulness" as "books with a relaxing effect" and presents the list to the user.

[1181] An example prompt is, "I've been busy and stressed lately, so I'm looking for a book that will calm me down."

[1182] This system enables more personalized book recommendations that take into account the user's emotional state, thereby increasing user satisfaction.

[1183] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1184] Step 1:

[1185] The user uses the device to input text related to their reading history, internet browsing history, and their current emotional state. This input includes not only their reading history and internet browsing history, but also sentences that indicate their emotional state (e.g., "I've been feeling stressed lately.") This allows the user's areas of interest and current emotional state to be collected as initial data.

[1186] Step 2:

[1187] The device converts the collected data into an appropriate format and sends it to the server, using, for example, JSON format. The data includes the user's reading history, internet browsing history, and input emotional state text. The server receives this data and stores it in an initial database.

[1188] Step 3:

[1189] The server uses libraries such as TextBlob to analyze the input emotional state text. The emotion analysis engine performs the analysis and outputs the user's emotional state (e.g., positive, negative, neutral) as numerical data. This numerical emotional state data is also stored in the database.

[1190] Step 4:

[1191] The server generates a recommendation algorithm based on the collected reading history, internet browsing history, and emotional state data. A recommendation algorithm is a computational method for selecting the most suitable books for a user based on past data analysis. This algorithm generation process may use machine learning models (e.g., generative AI models).

[1192] Step 5:

[1193] The server then generates a list of books that best fit the user's emotional state based on the recommendation algorithm. Taking into account the analysis results of the emotion engine, the server lists books that have a "stress-relieving" or "relaxing" effect, for example. These recommended book lists also include summaries of each book, pricing information, and inventory information for online stores and libraries.

[1194] Step 6:

[1195] The server sends the generated recommended book list to the terminal, which visually presents the list to the user. The user can browse the recommended list and select books that interest them, allowing the user to easily find the books they currently need most.

[1196] Step 7:

[1197] After reading, users can use their devices to input feedback, including their emotional state after reading and their rating of the book. The feedback data provides users with an opportunity to specifically input their rating for the recommendation system.

[1198] Step 8:

[1199] The device sends the feedback data to the server. The server stores the received feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future. The emotion engine reanalyzes the feedback information, evaluates changes in the user's emotional state, and updates the recommendation algorithm based on this. This allows the system to continuously learn and make even more accurate recommendations.

[1200] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1201] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1202] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1203] [Fourth embodiment]

[1204] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1205] 7, a 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.

[1206] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1207] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1208] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1209] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1210] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1211] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1212] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1213] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1214] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1215] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1216] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1217] The system of the present invention analyzes a user's reading history and internet browsing history and recommends the most suitable books, effectively providing books that match the user's interests and challenges. This system mainly exchanges information between the user, the terminal, and the server, and is implemented in the following procedure.

[1218] 1. Enter your user information

[1219] Users can input their reading history, internet browsing history, current issues or concerns they want to resolve, etc. For example, if they want to learn a specific business skill, they can input that information.

[1220] 2. Information Collection and Storage

[1221] The terminal sends the input information to the server, which stores the received information in a database, thereby accumulating user history data.

[1222] 3. Data Analysis

[1223] The server analyzes the information stored in the database and generates algorithms that identify users' interests, such as the business books they have read or the web pages they have visited.

[1224] 4. Generating Recommendations

[1225] The server uses the generated algorithm to create a list of books suitable for the user, including a summary of each book, and also queries inventory information from libraries and online stores to provide information on where the book is available.

[1226] 5. Presentation of recommendation results

[1227] The server sends the recommendation list to the device, which displays the list to the user in an easy-to-understand format, allowing the user to easily decide which book to choose.

[1228] 6. Gathering Feedback

[1229] After reading a recommended book, users can enter feedback via their device, such as "It was very helpful" or "I would like to read another book by this author."

[1230] 7. Processing and storing feedback

[1231] The device sends the feedback information to the server, which then stores it in the database and uses it to improve the accuracy of the recommendation algorithm next time.

[1232] Specific examples

[1233] A specific usage scenario using the system of the present invention is shown below.

[1234] Scenario 1: Businessman's Case

[1235] Let's say a user is looking for a book to improve their business skills.

[1236] Through the terminal, users input tasks such as "improving business skills" and also enter a history of related books they have read in the past, such as "leadership" and "marketing."

[1237] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Marketing Fundamentals."

[1238] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[1239] After purchasing and reading "Essential Thinking," users enter feedback such as "It was very helpful."

[1240] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm next time.

[1241] Scenario 2: Student Case

[1242] Let's say a user is a student looking for books related to a particular course.

[1243] Assignments such as "Fundamentals of Statistics" are entered via the terminal.

[1244] The server also analyzes information about mathematics-related books that students have read in the past and educational websites that they have visited.

[1245] The server recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Introduction to Statistical Thinking" and presents them to users.

[1246] The device will present this list of recommendations along with links to check the library's holdings and purchase the book online.

[1247] The user finishes reading "Introduction to Statistics" and enters feedback such as "The content was easy to understand."

[1248] The server receives this feedback and uses it to improve its recommendation algorithm for future visits.

[1249] This allows users to find the books that best suit their interests and challenges, enriching their reading experience, and feedback allows the system to continually evolve and provide even more accurate recommendations.

[1250] The processing flow will be explained below.

[1251] Step 1:

[1252] Users access the device's interface and enter their reading history, internet browsing history, problems they want to solve, and areas of interest.

[1253] Step 2:

[1254] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency.

