System

Abstract

A system is provided.SOLUTION: A system comprising: a setting means for setting a knowledge level, an interest field, and a depth of annotation of a user; an input means for inputting a sentence or a document to be annotated by the user; a search means for generating a search query based on data obtained from the setting means and the input means, and searching for related information; an annotation generation means for analyzing and arranging the related information obtained by the search means, and generating an annotation based on a setting parameter of the user; a display means for displaying the generated annotation to the user; and a learning means for monitoring a use situation of the user, and updating an algorithm of the annotation generation means.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] In today's world, users with different knowledge levels and interests need to efficiently acquire information and engage in learning and communication. However, conventional information retrieval and annotation systems have struggled to provide optimal information tailored to each user's knowledge level and areas of interest. In particular, conventional systems are unable to adequately address users who require advanced information or situations where the content of information needs to be flexibly changed as their learning progresses, resulting in a loss of user convenience. Furthermore, methods for systems to self-learn and improve accuracy based on the usage of search results are also lacking. Therefore, there is a need for a system that allows multiple users with different knowledge levels and areas of interest to efficiently acquire the information and annotations that are optimal for each user. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including: a setting means for a user to set their own knowledge level, areas of interest, and annotation depth; an input means for inputting sentences or documents to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; and a learning means for monitoring the user's usage and updating the algorithm of the annotation generation means. Furthermore, a transmission means for transmitting data including the user's input text data and user ID to a server and a receiving means for presenting the annotation data received from the server to the user allow the user to efficiently obtain annotations optimal for their interests and level of understanding. Furthermore, the search query generated by the search means is optimized based on the user's knowledge level and areas of interest, enabling the provision of highly accurate information customized for each user. This allows users with different knowledge levels and areas of interest to easily obtain information and annotations appropriate for them.

[0006] The "setting means" refers to an interface and its implementation means for allowing a user to set his / her own knowledge level, field of interest, and depth of annotation.

[0007] "Input means" refers to an interface and its implementation means for inputting sentences or documents that a user wants to annotate into the system.

[0008] The "search means" is a means having a function of generating a search query based on data obtained from the setting means and the input means, and searching the Internet or a database for related information.

[0009] The "annotation generating means" is a means for analyzing and organizing the related information acquired by the search means, and creating appropriate annotations based on parameters set by the user.

[0010] A "display means" is a means, including a display or other output device, for visually presenting generated annotations to a user.

[0011] The "learning method" is a method for monitoring user usage and continuously improving and updating the annotation generation algorithm based on that data.

[0012] The "transmission means" is a means having a function for transmitting data including the text data and the user ID input by the user to the server.

[0013] The "receiving means" is a means having a function for presenting annotation data received from the server to the user.

[0014] A "search query" is a search string or code that is generated in an optimized manner based on the user's knowledge level and areas of interest. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

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

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

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

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and has a learning function that improves the accuracy of the annotation generation. Specific embodiments of this system are described below.

[0037] User parameter settings

[0038] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), areas of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is saved as the user's individual profile.

[0039] Text Input

[0040] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[0041] Generating a search query

[0042] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate working principle" will be generated.

[0043] Search for related information

[0044] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0045] Annotation Generation

[0046] The server generates annotations based on the analyzed and filtered information and the user's set parameters. For example, if an intermediate-level explanation of lithium-ion batteries is required, the server generates text in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The intermediate-level points are ____."

[0047] Viewing annotations

[0048] The generated annotations are sent from the server to the terminal, which displays them to the user, who can view them in the form of popups or tooltips, for example, by highlighting the annotated portion of the original text.

[0049] Usage monitoring and learning

[0050] As users use annotations, their usage (e.g., view time, clicks, frequency of viewing, etc.) is sent from the device to the server, which uses this data to continuously learn and optimize the annotation generation algorithm, improving the accuracy and relevance of annotations over time.

[0051] Specific examples

[0052] As a specific example, consider the case where a user inputs the question "How does a lithium-ion battery work?"

[0053] 1. The user has an intermediate level of science knowledge.

[0054] 2. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information from the internet and databases.

[0055] 3. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[0056] 4. The server sends the annotations to the terminal, which displays them to the user.

[0057] 5. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[0058] In this way, the present invention provides a system that contributes to the promotion of personalized learning and communication.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user opens the system's settings screen and enters their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). The settings information is saved as the user's individual profile.

[0062] Step 2:

[0063] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[0064] Step 3:

[0065] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[0066] Step 4:

[0067] The terminal sends the entered text data and user ID to the server, which receives it.

[0068] Step 5:

[0069] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[0070] Step 6:

[0071] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0072] Step 7:

[0073] The server analyzes the collected information and filters and formats it based on the user's knowledge level and areas of interest, thereby extracting annotation information appropriate for the user.

[0074] Step 8:

[0075] The server generates annotations based on the analyzed information. For example, it might generate annotations like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0076] Step 9:

[0077] The server sends the generated annotations to the terminal, which then displays them to the user. The user can view the annotations in a popup or tooltip format.

[0078] Step 10:

[0079] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[0080] Step 11:

[0081] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0082] Through these steps, our system efficiently generates and provides annotations optimized for each user, allowing users with different knowledge levels and areas of interest to easily obtain information and annotations that are appropriate for them.

[0083] Example 1

[0084] 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."

[0085] Conventional annotation generation systems have the difficulty of providing individualized annotations tailored to the user's knowledge level or area of ​​interest, and are only able to provide general information. Another problem is that they lack the ability to continuously train the annotation generation algorithm based on the user's usage, making it difficult to expect long-term accuracy improvements.

[0086] 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.

[0087] In this invention, the server includes: a setting means for a user to set their own knowledge level, areas of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the acquired related information using a generative AI model and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide highly accurate annotations suited to the knowledge level and areas of interest of each individual user, and the accuracy and relevance of the annotation generation can be improved over time.

[0088] A "user" is someone who uses the system to obtain annotations based on their level of knowledge and areas of interest.

[0089] The "setting means" refers to an interface that allows a user to input parameters such as his / her knowledge level, areas of interest, and annotation depth.

[0090] "Input means" refers to an interface through which a user inputs a sentence or document to be annotated.

[0091] The "search means" refers to a function that generates a search query based on data obtained from the setting means and the input means, and searches for related information.

[0092] A "generative AI model" is a type of artificial intelligence used to generate text for annotation generation.

[0093] "Annotation generation means" refers to a function that analyzes the relevant information obtained using a generative AI model and generates annotations based on the user's set parameters.

[0094] "Display means" refers to an interface for visually presenting the generated annotations to the user.

[0095] The "learning means" refers to a function for monitoring user usage and updating the algorithm of the annotation generation means.

[0096] "Transmission means" refers to a function for transmitting the text data entered by the user and the user identification information to the server.

[0097] The "receiving means" refers to a function for presenting annotation data received from the server to the user.

[0098] This invention is a system that automatically generates annotations based on each user's knowledge level and area of ​​interest, and has a learning function that improves the accuracy of the annotation generation.

[0099] 1. Setting user parameters

[0100] First, the user opens the system's settings screen and sets their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This information is sent to the server via the "settings means" and saved as the user's profile. Databases such as "ElasticSearch (registered trademark)" and "MongoDB" are used.

[0101] 2. Enter text

[0102] Next, the user enters the sentence or document they want to annotate into the system's text input field. For example, if they want to annotate on the topic "Principles of operation of lithium-ion batteries," they simply enter the text. This information is sent to the server via the "input means."

[0103] 3. Generating search queries

[0104] The server generates an appropriate search query based on the received user settings and the entered text. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate operating principle" is generated. Python and Elasticsearch are used to generate the search query.

[0105] 4. Searching for related information

[0106] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting and filtering data from multiple sources, using databases such as Google Scholar and JSTOR.

[0107] 5. Generating Annotations

[0108] The server generates annotations based on the collected and filtered information in accordance with the user's set parameters. This is done using a "generative AI model," such as GPT-3 (registered trademark). The specific annotation generated is, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes."

[0109] 6. Viewing annotations

[0110] The generated annotations are sent from the server to the device, which then displays them to the user. The annotations are provided in pop-up or tooltip format, and the user can check them by clicking or touching them. Web technologies such as HTML, CSS, and JavaScript (registered trademark) are used for display.

[0111] 7. Usage monitoring and learning

[0112] When a user uses annotations, their device sends usage information, such as reference time, number of clicks, and frequency of viewing, to the server. The server uses this data to train and optimize the annotation generation algorithm. This process uses Tensorflow (registered trademark) and PyTorch. This allows the accuracy and relevance of annotations to improve over time.

[0113] Specific examples

[0114] Here is a concrete example of how a lithium-ion battery works:

[0115] 1. The user has an intermediate level of science knowledge.

[0116] 2. The user types the question, "What is the working principle of a lithium-ion battery?"

[0117] 3. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information.

[0118] 4. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[0119] 5. The server sends the annotations to the terminal, which displays them to the user.

[0120] 6. When a user refers to the annotations and obtains information, the usage status is sent to the server and processed as learning data.

[0121] Prompt Sentence Examples

[0122] "Generate detailed annotations for users with intermediate scientific knowledge on the working principles of lithium-ion batteries, including how lithium ions move and the process of energy generation."

[0123] In this way, the present invention can promote personalized learning and communication, providing optimal annotations for each user.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] The user opens the system's setting screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). These inputs are sent to the server through the setting means. The server stores the received data in a database and manages it as a user profile. After the setting information is saved, the server sends a confirmation message to the user (input: user setting information, output: confirmation message).

[0127] Step 2:

[0128] The user inputs the sentence or document they want to annotate into the system's text input field. This information is sent to the server via the input means. For example, a sentence about "the working principle of lithium-ion batteries" is input. The server receives the text data and saves it for analysis (input: user's text data, output: saved text data).

[0129] Step 3:

[0130] The server generates an appropriate search query based on the received user settings and the input text data. In this example, if the user's knowledge level is intermediate and their field of interest is chemistry, a query such as "lithium ion battery intermediate operating principle" is generated. This process is performed using a Python script (input: user settings and text data, output: generated search query).

[0131] Step 4:

[0132] The server uses the generated search query to search for relevant information from the Internet and internal databases. The search query is passed to the Elasticsearch engine, which filters relevant documents from the index. As a result, multiple pieces of relevant information are collected from the Internet (e.g., Google Scholar) (Input: Generated search query, Output: Collected relevant information).

[0133] Step 5:

[0134] The server generates annotations based on the collected and filtered information and the user's set parameters. This process uses a "generative AI model." For example, the AI ​​model "GPT-3" is selected, and annotations are generated based on prompt statements. For example, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes" is generated (input: collected related information, output: generated annotation).

[0135] Step 6:

[0136] The generated annotations are sent from the server to the terminal, where they are displayed to the user in a popup or tooltip format along with the original input text. For example, the original text is displayed on a web page, and the annotations are displayed in tooltip format nearby (input: generated annotations, output: annotations displayed to the user).

[0137] Step 7:

[0138] When a user uses annotations, their usage (e.g., time spent viewing, number of clicks, frequency of viewing, etc.) is sent from the device to the server. The server analyzes this data and updates the annotation generation algorithm. This process involves machine learning using TensorFlow and PyTorch, which improves the accuracy and relevance of annotations over time (input: user usage data, output: optimized annotation generation algorithm).

[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] Conventional annotation generation systems have difficulty providing information tailored to the user's knowledge level and areas of interest, and especially in physical stores, there is a lack of efficient ways for users to obtain the information they are looking for. In addition, it is difficult to provide product information in real time, and there is a need to improve the user experience.

[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: a setting means for a user to set their own knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; a visual information collection means for collecting product information using a visual display device worn by the user and generating annotations based on the user's setting information; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This enables users to obtain product information in real time at a physical store and obtain annotations optimized for their own knowledge level and field of interest.

[0144] The "setting means" is a means for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[0145] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[0146] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[0147] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means and generating annotations based on the parameters set by the user.

[0148] The "display means" is a means for displaying the generated annotation to the user.

[0149] The "visual information gathering means" is a means for gathering product information using a visual display device worn by the user and generating annotations based on the user's settings.

[0150] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[0151] The "transmission means" is a means for transmitting the text data entered by the user and the user ID to the server.

[0152] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[0153] A "search query" is a question for information search that is generated based on the user's knowledge level and areas of interest.

[0154] A "server" is a host computer for data processing and storage.

[0155] A "visual display device" is a device worn by a user that visually displays information.

[0156] The present invention provides a system for generating annotation information based on a user's knowledge level and areas of interest, thereby improving the user experience in a physical store. Detailed embodiments for realizing this system are described below.

[0157] User parameter settings

[0158] The user sets his / her knowledge level (e.g., beginner, intermediate, advanced), interest area (e.g., wine, cosmetics, technical products, etc.), and annotation depth (e.g., overview, detailed, specialized) through the setting screen of the smart glasses. This setting information is stored on the visual display device and on the server.

[0159] Collecting product information

[0160] When a user wears smart glasses and walks around a physical store, the camera captures product information in real time using the visual information collection means. For example, if a user sees a particular wine in the wine section, image data recognizing that product is acquired.

[0161] Generating a search query

[0162] The server generates an appropriate search query based on the product data acquired by the visual information gathering means and the user's settings. For example, it creates a search query such as "Bordeaux wine, mid-range, taste characteristics."

[0163] Search for related information

[0164] The server then searches for relevant information from the internet and internal databases based on the generated search query, using a search engine such as Elasticsearch.

[0165] Annotation Generation

[0166] The server analyzes the relevant information obtained through the search tool and generates annotations based on the user's set parameters. This analysis process uses a generative AI model (such as GPT or BERT). A specific example of an annotation generated is the following: "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon."

[0167] Viewing annotations

[0168] The generated annotation information is transmitted from the server to the smart glasses and displayed to the user in real time.

[0169] Usage monitoring and learning

[0170] As users browse the annotations displayed and access additional information, their usage is monitored, including viewing time, number of clicks, etc. This data is stored on the server to help train and continuously optimize the annotation generation algorithm.

[0171] Examples and prompts

[0172] As a concrete example, consider the case where a user looks at "a specific wine":

[0173] Configuration information

[0174] Knowledge level: Intermediate

[0175] Interests: Wine

[0176] Annotation Depth:Details

[0177] Prompt Sentence Examples

[0178] If the user is looking at a "specific wine":

[0179] User Settings:

[0180] Knowledge level: Intermediate

[0181] Interests: Wine

[0182] Annotation Depth: Detailed

[0183] Generated notes: "This particular wine is a red wine from a prestigious winery in the Bordeaux region of France. This vintage is particularly outstanding, dominated by Cabernet Sauvignon, with a perfect balance of berry fruit and tannins."

[0184] As described above, the present invention provides a system that enables users to obtain product information in real time at a physical store and obtain annotation information that is suited to their own level of knowledge and areas of interest.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] The user opens the settings screen of the smart glasses and sets their knowledge level, areas of interest, and annotation depth.

[0188] Input: User knowledge level (e.g., intermediate), area of ​​interest (e.g., wine), depth of annotation (e.g., detailed)

[0189] Output: Configuration information (user profile)

[0190] Step 2:

[0191] The user wears the smart glasses in a physical store and captures the product on the camera using a visual information collection means.

[0192] Input: Product image captured by the smart glasses camera

[0193] Output: Product recognition data (image data)

[0194] Step 3:

[0195] The server receives the product data acquired by the visual information gathering means and the user's setting data, and generates an appropriate search query.

[0196] Input: Product recognition data, user profile

[0197] Data processing / data calculation: Image recognition processing using OpenCV, query generation based on user settings

[0198] Output: Search query (e.g., "Wine Bordeaux mid-range flavor profile")

[0199] Step 4:

[0200] The server searches for relevant information from the Internet and internal databases based on the generated search query.

[0201] Input: search query

[0202] Data processing / data calculation: Finding relevant information using Elasticsearch

[0203] Output: Related information (collection of information from multiple data sources)

[0204] Step 5:

[0205] The server analyzes the relevant information obtained by the search means and generates annotations based on user-specified parameters.

