System

Abstract

A system is provided.SOLUTION: The system includes a means for a user to input a performance style, a personal preference, and a skill level, a means for transmitting the input information to a server, a means for the server to perform analysis using a AI model on the basis of the received information, a means for recommending an optimum musical instrument on the basis of an analysis result, and a means for displaying a recommendation result to the user.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] The wide variety of options and lack of personalized guidance when selecting a guitar makes it difficult for customers to find the perfect guitar for them. This problem is particularly pronounced for beginners and less experienced users, who lack proper advice and guidelines on how to choose a guitar that suits their playing style and preferences. [Means for solving the problem]

[0005] This invention solves the above-mentioned problems by providing a system that recommends the optimal guitar based on a customer's playing style, preferences, and skill level. Specifically, the system includes a means for a user to input their playing style, personal preferences, and skill level, a means for transmitting the input information to a server, a means for the server to analyze the received information using an AI model, a means for recommending the optimal instrument based on the analysis results, and a means for displaying the recommendation results to the user. This allows users to easily find the guitar that's best for them.

[0006] "User" refers to an individual consumer or customer who uses the system.

[0007] "Performance style" refers to the genre of music and performance method that the user prefers.

[0008] "Personal preference" refers to the specific characteristics of the guitar that a user desires, such as color, shape, material, etc.

[0009] "Skill level" refers to the user's level of proficiency in playing technique, such as beginner, intermediate, or advanced.

[0010] "Means of input" refers to the interface, such as a form or input field, through which a user can provide the required information to the system.

[0011] "Means for sending" refers to the communication protocol or device used to transfer the information entered by the user to the server.

[0012] "Server" refers to the computer system that processes information received from users and performs analysis using AI models.

[0013] An "AI model" refers to a program that uses machine learning algorithms and data analysis techniques to derive appropriate results based on user information.

[0014] "Means of analysis" refers to the process of applying an AI model to evaluate and analyze user-provided information.

[0015] "Recommendation means" refers to a method of selecting the most suitable instrument for the user based on the analysis results and displaying it.

[0016] "Means for displaying" refers to a display or interface that visually presents the analysis results and recommendations to the user. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the best instrument based on the input information, allowing users to easily find the guitar that best suits them. This system is implemented as follows.

[0039] Enter user information

[0040] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[0041] Sending information

[0042] The terminal sends the information entered by the user to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[0043] Analysis of information

[0044] The server analyzes the data received from the user. Using AI models, the server evaluates the user's playing style and preferences based on the information provided, and recommends the most suitable guitar model. This analysis also takes into account past data and other user information to make more accurate recommendations.

[0045] Guitar Recommendations

[0046] The server generates a list of suitable guitars from the analysis results and recommends them along with detailed information (manufacturer, model, features, etc.). For example, for a beginner who likes a rock style and red, "ABC model (red) from XYZ manufacturer" will be recommended.

[0047] Sending Recommendations

[0048] The server generates recommendations and sends them to the device, which include information customized based on the specific needs entered by the user.

[0049] Displaying the results

[0050] The device receives the recommendations from the server and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[0051] Specific examples

[0052] As a specific example, consider a beginner rock player looking for a red guitar.

[0053] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0054] 2. The device sends this information to the server.

[0055] 3. The server analyzes the received data using an AI model and then selects the appropriate guitar.

[0056] 4. The server recommends "XYZ manufacturer's ABC model (red)" and sends this information to the device.

[0057] 5. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0058] In this way, the system helps users find the perfect guitar for them.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] Users access the system and enter their playing style, personal preferences, and skill level, providing detailed information via a web form or app interface.

[0062] Step 2:

[0063] The device collects user input information and converts it into a data format for sending to the server, for example, packaging the data in JSON format.

[0064] Step 3:

[0065] The device sends the converted data to the server using a secure communication protocol (e.g., HTTPS).

[0066] Step 4:

[0067] Validate the data received by the server to ensure it is in the correct format and contains all required fields.

[0068] Step 5:

[0069] The server then inputs the verified data into an AI model for analysis, which then selects the best guitar for you based on your playing style, preferences, and skill level.