[1255] Step 3:

[1256] The server receives the user data sent from the device and stores it in a database, which includes inserting it into the database using SQL queries.

[1257] Step 4:

[1258] The server analyzes the stored data periodically or as needed to generate a recommendation algorithm based on the user's interests, which involves applying machine learning models based on similar past data.

[1259] Step 5:

[1260] The server uses the generated recommendation algorithm to create a list of books that are most suitable for the user, along with associated summaries that are also generated and included in the list.

[1261] Step 6:

[1262] The server uses APIs from libraries and online stores to gather book availability and price information, which is then added to the recommendation list.

[1263] Step 7:

[1264] The server sends a recommendation list including detailed information to the terminal.

[1265] Step 8:

[1266] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[1267] Step 9:

[1268] After reading a recommended book, users can enter their feedback on the device, including their rating and impressions of the book.

[1269] Step 10:

[1270] The terminal converts the feedback data into an appropriate format and sends it to the server.

[1271] Step 11:

[1272] The server receives the feedback data sent from the terminal and stores it in a database.

[1273] Step 12:

[1274] The server analyzes the stored feedback data and makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[1275] This allows the system to continually improve and provide even more accurate recommendations to users.

[1276] Example 1

[1277] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1278] Current book recommendation systems struggle to recommend appropriate books that fully take into account a user's individual interests, past reading history, and internet browsing history. Furthermore, recommendations do not address the specific challenges or concerns of users, limiting the reading experience. Furthermore, improvements to the accuracy of recommendation algorithms using feedback information are insufficient.

[1279] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1280] In this invention, the server includes: means for inputting a user's reading history and internet browsing history; means for collecting the user's reading history and internet browsing history and storing it in a database; means for analyzing the collected data and generating a recommendation algorithm based on the user's interests; means for presenting a list of recommended books and summaries to the user; means for providing information on where the recommended books are available and their prices; means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm; means for identifying the user's areas of interest using a machine learning algorithm; means for generating a list of books that are best suited to the user using collaborative filtering or content-based filtering technology; and means for saving the user's input information in the database in real time. This enables the server to recommend books that are best suited to the user's individual interests, specific challenges, and concerns. The accuracy of the recommendation algorithm is also improved based on the feedback.

[1281] "Reading history" is a record of information such as the title, summary, and date and time of books that a user has read in the past.

[1282] "Web browsing history" refers to the history of web pages and online materials that a user has viewed in the past.

[1283] An "input means" is a device or interface that allows users to input their reading history, internet browsing history, problems or concerns they want to solve, etc. into the system.

[1284] A "database" is a system for systematically storing collected information such as a user's reading history and internet browsing history.

[1285] A "recommendation algorithm" is a program and calculation method for recommending the most suitable books based on a user's interests and concerns.

[1286] A "machine learning algorithm" is a method for analyzing large amounts of data and finding patterns in it to make future predictions and classifications.

[1287] "Collaborative filtering" is a method of analyzing a user's interests and the behavior of other users to recommend items that are common to users with similar interests.

[1288] "Content-based filtering" is a method of recommending items with similar content based on a user's past behavior and preferences.

[1289] "Feedback" refers to the ratings and impressions that users enter after reading a recommended book.

[1290] "Real-time" means that the processing occurs immediately, without delay.

[1291] The system of the present invention analyzes a user's reading history and internet browsing history to recommend the most suitable books, providing books that match the user's interests and themes. This system is implemented by exchanging information mainly between the user, the terminal, and the server.

[1292] First, users input their reading and internet browsing history via the device, and then input information about the problems they currently want to solve and areas of interest, using prompts such as "improving business skills" or "basics of statistics."

[1293] The device then transmits the information entered by the user in real time to a server, which receives the information and stores it in a database that stores each user's reading history, internet browsing history, and input information about topics and interests.

[1294] The server analyzes the information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest. Specifically, it analyzes the content of books the user has read and web pages they have viewed to determine the user's interests.

[1295] The server then uses the analysis results to generate a list of books suitable for the user using collaborative or content-based filtering techniques, including each book's summary, author name, and availability information at libraries and online stores.

[1296] The generated recommendation list is sent from the server to the device, which then displays the list to the user in an easy-to-read format. The user can then decide which book to choose based on the list of recommended books. The list also includes a purchase link and library information, making it easy for the user to obtain the book.

[1297] After a user finishes reading a book, they can enter their feedback via their device. The feedback includes their rating and impressions of the book, such as "It was very helpful" or "I would like to read another book by this author."

[1298] The feedback information is sent from the device to the server, which stores it in a database. The server then analyzes the stored feedback data and uses it to improve the accuracy of the recommendation algorithm next time.

[1299] In this way, the system of the present invention can recommend books that are optimal for a user's individual interests, concerns, and specific problems and concerns. Furthermore, since the accuracy of the recommendation algorithm is improved based on feedback, high-quality recommendations that meet the user's needs are continuously provided.

[1300] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1301] Step 1:

[1302] Users access the device's application or web interface and input their reading history, internet browsing history, current problems they want to solve, and areas of interest. For example, they input prompts such as "improve business skills" or "basics of statistics." The input data is sent to the system as user interest information (input: user information, output: user interest information).

[1303] Step 2:

[1304] The device sends the information entered by the user to the server in real time (input: user interest information, output: server-sent data). The server receives this information, associates it with the user ID, and stores it in a database (input: server-sent data, output: database-stored data). The database stores each user's reading history, internet browsing history, and entered assignments and interest information.