[0206] Input: Related information, User profile

[0207] Data processing / data calculation: annotation generation using generative AI models (e.g., GPT, BERT)

[0208] Output: Generated annotations (e.g., "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon.")

[0209] Step 6:

[0210] The server sends the generated annotations to the smart glasses, which display them to the user in real time.

[0211] Input: Generated annotation data

[0212] Output: Visual display of annotation information (displayed on smart glasses)

[0213] Step 7:

[0214] The server monitors the user's usage and continuously learns and optimizes the annotation generation algorithm.

[0215] Input: User operation data (viewing time, number of clicks, etc.)

[0216] Data processing / data calculation: Analysis of user operation data, model updating using machine learning algorithms

[0217] Output: Improved annotation generation algorithm

[0218] This series of processes allows users to obtain product information in real time at a physical store and obtain annotation information customized to their own knowledge level and areas of interest.

[0219] 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.

[0220] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[0221] User parameter settings

[0222] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is stored in the database as the user's individual profile.

[0223] Text Input

[0224] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[0225] Generating a search query

[0226] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[0227] Search for related information

[0228] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0229] emotion recognition

[0230] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0231] Analyzing sentiment data and adjusting search queries

[0232] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[0233] Annotation Generation

[0234] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0235] Viewing annotations

[0236] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[0237] Usage monitoring and learning

[0238] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0239] Specific examples

[0240] For example, consider the case where a user enters a question about "how lithium ion batteries work."

[0241] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[0242] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[0243] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[0244] 4. The server adjusts the search query to simplify it based on the sentiment data.

[0245] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[0246] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[0247] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[0248] In this way, the present invention improves the quality of learning and communication by creating and providing optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest.

[0249] The processing flow will be explained below.

[0250] Step 1:

[0251] The user opens the system's settings screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This setting information is then saved in the database as the user's individual profile.

[0252] Step 2:

[0253] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[0254] Step 3:

[0255] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[0256] Step 4:

[0257] The terminal sends the entered text data and user ID to the server, which receives it.

[0258] Step 5:

[0259] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[0260] Step 6:

[0261] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0262] Step 7:

[0263] The device collects data from sensors (cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0264] Step 8:

[0265] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[0266] Step 9:

[0267] The server generates annotations based on the analyzed information, incorporating set parameters and emotional data. For example, it might generate an annotation like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0268] Step 10:

[0269] The server sends the generated annotations to the terminal, which receives them and displays them to the user, who can view them in popup or tooltip format.

[0270] Step 11:

[0271] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[0272] Step 12:

[0273] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0274] Through these steps, our system efficiently generates and provides annotations optimized for each user, enabling information provision tailored to different knowledge levels and areas of interest. Further optimization according to the user's emotional state improves the quality of learning and communication.

[0275] Example 2

[0276] 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."

[0277] In today's information-saturated society, it is difficult for users to efficiently obtain information appropriate to their own knowledge level and areas of interest. Furthermore, while it is important to provide annotations that reflect the user's emotional state, existing systems do not adequately fulfill this requirement. As a result, users are unable to obtain information that is optimal for them, reducing the effectiveness of learning and information gathering. Therefore, there is a need for an annotation generation system that is appropriate for the user's knowledge level, areas of interest, and emotional state.

[0278] 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.

[0279] In this invention, the server includes a setting means for a user to set his / her knowledge level, field of interest, and annotation depth, an input means for a user to input a sentence or document to which the user wants to annotate, a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information, an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters and emotional data, an emotion recognition means for recognizing the user's emotions and collecting that data, a display means for displaying the generated annotations to the user, and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide optimal information based on the user's knowledge level, field of interest, and emotional state.

[0280] The "setting means" is a means for a user to input his / her own knowledge level, field of interest, and depth of annotation, and store it in the database.

[0281] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[0282] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[0283] The "annotation generation means" is a means for analyzing and organizing the related information acquired by the search means, and generating appropriate annotations based on the user's set parameters and emotion data.

[0284] The "display means" is a means for visually presenting the generated annotation to the user.

[0285] The "learning means" is a means for monitoring user usage and using that data to continuously learn and update the algorithms of the annotation generation means.

[0286] The "transmission means" is a means for transmitting the text data, user ID, and emotion data input by the user to the server.

[0287] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[0288] An "emotion recognition means" is a means using sensors and software to recognize and collect the user's emotional state.

[0289] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[0290] User parameter settings

[0291] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is then saved in the database by the terminal as the user's individual profile.

[0292] Text Input

[0293] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text. The device then sends the entered text to the server.

[0294] Generating a search query

[0295] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[0296] Search for related information

[0297] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0298] emotion recognition

[0299] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0300] Analyzing sentiment data and adjusting search queries

[0301] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[0302] Annotation Generation

[0303] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0304] Viewing annotations

[0305] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[0306] Usage monitoring and learning

[0307] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0308] Specific examples

[0309] For example, consider the case where a user inputs a question about "how lithium-ion batteries work."

[0310] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[0311] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[0312] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[0313] 4. The server adjusts the search query to simplify it based on the sentiment data.

[0314] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[0315] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[0316] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[0317] Prompt Sentence Examples

[0318] "Please provide an intermediate level explanation of how lithium-ion batteries work. If users are confused, simplify the explanation."

[0319] "Generate detailed annotations in the chemical domain based on user sentiment data."

[0320] In this way, the present invention creates and provides optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest, thereby improving the quality of learning and communication.

[0321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0322] Step 1:

[0323] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). The terminal receives these settings and stores them in a database. This setting information is used for subsequent processing.

[0324] Input: User knowledge level, areas of interest, depth of annotations

[0325] Output: User preferences stored in the database

[0326] Specific behavior:

[0327] The user accesses the settings screen

[0328] The user enters the settings.

[0329] The device saves the configuration information in a database

[0330] Step 2:

[0331] The user enters the sentence or document they want to annotate into the text entry field of the system, and the device receives the entered text and sends it to the server.

[0332] Input: The sentence or document you want to annotate

[0333] Output: Text data sent to the server

[0334] Specific behavior:

[0335] The user types text into the text field

[0336] The device sends the entered text to the server

[0337] Step 3:

[0338] The server generates a search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, the server generates a search query such as "Lithium-ion battery intermediate working principle."

[0339] Input: Text data, user setting information

[0340] Output: Generated search query

[0341] Specific behavior:

[0342] The server parses the text data and configuration information

[0343] The server generates a search query based on the analysis results.

[0344] Step 4:

[0345] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0346] Input: Search query

[0347] Output: Filtered relevant information

[0348] Specific behavior:

[0349] The server sends the search query to the internet or to an internal database

[0350] The server collects and filters the information obtained

[0351] Step 5:

[0352] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0353] Input: User facial expressions and tone of voice

[0354] Output: Collected emotion data

[0355] Specific behavior:

[0356] The device activates the camera and voice recognition devices.

[0357] The device analyzes the user's facial expressions and tone of voice to collect emotional data.

[0358] Step 6:

[0359] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the search query accordingly. For example, if the user has a confused expression, the server modifies the search query to make it simpler to explain.

[0360] Input: Collected sentiment data, generated search queries

[0361] Output: Adjusted search query

[0362] Specific behavior:

[0363] The server receives the emotion data.

[0364] The server adjusts search queries based on sentiment data

[0365] Step 7:

[0366] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it generates annotations such as, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0367] Input: Tailored search queries, related information, user preference information, sentiment data

[0368] Output: Generated annotations

[0369] Specific behavior:

[0370] The server analyzes the relevant information, parameters, and emotion data.

[0371] The server generates the best annotation

[0372] Step 8:

[0373] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[0374] Input: Generated annotation data

[0375] Output: Annotations that are visible to the user

[0376] Specific behavior:

[0377] The server sends the annotation data to the device.

[0378] The device displays the annotation data

[0379] Step 9:

[0380] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0381] Input: User usage data

[0382] Output: Improved annotation generation algorithm

[0383] Specific behavior:

[0384] Device monitors usage

[0385] The device sends usage data to the server

[0386] The server analyzes the data and trains and optimizes the algorithm.

[0387] (Application example 2)

[0388] 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."

[0389] While conventional annotation generation systems can generate annotations based on a user's knowledge level and areas of interest, they cannot provide optimal annotations that take into account the user's emotional state. This can lead to users finding it difficult to understand or becoming confused, resulting in reduced learning efficiency.

[0390] Furthermore, existing systems lack the flexibility to respond to user emotions, such as providing simpler explanations to confused users. This leads to a poor user experience. To address these issues, a new system is needed that can recognize user emotions and adjust annotation content accordingly.

[0391] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0392] In this invention, the server includes: a setting means for a user to set his / her knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating an annotation based on parameters set by the user; a display means for displaying the generated annotation to the user; a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means; an emotion recognition means for recognizing the user's emotions; and a query adjustment means for adjusting the search query based on emotion data obtained by the emotion recognition means. This makes it possible to provide optimal annotations according to the user's emotional state as well as their knowledge level and field of interest.

[0393] The "setting means" is a means for providing a function for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[0394] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[0395] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[0396] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means, and generating annotations based on the parameters set by the user.

[0397] The "display means" is a means for displaying the generated annotation to the user.

[0398] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[0399] The "emotion recognition means" is a means including a sensor and an analysis device for recognizing the user's emotions.

[0400] The "query adjustment means" is a means for adjusting a search query based on emotion data acquired by the emotion recognition means.

[0401] This invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using an emotion recognition function. This system includes a setting means, an input means, a search means, an annotation generation means, a display means, a learning means, an emotion recognition means, and a query adjustment means.

[0402] 1. Program Generation

[0403] The system for realizing this invention is composed of the following programs: First, a user inputs their knowledge level, field of interest, and annotation depth using the setting means. Then, they input the sentence or document they want to annotate using the input means. Based on this data, the search means generates an appropriate search query and searches for related information from the Internet or an internal database.

[0404] The retrieved information is analyzed and organized by the annotation generation means, and annotations are generated based on the user's set parameters. The generated annotations are displayed to the user by the display means. Furthermore, the learning means monitors the user's usage status and continuously updates the algorithm of the annotation generation means. The emotion recognition means also plays an important role in this invention. The emotion data acquired by the emotion recognition means is analyzed by the query adjustment means, and the search query is adjusted.

[0405] 2. Program processing explanation

[0406] The system is realized by combining multiple pieces of hardware and software, the details of which are explained below.

[0407] Hardware

[0408] Device: A device used by a user to set up or input information (e.g., smartphone, tablet, computer)

[0409] Server: Generates search queries, finds relevant information, generates annotations, stores data, and learns from it.

[0410] Emotion recognition sensors: Cameras and voice recognition devices to recognize user emotions

[0411] software

[0412] Settings and input app: An interface for users to set their knowledge level, areas of interest, and annotation depth, and then input sentences and documents.

[0413] Search algorithms: Software that generates search queries based on user preferences and input data to find relevant information.

[0414] Annotation generation algorithm: Software for analyzing and organizing retrieved information and generating annotations

[0415] Viewer app: An interface for displaying generated annotations to the user.

[0416] Learning algorithm: Software for monitoring user usage and updating the annotation generation algorithm

[0417] Emotion recognition algorithms: Software for analyzing user emotions and adjusting search queries based on the acquired emotional data.

[0418] These hardware and software are integrated to provide optimal annotations according to the user's knowledge level, areas of interest, and even emotions.

[0419] 3. Specific Examples

[0420] The following examples are used to illustrate how the invention may be put into practice.

[0421] Example 1:

[0422] If a user is interested in intermediate level chemistry and wants to generate annotations on "how lithium ion batteries work," the system works as follows:

[0423] 1. Settings: The user sets the knowledge level to "Intermediate", the area of ​​interest to "Chemistry", and the annotation depth to "Detailed".

[0424] 2. Input: Enter the sentence "How lithium-ion batteries work."

[0425] 3. Emotion Recognition: Detects confused facial expressions of the user.

[0426] 4. Query generation: Generate a search query based on “Lithium ion battery intermediate working principle.”

[0427] 5. Information retrieval: Searching for information from the internet and internal databases.

[0428] 6. Annotation generation: Annotations are generated in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[0429] 7. Display: Show the generated annotations to the user.

[0430] Example prompt sentence:

[0431] By inputting the following prompt sentence into the generative AI model, the optimal annotation will be generated.

[0432] Lithium-ion Battery Working Principle Intermediate Chemistry

[0433] In this way, the efficiency of learning and understanding can be improved by providing optimal annotations based on the user's knowledge level, areas of interest, and emotional state.

[0434] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0435] Program processing steps

[0436] Step 1:

[0437] The user uses the setting means to set his / her knowledge level, field of interest, and depth of annotation.

[0438] Input: Knowledge level, area of ​​interest, depth of annotation

[0439] Output: User profile (e.g. {"knowledge_level": "Intermediate", "interest_field": "Chemistry", "annotation_depth": "Detailed"})

[0440] Specifically, a user opens the application's settings screen, selects their knowledge level (beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics), and annotation depth (overview, detailed, specialized), and then presses the save button. This information is saved in the database as a user profile.

[0441] Step 2:

[0442] The user uses the input means to input a sentence or document to which the user wishes to add an annotation.

[0443] Input: A sentence or document (e.g., "How a lithium-ion battery works")

[0444] Output: User input data

[0445] Specifically, the user types the sentence or document they want to annotate into the text input field and presses the enter key. The entered data is sent to the server along with the user ID.

[0446] Step 3:

[0447] The terminal recognizes the user's emotions using the emotion recognition means.

[0448] Input: User facial and voice data

[0449] Output: Emotion data (e.g., "confused")

[0450] Specifically, the device's built-in camera and microphone collect the user's facial expressions and voice in real time, which are then analyzed using an emotion recognition algorithm. The analysis results determine whether the user is confused or not, and emotional data is generated.

[0451] Step 4:

[0452] The server generates a search query based on the data obtained from the setting means and the input means, and further adjusts the search query based on emotion data, if any.

[0453] Input: User profile, user input data, emotion data

[0454] Output: Adjusted search query (e.g., "Lithium-ion battery intermediate working principle easy")

[0455] Specifically, the server generates an initial search query based on the user profile and input data. It then checks the emotion data and adjusts the query, such as adding "easy" if the user is confused.

[0456] Step 5:

[0457] The server uses the tailored search query to search for relevant information.

[0458] Input: Adjusted search query

[0459] Output: Search result data (e.g., search result list)

[0460] Specifically, the server submits tailored search queries to the internet and internal databases to gather relevant information, and the search results list is scored and filtered based on the relevance of the information.

[0461] Step 6:

[0462] The server analyzes and organizes the relevant information retrieved by the search tool and generates annotations based on the user's set parameters.

[0463] Input: Search result data, user profile

[0464] Output: Annotation data (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.")

[0465] Specifically, the server generates annotations based on the search result list, tailored to the user's knowledge level and area of ​​interest. For example, an intermediate-level user might be provided with annotations that include more detailed and technical content.

[0466] Step 7:

[0467] The server transmits the generated annotations to the user terminal, which displays them to the user.

[0468] Input: annotation data

[0469] Output: Display annotations

[0470] Specifically, the generated annotation data is sent from the server to the user's terminal and displayed to the user through a display application on the terminal. The user can check the annotations in a pop-up format or a tooltip format.

[0471] Step 8:

[0472] The device monitors the user's usage and sends the data to the server, which then updates the annotation generation algorithm based on the data.

[0473] Input: Usage data (e.g., browsing time, clicks)

[0474] Output: Updated algorithm

[0475] Specifically, the device records how long the user views the annotation, which parts they clicked on, how often they viewed it, and so on, and sends this information to the server. The server analyzes this data and continues to improve the annotation generation algorithm.

[0476] Through these steps, it is possible to provide annotations that are optimal for the user's knowledge level, areas of interest, and emotional state.

[0477] 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.

[0478] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0479] 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.

[0480] [Second embodiment]

[0481] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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).

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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.

[0492] 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."

[0493] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and has a learning function that improves the accuracy of the annotation generation. Specific embodiments of this system are described below.

[0494] User parameter settings

[0495] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), areas of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is saved as the user's individual profile.