[0070] Step 6:

[0071] The server generates a list of suitable guitars based on the analysis results of the AI ​​model, including details about the instrument (e.g., manufacturer, model, color, features).

[0072] Step 7:

[0073] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[0074] Step 8:

[0075] The device receives the recommendation results and displays them to the user, who can then check the details and choose the best guitar based on the displayed information.

[0076] Example 1

[0077] 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."

[0078] Today's users are often overwhelmed by the sheer number of options available when choosing the perfect instrument for them, which can be a time-consuming and labor-intensive process. Another factor is the difficulty of obtaining recommendations that adequately reflect the user's personal preferences and skill level. In these circumstances, there is a need to efficiently and accurately find an instrument that meets the user's needs.

[0079] 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.

[0080] In this invention, the server includes means for a user to input their playing style, personal preferences, and skill level, means for transmitting the input information to a data processing device, means for the data processing device to analyze the received information using an artificial intelligence model, means for recommending an optimal instrument based on the analysis results, means for displaying the recommendation results to the user, means for using a communication protocol to encrypt and transmit the user's data, and means for including detailed descriptions and images in the recommendation results, thereby enabling optimal instrument recommendations based on the user's personal needs and preferences.

[0081] A "user" is an individual who accesses the system and inputs their playing style, personal preferences, and skill level.

[0082] "Performance style" refers to the type or genre of music (e.g., rock, jazz, classical) that a user inputs into the system.

[0083] "Personal preferences" refers to information that a user inputs into the system, such as preferred attributes of an instrument, such as color or material.

[0084] "Skill level" refers to the degree of skill a user has in playing a musical instrument (e.g., beginner, intermediate, advanced) that the user inputs into the system.

[0085] "Data processing device" refers to a server or computer system that receives and analyzes information sent by a user.

[0086] "Artificial intelligence model" refers to algorithms and programs that use machine learning and deep learning technologies to analyze user input and recommend the most suitable instrument.

[0087] A "communication protocol" is a data communication rule for securely transmitting user data, and refers to one that employs encryption technology (e.g., HTTPS).

[0088] "Analysis results" refers to the output information after the artificial intelligence model recommends the optimal instrument based on the user's input information.

[0089] "Detailed Description" refers to information about the recommended instrument, including the make, model, and features.

[0090] "Images" are visual information about the recommended musical instrument displayed as diagrams or photographs.

[0091] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the most suitable instrument based on the input information, allowing users to easily find the instrument that best suits them. This system is specifically implemented as follows.

[0092] A user accesses the system using a web browser or mobile application. First, the user uses the interface provided to input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., instrument color, material), and skill level (e.g., beginner, intermediate, advanced). This information is sent to a data processing device and stored in the system as a user profile.

[0093] The device automatically converts the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, which encrypts the data and ensures its security during transmission.

[0094] The server uses a generative AI model to analyze the received JSON data. For example, a generative AI model such as OpenAI's GPT-4 is used. This generative AI model receives the user's input information in the form of a prompt and analyzes it. An example of a specific prompt is as follows:

[0095] User Information:

[0096] Playing style: Rock

[0097] Favorite color: Red

[0098] Skill level: Beginner

[0099] Recommend the best instrument for this user.

[0100] The server generates a list of optimal instruments based on the analysis results from the generative AI model. This list includes detailed information about each instrument (manufacturer, model, features, etc.). For example, the analysis may recommend "Manufacturer ABC model (red)."

[0101] The generated instrument recommendation list is converted to JSON format and sent to the device using HTTPS. The device parses the received data and displays it in a user-friendly format, including detailed descriptions and images.

[0102] To give a specific example, if a beginner rock player is looking for a red instrument, the user accesses the system and enters the following information:

[0103] Playing style: Rock

[0104] Favorite color: Red

[0105] Skill level: Beginner

[0106] The device sends this information to the server, which then uses the generative AI model to analyze it and recommend "Manufacturer ABC Model (Red)." This information is then sent back to the device, where the user can finally view detailed information about the instrument.