[1305] Step 3:

[1306] The server analyzes the user information stored in the database. This analysis uses machine learning algorithms (e.g., Python's Scikit-learn or TensorFlow) to identify the user's areas of interest (input: data stored in the database, output: user interest trends). Specifically, it analyzes the content of books the user has read in the past and web pages they have viewed to determine the user's interests. For example, it identifies trends in specific areas such as "marketing" or "leadership."

[1307] Step 4:

[1308] Based on the analysis results, the server uses collaborative filtering or content-based filtering techniques to generate a list of books that are best suited to the user (input: user's interest trends, output: recommended book list). This list includes each book's summary, author name, and availability information at libraries and online stores. The algorithm pulls out historical data of users with similar interests and books with related content from the past.

[1309] Step 5:

[1310] The server sends the generated recommended book list to the terminal (input: recommended book list, output: terminal-sent data). The terminal displays the list to the user in an easy-to-read format (input: terminal-sent data, output: user-displayed data). The recommended list includes the book title, summary, author name, and link to where the book is available. The user can decide which book to choose based on this list.

[1311] Step 6:

[1312] After reading a recommended book, the user inputs their evaluation and thoughts about the book into the device (input: thoughts after reading, output: feedback information). For example, they can input feedback such as "It was very helpful" or "I would like to read another book by the same author."

[1313] Step 7:

[1314] The device sends the input feedback information to the server (input: feedback information, output: server-sent feedback). The server stores this feedback in a database (input: server-sent feedback, output: database feedback storage). The server then analyzes the stored feedback data again and uses it to improve the accuracy of the next recommendation algorithm (input: database feedback storage, output: accuracy improvement data).

[1315] Through these steps, the system is able to recommend the most suitable books based on the user's individual interests, concerns, and specific problems and concerns. Furthermore, the accuracy of the recommendation algorithm is improved based on feedback, allowing the system to continuously provide high-quality recommendations that meet the user's needs.

[1316] (Application example 1)

[1317] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1318] Previously, there were systems that recommended books based on a user's reading and internet browsing history, reflecting their individual preferences. However, the accuracy and diversity of the recommendations were insufficient, and they were unable to sufficiently increase user satisfaction. Furthermore, existing systems did not provide sufficient information on where to obtain the recommended books and content, nor did they provide pricing information, and lacked a mechanism to enable users to easily obtain the content.

[1319] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1320] In this invention, the server includes means for inputting a user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing it in a database, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests and concerns, means for presenting a list and summary of recommended content to the user, means for providing information on where the recommended content is available and its price, means for collecting feedback after reading and analyzing and storing the feedback data to improve the accuracy of the recommendation algorithm, means for improving the recommendation algorithm based on the feedback, and means for making recommendations optimized to the user's interests and needs through prompt sentences using a generative AI model. This enables highly accurate content recommendations tailored to the user's needs and the provision of information on where and how to obtain the content.

[1321] "User reading history" is information about books and documents that a user has read in the past.

[1322] "Web browsing history" is information about the web pages and content a user has viewed on the Internet.

[1323] An "input means" is a device or interface through which a user provides information to a system, either manually or automatically.

[1324] "Means of collection" refers to the devices and methods used to properly acquire information entered by users and store it in a database.

[1325] A "database storage means" is a system or device that organizes collected information and stores it in a form that can be reused later.

[1326] "Analytical means" refers to the algorithms and programs used to process collected data and identify user interests.

[1327] A "recommendation algorithm" is a mathematical or programmatic method for selecting the most appropriate content based on a user's past behavioral data.

[1328] A "means for presenting lists and summaries" is an interface for displaying the recommendation results to the user in visual or text form.

[1329] "Means for providing" refers to a system or device that informs users where the recommended content is available and its price information.

[1330] "Means for collecting feedback" refers to devices or programs that obtain opinions and evaluations about the content used by users and reflect them in the system.

[1331] "Means for analyzing and storing feedback data" refers to a system or device that stores the feedback collected from users in a database and uses it to improve the recommendation algorithm for the next time.

[1332] "Means for improving recommendation algorithms" refers to techniques and methods for updating existing recommendation algorithms based on new feedback information and improving their accuracy.

[1333] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms for a specific task.

[1334] A "prompt sentence" is an input sentence given to a generative AI model, and is text data that serves as a trigger to obtain appropriate output from the model.

[1335] In order to put this invention into practice, it is necessary to build a system that analyzes a user's reading history and internet browsing history and recommends optimal content. Here, we will explain the various programs that make up this system and their processing.

[1336] 1. Collecting and entering user information

[1337] The device (e.g., a smartphone) provides an interface for users to input their reading history and internet browsing history. This information is collected by manual input or by syncing the browser history. The device then transmits this data to a cloud server. This transmission is secured using the HTTPS protocol.

[1338] 2. Data storage

[1339] The cloud server stores the received data in a database, where users' reading and browsing histories are accumulated and later used for analysis. This storage process is handled by a database management system such as MySQL or PostgreSQL.

[1340] 3. Data Analysis

[1341] The cloud server analyzes the information stored in the database and generates algorithms to identify user interests. This process uses data analysis tools such as Python and R and applies machine learning algorithms (e.g., collaborative filtering).

[1342] 4. Generating a recommendation list

[1343] The cloud server creates a list of content that is best suited to the user based on the analysis results. The recommendation list also includes a summary of each piece of content and available information (e.g., purchase links and stock information). This allows users to easily access the recommended content.

[1344] 5. Presentation of recommendation results

[1345] The device receives a list of recommendations from the cloud server and presents them to the user. The screen interface uses web technologies such as HTML and CSS to display information in a visually easy-to-understand format.