[0496] Text Input

[0497] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[0498] Generating a search query

[0499] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate working principle" will be generated.

[0500] Search for related information

[0501] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0502] Annotation Generation

[0503] The server generates annotations based on the analyzed and filtered information and the user's set parameters. For example, if an intermediate-level explanation of lithium-ion batteries is required, the server generates text in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The intermediate-level points are ____."

[0504] Viewing annotations

[0505] The generated annotations are sent from the server to the terminal, which displays them to the user, who can view them in the form of popups or tooltips, for example, by highlighting the annotated portion of the original text.

[0506] Usage monitoring and learning

[0507] As users use annotations, their usage (e.g., view time, clicks, frequency of viewing, etc.) is sent from the device to the server, which uses this data to continuously learn and optimize the annotation generation algorithm, improving the accuracy and relevance of annotations over time.

[0508] Specific examples

[0509] As a specific example, consider the case where a user inputs the question "How does a lithium-ion battery work?"

[0510] 1. The user has an intermediate level of science knowledge.

[0511] 2. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information from the internet and databases.

[0512] 3. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[0513] 4. The server sends the annotations to the terminal, which displays them to the user.

[0514] 5. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[0515] In this way, the present invention provides a system that contributes to the promotion of personalized learning and communication.

[0516] The processing flow will be explained below.

[0517] Step 1:

[0518] The user opens the system's settings screen and enters their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). The settings information is saved as the user's individual profile.

[0519] Step 2:

[0520] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[0521] Step 3:

[0522] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[0523] Step 4:

[0524] The terminal sends the entered text data and user ID to the server, which receives it.

[0525] Step 5:

[0526] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[0527] Step 6:

[0528] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0529] Step 7:

[0530] The server analyzes the collected information and filters and formats it based on the user's knowledge level and areas of interest, thereby extracting annotation information appropriate for the user.

[0531] Step 8:

[0532] The server generates annotations based on the analyzed information. For example, it might generate annotations like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0533] Step 9:

[0534] The server sends the generated annotations to the terminal, which then displays them to the user. The user can view the annotations in a popup or tooltip format.

[0535] Step 10:

[0536] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[0537] Step 11:

[0538] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0539] Through these steps, our system efficiently generates and provides annotations optimized for each user, allowing users with different knowledge levels and areas of interest to easily obtain information and annotations that are appropriate for them.

[0540] Example 1

[0541] 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."

[0542] Conventional annotation generation systems have the difficulty of providing individualized annotations tailored to the user's knowledge level or area of ​​interest, and are only able to provide general information. Another problem is that they lack the ability to continuously train the annotation generation algorithm based on the user's usage, making it difficult to expect long-term accuracy improvements.

[0543] 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.

[0544] In this invention, the server includes: a setting means for a user to set their own knowledge level, areas of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the acquired related information using a generative AI model and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide highly accurate annotations suited to the knowledge level and areas of interest of each individual user, and the accuracy and relevance of the annotation generation can be improved over time.

[0545] A "user" is someone who uses the system to obtain annotations based on their level of knowledge and areas of interest.

[0546] The "setting means" refers to an interface that allows a user to input parameters such as his / her knowledge level, areas of interest, and annotation depth.

[0547] "Input means" refers to an interface through which a user inputs a sentence or document to be annotated.

[0548] The "search means" refers to a function that generates a search query based on data obtained from the setting means and the input means, and searches for related information.

[0549] A "generative AI model" is a type of artificial intelligence used to generate text for annotation generation.

[0550] "Annotation generation means" refers to a function that analyzes the relevant information obtained using a generative AI model and generates annotations based on the user's set parameters.

[0551] "Display means" refers to an interface for visually presenting the generated annotations to the user.

[0552] The "learning means" refers to a function for monitoring user usage and updating the algorithm of the annotation generation means.

[0553] "Transmission means" refers to a function for transmitting the text data entered by the user and the user identification information to the server.

[0554] The "receiving means" refers to a function for presenting annotation data received from the server to the user.

[0555] This invention is a system that automatically generates annotations based on each user's knowledge level and area of ​​interest, and has a learning function that improves the accuracy of the annotation generation.

[0556] 1. Setting user parameters

[0557] First, the user opens the system's settings screen and sets their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This information is sent to the server via the "settings tool" and saved as the user's profile. Databases such as "Elasticsearch" and "MongoDB" are used.

[0558] 2. Enter text

[0559] Next, the user enters the sentence or document they want to annotate into the system's text input field. For example, if they want to annotate on the topic "Principles of operation of lithium-ion batteries," they simply enter the text. This information is sent to the server via the "input means."

[0560] 3. Generating search queries

[0561] The server generates an appropriate search query based on the received user settings and the entered text. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate operating principle" is generated. Python and Elasticsearch are used to generate the search query.

[0562] 4. Searching for related information

[0563] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting and filtering data from multiple sources, using databases such as Google Scholar and JSTOR.

[0564] 5. Generating Annotations

[0565] The server generates annotations based on the collected and filtered information, in line with the user's set parameters. This is done using a "generative AI model," such as GPT-3. The specific annotation generated is, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes."

[0566] 6. Viewing annotations

[0567] The generated annotations are sent from the server to the device, which then displays them to the user. The annotations are provided in pop-up or tooltip format, and the user can check them by clicking or touching them. Web technologies such as HTML, CSS, and JavaScript are used for display.

[0568] 7. Usage monitoring and learning

[0569] When a user uses annotations, their device sends usage information, such as reference time, clicks, and frequency of viewing, to the server. The server uses this data to train and optimize the annotation generation algorithm. This process uses TensorFlow and PyTorch, allowing the accuracy and relevance of annotations to improve over time.

[0570] Specific examples

[0571] Here is a concrete example of how a lithium-ion battery works:

[0572] 1. The user has an intermediate level of science knowledge.

[0573] 2. The user types the question, "What is the working principle of a lithium-ion battery?"

[0574] 3. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information.

[0575] 4. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[0576] 5. The server sends the annotations to the terminal, which displays them to the user.

[0577] 6. When a user refers to the annotations and obtains information, the usage status is sent to the server and processed as learning data.

[0578] Prompt Sentence Examples

[0579] "Generate detailed annotations for users with intermediate scientific knowledge on the working principles of lithium-ion batteries, including how lithium ions move and the process of energy generation."

[0580] In this way, the present invention can promote personalized learning and communication, providing optimal annotations for each user.

[0581] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0582] Step 1:

[0583] The user opens the system's setting screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). These inputs are sent to the server through the setting means. The server stores the received data in a database and manages it as a user profile. After the setting information is saved, the server sends a confirmation message to the user (input: user setting information, output: confirmation message).

[0584] Step 2:

[0585] The user inputs the sentence or document they want to annotate into the system's text input field. This information is sent to the server via the input means. For example, a sentence about "the working principle of lithium-ion batteries" is input. The server receives the text data and saves it for analysis (input: user's text data, output: saved text data).

[0586] Step 3:

[0587] The server generates an appropriate search query based on the received user settings and the input text data. In this example, if the user's knowledge level is intermediate and their field of interest is chemistry, a query such as "lithium ion battery intermediate operating principle" is generated. This process is performed using a Python script (input: user settings and text data, output: generated search query).

[0588] Step 4:

[0589] The server uses the generated search query to search for relevant information from the Internet and internal databases. The search query is passed to the Elasticsearch engine, which filters relevant documents from the index. As a result, multiple pieces of relevant information are collected from the Internet (e.g., Google Scholar) (Input: Generated search query, Output: Collected relevant information).

[0590] Step 5:

[0591] The server generates annotations based on the collected and filtered information and the user's set parameters. This process uses a "generative AI model." For example, the AI ​​model "GPT-3" is selected, and annotations are generated based on prompt statements. For example, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes" is generated (input: collected related information, output: generated annotation).

[0592] Step 6:

[0593] The generated annotations are sent from the server to the terminal, where they are displayed to the user in a popup or tooltip format along with the original input text. For example, the original text is displayed on a web page, and the annotations are displayed in tooltip format nearby (input: generated annotations, output: annotations displayed to the user).

[0594] Step 7:

[0595] When a user uses annotations, their usage (e.g., time spent viewing, number of clicks, frequency of viewing, etc.) is sent from the device to the server. The server analyzes this data and updates the annotation generation algorithm. This process involves machine learning using TensorFlow and PyTorch, which improves the accuracy and relevance of annotations over time (input: user usage data, output: optimized annotation generation algorithm).

[0596] (Application example 1)

[0597] 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."

[0598] Conventional annotation generation systems have difficulty providing information tailored to the user's knowledge level and areas of interest, and especially in physical stores, there is a lack of efficient ways for users to obtain the information they are looking for. In addition, it is difficult to provide product information in real time, and there is a need to improve the user experience.

[0599] 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.

[0600] In this invention, the server includes: a setting means for a user to set their own knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; a visual information collection means for collecting product information using a visual display device worn by the user and generating annotations based on the user's setting information; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This enables users to obtain product information in real time at a physical store and obtain annotations optimized for their own knowledge level and field of interest.

[0601] The "setting means" is a means for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[0602] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[0603] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[0604] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means and generating annotations based on the parameters set by the user.

[0605] The "display means" is a means for displaying the generated annotation to the user.

[0606] The "visual information gathering means" is a means for gathering product information using a visual display device worn by the user and generating annotations based on the user's settings.

[0607] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[0608] The "transmission means" is a means for transmitting the text data entered by the user and the user ID to the server.

[0609] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[0610] A "search query" is a question for information search that is generated based on the user's knowledge level and areas of interest.

[0611] A "server" is a host computer for data processing and storage.

[0612] A "visual display device" is a device worn by a user that visually displays information.

[0613] The present invention provides a system for generating annotation information based on a user's knowledge level and areas of interest, thereby improving the user experience in a physical store. Detailed embodiments for realizing this system are described below.

[0614] User parameter settings

[0615] The user sets his / her knowledge level (e.g., beginner, intermediate, advanced), interest area (e.g., wine, cosmetics, technical products, etc.), and annotation depth (e.g., overview, detailed, specialized) through the setting screen of the smart glasses. This setting information is stored on the visual display device and on the server.

[0616] Collecting product information

[0617] When a user wears smart glasses and walks around a physical store, the camera captures product information in real time using the visual information collection means. For example, if a user sees a particular wine in the wine section, image data recognizing that product is acquired.

[0618] Generating a search query

[0619] The server generates an appropriate search query based on the product data acquired by the visual information gathering means and the user's settings. For example, it creates a search query such as "Bordeaux wine, mid-range, taste characteristics."

[0620] Search for related information

[0621] The server then searches for relevant information from the internet and internal databases based on the generated search query, using a search engine such as Elasticsearch.

[0622] Annotation Generation

[0623] The server analyzes the relevant information obtained through the search tool and generates annotations based on the user's set parameters. This analysis process uses a generative AI model (such as GPT or BERT). A specific example of an annotation generated is the following: "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon."

[0624] Viewing annotations

[0625] The generated annotation information is transmitted from the server to the smart glasses and displayed to the user in real time.

[0626] Usage monitoring and learning

[0627] As users browse the annotations displayed and access additional information, their usage is monitored, including viewing time, number of clicks, etc. This data is stored on the server to help train and continuously optimize the annotation generation algorithm.

[0628] Examples and prompts

[0629] As a concrete example, consider the case where a user looks at "a specific wine":

[0630] Configuration information

[0631] Knowledge level: Intermediate

[0632] Interests: Wine

[0633] Annotation Depth:Details

[0634] Prompt Sentence Examples

[0635] If the user is looking at a "specific wine":

[0636] User Settings:

[0637] Knowledge level: Intermediate

[0638] Interests: Wine

[0639] Annotation Depth: Detailed

[0640] Generated notes: "This particular wine is a red wine from a prestigious winery in the Bordeaux region of France. This vintage is particularly outstanding, dominated by Cabernet Sauvignon, with a perfect balance of berry fruit and tannins."

[0641] As described above, the present invention provides a system that enables users to obtain product information in real time at a physical store and obtain annotation information that is suited to their own level of knowledge and areas of interest.

[0642] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0643] Step 1:

[0644] The user opens the settings screen of the smart glasses and sets their knowledge level, areas of interest, and annotation depth.

[0645] Input: User knowledge level (e.g., intermediate), area of ​​interest (e.g., wine), depth of annotation (e.g., detailed)

[0646] Output: Configuration information (user profile)

[0647] Step 2:

[0648] The user wears the smart glasses in a physical store and captures the product on the camera using a visual information collection means.

[0649] Input: Product image captured by the smart glasses camera

[0650] Output: Product recognition data (image data)

[0651] Step 3:

[0652] The server receives the product data acquired by the visual information gathering means and the user's setting data, and generates an appropriate search query.

[0653] Input: Product recognition data, user profile

[0654] Data processing / data calculation: Image recognition processing using OpenCV, query generation based on user settings

[0655] Output: Search query (e.g., "Wine Bordeaux mid-range flavor profile")

[0656] Step 4:

[0657] The server searches for relevant information from the Internet and internal databases based on the generated search query.

[0658] Input: search query

[0659] Data processing / data calculation: Finding relevant information using Elasticsearch

[0660] Output: Related information (collection of information from multiple data sources)

[0661] Step 5:

[0662] The server analyzes the relevant information obtained by the search means and generates annotations based on user-specified parameters.

[0663] Input: Related information, User profile

[0664] Data processing / data calculation: annotation generation using generative AI models (e.g., GPT, BERT)

[0665] Output: Generated annotations (e.g., "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon.")

[0666] Step 6:

[0667] The server sends the generated annotations to the smart glasses, which display them to the user in real time.

[0668] Input: Generated annotation data

[0669] Output: Visual display of annotation information (displayed on smart glasses)

[0670] Step 7:

[0671] The server monitors the user's usage and continuously learns and optimizes the annotation generation algorithm.

[0672] Input: User operation data (viewing time, number of clicks, etc.)

[0673] Data processing / data calculation: Analysis of user operation data, model updating using machine learning algorithms

[0674] Output: Improved annotation generation algorithm

[0675] This series of processes allows users to obtain product information in real time at a physical store and obtain annotation information customized to their own knowledge level and areas of interest.

[0676] 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.

[0677] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[0678] User parameter settings

[0679] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is stored in the database as the user's individual profile.

[0680] Text Input

[0681] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[0682] Generating a search query

[0683] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[0684] Search for related information

[0685] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0686] emotion recognition

[0687] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0688] Analyzing sentiment data and adjusting search queries

[0689] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[0690] Annotation Generation

[0691] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0692] Viewing annotations

[0693] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[0694] Usage monitoring and learning

[0695] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0696] Specific examples

[0697] For example, consider the case where a user enters a question about "how lithium ion batteries work."

[0698] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[0699] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[0700] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[0701] 4. The server adjusts the search query to simplify it based on the sentiment data.

[0702] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[0703] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[0704] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[0705] In this way, the present invention improves the quality of learning and communication by creating and providing optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest.

[0706] The processing flow will be explained below.

[0707] Step 1:

[0708] The user opens the system's settings screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This setting information is then saved in the database as the user's individual profile.

[0709] Step 2:

[0710] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[0711] Step 3:

[0712] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[0713] Step 4:

[0714] The terminal sends the entered text data and user ID to the server, which receives it.

[0715] Step 5:

[0716] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[0717] Step 6:

[0718] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0719] Step 7:

[0720] The device collects data from sensors (cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0721] Step 8:

[0722] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[0723] Step 9:

[0724] The server generates annotations based on the analyzed information, incorporating set parameters and emotional data. For example, it might generate an annotation like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0725] Step 10:

[0726] The server sends the generated annotations to the terminal, which receives them and displays them to the user, who can view them in popup or tooltip format.

[0727] Step 11:

[0728] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[0729] Step 12:

[0730] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0731] Through these steps, our system efficiently generates and provides annotations optimized for each user, enabling information provision tailored to different knowledge levels and areas of interest. Further optimization according to the user's emotional state improves the quality of learning and communication.

[0732] Example 2

[0733] 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."