[0107] The system recommends instruments based on the user's specific needs and provides useful assistance to help the user make an appropriate choice.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] A user accesses the system and inputs their playing style, personal preferences, and skill level into the provided interface. For example, a user might input information such as "playing style: rock, preferences: red, skill level: beginner." After input, the device converts this information into JSON format. The input is information such as the user's preferences and skill level, and the output is user data in JSON format.

[0111] Step 2:

[0112] The terminal sends the JSON-formatted user data generated in step 1 to the server using the HTTPS protocol. The input is the JSON data generated in step 1, and the output is the data securely transferred to the server. Data encryption is performed during this process to ensure security.

[0113] Step 3:

[0114] The server parses the received JSON data using a generative AI model (e.g., GPT-4). The server converts the JSON data into a prompt and inputs it into the generative AI model. The specific prompt is as follows:

[0115] User Information:

[0116] Playing style: Rock

[0117] Favorite color: Red

[0118] Skill level: Beginner

[0119] Recommend the best instrument for this user.

[0120] The input is JSON data containing user information, and the output is the recommendation results generated by the generative AI model, which are returned as a list of optimal instruments.

[0121] Step 4:

[0122] The server further processes the recommendation results from the generative AI model and retrieves detailed instrument information (e.g., manufacturer, model, features, etc.), which may include retrieving information from an SQL database or other REST API. The input is the recommendation results from the generative AI model, and the output is data containing detailed instrument information.

[0123] Step 5:

[0124] The server converts the detailed instrument information it acquires into JSON format and sends it to the device using the HTTPS protocol. The input is data containing the detailed instrument information, and the output is the JSON-formatted data sent to the device. This data is also encrypted to ensure security.

[0125] Step 6:

[0126] The device analyzes the JSON format recommendation results received and displays them in a user-friendly format. Specifically, detailed information and images of the recommended instruments are displayed on the UI of a web page or mobile app. The input is JSON data containing detailed instrument information received from the server, and the output is a display format that the user can visually confirm. This allows the user to check detailed information about the recommended instruments and make a purchasing decision.

[0127] (Application example 1)

[0128] 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."

[0129] Conventional instrument recommendation systems have had the problem of making it difficult for users to find the instrument that best suits them. Furthermore, the information about the recommended instruments is insufficient, making them inadequate for users to use as a basis for making a final selection. Furthermore, it is difficult to provide recommendations that meet the specific needs of users, and the accuracy of recommendations is low, especially when multiple parameters need to be considered.

[0130] 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.

[0131] In this invention, the server includes: a means for a user to input their playing style, personal preferences, and skill level; a means for transmitting the input information to the server; a means for the server to analyze the received information using a generative AI model; a means for recommending an optimal instrument based on the analysis results; a means for displaying the recommendation results on the user's device; a means for transmitting the user's input information to the server in JSON format; and a means for the server to send a prompt to the generative AI model to obtain a recommendation result. This enables highly accurate instrument recommendations based on the user's specific needs. In addition, providing detailed information about the recommended instruments makes it easier for the user to make an appropriate selection.

[0132] "User" means any person or entity that accesses the System and inputs their playing style, preferences, and skill level.

[0133] "Performance style" refers to the musical genre or specific performance technique that a user prefers to play.

[0134] "Personal preference" refers to specific elements of the instrument that a user chooses, such as color, material, and design.

[0135] "Skill level" is an index that indicates the user's level of proficiency in playing technique, and is classified as beginner, intermediate, advanced, etc.

[0136] "Server" refers to the computer system that analyzes the information received from the user and recommends appropriate instruments using a generative AI model.

[0137] "Generative AI model" refers to an artificial intelligence model that analyzes user input information and takes into account past data and other user profiles to recommend the most suitable instrument.

[0138] "Input means" refers to an interface or device that allows a user to input playing style, personal preferences, and skill level.

[0139] "Transmission means" refers to a communication protocol and communication device for transmitting user input information to a server.

[0140] "Analysis means" refers to the computational process by which the server uses a generative AI model to recommend instruments based on information received from the user.