[1346] 6. Gathering Feedback

[1347] After using the recommended content, users can enter their ratings and feedback via their devices, which is then sent back to the cloud server and stored in a database.

[1348] 7. Algorithm Improvements

[1349] The cloud server analyzes the collected feedback data and improves the recommendation algorithm, which improves the accuracy of recommendations from the next time onwards and increases user satisfaction.

[1350] 8. Generative AI Model and Prompts

[1351] The system uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are inputs given to an artificial intelligence model trained using machine learning algorithms for a specific task, and are text data that triggers the model to produce an appropriate output.

[1352] As a concrete example, the following is an example of an input prompt for a generative AI model:

[1353] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[1354] Reading history: Leadership, Marketing

[1355] Browsing History: Digital Transformation

[1356] In this way, it is possible to recommend highly accurate content that meets the user's needs, and to provide information on where to obtain that content and its price, allowing users to select content that will give them greater satisfaction.

[1357] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1358] Step 1:

[1359] The device provides an interface for users to input their reading history and internet browsing history. Users can manually input information about books they have read and web pages they have visited, or synchronize their browser history. This data is input into the device. The input data is the user's past reading materials and internet browsing records.

[1360] Step 2:

[1361] The device sends the user's reading and browsing history to the cloud server, using the HTTPS protocol to ensure data security. The output data is the user's reading and browsing history.

[1362] Step 3:

[1363] The server stores the received data in a database. The database management system used (e.g., MySQL or PostgreSQL) structures and stores the user's reading and browsing history. The input data is the user's history data, and the output is stored in the database.

[1364] Step 4:

[1365] The server analyzes the information stored in the database. In this process, it applies machine learning algorithms (e.g., collaborative filtering) using Python or R languages ​​to identify the user's interests. The input is the stored user history data, and the output is the analysis results based on the user's interests.

[1366] Step 5:

[1367] The server generates a list of optimal content based on the user's interests. This list includes a summary of each piece of content and acquisition information (purchase link and stock information). This allows the user to easily access the recommended content. The input is the analysis results, and the output is a list of several recommended contents.

[1368] Step 6:

[1369] The device presents the recommendation list received from the server to the user. The screen interface is constructed using HTML and CSS, and information is displayed in a visually easy-to-understand format. The input is the recommendation list data, and the output is the visual recommendation list presented to the user.

[1370] Step 7:

[1371] The user uses the recommended content and enters their rating and feedback through their device. This feedback is then sent back to the cloud server. The input is the user's feedback data, and the output is the sent feedback information.

[1372] Step 8:

[1373] The server analyzes the collected feedback data and improves the recommendation algorithm. It uses the new feedback information to update the existing recommendation algorithm and improve its accuracy, which will result in more accurate recommendations in the future. The input is the feedback data and the output is the improved recommendation algorithm.

[1374] Step 9:

[1375] The server uses a generative AI model to create prompts and make recommendations optimized for the user's interests and needs. These prompts are given to the generative AI model and act as triggers to obtain appropriate output. The input is the user's history data and feedback data, and the output is a highly accurate content recommendation prompt.

[1376] As a concrete example, the following is an example of an input prompt for a generative AI model:

[1377] Analyze users' reading and internet browsing history and recommend books that are likely to be of interest to business people.

[1378] Reading history: Leadership, Marketing

[1379] Browsing History: Digital Transformation

[1380] In this way, by combining each step, a highly accurate content recommendation system that meets the user's needs is realized.

[1381] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1382] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotions to provide more personalized recommendations for the user. This system consists of four main components: the user, the device, the server, and the emotion engine.

[1383] 1. Enter your user information

[1384] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. Emotional information obtained through the user's input and actions is also recorded by the emotion engine.

[1385] 2. Information Collection and Storage

[1386] The device converts the input data into an appropriate format and sends it to the server, which stores the received information in a database, including the user's emotional state.

[1387] 3. Data Analysis

[1388] The server analyzes the saved reading history, browsing history, problems to be solved, and emotional information. The emotion engine analyzes the content entered by the user and the emotions expressed while browsing, and records them in a database. The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[1389] 4. Generating Recommendations

[1390] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[1391] 5. Presentation of recommendation results

[1392] The server sends a list of recommended books, along with summaries, pricing information, and inventory information from libraries and online stores, to the device, which then presents this information visually to the user.

[1393] 6. Gathering Feedback

[1394] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[1395] 7. Processing and storing feedback

[1396] The device sends the feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[1397] Specific examples

[1398] A specific usage scenario using the system of the present invention is shown below.

[1399] Scenario 1: Busy businessman

[1400] The user is looking for a book to help them improve their work efficiency, but is currently feeling stressed.

[1401] Users input tasks such as "How to improve work efficiency" via the device, as well as business-related books they have read in the past. The emotion engine then detects their current stress level.

[1402] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[1403] The device will present the user with a list of recommended books, summaries, and links to purchase from the online store.

[1404] After purchasing and reading "Stress Management," a user enters feedback saying, "I found it very relaxing."

[1405] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[1406] Scenario 2: A student studying for a test

[1407] A student user is looking for books related to a particular subject, but is currently experiencing low motivation.

[1408] A user inputs a topic such as "Basics of Statistics" via a terminal, and the emotion engine detects when the user's motivation is declining.

[1409] The server also analyzes information from academic books that have been read in the past and educational sites that have been visited, and recommends books such as "Introduction to Statistics," "Data Analysis Basics," and "Study Methods to Motivate You."