[0734] In today's information-saturated society, it is difficult for users to efficiently obtain information appropriate to their own knowledge level and areas of interest. Furthermore, while it is important to provide annotations that reflect the user's emotional state, existing systems do not adequately fulfill this requirement. As a result, users are unable to obtain information that is optimal for them, reducing the effectiveness of learning and information gathering. Therefore, there is a need for an annotation generation system that is appropriate for the user's knowledge level, areas of interest, and emotional state.

[0735] 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.

[0736] In this invention, the server includes a setting means for a user to set his / her knowledge level, field of interest, and annotation depth, an input means for a user to input a sentence or document to which the user wants to annotate, a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information, an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters and emotional data, an emotion recognition means for recognizing the user's emotions and collecting that data, a display means for displaying the generated annotations to the user, and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide optimal information based on the user's knowledge level, field of interest, and emotional state.

[0737] The "setting means" is a means for a user to input his / her own knowledge level, field of interest, and depth of annotation, and store it in the database.

[0738] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[0739] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[0740] The "annotation generation means" is a means for analyzing and organizing the related information acquired by the search means, and generating appropriate annotations based on the user's set parameters and emotion data.

[0741] The "display means" is a means for visually presenting the generated annotation to the user.

[0742] The "learning means" is a means for monitoring user usage and using that data to continuously learn and update the algorithms of the annotation generation means.

[0743] The "transmission means" is a means for transmitting the text data, user ID, and emotion data input by the user to the server.

[0744] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[0745] An "emotion recognition means" is a means using sensors and software to recognize and collect the user's emotional state.

[0746] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[0747] User parameter settings

[0748] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is then saved in the database by the terminal as the user's individual profile.

[0749] Text Input

[0750] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text. The device then sends the entered text to the server.

[0751] Generating a search query

[0752] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[0753] Search for related information

[0754] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0755] emotion recognition

[0756] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0757] Analyzing sentiment data and adjusting search queries

[0758] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[0759] Annotation Generation

[0760] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0761] Viewing annotations

[0762] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[0763] Usage monitoring and learning

[0764] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0765] Specific examples

[0766] For example, consider the case where a user inputs a question about "how lithium-ion batteries work."

[0767] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[0768] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[0769] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[0770] 4. The server adjusts the search query to simplify it based on the sentiment data.

[0771] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[0772] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[0773] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[0774] Prompt Sentence Examples

[0775] "Please provide an intermediate level explanation of how lithium-ion batteries work. If users are confused, simplify the explanation."

[0776] "Generate detailed annotations in the chemical domain based on user sentiment data."

[0777] In this way, the present invention creates and provides optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest, thereby improving the quality of learning and communication.

[0778] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0779] Step 1:

[0780] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). The terminal receives these settings and stores them in a database. This setting information is used for subsequent processing.

[0781] Input: User knowledge level, areas of interest, depth of annotations

[0782] Output: User preferences stored in the database

[0783] Specific behavior:

[0784] The user accesses the settings screen

[0785] The user enters the settings.

[0786] The device saves the configuration information in a database

[0787] Step 2:

[0788] The user enters the sentence or document they want to annotate into the text entry field of the system, and the device receives the entered text and sends it to the server.

[0789] Input: The sentence or document you want to annotate

[0790] Output: Text data sent to the server

[0791] Specific behavior:

[0792] The user types text into the text field

[0793] The device sends the entered text to the server

[0794] Step 3:

[0795] The server generates a search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, the server generates a search query such as "Lithium-ion battery intermediate working principle."

[0796] Input: Text data, user setting information

[0797] Output: Generated search query

[0798] Specific behavior:

[0799] The server parses the text data and configuration information

[0800] The server generates a search query based on the analysis results.

[0801] Step 4:

[0802] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0803] Input: Search query

[0804] Output: Filtered relevant information

[0805] Specific behavior:

[0806] The server sends the search query to the internet or to an internal database

[0807] The server collects and filters the information obtained

[0808] Step 5:

[0809] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[0810] Input: User facial expressions and tone of voice

[0811] Output: Collected emotion data

[0812] Specific behavior:

[0813] The device activates the camera and voice recognition devices.

[0814] The device analyzes the user's facial expressions and tone of voice to collect emotional data.

[0815] Step 6:

[0816] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the search query accordingly. For example, if the user has a confused expression, the server modifies the search query to make it simpler to explain.

[0817] Input: Collected sentiment data, generated search queries

[0818] Output: Adjusted search query

[0819] Specific behavior:

[0820] The server receives the emotion data.

[0821] The server adjusts search queries based on sentiment data

[0822] Step 7:

[0823] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it generates annotations such as, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0824] Input: Tailored search queries, related information, user preference information, sentiment data

[0825] Output: Generated annotations

[0826] Specific behavior:

[0827] The server analyzes the relevant information, parameters, and emotion data.

[0828] The server generates the best annotation

[0829] Step 8:

[0830] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[0831] Input: Generated annotation data

[0832] Output: Annotations that are visible to the user

[0833] Specific behavior:

[0834] The server sends the annotation data to the device.

[0835] The device displays the annotation data

[0836] Step 9:

[0837] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0838] Input: User usage data

[0839] Output: Improved annotation generation algorithm

[0840] Specific behavior:

[0841] Device monitors usage

[0842] The device sends usage data to the server

[0843] The server analyzes the data and trains and optimizes the algorithm.

[0844] (Application example 2)

[0845] 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."

[0846] While conventional annotation generation systems can generate annotations based on a user's knowledge level and areas of interest, they cannot provide optimal annotations that take into account the user's emotional state. This can lead to users finding it difficult to understand or becoming confused, resulting in reduced learning efficiency.

[0847] Furthermore, existing systems lack the flexibility to respond to user emotions, such as providing simpler explanations to confused users. This leads to a poor user experience. To address these issues, a new system is needed that can recognize user emotions and adjust annotation content accordingly.

[0848] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0849] In this invention, the server includes: a setting means for a user to set his / her knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating an annotation based on parameters set by the user; a display means for displaying the generated annotation to the user; a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means; an emotion recognition means for recognizing the user's emotions; and a query adjustment means for adjusting the search query based on emotion data obtained by the emotion recognition means. This makes it possible to provide optimal annotations according to the user's emotional state as well as their knowledge level and field of interest.

[0850] The "setting means" is a means for providing a function for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[0851] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[0852] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[0853] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means, and generating annotations based on the parameters set by the user.

[0854] The "display means" is a means for displaying the generated annotation to the user.

[0855] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[0856] The "emotion recognition means" is a means including a sensor and an analysis device for recognizing the user's emotions.

[0857] The "query adjustment means" is a means for adjusting a search query based on emotion data acquired by the emotion recognition means.

[0858] This invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using an emotion recognition function. This system includes a setting means, an input means, a search means, an annotation generation means, a display means, a learning means, an emotion recognition means, and a query adjustment means.

[0859] 1. Program Generation

[0860] The system for realizing this invention is composed of the following programs: First, a user inputs their knowledge level, field of interest, and annotation depth using the setting means. Then, they input the sentence or document they want to annotate using the input means. Based on this data, the search means generates an appropriate search query and searches for related information from the Internet or an internal database.

[0861] The retrieved information is analyzed and organized by the annotation generation means, and annotations are generated based on the user's set parameters. The generated annotations are displayed to the user by the display means. Furthermore, the learning means monitors the user's usage status and continuously updates the algorithm of the annotation generation means. The emotion recognition means also plays an important role in this invention. The emotion data acquired by the emotion recognition means is analyzed by the query adjustment means, and the search query is adjusted.

[0862] 2. Program processing explanation

[0863] The system is realized by combining multiple pieces of hardware and software, the details of which are explained below.

[0864] Hardware

[0865] Device: A device used by a user to set up or input information (e.g., smartphone, tablet, computer)

[0866] Server: Generates search queries, finds relevant information, generates annotations, stores data, and learns from it.

[0867] Emotion recognition sensors: Cameras and voice recognition devices to recognize user emotions

[0868] software

[0869] Settings and input app: An interface for users to set their knowledge level, areas of interest, and annotation depth, and then input sentences and documents.

[0870] Search algorithms: Software that generates search queries based on user preferences and input data to find relevant information.

[0871] Annotation generation algorithm: Software for analyzing and organizing retrieved information and generating annotations

[0872] Viewer app: An interface for displaying generated annotations to the user.

[0873] Learning algorithm: Software for monitoring user usage and updating the annotation generation algorithm

[0874] Emotion recognition algorithms: Software for analyzing user emotions and adjusting search queries based on the acquired emotional data.

[0875] These hardware and software are integrated to provide optimal annotations according to the user's knowledge level, areas of interest, and even emotions.

[0876] 3. Specific Examples

[0877] The following examples are used to illustrate how the invention may be put into practice.

[0878] Example 1:

[0879] If a user is interested in intermediate level chemistry and wants to generate annotations on "how lithium ion batteries work," the system works as follows:

[0880] 1. Settings: The user sets the knowledge level to "Intermediate", the area of ​​interest to "Chemistry", and the annotation depth to "Detailed".

[0881] 2. Input: Enter the sentence "How lithium-ion batteries work."

[0882] 3. Emotion Recognition: Detects confused facial expressions of the user.

[0883] 4. Query generation: Generate a search query based on “Lithium ion battery intermediate working principle.”

[0884] 5. Information retrieval: Searching for information from the internet and internal databases.

[0885] 6. Annotation generation: Annotations are generated in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[0886] 7. Display: Show the generated annotations to the user.

[0887] Example prompt sentence:

[0888] By inputting the following prompt sentence into the generative AI model, the optimal annotation will be generated.

[0889] Lithium-ion Battery Working Principle Intermediate Chemistry

[0890] In this way, the efficiency of learning and understanding can be improved by providing optimal annotations based on the user's knowledge level, areas of interest, and emotional state.

[0891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0892] Program processing steps

[0893] Step 1:

[0894] The user uses the setting means to set his / her knowledge level, field of interest, and depth of annotation.

[0895] Input: Knowledge level, area of ​​interest, depth of annotation

[0896] Output: User profile (e.g. {"knowledge_level": "Intermediate", "interest_field": "Chemistry", "annotation_depth": "Detailed"})

[0897] Specifically, a user opens the application's settings screen, selects their knowledge level (beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics), and annotation depth (overview, detailed, specialized), and then presses the save button. This information is saved in the database as a user profile.

[0898] Step 2:

[0899] The user uses the input means to input a sentence or document to which the user wishes to add an annotation.

[0900] Input: A sentence or document (e.g., "How a lithium-ion battery works")

[0901] Output: User input data

[0902] Specifically, the user types the sentence or document they want to annotate into the text input field and presses the enter key. The entered data is sent to the server along with the user ID.

[0903] Step 3:

[0904] The terminal recognizes the user's emotions using the emotion recognition means.

[0905] Input: User facial and voice data

[0906] Output: Emotion data (e.g., "confused")

[0907] Specifically, the device's built-in camera and microphone collect the user's facial expressions and voice in real time, which are then analyzed using an emotion recognition algorithm. The analysis results determine whether the user is confused or not, and emotional data is generated.

[0908] Step 4:

[0909] The server generates a search query based on the data obtained from the setting means and the input means, and further adjusts the search query based on emotion data, if any.

[0910] Input: User profile, user input data, emotion data

[0911] Output: Adjusted search query (e.g., "Lithium-ion battery intermediate working principle easy")

[0912] Specifically, the server generates an initial search query based on the user profile and input data. It then checks the emotion data and adjusts the query, such as adding "easy" if the user is confused.

[0913] Step 5:

[0914] The server uses the tailored search query to search for relevant information.

[0915] Input: Adjusted search query

[0916] Output: Search result data (e.g., search result list)

[0917] Specifically, the server submits tailored search queries to the internet and internal databases to gather relevant information, and the search results list is scored and filtered based on the relevance of the information.

[0918] Step 6:

[0919] The server analyzes and organizes the relevant information retrieved by the search tool and generates annotations based on the user's set parameters.

[0920] Input: Search result data, user profile

[0921] Output: Annotation data (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.")

[0922] Specifically, the server generates annotations based on the search result list, tailored to the user's knowledge level and area of ​​interest. For example, an intermediate-level user might be provided with annotations that include more detailed and technical content.

[0923] Step 7:

[0924] The server transmits the generated annotations to the user terminal, which displays them to the user.

[0925] Input: annotation data

[0926] Output: Display annotations

[0927] Specifically, the generated annotation data is sent from the server to the user's terminal and displayed to the user through a display application on the terminal. The user can check the annotations in a pop-up format or a tooltip format.

[0928] Step 8:

[0929] The device monitors the user's usage and sends the data to the server, which then updates the annotation generation algorithm based on the data.

[0930] Input: Usage data (e.g., browsing time, clicks)

[0931] Output: Updated algorithm

[0932] Specifically, the device records how long the user views the annotation, which parts they clicked on, how often they viewed it, and so on, and sends this information to the server. The server analyzes this data and continues to improve the annotation generation algorithm.

[0933] Through these steps, it is possible to provide annotations that are optimal for the user's knowledge level, areas of interest, and emotional state.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] [Third embodiment]

[0938] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0939] 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.

[0940] 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).

[0941] 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.

[0942] 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.

[0943] 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).

[0944] 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.

[0945] 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.

[0946] 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.

[0947] 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.

[0948] 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.

[0949] 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."

[0950] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and has a learning function that improves the accuracy of the annotation generation. Specific embodiments of this system are described below.

[0951] User parameter settings

[0952] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), areas of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is saved as the user's individual profile.

[0953] Text Input

[0954] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[0955] Generating a search query

[0956] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate working principle" will be generated.

[0957] Search for related information

[0958] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0959] Annotation Generation

[0960] The server generates annotations based on the analyzed and filtered information and the user's set parameters. For example, if an intermediate-level explanation of lithium-ion batteries is required, the server generates text in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The intermediate-level points are ____."

[0961] Viewing annotations

[0962] The generated annotations are sent from the server to the terminal, which displays them to the user, who can view them in the form of popups or tooltips, for example, by highlighting the annotated portion of the original text.

[0963] Usage monitoring and learning

[0964] As users use annotations, their usage (e.g., view time, clicks, frequency of viewing, etc.) is sent from the device to the server, which uses this data to continuously learn and optimize the annotation generation algorithm, improving the accuracy and relevance of annotations over time.

[0965] Specific examples

[0966] As a specific example, consider the case where a user inputs the question "How does a lithium-ion battery work?"

[0967] 1. The user has an intermediate level of science knowledge.

[0968] 2. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information from the internet and databases.

[0969] 3. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[0970] 4. The server sends the annotations to the terminal, which displays them to the user.

[0971] 5. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[0972] In this way, the present invention provides a system that contributes to the promotion of personalized learning and communication.

[0973] The processing flow will be explained below.

[0974] Step 1:

[0975] The user opens the system's settings screen and enters their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). The settings information is saved as the user's individual profile.

[0976] Step 2:

[0977] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[0978] Step 3:

[0979] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[0980] Step 4:

[0981] The terminal sends the entered text data and user ID to the server, which receives it.

[0982] Step 5:

[0983] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[0984] Step 6:

[0985] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[0986] Step 7:

[0987] The server analyzes the collected information and filters and formats it based on the user's knowledge level and areas of interest, thereby extracting annotation information appropriate for the user.

[0988] Step 8:

[0989] The server generates annotations based on the analyzed information. For example, it might generate annotations like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[0990] Step 9:

[0991] The server sends the generated annotations to the terminal, which then displays them to the user. The user can view the annotations in a popup or tooltip format.

[0992] Step 10:

[0993] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[0994] Step 11:

[0995] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[0996] Through these steps, our system efficiently generates and provides annotations optimized for each user, allowing users with different knowledge levels and areas of interest to easily obtain information and annotations that are appropriate for them.

[0997] Example 1

[0998] 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."

[0999] Conventional annotation generation systems have the difficulty of providing individualized annotations tailored to the user's knowledge level or area of ​​interest, and are only able to provide general information. Another problem is that they lack the ability to continuously train the annotation generation algorithm based on the user's usage, making it difficult to expect long-term accuracy improvements.