[0141] "Recommendation means" refers to the method and function of presenting the most suitable instrument to the user based on the results of analysis by the generative AI model.

[0142] "Display means" refers to an interface or device that visually presents the recommendation results sent from the server to the user.

[0143] "JSON format" is an abbreviation for JavaScript Object Notation and refers to a data exchange format that represents structured data in text format.

[0144] A "prompt sentence" refers to an input sentence that follows a specific format or rules to send instructions to a generative AI model.

[0145] The system for implementing this invention recommends the most suitable instrument to a user based on their playing style, preferences, and skill level. The system operates as follows:

[0146] First, a user accesses the system and inputs their playing style, personal preferences, and skill level through the user interface. The playing style input by the user can be, for example, rock, jazz, or classical. Personal preferences, on the other hand, include information about the color, material, and design of the instrument. Skill level indicates the user's level of proficiency in playing techniques, such as beginner, intermediate, or advanced.

[0147] The user's device then sends this input information in JSON format to the server, using a secure protocol such as HTTPS.

[0148] The server inputs the received user information into a generative AI model for analysis. This analysis takes into account past data and the profiles of other users, resulting in a highly accurate model that recommends the most suitable instrument for the user. Generative AI models are sometimes built using Python libraries such as TensorFlow and PyTorch.

[0149] Based on the analysis results, the server generates a list of suitable instruments and generates a recommendation result including detailed information (manufacturer, model, features, etc.). This recommendation result is obtained by sending instructions to the generative AI model using a prompt. For example, the prompt might be in the format "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner."

[0150] Finally, the server sends the recommendation results to the user's device, which displays them, including detailed information and images of the recommended instruments, allowing the user to visually confirm and select the instrument that best suits them.

[0151] As a concrete example, if a user inputs parameters such as "rock," "red," and "beginner" into the system, the server receives that information and analyzes it using a generative AI model. As a result of the analysis, a specific recommendation result such as "a certain model (red) from a certain manufacturer" is generated and sent to the user's device. As a result, the user can easily find the perfect guitar.

[0152] In this way, the system can recommend instruments with high accuracy according to the specific needs of the user, allowing a wide range of users, from beginners to advanced players, to reduce the effort required for choosing an instrument.

[0153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The user enters their playing style, personal preferences, and skill level into the interface. For example, the information entered by the user might be in the form of "playing style: rock," "preferences: red," or "skill level: beginner." This input data is then sent to the server in the next step.

[0156] Step 2:

[0157] The device sends the information entered by the user to the server in JSON format using a secure communication protocol such as HTTPS. The input data (playing style, preferences, skill level) is converted to JSON format and sent to the server.

[0158] Step 3:

[0159] The server parses the received JSON data and inputs it into a generative AI model. Based on the input data (playing style, preferences, skill level), the generative AI model analyzes the data and begins the process of recommending the most suitable instrument. The AI ​​models used here are often built using TensorFlow or PyTorch.

[0160] Step 4:

[0161] The generative AI model analyzes the incoming data, taking into account past data and other users' profiles. Instructions are sent to the generative AI model using prompts (e.g., "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner"). Data calculations are performed using the input data to generate the best instrument recommendation.

[0162] Step 5:

[0163] The server generates an optimal instrument list based on the analysis results from the generative AI model. The recommendation results include detailed information such as manufacturer, model, and features. This data is organized on the server and prepared for transmission to the user.

[0164] Step 6:

[0165] The server sends the generated recommendation results to the user's device. These recommendation results are converted back to JSON format and sent to the user's device. Examples of recommendation results include "Manufacturer: A," "Model: B," "Color: Red," and "Features: Rock guitar for beginners."

[0166] Step 7:

[0167] The device displays the recommendation results received from the server on the user interface. This allows the user to check detailed information and images of the recommended instruments. Based on the displayed information, the user can select and purchase the instrument of their choice.

[0168] These steps allow users to easily find the instrument that best suits their needs, significantly reducing the effort required to choose an instrument.

[0169] 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.