[1410] The device will present this list of recommendations along with library holdings information and online purchase links.

[1411] After reading "Study Methods to Motivate You," the user enters feedback such as "It was very encouraging."

[1412] The server and emotion engine receive this feedback information to help adjust the recommendation algorithm next time.

[1413] This allows users to receive recommendations for books that best fit their current emotional state, enhancing their reading experience, and feedback allows the system to continually evolve and improve its recommendations.

[1414] The processing flow will be explained below.

[1415] Step 1:

[1416] Users access the device's interface and input their reading history, internet browsing history, problems they want to solve, and areas of interest, such as "how to improve work efficiency" or "books on leadership."

[1417] Step 2:

[1418] The terminal converts the input data into an appropriate format (e.g., JSON format) and sends it to the server, which ensures data consistency and makes it easier for the server to parse.

[1419] Step 3:

[1420] The server receives the user data sent from the device and stores it in a database, including the user's emotional state.

[1421] Step 4:

[1422] The emotion engine analyzes user input and behavior (e.g., reading history, time spent on web pages, etc.) to identify the user's emotional state. For example, it can detect that the user's current stress level is high based on their writing and selections.

[1423] Step 5:

[1424] The server uses the stored data and the analysis results of the emotion engine to generate a recommendation algorithm based on the user's interests, which also takes into account the user's current emotional state.

[1425] Step 6:

[1426] The server then uses the generated recommendation algorithm to create a list of books that are best suited to the user. For example, it might recommend books that have a relaxing effect to a user who is feeling stressed, or books about efficiency to a user who wants to improve their work efficiency.

[1427] Step 7:

[1428] The server uses library collection information and online store APIs to collect book availability and price information, which is then added to the recommendation list.

[1429] Step 8:

[1430] The server sends a recommendation list including detailed information to the terminal.

[1431] Step 9:

[1432] The device visually presents the user with the list of recommendations it receives, including summaries, purchase links, and library holdings information.

[1433] Step 10:

[1434] After reading the recommended book, users can input feedback via their device, including their emotional state after reading.

[1435] Step 11:

[1436] The terminal converts the feedback data into an appropriate format and sends it to the server, which ensures data consistency.

[1437] Step 12:

[1438] The server receives the feedback data sent from the terminal and stores it in a database.

[1439] Step 13:

[1440] Based on the stored feedback data and the analysis results of the emotion engine, the server makes adjustments to improve the accuracy of the recommendation algorithm, including retraining the machine learning model and adjusting its parameters.

[1441] This allows the system to continuously improve and provide users with more accurate recommendations, specifically those that reflect the user's emotional state in real time, resulting in a more personalized reading experience.

[1442] Example 2

[1443] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1444] Recommendation systems that take into account a user's reading and internet browsing history are required to realize more personalized recommendations that reflect the user's current emotional state, rather than simply being based on past history. In particular, accurate recommendations that meet the specific needs of busy business people or students are heavily influenced by daily fluctuations in stress and motivation, so incorporating emotional information is important.

[1445] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1446] In this invention, the server includes means for collecting a user's reading history and internet browsing history and storing them in an information storage device, means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, and means for recognizing and analyzing the user's emotional information to evaluate the user's current emotional state. This enables the server to recommend books that take into account the user's reading history and internet browsing history, as well as the user's current stress and motivation levels. This provides the user with an optimal reading experience, and by utilizing this feedback in subsequent recommendations, the accuracy of recommendations can be continuously improved.

[1447] "Reading history" is information about books a user has read in the past.

[1448] "Internet browsing history" is information about web pages and content that a user has viewed on the Internet in the past.

[1449] An "information storage device" is a device that stores and manages data collected by the server from users.

[1450] "Emotional information" is information about the emotional state a user expresses through their input and actions.

[1451] A "recommendation algorithm" is a set of calculation procedures and rules for recommending books and content suitable for a user based on collected user data.

[1452] An "emotion engine" is a system that analyzes a user's emotional state and reflects that data in the recommendation algorithm.

[1453] "Feedback" refers to information about ratings and impressions provided by users after using recommended books or content.

[1454] The "database" is a data storage system for centrally managing collected user reading history, internet browsing history, emotional information, etc.

[1455] "User" refers to an individual who uses this system to receive recommendations for books and content.

[1456] A "terminal" is an electronic device that a user uses to interface with the system.

[1457] This invention combines a recommendation system based on a user's reading history and internet browsing history with an emotion engine that recognizes the user's emotional information to achieve more personalized recommendations for the user. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[1458] Entering user information

[1459] Users input their reading history, internet browsing history, problems they want to solve, and areas they are interested in through their devices. In addition, emotional information is also recorded through the emotion engine, which analyzes the user's input and actions.

[1460] Information Collection and Storage

[1461] The terminal converts the input data into an appropriate format (such as JSON format) and sends it to the server.

[1462] The server stores the received information in a database, including the user's emotional state.

[1463] Analyzing the data

[1464] The server analyzes saved reading history, internet browsing history, problems to be solved, and emotional information.

[1465] The emotion engine analyzes the content users enter and the emotions they express while browsing, and records them in a database.

[1466] The server uses this data to generate a recommendation algorithm based on the user's interests and current emotional state.

[1467] Generating Recommendations

[1468] The server then uses the analysis results to create a list of books suitable for the user. By taking into account information from the emotion engine, the server can recommend books that fit the user's current emotional state. For example, if a user is feeling stressed, the server can recommend books that have a relaxing effect.

[1469] Presentation of recommendation results

[1470] The server sends the device a list of recommended books, as well as summaries, pricing information, and inventory information from libraries and online stores.