[1000] 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.

[1001] In this invention, the server includes: a setting means for a user to set their own knowledge level, areas of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the acquired related information using a generative AI model and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide highly accurate annotations suited to the knowledge level and areas of interest of each individual user, and the accuracy and relevance of the annotation generation can be improved over time.

[1002] A "user" is someone who uses the system to obtain annotations based on their level of knowledge and areas of interest.

[1003] The "setting means" refers to an interface that allows a user to input parameters such as his / her knowledge level, areas of interest, and annotation depth.

[1004] "Input means" refers to an interface through which a user inputs a sentence or document to be annotated.

[1005] The "search means" refers to a function that generates a search query based on data obtained from the setting means and the input means, and searches for related information.

[1006] A "generative AI model" is a type of artificial intelligence used to generate text for annotation generation.

[1007] "Annotation generation means" refers to a function that analyzes the relevant information obtained using a generative AI model and generates annotations based on the user's set parameters.

[1008] "Display means" refers to an interface for visually presenting the generated annotations to the user.

[1009] The "learning means" refers to a function for monitoring user usage and updating the algorithm of the annotation generation means.

[1010] "Transmission means" refers to a function for transmitting the text data entered by the user and the user identification information to the server.

[1011] The "receiving means" refers to a function for presenting annotation data received from the server to the user.

[1012] This invention is a system that automatically generates annotations based on each user's knowledge level and area of ​​interest, and has a learning function that improves the accuracy of the annotation generation.

[1013] 1. Setting user parameters

[1014] First, the user opens the system's settings screen and sets their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This information is sent to the server via the "settings tool" and saved as the user's profile. Databases such as "Elasticsearch" and "MongoDB" are used.

[1015] 2. Enter text

[1016] Next, the user enters the sentence or document they want to annotate into the system's text input field. For example, if they want to annotate on the topic "Principles of operation of lithium-ion batteries," they simply enter the text. This information is sent to the server via the "input means."

[1017] 3. Generating search queries

[1018] The server generates an appropriate search query based on the received user settings and the entered text. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate operating principle" is generated. Python and Elasticsearch are used to generate the search query.

[1019] 4. Searching for related information

[1020] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting and filtering data from multiple sources, using databases such as Google Scholar and JSTOR.

[1021] 5. Generating Annotations

[1022] The server generates annotations based on the collected and filtered information, in line with the user's set parameters. This is done using a "generative AI model," such as GPT-3. The specific annotation generated is, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes."

[1023] 6. Viewing annotations

[1024] The generated annotations are sent from the server to the device, which then displays them to the user. The annotations are provided in pop-up or tooltip format, and the user can check them by clicking or touching them. Web technologies such as HTML, CSS, and JavaScript are used for display.

[1025] 7. Usage monitoring and learning

[1026] When a user uses annotations, their device sends usage information, such as reference time, clicks, and frequency of viewing, to the server. The server uses this data to train and optimize the annotation generation algorithm. This process uses TensorFlow and PyTorch, allowing the accuracy and relevance of annotations to improve over time.

[1027] Specific examples

[1028] Here is a concrete example of how a lithium-ion battery works:

[1029] 1. The user has an intermediate level of science knowledge.

[1030] 2. The user types the question, "What is the working principle of a lithium-ion battery?"

[1031] 3. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information.

[1032] 4. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[1033] 5. The server sends the annotations to the terminal, which displays them to the user.

[1034] 6. When a user refers to the annotations and obtains information, the usage status is sent to the server and processed as learning data.

[1035] Prompt Sentence Examples

[1036] "Generate detailed annotations for users with intermediate scientific knowledge on the working principles of lithium-ion batteries, including how lithium ions move and the process of energy generation."

[1037] In this way, the present invention can promote personalized learning and communication, providing optimal annotations for each user.

[1038] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1039] Step 1:

[1040] The user opens the system's setting screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). These inputs are sent to the server through the setting means. The server stores the received data in a database and manages it as a user profile. After the setting information is saved, the server sends a confirmation message to the user (input: user setting information, output: confirmation message).

[1041] Step 2:

[1042] The user inputs the sentence or document they want to annotate into the system's text input field. This information is sent to the server via the input means. For example, a sentence about "the working principle of lithium-ion batteries" is input. The server receives the text data and saves it for analysis (input: user's text data, output: saved text data).

[1043] Step 3:

[1044] The server generates an appropriate search query based on the received user settings and the input text data. In this example, if the user's knowledge level is intermediate and their field of interest is chemistry, a query such as "lithium ion battery intermediate operating principle" is generated. This process is performed using a Python script (input: user settings and text data, output: generated search query).

[1045] Step 4:

[1046] The server uses the generated search query to search for relevant information from the Internet and internal databases. The search query is passed to the Elasticsearch engine, which filters relevant documents from the index. As a result, multiple pieces of relevant information are collected from the Internet (e.g., Google Scholar) (Input: Generated search query, Output: Collected relevant information).

[1047] Step 5:

[1048] The server generates annotations based on the collected and filtered information and the user's set parameters. This process uses a "generative AI model." For example, the AI ​​model "GPT-3" is selected, and annotations are generated based on prompt statements. For example, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes" is generated (input: collected related information, output: generated annotation).

[1049] Step 6:

[1050] The generated annotations are sent from the server to the terminal, where they are displayed to the user in a popup or tooltip format along with the original input text. For example, the original text is displayed on a web page, and the annotations are displayed in tooltip format nearby (input: generated annotations, output: annotations displayed to the user).

[1051] Step 7:

[1052] When a user uses annotations, their usage (e.g., time spent viewing, number of clicks, frequency of viewing, etc.) is sent from the device to the server. The server analyzes this data and updates the annotation generation algorithm. This process involves machine learning using TensorFlow and PyTorch, which improves the accuracy and relevance of annotations over time (input: user usage data, output: optimized annotation generation algorithm).

[1053] (Application example 1)

[1054] 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."

[1055] Conventional annotation generation systems have difficulty providing information tailored to the user's knowledge level and areas of interest, and especially in physical stores, there is a lack of efficient ways for users to obtain the information they are looking for. In addition, it is difficult to provide product information in real time, and there is a need to improve the user experience.

[1056] 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.

[1057] In this invention, the server includes: a setting means for a user to set their own knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; a visual information collection means for collecting product information using a visual display device worn by the user and generating annotations based on the user's setting information; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This enables users to obtain product information in real time at a physical store and obtain annotations optimized for their own knowledge level and field of interest.

[1058] The "setting means" is a means for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[1059] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[1060] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[1061] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means and generating annotations based on the parameters set by the user.

[1062] The "display means" is a means for displaying the generated annotation to the user.

[1063] The "visual information gathering means" is a means for gathering product information using a visual display device worn by the user and generating annotations based on the user's settings.

[1064] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[1065] The "transmission means" is a means for transmitting the text data entered by the user and the user ID to the server.

[1066] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[1067] A "search query" is a question for information search that is generated based on the user's knowledge level and areas of interest.

[1068] A "server" is a host computer for data processing and storage.

[1069] A "visual display device" is a device worn by a user that visually displays information.

[1070] The present invention provides a system for generating annotation information based on a user's knowledge level and areas of interest, thereby improving the user experience in a physical store. Detailed embodiments for realizing this system are described below.

[1071] User parameter settings

[1072] The user sets his / her knowledge level (e.g., beginner, intermediate, advanced), interest area (e.g., wine, cosmetics, technical products, etc.), and annotation depth (e.g., overview, detailed, specialized) through the setting screen of the smart glasses. This setting information is stored on the visual display device and on the server.

[1073] Collecting product information

[1074] When a user wears smart glasses and walks around a physical store, the camera captures product information in real time using the visual information collection means. For example, if a user sees a particular wine in the wine section, image data recognizing that product is acquired.

[1075] Generating a search query

[1076] The server generates an appropriate search query based on the product data acquired by the visual information gathering means and the user's settings. For example, it creates a search query such as "Bordeaux wine, mid-range, taste characteristics."

[1077] Search for related information

[1078] The server then searches for relevant information from the internet and internal databases based on the generated search query, using a search engine such as Elasticsearch.

[1079] Annotation Generation

[1080] The server analyzes the relevant information obtained through the search tool and generates annotations based on the user's set parameters. This analysis process uses a generative AI model (such as GPT or BERT). A specific example of an annotation generated is the following: "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon."

[1081] Viewing annotations

[1082] The generated annotation information is transmitted from the server to the smart glasses and displayed to the user in real time.

[1083] Usage monitoring and learning

[1084] As users browse the annotations displayed and access additional information, their usage is monitored, including viewing time, number of clicks, etc. This data is stored on the server to help train and continuously optimize the annotation generation algorithm.

[1085] Examples and prompts

[1086] As a concrete example, consider the case where a user looks at "a specific wine":

[1087] Configuration information

[1088] Knowledge level: Intermediate

[1089] Interests: Wine

[1090] Annotation Depth:Details

[1091] Prompt Sentence Examples

[1092] If the user is looking at a "specific wine":

[1093] User Settings:

[1094] Knowledge level: Intermediate

[1095] Interests: Wine

[1096] Annotation Depth: Detailed

[1097] Generated notes: "This particular wine is a red wine from a prestigious winery in the Bordeaux region of France. This vintage is particularly outstanding, dominated by Cabernet Sauvignon, with a perfect balance of berry fruit and tannins."

[1098] As described above, the present invention provides a system that enables users to obtain product information in real time at a physical store and obtain annotation information that is suited to their own level of knowledge and areas of interest.

[1099] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1100] Step 1:

[1101] The user opens the settings screen of the smart glasses and sets their knowledge level, areas of interest, and annotation depth.

[1102] Input: User knowledge level (e.g., intermediate), area of ​​interest (e.g., wine), depth of annotation (e.g., detailed)

[1103] Output: Configuration information (user profile)

[1104] Step 2:

[1105] The user wears the smart glasses in a physical store and captures the product on the camera using a visual information collection means.

[1106] Input: Product image captured by the smart glasses camera

[1107] Output: Product recognition data (image data)

[1108] Step 3:

[1109] The server receives the product data acquired by the visual information gathering means and the user's setting data, and generates an appropriate search query.

[1110] Input: Product recognition data, user profile

[1111] Data processing / data calculation: Image recognition processing using OpenCV, query generation based on user settings

[1112] Output: Search query (e.g., "Wine Bordeaux mid-range flavor profile")

[1113] Step 4:

[1114] The server searches for relevant information from the Internet and internal databases based on the generated search query.

[1115] Input: search query

[1116] Data processing / data calculation: Finding relevant information using Elasticsearch

[1117] Output: Related information (collection of information from multiple data sources)

[1118] Step 5:

[1119] The server analyzes the relevant information obtained by the search means and generates annotations based on user-specified parameters.

[1120] Input: Related information, User profile

[1121] Data processing / data calculation: annotation generation using generative AI models (e.g., GPT, BERT)

[1122] Output: Generated annotations (e.g., "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon.")

[1123] Step 6:

[1124] The server sends the generated annotations to the smart glasses, which display them to the user in real time.

[1125] Input: Generated annotation data

[1126] Output: Visual display of annotation information (displayed on smart glasses)

[1127] Step 7:

[1128] The server monitors the user's usage and continuously learns and optimizes the annotation generation algorithm.

[1129] Input: User operation data (viewing time, number of clicks, etc.)

[1130] Data processing / data calculation: Analysis of user operation data, model updating using machine learning algorithms

[1131] Output: Improved annotation generation algorithm

[1132] This series of processes allows users to obtain product information in real time at a physical store and obtain annotation information customized to their own knowledge level and areas of interest.

[1133] 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.

[1134] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[1135] User parameter settings

[1136] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is stored in the database as the user's individual profile.

[1137] Text Input

[1138] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[1139] Generating a search query

[1140] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[1141] Search for related information

[1142] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1143] emotion recognition

[1144] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1145] Analyzing sentiment data and adjusting search queries

[1146] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[1147] Annotation Generation

[1148] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1149] Viewing annotations

[1150] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[1151] Usage monitoring and learning

[1152] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1153] Specific examples

[1154] For example, consider the case where a user enters a question about "how lithium ion batteries work."

[1155] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[1156] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[1157] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[1158] 4. The server adjusts the search query to simplify it based on the sentiment data.

[1159] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[1160] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[1161] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[1162] In this way, the present invention improves the quality of learning and communication by creating and providing optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest.

[1163] The processing flow will be explained below.

[1164] Step 1:

[1165] The user opens the system's settings screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This setting information is then saved in the database as the user's individual profile.

[1166] Step 2:

[1167] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[1168] Step 3:

[1169] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[1170] Step 4:

[1171] The terminal sends the entered text data and user ID to the server, which receives it.

[1172] Step 5:

[1173] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[1174] Step 6:

[1175] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1176] Step 7:

[1177] The device collects data from sensors (cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1178] Step 8:

[1179] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[1180] Step 9:

[1181] The server generates annotations based on the analyzed information, incorporating set parameters and emotional data. For example, it might generate an annotation like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1182] Step 10:

[1183] The server sends the generated annotations to the terminal, which receives them and displays them to the user, who can view them in popup or tooltip format.

[1184] Step 11:

[1185] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[1186] Step 12:

[1187] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1188] Through these steps, our system efficiently generates and provides annotations optimized for each user, enabling information provision tailored to different knowledge levels and areas of interest. Further optimization according to the user's emotional state improves the quality of learning and communication.

[1189] Example 2

[1190] 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."

[1191] In today's information-saturated society, it is difficult for users to efficiently obtain information appropriate to their own knowledge level and areas of interest. Furthermore, while it is important to provide annotations that reflect the user's emotional state, existing systems do not adequately fulfill this requirement. As a result, users are unable to obtain information that is optimal for them, reducing the effectiveness of learning and information gathering. Therefore, there is a need for an annotation generation system that is appropriate for the user's knowledge level, areas of interest, and emotional state.

[1192] 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.

[1193] In this invention, the server includes a setting means for a user to set his / her knowledge level, field of interest, and annotation depth, an input means for a user to input a sentence or document to which the user wants to annotate, a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information, an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters and emotional data, an emotion recognition means for recognizing the user's emotions and collecting that data, a display means for displaying the generated annotations to the user, and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide optimal information based on the user's knowledge level, field of interest, and emotional state.

[1194] The "setting means" is a means for a user to input his / her own knowledge level, field of interest, and depth of annotation, and store it in the database.

[1195] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[1196] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[1197] The "annotation generation means" is a means for analyzing and organizing the related information acquired by the search means, and generating appropriate annotations based on the user's set parameters and emotion data.

[1198] The "display means" is a means for visually presenting the generated annotation to the user.

[1199] The "learning means" is a means for monitoring user usage and using that data to continuously learn and update the algorithms of the annotation generation means.

[1200] The "transmission means" is a means for transmitting the text data, user ID, and emotion data input by the user to the server.

[1201] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[1202] An "emotion recognition means" is a means using sensors and software to recognize and collect the user's emotional state.

[1203] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[1204] User parameter settings

[1205] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is then saved in the database by the terminal as the user's individual profile.

[1206] Text Input

[1207] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text. The device then sends the entered text to the server.

[1208] Generating a search query

[1209] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[1210] Search for related information

[1211] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1212] emotion recognition

[1213] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1214] Analyzing sentiment data and adjusting search queries

[1215] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[1216] Annotation Generation

[1217] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1218] Viewing annotations

[1219] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[1220] Usage monitoring and learning

[1221] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1222] Specific examples

[1223] For example, consider the case where a user inputs a question about "how lithium-ion batteries work."

[1224] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[1225] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[1226] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[1227] 4. The server adjusts the search query to simplify it based on the sentiment data.

[1228] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[1229] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[1230] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[1231] Prompt Sentence Examples

[1232] "Please provide an intermediate level explanation of how lithium-ion batteries work. If users are confused, simplify the explanation."

[1233] "Generate detailed annotations in the chemical domain based on user sentiment data."

[1234] In this way, the present invention creates and provides optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest, thereby improving the quality of learning and communication.

[1235] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1236] Step 1:

[1237] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). The terminal receives these settings and stores them in a database. This setting information is used for subsequent processing.

[1238] Input: User knowledge level, areas of interest, depth of annotations

[1239] Output: User preferences stored in the database

[1240] Specific behavior:

[1241] The user accesses the settings screen

[1242] The user enters the settings.

[1243] The device saves the configuration information in a database

[1244] Step 2:

[1245] The user enters the sentence or document they want to annotate into the text entry field of the system, and the device receives the entered text and sends it to the server.

[1246] Input: The sentence or document you want to annotate

[1247] Output: Text data sent to the server

[1248] Specific behavior:

[1249] The user types text into the text field

[1250] The device sends the entered text to the server

[1251] Step 3:

[1252] The server generates a search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, the server generates a search query such as "Lithium-ion battery intermediate working principle."

[1253] Input: Text data, user setting information

[1254] Output: Generated search query

[1255] Specific behavior:

[1256] The server parses the text data and configuration information

[1257] The server generates a search query based on the analysis results.

[1258] Step 4:

[1259] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1260] Input: Search query

[1261] Output: Filtered relevant information

[1262] Specific behavior:

[1263] The server sends the search query to the internet or to an internal database

[1264] The server collects and filters the information obtained

[1265] Step 5:

[1266] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1267] Input: User facial expressions and tone of voice

[1268] Output: Collected emotion data

[1269] Specific behavior:

[1270] The device activates the camera and voice recognition devices.

[1271] The device analyzes the user's facial expressions and tone of voice to collect emotional data.

[1272] Step 6:

[1273] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the search query accordingly. For example, if the user has a confused expression, the server modifies the search query to make it simpler to explain.

[1274] Input: Collected sentiment data, generated search queries

[1275] Output: Adjusted search query

[1276] Specific behavior:

[1277] The server receives the emotion data.

[1278] The server adjusts search queries based on sentiment data

[1279] Step 7:

[1280] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it generates annotations such as, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1281] Input: Tailored search queries, related information, user preference information, sentiment data

[1282] Output: Generated annotations

[1283] Specific behavior:

[1284] The server analyzes the relevant information, parameters, and emotion data.

[1285] The server generates the best annotation

[1286] Step 8:

[1287] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[1288] Input: Generated annotation data

[1289] Output: Annotations that are visible to the user

[1290] Specific behavior:

[1291] The server sends the annotation data to the device.

[1292] The device displays the annotation data

[1293] Step 9:

[1294] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1295] Input: User usage data

[1296] Output: Improved annotation generation algorithm

[1297] Specific behavior:

[1298] Device monitors usage

[1299] The device sends usage data to the server

[1300] The server analyzes the data and trains and optimizes the algorithm.

[1301] (Application example 2)

[1302] 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."

[1303] While conventional annotation generation systems can generate annotations based on a user's knowledge level and areas of interest, they cannot provide optimal annotations that take into account the user's emotional state. This can lead to users finding it difficult to understand or becoming confused, resulting in reduced learning efficiency.

[1304] Furthermore, existing systems lack the flexibility to respond to user emotions, such as providing simpler explanations to confused users. This leads to a poor user experience. To address these issues, a new system is needed that can recognize user emotions and adjust annotation content accordingly.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1306] In this invention, the server includes: a setting means for a user to set his / her knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating an annotation based on parameters set by the user; a display means for displaying the generated annotation to the user; a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means; an emotion recognition means for recognizing the user's emotions; and a query adjustment means for adjusting the search query based on emotion data obtained by the emotion recognition means. This makes it possible to provide optimal annotations according to the user's emotional state as well as their knowledge level and field of interest.

[1307] The "setting means" is a means for providing a function for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[1308] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[1309] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[1310] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means, and generating annotations based on the parameters set by the user.

[1311] The "display means" is a means for displaying the generated annotation to the user.

[1312] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[1313] The "emotion recognition means" is a means including a sensor and an analysis device for recognizing the user's emotions.

[1314] The "query adjustment means" is a means for adjusting a search query based on emotion data acquired by the emotion recognition means.

[1315] This invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using an emotion recognition function. This system includes a setting means, an input means, a search means, an annotation generation means, a display means, a learning means, an emotion recognition means, and a query adjustment means.

[1316] 1. Program Generation

[1317] The system for realizing this invention is composed of the following programs: First, a user inputs their knowledge level, field of interest, and annotation depth using the setting means. Then, they input the sentence or document they want to annotate using the input means. Based on this data, the search means generates an appropriate search query and searches for related information from the Internet or an internal database.

[1318] The retrieved information is analyzed and organized by the annotation generation means, and annotations are generated based on the user's set parameters. The generated annotations are displayed to the user by the display means. Furthermore, the learning means monitors the user's usage status and continuously updates the algorithm of the annotation generation means. The emotion recognition means also plays an important role in this invention. The emotion data acquired by the emotion recognition means is analyzed by the query adjustment means, and the search query is adjusted.

[1319] 2. Program processing explanation

[1320] The system is realized by combining multiple pieces of hardware and software, the details of which are explained below.

[1321] Hardware

[1322] Device: A device used by a user to set up or input information (e.g., smartphone, tablet, computer)

[1323] Server: Generates search queries, finds relevant information, generates annotations, stores data, and learns from it.

[1324] Emotion recognition sensors: Cameras and voice recognition devices to recognize user emotions

[1325] software

[1326] Settings and input app: An interface for users to set their knowledge level, areas of interest, and annotation depth, and then input sentences and documents.

[1327] Search algorithms: Software that generates search queries based on user preferences and input data to find relevant information.

[1328] Annotation generation algorithm: Software for analyzing and organizing retrieved information and generating annotations

[1329] Viewer app: An interface for displaying generated annotations to the user.

[1330] Learning algorithm: Software for monitoring user usage and updating the annotation generation algorithm

[1331] Emotion recognition algorithms: Software for analyzing user emotions and adjusting search queries based on the acquired emotional data.

[1332] These hardware and software are integrated to provide optimal annotations according to the user's knowledge level, areas of interest, and even emotions.

[1333] 3. Specific Examples

[1334] The following examples are used to illustrate how the invention may be put into practice.

[1335] Example 1:

[1336] If a user is interested in intermediate level chemistry and wants to generate annotations on "how lithium ion batteries work," the system works as follows:

[1337] 1. Settings: The user sets the knowledge level to "Intermediate", the area of ​​interest to "Chemistry", and the annotation depth to "Detailed".

[1338] 2. Input: Enter the sentence "How lithium-ion batteries work."

[1339] 3. Emotion Recognition: Detects confused facial expressions of the user.

[1340] 4. Query generation: Generate a search query based on “Lithium ion battery intermediate working principle.”

[1341] 5. Information retrieval: Searching for information from the internet and internal databases.

[1342] 6. Annotation generation: Annotations are generated in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[1343] 7. Display: Show the generated annotations to the user.

[1344] Example prompt sentence:

[1345] By inputting the following prompt sentence into the generative AI model, the optimal annotation will be generated.

[1346] Lithium-ion Battery Working Principle Intermediate Chemistry

[1347] In this way, the efficiency of learning and understanding can be improved by providing optimal annotations based on the user's knowledge level, areas of interest, and emotional state.

[1348] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1349] Program processing steps

[1350] Step 1:

[1351] The user uses the setting means to set his / her knowledge level, field of interest, and depth of annotation.

[1352] Input: Knowledge level, area of ​​interest, depth of annotation

[1353] Output: User profile (e.g. {"knowledge_level": "Intermediate", "interest_field": "Chemistry", "annotation_depth": "Detailed"})

[1354] Specifically, a user opens the application's settings screen, selects their knowledge level (beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics), and annotation depth (overview, detailed, specialized), and then presses the save button. This information is saved in the database as a user profile.

[1355] Step 2:

[1356] The user uses the input means to input a sentence or document to which the user wishes to add an annotation.

[1357] Input: A sentence or document (e.g., "How a lithium-ion battery works")

[1358] Output: User input data

[1359] Specifically, the user types the sentence or document they want to annotate into the text input field and presses the enter key. The entered data is sent to the server along with the user ID.

[1360] Step 3:

[1361] The terminal recognizes the user's emotions using the emotion recognition means.

[1362] Input: User facial and voice data

[1363] Output: Emotion data (e.g., "confused")

[1364] Specifically, the device's built-in camera and microphone collect the user's facial expressions and voice in real time, which are then analyzed using an emotion recognition algorithm. The analysis results determine whether the user is confused or not, and emotional data is generated.

[1365] Step 4:

[1366] The server generates a search query based on the data obtained from the setting means and the input means, and further adjusts the search query based on emotion data, if any.

[1367] Input: User profile, user input data, emotion data

[1368] Output: Adjusted search query (e.g., "Lithium-ion battery intermediate working principle easy")

[1369] Specifically, the server generates an initial search query based on the user profile and input data. It then checks the emotion data and adjusts the query, such as adding "easy" if the user is confused.

[1370] Step 5:

[1371] The server uses the tailored search query to search for relevant information.

[1372] Input: Adjusted search query

[1373] Output: Search result data (e.g., search result list)

[1374] Specifically, the server submits tailored search queries to the internet and internal databases to gather relevant information, and the search results list is scored and filtered based on the relevance of the information.

[1375] Step 6:

[1376] The server analyzes and organizes the relevant information retrieved by the search tool and generates annotations based on the user's set parameters.

[1377] Input: Search result data, user profile

[1378] Output: Annotation data (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.")

[1379] Specifically, the server generates annotations based on the search result list, tailored to the user's knowledge level and area of ​​interest. For example, an intermediate-level user might be provided with annotations that include more detailed and technical content.

[1380] Step 7:

[1381] The server transmits the generated annotations to the user terminal, which displays them to the user.

[1382] Input: annotation data

[1383] Output: Display annotations

[1384] Specifically, the generated annotation data is sent from the server to the user's terminal and displayed to the user through a display application on the terminal. The user can check the annotations in a pop-up format or a tooltip format.

[1385] Step 8:

[1386] The device monitors the user's usage and sends the data to the server, which then updates the annotation generation algorithm based on the data.

[1387] Input: Usage data (e.g., browsing time, clicks)

[1388] Output: Updated algorithm

[1389] Specifically, the device records how long the user views the annotation, which parts they clicked on, how often they viewed it, and so on, and sends this information to the server. The server analyzes this data and continues to improve the annotation generation algorithm.

[1390] Through these steps, it is possible to provide annotations that are optimal for the user's knowledge level, areas of interest, and emotional state.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] [Fourth embodiment]

[1395] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1396] 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.

[1397] 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).

[1398] 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.

[1399] 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.

[1400] 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).

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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."

[1408] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and has a learning function that improves the accuracy of the annotation generation. Specific embodiments of this system are described below.

[1409] User parameter settings

[1410] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), areas of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is saved as the user's individual profile.

[1411] Text Input

[1412] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[1413] Generating a search query

[1414] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate working principle" will be generated.

[1415] Search for related information

[1416] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1417] Annotation Generation

[1418] The server generates annotations based on the analyzed and filtered information and the user's set parameters. For example, if an intermediate-level explanation of lithium-ion batteries is required, the server generates text in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The intermediate-level points are ____."

[1419] Viewing annotations

[1420] The generated annotations are sent from the server to the terminal, which displays them to the user, who can view them in the form of popups or tooltips, for example, by highlighting the annotated portion of the original text.

[1421] Usage monitoring and learning

[1422] As users use annotations, their usage (e.g., view time, clicks, frequency of viewing, etc.) is sent from the device to the server, which uses this data to continuously learn and optimize the annotation generation algorithm, improving the accuracy and relevance of annotations over time.

[1423] Specific examples

[1424] As a specific example, consider the case where a user inputs the question "How does a lithium-ion battery work?"

[1425] 1. The user has an intermediate level of science knowledge.

[1426] 2. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information from the internet and databases.

[1427] 3. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[1428] 4. The server sends the annotations to the terminal, which displays them to the user.

[1429] 5. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[1430] In this way, the present invention provides a system that contributes to the promotion of personalized learning and communication.

[1431] The processing flow will be explained below.

[1432] Step 1:

[1433] The user opens the system's settings screen and enters their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). The settings information is saved as the user's individual profile.

[1434] Step 2:

[1435] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[1436] Step 3:

[1437] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[1438] Step 4:

[1439] The terminal sends the entered text data and user ID to the server, which receives it.

[1440] Step 5:

[1441] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[1442] Step 6:

[1443] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1444] Step 7:

[1445] The server analyzes the collected information and filters and formats it based on the user's knowledge level and areas of interest, thereby extracting annotation information appropriate for the user.

[1446] Step 8:

[1447] The server generates annotations based on the analyzed information. For example, it might generate annotations like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1448] Step 9:

[1449] The server sends the generated annotations to the terminal, which then displays them to the user. The user can view the annotations in a popup or tooltip format.

[1450] Step 10:

[1451] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[1452] Step 11:

[1453] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1454] Through these steps, our system efficiently generates and provides annotations optimized for each user, allowing users with different knowledge levels and areas of interest to easily obtain information and annotations that are appropriate for them.

[1455] Example 1

[1456] 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."

[1457] Conventional annotation generation systems have the difficulty of providing individualized annotations tailored to the user's knowledge level or area of ​​interest, and are only able to provide general information. Another problem is that they lack the ability to continuously train the annotation generation algorithm based on the user's usage, making it difficult to expect long-term accuracy improvements.

[1458] 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.

[1459] In this invention, the server includes: a setting means for a user to set their own knowledge level, areas of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the acquired related information using a generative AI model and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide highly accurate annotations suited to the knowledge level and areas of interest of each individual user, and the accuracy and relevance of the annotation generation can be improved over time.

[1460] A "user" is someone who uses the system to obtain annotations based on their level of knowledge and areas of interest.

[1461] The "setting means" refers to an interface that allows a user to input parameters such as his / her knowledge level, areas of interest, and annotation depth.

[1462] "Input means" refers to an interface through which a user inputs a sentence or document to be annotated.

[1463] The "search means" refers to a function that generates a search query based on data obtained from the setting means and the input means, and searches for related information.

[1464] A "generative AI model" is a type of artificial intelligence used to generate text for annotation generation.

[1465] "Annotation generation means" refers to a function that analyzes the relevant information obtained using a generative AI model and generates annotations based on the user's set parameters.

[1466] "Display means" refers to an interface for visually presenting the generated annotations to the user.

[1467] The "learning means" refers to a function for monitoring user usage and updating the algorithm of the annotation generation means.

[1468] "Transmission means" refers to a function for transmitting the text data entered by the user and the user identification information to the server.

[1469] The "receiving means" refers to a function for presenting annotation data received from the server to the user.

[1470] This invention is a system that automatically generates annotations based on each user's knowledge level and area of ​​interest, and has a learning function that improves the accuracy of the annotation generation.

[1471] 1. Setting user parameters

[1472] First, the user opens the system's settings screen and sets their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This information is sent to the server via the "settings tool" and saved as the user's profile. Databases such as "Elasticsearch" and "MongoDB" are used.

[1473] 2. Enter text

[1474] Next, the user enters the sentence or document they want to annotate into the system's text input field. For example, if they want to annotate on the topic "Principles of operation of lithium-ion batteries," they simply enter the text. This information is sent to the server via the "input means."

[1475] 3. Generating search queries

[1476] The server generates an appropriate search query based on the received user settings and the entered text. For example, if the user has intermediate level knowledge, a query such as "Lithium-ion battery intermediate operating principle" is generated. Python and Elasticsearch are used to generate the search query.

[1477] 4. Searching for related information

[1478] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting and filtering data from multiple sources, using databases such as Google Scholar and JSTOR.

[1479] 5. Generating Annotations

[1480] The server generates annotations based on the collected and filtered information, in line with the user's set parameters. This is done using a "generative AI model," such as GPT-3. The specific annotation generated is, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes."

[1481] 6. Viewing annotations

[1482] The generated annotations are sent from the server to the device, which then displays them to the user. The annotations are provided in pop-up or tooltip format, and the user can check them by clicking or touching them. Web technologies such as HTML, CSS, and JavaScript are used for display.