[1471] The device visually presents this information to the user.

[1472] Collecting feedback

[1473] After reading a recommended book, users can input their feedback via their device, including their emotional state after reading. This information is also sent to the emotion engine.

[1474] Processing and storing feedback

[1475] The terminal transmits the feedback data to the server.

[1476] The server stores the received feedback information in a database and uses it to improve the recommendation algorithm in future.

[1477] The emotion engine reassess the user's emotional state from the feedback information and updates the recommendation algorithm based on this.

[1478] Specific examples

[1479] Scenario 1: Busy businessman

[1480] The user types "ways to improve work efficiency" into the device and also enters the business-related books they have read in the past.

[1481] The emotion engine detects the current stress state.

[1482] The server analyzes this information and recommends books such as "Essential Thinking," "Mental Models," and "Stress Management."

[1483] The device will present the user with a list of recommended books, summaries, and a link to purchase from the online store.

[1484] After a user purchases and reads "Stress Management," they enter feedback saying, "I found it very relaxing."

[1485] This feedback information is sent to the server and used to improve the accuracy of the recommendation algorithm and emotion engine next time.

[1486] Prompt Sentence Examples

[1487] "I want to know how to improve my work efficiency. I've read books like 'The 7 Habits' and 'Essential Thinking' in the past. I've been feeling stressed lately."

[1488] "I want to learn the basics of statistics. The only book I've read on the subject is 'Introduction to Statistics.' I'm currently feeling unmotivated."

[1489] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1490] Step 1: Enter your user information

[1491] Users use the device to input their reading history, internet browsing history, problems they want to solve, and areas of interest. The device converts the user's input into an appropriate data format, such as JSON. The emotion engine also analyzes the user's input and behavior and records the emotional information as an emotional status. The input data are raw text, qualitative comments, and rating scores. The output is formatted user information and emotional status.

[1492] Examples:

[1493] The user types in "How to improve work efficiency" and adds "essential thoughts" they have read in the past. The emotion engine detects stress from the user's input.

[1494] Step 2: Collecting and storing information

[1495] The device will format the data entered by the user, convert it into the appropriate data format, and then send it to the server. The server will store the received data in a database. This storage process includes the user's reading history, internet browsing history, and emotional information.

[1496] Input: Data entered by the user (reading history, internet browsing history, emotional information)

[1497] Output: Formatted data sent to the server

[1498] Examples:

[1499] The device sends the following data to the server:

[1500] json

[1501] {

[1502] "Reading history": ["Essential Thinking"],

[1503] "Web browsing history": ["How to improve work efficiency"],

[1504] "Emotional state": "Stress"

[1505] }

[1506] Step 3: Analyze the data

[1507] The server extracts stored user data and analyzes it based on reading history, internet browsing history, and emotional information. This analysis uses natural language processing algorithms and generative AI models to identify user interests and evaluate emotional information. The analysis results are then combined with the analysis data from the emotional engine to form a user profile.

[1508] Input: User data extracted from the database (reading history, internet browsing history, emotional information)

[1509] Output: User interest profile and emotional state

[1510] Examples:

[1511] The server analyzes the following information to create a profile of the user's attributes and emotional state:

[1512] Reading History: Essential Thinking

[1513] Web browsing history: How to improve your work efficiency

[1514] Emotional state: Stress

[1515] Step 4: Generate recommendations

[1516] The server then applies a recommendation algorithm based on the analysis results to generate a list of books that are best suited to the user, taking into account emotional information from the emotion engine. The algorithm reflects the user's current emotional state and selects books that fit that sentiment.

[1517] Input: User profile data (interests, concerns, emotional state)

[1518] Output: Recommended book list

[1519] Examples:

[1520] The server recommends the following book:

[1521] Essential Thinking

[1522] Mental Model

[1523] Stress management

[1524] Step 5: Presenting the Recommendations

[1525] The server sends the generated recommended book list, summaries, price information, and inventory information from libraries and online stores to the terminal, which visually displays this information to the user.

[1526] Input: Recommendation results provided by the server

[1527] Output: The list of recommendations and details displayed to the user

[1528] Examples:

[1529] The terminal will display the following list:

[1530] Essential Thinking (price, summary)

[1531] Mental model (price, summary)

[1532] Stress Management (Price, Summary)

[1533] Step 6: Gather feedback

[1534] After reading the recommended book, the user inputs feedback via the terminal, including their emotional state and specific impressions after reading. The terminal then sends the feedback data to the database.

[1535] Input: User feedback (emotional state, thoughts)

[1536] Output: Feedback data sent to the server

[1537] Examples:

[1538] A user finishes reading "Stress Management" and gives feedback that it was "very relaxing."

[1539] Step 7: Processing and storing feedback

[1540] The device sends the collected feedback data to the server, which stores the received feedback information in a database and uses it to improve the recommendation algorithm for future use. The emotion engine reevaluates the user's emotional state based on the feedback information and updates the recommendation algorithm.

[1541] Input: Feedback data

[1542] Output: Updated recommendation algorithm

[1543] Examples:

[1544] Your feedback information will be saved and used for future recommendations as follows:

[1545] json

[1546] {

[1547] "Books I've read": "Stress Management",

[1548] "Emotional state": "Very relaxed"

[1549] }

[1550] (Application example 2)

[1551] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1552] Conventional recommendation systems are based on a user's reading history and internet browsing history, and do not take into account the user's specific emotional state. This makes it difficult to recommend optimal books that vary depending on the user's current emotions, such as stress or lack of motivation. Furthermore, they lack the ability to effectively utilize user feedback to improve the accuracy of next recommendations. This has led to issues such as a decrease in user satisfaction and difficulty in promoting long-term use.