[1483] 7. Usage monitoring and learning

[1484] When a user uses annotations, their device sends usage information, such as reference time, clicks, and frequency of viewing, to the server. The server uses this data to train and optimize the annotation generation algorithm. This process uses TensorFlow and PyTorch, allowing the accuracy and relevance of annotations to improve over time.

[1485] Specific examples

[1486] Here is a concrete example of how a lithium-ion battery works:

[1487] 1. The user has an intermediate level of science knowledge.

[1488] 2. The user types the question, "What is the working principle of a lithium-ion battery?"

[1489] 3. The server generates a search query for "Lithium-ion battery intermediate working principle" and collects related information.

[1490] 4. From the collected information, an annotation is generated: "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[1491] 5. The server sends the annotations to the terminal, which displays them to the user.

[1492] 6. When a user refers to the annotations and obtains information, the usage status is sent to the server and processed as learning data.

[1493] Prompt Sentence Examples

[1494] "Generate detailed annotations for users with intermediate scientific knowledge on the working principles of lithium-ion batteries, including how lithium ions move and the process of energy generation."

[1495] In this way, the present invention can promote personalized learning and communication, providing optimal annotations for each user.

[1496] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1497] Step 1:

[1498] The user opens the system's setting screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). These inputs are sent to the server through the setting means. The server stores the received data in a database and manages it as a user profile. After the setting information is saved, the server sends a confirmation message to the user (input: user setting information, output: confirmation message).

[1499] Step 2:

[1500] The user inputs the sentence or document they want to annotate into the system's text input field. This information is sent to the server via the input means. For example, a sentence about "the working principle of lithium-ion batteries" is input. The server receives the text data and saves it for analysis (input: user's text data, output: saved text data).

[1501] Step 3:

[1502] The server generates an appropriate search query based on the received user settings and the input text data. In this example, if the user's knowledge level is intermediate and their field of interest is chemistry, a query such as "lithium ion battery intermediate operating principle" is generated. This process is performed using a Python script (input: user settings and text data, output: generated search query).

[1503] Step 4:

[1504] The server uses the generated search query to search for relevant information from the Internet and internal databases. The search query is passed to the Elasticsearch engine, which filters relevant documents from the index. As a result, multiple pieces of relevant information are collected from the Internet (e.g., Google Scholar) (Input: Generated search query, Output: Collected relevant information).

[1505] Step 5:

[1506] The server generates annotations based on the collected and filtered information and the user's set parameters. This process uses a "generative AI model." For example, the AI ​​model "GPT-3" is selected, and annotations are generated based on prompt statements. For example, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes" is generated (input: collected related information, output: generated annotation).

[1507] Step 6:

[1508] The generated annotations are sent from the server to the terminal, where they are displayed to the user in a popup or tooltip format along with the original input text. For example, the original text is displayed on a web page, and the annotations are displayed in tooltip format nearby (input: generated annotations, output: annotations displayed to the user).

[1509] Step 7:

[1510] When a user uses annotations, their usage (e.g., time spent viewing, number of clicks, frequency of viewing, etc.) is sent from the device to the server. The server analyzes this data and updates the annotation generation algorithm. This process involves machine learning using TensorFlow and PyTorch, which improves the accuracy and relevance of annotations over time (input: user usage data, output: optimized annotation generation algorithm).

[1511] (Application example 1)

[1512] 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."

[1513] Conventional annotation generation systems have difficulty providing information tailored to the user's knowledge level and areas of interest, and especially in physical stores, there is a lack of efficient ways for users to obtain the information they are looking for. In addition, it is difficult to provide product information in real time, and there is a need to improve the user experience.

[1514] 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.

[1515] In this invention, the server includes: a setting means for a user to set their own knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters; a display means for displaying the generated annotations to the user; a visual information collection means for collecting product information using a visual display device worn by the user and generating annotations based on the user's setting information; and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This enables users to obtain product information in real time at a physical store and obtain annotations optimized for their own knowledge level and field of interest.

[1516] The "setting means" is a means for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[1517] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[1518] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[1519] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means and generating annotations based on the parameters set by the user.

[1520] The "display means" is a means for displaying the generated annotation to the user.

[1521] The "visual information gathering means" is a means for gathering product information using a visual display device worn by the user and generating annotations based on the user's settings.

[1522] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[1523] The "transmission means" is a means for transmitting the text data entered by the user and the user ID to the server.

[1524] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[1525] A "search query" is a question for information search that is generated based on the user's knowledge level and areas of interest.

[1526] A "server" is a host computer for data processing and storage.

[1527] A "visual display device" is a device worn by a user that visually displays information.

[1528] The present invention provides a system for generating annotation information based on a user's knowledge level and areas of interest, thereby improving the user experience in a physical store. Detailed embodiments for realizing this system are described below.

[1529] User parameter settings

[1530] The user sets his / her knowledge level (e.g., beginner, intermediate, advanced), interest area (e.g., wine, cosmetics, technical products, etc.), and annotation depth (e.g., overview, detailed, specialized) through the setting screen of the smart glasses. This setting information is stored on the visual display device and on the server.

[1531] Collecting product information

[1532] When a user wears smart glasses and walks around a physical store, the camera captures product information in real time using the visual information collection means. For example, if a user sees a particular wine in the wine section, image data recognizing that product is acquired.

[1533] Generating a search query

[1534] The server generates an appropriate search query based on the product data acquired by the visual information gathering means and the user's settings. For example, it creates a search query such as "Bordeaux wine, mid-range, taste characteristics."

[1535] Search for related information

[1536] The server then searches for relevant information from the internet and internal databases based on the generated search query, using a search engine such as Elasticsearch.

[1537] Annotation Generation

[1538] The server analyzes the relevant information obtained through the search tool and generates annotations based on the user's set parameters. This analysis process uses a generative AI model (such as GPT or BERT). A specific example of an annotation generated is the following: "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon."

[1539] Viewing annotations

[1540] The generated annotation information is transmitted from the server to the smart glasses and displayed to the user in real time.

[1541] Usage monitoring and learning

[1542] As users browse the annotations displayed and access additional information, their usage is monitored, including viewing time, number of clicks, etc. This data is stored on the server to help train and continuously optimize the annotation generation algorithm.

[1543] Examples and prompts

[1544] As a concrete example, consider the case where a user looks at "a specific wine":

[1545] Configuration information

[1546] Knowledge level: Intermediate

[1547] Interests: Wine

[1548] Annotation Depth:Details

[1549] Prompt Sentence Examples

[1550] If the user is looking at a "specific wine":

[1551] User Settings:

[1552] Knowledge level: Intermediate

[1553] Interests: Wine

[1554] Annotation Depth: Detailed

[1555] Generated notes: "This particular wine is a red wine from a prestigious winery in the Bordeaux region of France. This vintage is particularly outstanding, dominated by Cabernet Sauvignon, with a perfect balance of berry fruit and tannins."

[1556] As described above, the present invention provides a system that enables users to obtain product information in real time at a physical store and obtain annotation information that is suited to their own level of knowledge and areas of interest.

[1557] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1558] Step 1:

[1559] The user opens the settings screen of the smart glasses and sets their knowledge level, areas of interest, and annotation depth.

[1560] Input: User knowledge level (e.g., intermediate), area of ​​interest (e.g., wine), depth of annotation (e.g., detailed)

[1561] Output: Configuration information (user profile)

[1562] Step 2:

[1563] The user wears the smart glasses in a physical store and captures the product on the camera using a visual information collection means.

[1564] Input: Product image captured by the smart glasses camera

[1565] Output: Product recognition data (image data)

[1566] Step 3:

[1567] The server receives the product data acquired by the visual information gathering means and the user's setting data, and generates an appropriate search query.

[1568] Input: Product recognition data, user profile

[1569] Data processing / data calculation: Image recognition processing using OpenCV, query generation based on user settings

[1570] Output: Search query (e.g., "Wine Bordeaux mid-range flavor profile")

[1571] Step 4:

[1572] The server searches for relevant information from the Internet and internal databases based on the generated search query.

[1573] Input: search query

[1574] Data processing / data calculation: Finding relevant information using Elasticsearch

[1575] Output: Related information (collection of information from multiple data sources)

[1576] Step 5:

[1577] The server analyzes the relevant information obtained by the search means and generates annotations based on user-specified parameters.

[1578] Input: Related information, User profile

[1579] Data processing / data calculation: annotation generation using generative AI models (e.g., GPT, BERT)

[1580] Output: Generated annotations (e.g., "This wine is a red wine from the Bordeaux region of France, characterized by its deep flavor, primarily made from Cabernet Sauvignon.")

[1581] Step 6:

[1582] The server sends the generated annotations to the smart glasses, which display them to the user in real time.

[1583] Input: Generated annotation data

[1584] Output: Visual display of annotation information (displayed on smart glasses)

[1585] Step 7:

[1586] The server monitors the user's usage and continuously learns and optimizes the annotation generation algorithm.

[1587] Input: User operation data (viewing time, number of clicks, etc.)

[1588] Data processing / data calculation: Analysis of user operation data, model updating using machine learning algorithms

[1589] Output: Improved annotation generation algorithm

[1590] This series of processes allows users to obtain product information in real time at a physical store and obtain annotation information customized to their own knowledge level and areas of interest.

[1591] 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.

[1592] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[1593] User parameter settings

[1594] Users open the system's settings screen and enter their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is stored in the database as the user's individual profile.

[1595] Text Input

[1596] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text.

[1597] Generating a search query

[1598] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[1599] Search for related information

[1600] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1601] emotion recognition

[1602] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1603] Analyzing sentiment data and adjusting search queries

[1604] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[1605] Annotation Generation

[1606] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1607] Viewing annotations

[1608] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[1609] Usage monitoring and learning

[1610] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1611] Specific examples

[1612] For example, consider the case where a user enters a question about "how lithium ion batteries work."

[1613] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[1614] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[1615] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[1616] 4. The server adjusts the search query to simplify it based on the sentiment data.

[1617] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[1618] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[1619] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[1620] In this way, the present invention improves the quality of learning and communication by creating and providing optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest.

[1621] The processing flow will be explained below.

[1622] Step 1:

[1623] The user opens the system's settings screen and inputs their knowledge level (beginner, intermediate, advanced), field of interest (chemistry, physics, economics, etc.), and annotation depth (overview, detailed, specialized). This setting information is then saved in the database as the user's individual profile.

[1624] Step 2:

[1625] The device converts the setting information entered by the user into JSON format and sends it to the server, which then stores the received setting information in a database for each user.

[1626] Step 3:

[1627] The user inputs the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply input the text.

[1628] Step 4:

[1629] The terminal sends the entered text data and user ID to the server, which receives it.

[1630] Step 5:

[1631] The server generates an appropriate search query based on the received text data and pre-set user parameters. For example, if the user has intermediate level knowledge, it generates a query such as "Lithium-ion battery intermediate working principle."

[1632] Step 6:

[1633] The server uses the generated search query to search for relevant information from the Internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1634] Step 7:

[1635] The device collects data from sensors (cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1636] Step 8:

[1637] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the analysis results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[1638] Step 9:

[1639] The server generates annotations based on the analyzed information, incorporating set parameters and emotional data. For example, it might generate an annotation like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1640] Step 10:

[1641] The server sends the generated annotations to the terminal, which receives them and displays them to the user, who can view them in popup or tooltip format.

[1642] Step 11:

[1643] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server, which receives it.

[1644] Step 12:

[1645] The server analyzes the received usage data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1646] Through these steps, our system efficiently generates and provides annotations optimized for each user, enabling information provision tailored to different knowledge levels and areas of interest. Further optimization according to the user's emotional state improves the quality of learning and communication.

[1647] Example 2

[1648] 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."

[1649] In today's information-saturated society, it is difficult for users to efficiently obtain information appropriate to their own knowledge level and areas of interest. Furthermore, while it is important to provide annotations that reflect the user's emotional state, existing systems do not adequately fulfill this requirement. As a result, users are unable to obtain information that is optimal for them, reducing the effectiveness of learning and information gathering. Therefore, there is a need for an annotation generation system that is appropriate for the user's knowledge level, areas of interest, and emotional state.

[1650] 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.

[1651] In this invention, the server includes a setting means for a user to set his / her knowledge level, field of interest, and annotation depth, an input means for a user to input a sentence or document to which the user wants to annotate, a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information, an annotation generation means for analyzing and organizing the related information obtained by the search means and generating annotations based on the user's setting parameters and emotional data, an emotion recognition means for recognizing the user's emotions and collecting that data, a display means for displaying the generated annotations to the user, and a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means. This makes it possible to provide optimal information based on the user's knowledge level, field of interest, and emotional state.

[1652] The "setting means" is a means for a user to input his / her own knowledge level, field of interest, and depth of annotation, and store it in the database.

[1653] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[1654] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[1655] The "annotation generation means" is a means for analyzing and organizing the related information acquired by the search means, and generating appropriate annotations based on the user's set parameters and emotion data.

[1656] The "display means" is a means for visually presenting the generated annotation to the user.

[1657] The "learning means" is a means for monitoring user usage and using that data to continuously learn and update the algorithms of the annotation generation means.

[1658] The "transmission means" is a means for transmitting the text data, user ID, and emotion data input by the user to the server.

[1659] The "receiving means" is a means for presenting the annotation data received from the server to the user.

[1660] An "emotion recognition means" is a means using sensors and software to recognize and collect the user's emotional state.

[1661] The present invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using emotion recognition. Specific embodiments of this system are described below.

[1662] User parameter settings

[1663] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). This setting information is then saved in the database by the terminal as the user's individual profile.

[1664] Text Input

[1665] The user enters the sentence or document they want to annotate into the text input field of the system. For example, if they want to annotate "the working principle of lithium-ion batteries," they simply enter the text. The device then sends the entered text to the server.

[1666] Generating a search query

[1667] The server generates an appropriate search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, it generates a search query such as "Lithium-ion battery intermediate operating principle."

[1668] Search for related information

[1669] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1670] emotion recognition

[1671] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1672] Analyzing sentiment data and adjusting search queries

[1673] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the generated search query based on the results. For example, if the user has a confused expression, the algorithm is modified to prioritize information with simpler explanations.

[1674] Annotation Generation

[1675] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it might generate text like, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1676] Viewing annotations

[1677] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[1678] Usage monitoring and learning

[1679] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1680] Specific examples

[1681] For example, consider the case where a user inputs a question about "how lithium-ion batteries work."

[1682] 1. The user has an intermediate level of science knowledge and has set their field of interest to chemistry.

[1683] 2. The server generates the search query "Lithium-ion battery intermediate working principle" and collects and filters related information.

[1684] 3. The device recognizes the user's facial expressions and tone of voice to detect confusion.

[1685] 4. The server adjusts the search query to simplify it based on the sentiment data.

[1686] 5. From the collected information, annotations are generated that include simple explanations (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.").

[1687] 6. The server sends the generated annotations to the terminal, which displays them to the user.

[1688] 7. When the user refers to the annotations and obtains the necessary information, usage is monitored and the server accumulates it as learning data.

[1689] Prompt Sentence Examples

[1690] "Please provide an intermediate level explanation of how lithium-ion batteries work. If users are confused, simplify the explanation."

[1691] "Generate detailed annotations in the chemical domain based on user sentiment data."

[1692] In this way, the present invention creates and provides optimal annotations based on the user's emotional state as well as their knowledge level and areas of interest, thereby improving the quality of learning and communication.

[1693] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1694] Step 1:

[1695] The user opens the system's settings screen and inputs their knowledge level (e.g., beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics, etc.), and annotation depth (e.g., summary, detailed, specialized). The terminal receives these settings and stores them in a database. This setting information is used for subsequent processing.

[1696] Input: User knowledge level, areas of interest, depth of annotations

[1697] Output: User preferences stored in the database

[1698] Specific behavior:

[1699] The user accesses the settings screen

[1700] The user enters the settings.

[1701] The device saves the configuration information in a database

[1702] Step 2:

[1703] The user enters the sentence or document they want to annotate into the text entry field of the system, and the device receives the entered text and sends it to the server.