[1553] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the user's reading history and internet browsing history, means for collecting the user's reading history and internet browsing history and storing them in a database, and means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, concerns, and emotional state. This enables personalized recommendations that take the user's emotional state into consideration.

[1554] A "user" is an entity that uses this system and performs activities such as reading or browsing the Internet.

[1555] "Reading history" is a record of books a user has read in the past, including their content and impressions.

[1556] "Web browsing history" is a record of the web pages a user has accessed and articles they have read on the Internet.

[1557] "Emotional state" refers to the emotional state a user is feeling at a particular point in time, and can include stress, joy, motivation, etc.

[1558] A "recommendation algorithm" is a computational method for analyzing collected data and selecting the most suitable book for a user.

[1559] The "database" is a system that stores and centrally manages collected user information, emotional state, and feedback data.

[1560] A "recommended list" is a list of books presented to users based on analyzed data, including summaries and pricing information.

[1561] "Feedback" refers to the impressions and evaluations that users enter after reading a recommended book, and includes information about their emotional state.

[1562] "Server" means the central system that processes, stores and analyzes data received from Users.

[1563] "Data collection means" refers to interfaces or software used to collect information such as users' reading history and internet browsing history.

[1564] An "emotion engine" is a computer program that analyzes a user's emotional state and generates data based on that.

[1565] "Online store information" refers to inventory and price information on online book sales sites.

[1566] "Library information" refers to the stock status and lending information of books at libraries, etc.

[1567] "Terminal" refers to the device through which a user enters data and receives recommended book information, including smartphones and tablets.

[1568] The present invention is a book recommendation system that takes into account the emotional state of a user, and its main components are a user terminal, a server, and an emotion engine. This system is implemented using a user terminal such as a smartphone or tablet.

[1569] The user device is equipped with a means for collecting the user's reading history and internet browsing history and storing them in a database. Furthermore, the user device is equipped with an interface for inputting the user's current issues and concerns, and an interface for inputting feedback after reading. This allows the user to provide the system with their interests and emotional state.

[1570] The server analyzes data collected from the user's device and generates a recommendation algorithm based on the user's interests, concerns, and emotional state. An emotion analysis engine using libraries such as TextBlob determines the user's emotional state from the text they input. The analysis results are stored in a database and used to generate the recommendation algorithm.

[1571] Based on the generated recommendation algorithm, the server generates a list of books that are most suitable for the user. This list takes into account the user's emotional state, for example, recommending relaxing books to a user who is feeling stressed. The device then presents this recommendation list to the user, along with summaries, price information, and online store inventory information.

[1572] After the user finishes reading a recommended book, the device collects feedback from the user and sends it to the server. The server stores this feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future installments. The emotion engine reassess the user's emotional state based on the feedback information and updates the recommendation algorithm accordingly.

[1573] As a concrete example, User A is looking for books aimed at relieving work stress. Using this system, he searches for "stress management" and inputs his past reading history, and the sentiment analysis engine detects "stressed state." Based on this, the server recommends "books on mindfulness" as "books with a relaxing effect" and presents the list to the user.

[1574] An example prompt is, "I've been busy and stressed lately, so I'm looking for a book that will calm me down."

[1575] This system enables more personalized book recommendations that take into account the user's emotional state, thereby increasing user satisfaction.

[1576] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1577] Step 1:

[1578] The user uses the device to input text related to their reading history, internet browsing history, and their current emotional state. This input includes not only their reading history and internet browsing history, but also sentences that indicate their emotional state (e.g., "I've been feeling stressed lately.") This allows the user's areas of interest and current emotional state to be collected as initial data.

[1579] Step 2:

[1580] The device converts the collected data into an appropriate format and sends it to the server, using, for example, JSON format. The data includes the user's reading history, internet browsing history, and input emotional state text. The server receives this data and stores it in an initial database.

[1581] Step 3:

[1582] The server uses libraries such as TextBlob to analyze the input emotional state text. The emotion analysis engine performs the analysis and outputs the user's emotional state (e.g., positive, negative, neutral) as numerical data. This numerical emotional state data is also stored in the database.

[1583] Step 4:

[1584] The server generates a recommendation algorithm based on the collected reading history, internet browsing history, and emotional state data. A recommendation algorithm is a computational method for selecting the most suitable books for a user based on past data analysis. This algorithm generation process may use machine learning models (e.g., generative AI models).

[1585] Step 5:

[1586] The server then generates a list of books that best fit the user's emotional state based on the recommendation algorithm. Taking into account the analysis results of the emotion engine, the server lists books that have a "stress-relieving" or "relaxing" effect, for example. These recommended book lists also include summaries of each book, pricing information, and inventory information for online stores and libraries.

[1587] Step 6:

[1588] The server sends the generated recommended book list to the terminal, which visually presents the list to the user. The user can browse the recommended list and select books that interest them, allowing the user to easily find the books they currently need most.

[1589] Step 7:

[1590] After reading, users can use their devices to input feedback, including their emotional state after reading and their rating of the book. The feedback data provides users with an opportunity to specifically input their rating for the recommendation system.

[1591] Step 8:

[1592] The device sends the feedback data to the server. The server stores the received feedback data in a database and uses it to improve the accuracy of the recommendation algorithm in future. The emotion engine reanalyzes the feedback information, evaluates changes in the user's emotional state, and updates the recommendation algorithm based on this. This allows the system to continuously learn and make even more accurate recommendations.

[1593] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1594] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1595] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1596] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1597] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1598] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1599] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1600] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1601] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1602] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1603] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1604] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1605] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1606] 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.

[1607] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1608] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1609] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1610] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1611] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1612] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1613] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1614] The following is further disclosed regarding the above embodiment.

[1615] (Claim 1)

[1616] a means for inputting a user's reading and browsing history;

[1617] A means for collecting and storing users' reading and browsing history in a database;

[1618] A means for analyzing the collected data and generating recommendation algorithms based on the user's interests and concerns;

[1619] a means for presenting a list and summaries of recommended books to the user;

[1620] A means of providing information on where recommended books are available and their prices;

[1621] A system that includes a means for collecting post-reading feedback and analyzing and storing that feedback data to improve the accuracy of recommendation algorithms.

[1622] (Claim 2)

[1623] 10. The system of claim 1, further comprising means for a user to input a problem or concern that the user wishes to solve.

[1624] (Claim 3)

[1625] 10. The system of claim 1, further comprising means for collecting library collection information and online store inventory information.

[1626] "Example 1"

[1627] (Claim 1)

[1628] a means for inputting a user's reading and browsing history;

[1629] A means for collecting and storing users' reading and browsing history in a database;

[1630] A means for analyzing the collected data and generating recommendation algorithms based on the user's interests and concerns;

[1631] a means for presenting a list and summaries of recommended books to the user;

[1632] A means of providing information on where recommended books are available and their prices;

[1633] A means for collecting post-reading feedback and analyzing and storing that feedback data to improve the accuracy of recommendation algorithms;

[1634] A means for identifying user interests using machine learning algorithms;

[1635] means for generating a list of books that are most suitable for the user using collaborative filtering or content-based filtering techniques;

[1636] The system includes a means for saving user input information to a database in real time.

[1637] (Claim 2)

[1638] 10. The system of claim 1, further comprising means for a user to input a problem or concern that the user wishes to solve.

[1639] (Claim 3)

[1640] 10. The system of claim 1, further comprising means for collecting library collection information and online store inventory information.

[1641] "Application Example 1"

[1642] (Claim 1)

[1643] a means for inputting a user's reading and browsing history;

[1644] A means for collecting and storing users' reading and browsing history in a database;

[1645] A means for analyzing the collected data and generating recommendation algorithms based on the user's interests and concerns;

[1646] means for presenting a list and summary of recommended content to the user;

[1647] A means to provide location and pricing information for the recommended content;

[1648] A means for collecting post-reading feedback and analyzing and storing that feedback data to improve the accuracy of recommendation algorithms;

[1649] a means for improving the recommendation algorithm based on the feedback;

[1650] A means of making recommendations optimized for users' interests and needs through prompts using generative AI models

[1651] A system including:

[1652] (Claim 2)

[1653] 10. The system of claim 1, further comprising means for a user to input a problem or concern that the user wishes to solve.

[1654] (Claim 3)

[1655] 10. The system of claim 1, further comprising means for collecting library collection information and online store inventory information.

[1656] "Example 2: Combining Emotion Engines"

[1657] (Claim 1)

[1658] a means for inputting a user's reading history and internet browsing history;

[1659] A means for collecting and storing a user's reading history and internet browsing history in an information storage device;

[1660] A means for analyzing the collected data and generating recommendation algorithms based on the user's interests and concerns;

[1661] means for recognizing and analyzing the user's emotional information to assess the user's current emotional state;

[1662] means for presenting recommended information lists and summaries to the user;

[1663] A means of providing information on where to find the recommended information and pricing information;

[1664] A system that includes a means for collecting post-reading feedback and analyzing and storing that feedback data to improve the accuracy of recommendation algorithms.

[1665] (Claim 2)

[1666] 10. The system of claim 1, further comprising means for a user to input a problem or concern that the user wishes to solve.

[1667] (Claim 3)

[1668] 10. The system of claim 1, further comprising means for collecting library collection information and online store inventory information.

[1669] "Application example 2 when combining emotion engines"

[1670] (Claim 1)

[1671] a means for inputting a user's reading and browsing history;

[1672] A means for collecting and storing users' reading and browsing history in a database;

[1673] means for analyzing the collected data and generating a recommendation algorithm based on the user's interests, concerns, and emotional state;

[1674] means for presenting to the user a list of recommended books, summaries, and books tailored to an emotional state;

[1675] A means of providing availability and pricing information for recommended books;

[1676] A system that collects post-reading feedback, as well as a means to analyze and store that feedback data and improve the accuracy of recommendation algorithms.

[1677] (Claim 2)

[1678] 10. The system according to claim 1, further comprising means for inputting a problem or concern that a user wants to solve, and means for performing sentiment analysis.

[1679] (Claim 3)

[1680] 10. The system of claim 1, further comprising means for collecting library collection information and online store inventory information, and means for presenting book information based on an emotional state. [Explanation of symbols]

[1681] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for inputting a user's reading and browsing history; A means for collecting and storing users' reading and browsing history in a database; A means for analyzing the collected data and generating recommendation algorithms based on the user's interests and concerns; a means for presenting a list and summaries of recommended books to the user; A means of providing information on where recommended books are available and their prices; A system that includes means for collecting post-reading feedback and analyzing and storing that feedback data to improve the accuracy of recommendation algorithms.

2. The system according to claim 1, further comprising means for the user to input a problem or concern that the user wishes to solve.

3. The system of claim 1 further comprising means for collecting library collection information and online store inventory information.

Images