[1704] Input: The sentence or document you want to annotate

[1705] Output: Text data sent to the server

[1706] Specific behavior:

[1707] The user types text into the text field

[1708] The device sends the entered text to the server

[1709] Step 3:

[1710] The server generates a search query based on the received user text data and pre-set parameters. For example, for a user with intermediate knowledge, the server generates a search query such as "Lithium-ion battery intermediate working principle."

[1711] Input: Text data, user setting information

[1712] Output: Generated search query

[1713] Specific behavior:

[1714] The server parses the text data and configuration information

[1715] The server generates a search query based on the analysis results.

[1716] Step 4:

[1717] The server uses the generated search query to search for relevant information from the internet and internal databases, collecting data from multiple sources and filtering the most relevant information.

[1718] Input: Search query

[1719] Output: Filtered relevant information

[1720] Specific behavior:

[1721] The server sends the search query to the internet or to an internal database

[1722] The server collects and filters the information obtained

[1723] Step 5:

[1724] The device collects data from sensors (e.g., cameras and voice recognition devices) to recognize the user's emotions. It analyzes facial expressions and tone of voice when the user is viewing input fields or annotations, and obtains emotional data in real time.

[1725] Input: User facial expressions and tone of voice

[1726] Output: Collected emotion data

[1727] Specific behavior:

[1728] The device activates the camera and voice recognition devices.

[1729] The device analyzes the user's facial expressions and tone of voice to collect emotional data.

[1730] Step 6:

[1731] The server analyzes the emotion data acquired by the emotion recognition means and adjusts the search query accordingly. For example, if the user has a confused expression, the server modifies the search query to make it simpler to explain.

[1732] Input: Collected sentiment data, generated search queries

[1733] Output: Adjusted search query

[1734] Specific behavior:

[1735] The server receives the emotion data.

[1736] The server adjusts search queries based on sentiment data

[1737] Step 7:

[1738] The server generates annotations based on the analyzed and filtered information, incorporating set parameters and emotional data. For example, it generates annotations such as, "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. The key points for the intermediate level are ____."

[1739] Input: Tailored search queries, related information, user preference information, sentiment data

[1740] Output: Generated annotations

[1741] Specific behavior:

[1742] The server analyzes the relevant information, parameters, and emotion data.

[1743] The server generates the best annotation

[1744] Step 8:

[1745] The generated annotations are sent from the server to the terminal, and the terminal displays them to the user, who can check the annotations in a popup or tooltip format.

[1746] Input: Generated annotation data

[1747] Output: Annotations that are visible to the user

[1748] Specific behavior:

[1749] The server sends the annotation data to the device.

[1750] The device displays the annotation data

[1751] Step 9:

[1752] The device monitors the user's annotation usage (view time, number of clicks, viewing frequency, etc.) and sends the data to the server. The server analyzes this data and stores it in a database. Based on this data, the annotation generation algorithm is continuously trained and optimized.

[1753] Input: User usage data

[1754] Output: Improved annotation generation algorithm

[1755] Specific behavior:

[1756] Device monitors usage

[1757] The device sends usage data to the server

[1758] The server analyzes the data and trains and optimizes the algorithm.

[1759] (Application example 2)

[1760] 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."

[1761] While conventional annotation generation systems can generate annotations based on a user's knowledge level and areas of interest, they cannot provide optimal annotations that take into account the user's emotional state. This can lead to users finding it difficult to understand or becoming confused, resulting in reduced learning efficiency.

[1762] Furthermore, existing systems lack the flexibility to respond to user emotions, such as providing simpler explanations to confused users. This leads to a poor user experience. To address these issues, a new system is needed that can recognize user emotions and adjust annotation content accordingly.

[1763] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1764] In this invention, the server includes: a setting means for a user to set his / her knowledge level, field of interest, and annotation depth; an input means for a user to input a sentence or document to which the user wants to annotate; a search means for generating a search query based on data obtained from the setting means and the input means and searching for related information; an annotation generation means for analyzing and organizing the related information obtained by the search means and generating an annotation based on parameters set by the user; a display means for displaying the generated annotation to the user; a learning means for monitoring the user's usage status and updating the algorithm of the annotation generation means; an emotion recognition means for recognizing the user's emotions; and a query adjustment means for adjusting the search query based on emotion data obtained by the emotion recognition means. This makes it possible to provide optimal annotations according to the user's emotional state as well as their knowledge level and field of interest.

[1765] The "setting means" is a means for providing a function for a user to set his / her own knowledge level, field of interest, and depth of annotation.

[1766] An "input means" is a means for a user to input a sentence or document to which the user wishes to add an annotation.

[1767] The "search means" is a means for generating a search query based on data obtained from the setting means and input means, and for searching for related information.

[1768] The "annotation generation means" is a means for analyzing and organizing the related information obtained by the search means, and generating annotations based on the parameters set by the user.

[1769] The "display means" is a means for displaying the generated annotation to the user.

[1770] The "learning means" is a means for monitoring the user's usage and updating the algorithm of the annotation generating means.

[1771] The "emotion recognition means" is a means including a sensor and an analysis device for recognizing the user's emotions.

[1772] The "query adjustment means" is a means for adjusting a search query based on emotion data acquired by the emotion recognition means.

[1773] This invention provides a system that automatically generates annotations based on each user's knowledge level and areas of interest, and further provides annotations optimized according to the user's emotions using an emotion recognition function. This system includes a setting means, an input means, a search means, an annotation generation means, a display means, a learning means, an emotion recognition means, and a query adjustment means.

[1774] 1. Program Generation

[1775] The system for realizing this invention is composed of the following programs: First, a user inputs their knowledge level, field of interest, and annotation depth using the setting means. Then, they input the sentence or document they want to annotate using the input means. Based on this data, the search means generates an appropriate search query and searches for related information from the Internet or an internal database.

[1776] The retrieved information is analyzed and organized by the annotation generation means, and annotations are generated based on the user's set parameters. The generated annotations are displayed to the user by the display means. Furthermore, the learning means monitors the user's usage status and continuously updates the algorithm of the annotation generation means. The emotion recognition means also plays an important role in this invention. The emotion data acquired by the emotion recognition means is analyzed by the query adjustment means, and the search query is adjusted.

[1777] 2. Program processing explanation

[1778] The system is realized by combining multiple pieces of hardware and software, the details of which are explained below.

[1779] Hardware

[1780] Device: A device used by a user to set up or input information (e.g., smartphone, tablet, computer)

[1781] Server: Generates search queries, finds relevant information, generates annotations, stores data, and learns from it.

[1782] Emotion recognition sensors: Cameras and voice recognition devices to recognize user emotions

[1783] software

[1784] Settings and input app: An interface for users to set their knowledge level, areas of interest, and annotation depth, and then input sentences and documents.

[1785] Search algorithms: Software that generates search queries based on user preferences and input data to find relevant information.

[1786] Annotation generation algorithm: Software for analyzing and organizing retrieved information and generating annotations

[1787] Viewer app: An interface for displaying generated annotations to the user.

[1788] Learning algorithm: Software for monitoring user usage and updating the annotation generation algorithm

[1789] Emotion recognition algorithms: Software for analyzing user emotions and adjusting search queries based on the acquired emotional data.

[1790] These hardware and software are integrated to provide optimal annotations according to the user's knowledge level, areas of interest, and even emotions.

[1791] 3. Specific Examples

[1792] The following examples are used to illustrate how the invention may be put into practice.

[1793] Example 1:

[1794] If a user is interested in intermediate level chemistry and wants to generate annotations on "how lithium ion batteries work," the system works as follows:

[1795] 1. Settings: The user sets the knowledge level to "Intermediate", the area of ​​interest to "Chemistry", and the annotation depth to "Detailed".

[1796] 2. Input: Enter the sentence "How lithium-ion batteries work."

[1797] 3. Emotion Recognition: Detects confused facial expressions of the user.

[1798] 4. Query generation: Generate a search query based on “Lithium ion battery intermediate working principle.”

[1799] 5. Information retrieval: Searching for information from the internet and internal databases.

[1800] 6. Annotation generation: Annotations are generated in the form of "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process."

[1801] 7. Display: Show the generated annotations to the user.

[1802] Example prompt sentence:

[1803] By inputting the following prompt sentence into the generative AI model, the optimal annotation will be generated.

[1804] Lithium-ion Battery Working Principle Intermediate Chemistry

[1805] In this way, the efficiency of learning and understanding can be improved by providing optimal annotations based on the user's knowledge level, areas of interest, and emotional state.

[1806] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1807] Program processing steps

[1808] Step 1:

[1809] The user uses the setting means to set his / her knowledge level, field of interest, and depth of annotation.

[1810] Input: Knowledge level, area of ​​interest, depth of annotation

[1811] Output: User profile (e.g. {"knowledge_level": "Intermediate", "interest_field": "Chemistry", "annotation_depth": "Detailed"})

[1812] Specifically, a user opens the application's settings screen, selects their knowledge level (beginner, intermediate, advanced), field of interest (e.g., chemistry, physics, economics), and annotation depth (overview, detailed, specialized), and then presses the save button. This information is saved in the database as a user profile.

[1813] Step 2:

[1814] The user uses the input means to input a sentence or document to which the user wishes to add an annotation.

[1815] Input: A sentence or document (e.g., "How a lithium-ion battery works")

[1816] Output: User input data

[1817] Specifically, the user types the sentence or document they want to annotate into the text input field and presses the enter key. The entered data is sent to the server along with the user ID.

[1818] Step 3:

[1819] The terminal recognizes the user's emotions using the emotion recognition means.

[1820] Input: User facial and voice data

[1821] Output: Emotion data (e.g., "confused")

[1822] Specifically, the device's built-in camera and microphone collect the user's facial expressions and voice in real time, which are then analyzed using an emotion recognition algorithm. The analysis results determine whether the user is confused or not, and emotional data is generated.

[1823] Step 4:

[1824] The server generates a search query based on the data obtained from the setting means and the input means, and further adjusts the search query based on emotion data, if any.

[1825] Input: User profile, user input data, emotion data

[1826] Output: Adjusted search query (e.g., "Lithium-ion battery intermediate working principle easy")

[1827] Specifically, the server generates an initial search query based on the user profile and input data. It then checks the emotion data and adjusts the query, such as adding "easy" if the user is confused.

[1828] Step 5:

[1829] The server uses the tailored search query to search for relevant information.

[1830] Input: Adjusted search query

[1831] Output: Search result data (e.g., search result list)

[1832] Specifically, the server submits tailored search queries to the internet and internal databases to gather relevant information, and the search results list is scored and filtered based on the relevance of the information.

[1833] Step 6:

[1834] The server analyzes and organizes the relevant information retrieved by the search tool and generates annotations based on the user's set parameters.

[1835] Input: Search result data, user profile

[1836] Output: Annotation data (e.g., "Lithium-ion batteries generate energy by moving lithium ions between the positive and negative electrodes. XX is important in this process.")

[1837] Specifically, the server generates annotations based on the search result list, tailored to the user's knowledge level and area of ​​interest. For example, an intermediate-level user might be provided with annotations that include more detailed and technical content.

[1838] Step 7:

[1839] The server transmits the generated annotations to the user terminal, which displays them to the user.

[1840] Input: annotation data

[1841] Output: Display annotations

[1842] Specifically, the generated annotation data is sent from the server to the user's terminal and displayed to the user through a display application on the terminal. The user can check the annotations in a pop-up format or a tooltip format.

[1843] Step 8:

[1844] The device monitors the user's usage and sends the data to the server, which then updates the annotation generation algorithm based on the data.

[1845] Input: Usage data (e.g., browsing time, clicks)

[1846] Output: Updated algorithm

[1847] Specifically, the device records how long the user views the annotation, which parts they clicked on, how often they viewed it, and so on, and sends this information to the server. The server analyzes this data and continues to improve the annotation generation algorithm.

[1848] Through these steps, it is possible to provide annotations that are optimal for the user's knowledge level, areas of interest, and emotional state.

[1849] 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.

[1850] 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.

[1851] 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.

[1852] 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.

[1853] 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.

[1854] 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.

[1855] 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).

[1856] 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.

[1857] 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."

[1858] 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.

[1859] 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).

[1860] 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.

[1861] 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.

[1862] 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.

[1863] 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.

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] The following is further disclosed regarding the above embodiment.

[1871] (Claim 1)

[1872] A setting means for a user to set his / her own knowledge level, field of interest, and depth of annotation;

[1873] an input means for inputting a sentence or document to be annotated by a user;

[1874] a search means for generating a search query based on data obtained from the setting means and the input means, and searching for related information;

[1875] An annotation generating means for analyzing and organizing the related information acquired by the searching means and generating annotations based on parameters set by a user;

[1876] a display means for displaying the generated annotation to a user;

[1877] a learning means for monitoring a user's usage status and updating the algorithm of the annotation generating means;

[1878] A system including:

[1879] (Claim 2)

[1880] a transmitting means for transmitting data including the text data input by the user and the user ID to the server;

[1881] receiving means for presenting the annotation data received from the server to a user;

[1882] The system of claim 1 further comprising:

[1883] (Claim 3)

[1884] 2. The system according to claim 1, wherein the search query generated by the search means is optimized based on the user's knowledge level and areas of interest.

[1885] "Example 1"

[1886] (Claim 1)

[1887] A setting means for a user to set his / her own knowledge level, field of interest, and depth of annotation;

[1888] an input means for inputting a sentence or document to be annotated by a user;

[1889] a search means for generating a search query based on data obtained from the setting means and the input means, and searching for related information;

[1890] An annotation generation means using a generative AI model that analyzes and organizes the related information acquired by the search means and generates annotations based on parameters set by a user;

[1891] a display means for displaying the generated annotation to a user;

[1892] a learning means for monitoring a user's usage status and updating the algorithm of the annotation generating means;

[1893] A system including:

[1894] (Claim 2)

[1895] a transmitting means for transmitting the text data input by the user and the user identification information to the server;

[1896] receiving means for presenting the annotation data received from the server to a user;

[1897] The system of claim 1 further comprising:

[1898] (Claim 3)

[1899] 2. The system according to claim 1, wherein the search query generated by the search means is optimized based on the user's knowledge level and areas of interest.

[1900] "Application Example 1"

[1901] (Claim 1)

[1902] A setting means for a user to set his / her own knowledge level, field of interest, and depth of annotation;

[1903] an input means for inputting a sentence or document to be annotated by a user;

[1904] a search means for generating a search query based on data obtained from the setting means and the input means, and searching for related information;

[1905] An annotation generating means for analyzing and organizing the related information acquired by the searching means and generating annotations based on parameters set by a user;

[1906] a display means for displaying the generated annotation to a user;

[1907] a visual information gathering means for gathering product information using a visual display device worn by a user and generating annotations based on user settings;

[1908] a learning means for monitoring a user's usage status and updating the algorithm of the annotation generating means;

[1909] A system including:

[1910] (Claim 2)

[1911] a transmitting means for transmitting data including the text data input by the user and the user ID to the server;

[1912] receiving means for presenting the annotation data received from the server to a user;

[1913] The system of claim 1 further comprising:

[1914] (Claim 3)

[1915] 2. The system according to claim 1, wherein the search query generated by the search means is optimized based on the user's knowledge level and areas of interest.

[1916] "Example 2: Combining Emotion Engines"

[1917] (Claim 1)

[1918] A setting means for a user to set his / her own knowledge...

Claims

1. A setting means for a user to set his / her own knowledge level, field of interest, and depth of annotation; an input means for inputting a sentence or document to be annotated by a user; a search means for generating a search query based on data obtained from the setting means and the input means, and searching for related information; An annotation generating means for analyzing and organizing the related information acquired by the searching means and generating annotations based on parameters set by a user; a display means for displaying the generated annotation to a user; a learning means for monitoring a user's usage status and updating the algorithm of the annotation generating means; A system including:

2. a transmitting means for transmitting data including the text data input by the user and the user ID to the server; receiving means for presenting the annotation data received from the server to a user; The system of claim 1 further comprising:

3. 2. The system according to claim 1, wherein the search query generated by the search means is optimized based on the user's level of knowledge and areas of interest.

Images