[0170] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[0171] Enter user information

[0172] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[0173] Emotion recognition

[0174] The device collects the user's facial expressions, tone of voice, input text, etc. and sends them to the emotion engine, which analyzes this data and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[0175] Sending information

[0176] The device sends the information entered by the user and the analysis results of the emotion engine to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[0177] Analysis of information

[0178] The server validates the received data to ensure it is in the correct format, then analyzes it using an AI model that takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the best guitar.

[0179] Guitar Recommendations

[0180] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a calm design for beginners will be recommended.

[0181] Sending Recommendations

[0182] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[0183] Displaying the results

[0184] The device receives the recommendations and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[0185] Specific examples

[0186] For example, consider a beginner rock player looking for a red guitar.

[0187] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0188] 2. The device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state.

[0189] 3. The device sends this information to the server.

[0190] 4. The server analyzes the received data using an AI model and then selects the next appropriate guitar. Because the user is excited, a guitar with a brighter, more active design is recommended.

[0191] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[0192] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0193] In this way, the system makes more personalized guitar recommendations that take into account the user's emotional state.

[0194] The processing flow will be explained below.

[0195] Step 1:

[0196] Users access the system and input their playing style, personal preferences, and skill level through a web form or application interface.

[0197] Step 2:

[0198] The device collects user input information and sends it to the emotion engine. The user's facial expressions and tone of voice are provided to the emotion engine via the camera and microphone.

[0199] Step 3:

[0200] The terminal receives the analysis results of the emotion engine and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[0201] Step 4:

[0202] The device packages the user's emotional state and input information into a single data packet and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0203] Step 5:

[0204] The server validates the data packet it receives to ensure that it contains all required fields in the correct format, including verifying the integrity of the data.

[0205] Step 6:

[0206] The server inputs the verified data into an AI model for analysis, which then selects the best guitar for the user, taking into account their playing style, preferences, skill level, and emotional state.

[0207] Step 7:

[0208] The server uses the AI ​​model's analysis to generate a list of optimal guitars, including details about the instrument (e.g., make, model, color, features), and adjusts recommendations based on the user's emotional state.

[0209] Step 8:

[0210] The server generates a recommendation list and sends it to the terminal as a data packet. It is important that the criteria for selecting recommended guitars are adjusted according to the user's emotional state.

[0211] Step 9:

[0212] The device receives the recommendation list and displays it to the user, including detailed descriptions and images, allowing the user to learn more about the recommended guitars.

[0213] Step 10:

[0214] The user then selects from the recommended guitars based on the displayed information, and the user is provided with an easy-to-understand interface to help them choose the guitar that best suits them.

[0215] Example 2

[0216] 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."

[0217] Current instrument recommendation systems make recommendations based on a user's playing style, personal preferences, and skill level, but they are unable to take into account the user's emotional state, making personalized recommendations difficult. Furthermore, detailed information about the recommended instruments is often lacking, making it difficult for users to make informed decisions.

[0218] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for the user to input the playing style, personal preferences, and skill level; means for saving the input information; means for collecting the user's facial expression, tone of voice, and input text; means for recognizing the user's emotional state based on the collected information; means for transmitting the input information and the emotional state to the server; means for performing analysis using a generative AI model based on the information received by the server; means for recommending an optimal instrument based on the analysis results; and means for displaying the recommendation results to the user. This enables personalized instrument recommendations that take the user's emotional state into consideration, and by providing recommendation results that include detailed information and images, the user can make appropriate decisions with sufficient information.

[0219] "User" refers to a person who uses the instrument recommendation system.

[0220] "Performance style" refers to the genre of music the user prefers, such as rock, jazz, or classical.

[0221] "Personal preferences" refers to a user's particular preferences for musical instruments, such as guitar color, material, etc.

[0222] "Skill level" indicates the user's technical proficiency in playing a musical instrument, and includes categories such as beginner, intermediate, and advanced.

[0223] "Facial expressions" refer to the movements and expressions of a user's face and are used to read emotions.

[0224] "Tone of voice" refers to the tone of a user's speech that indicates their tone and emotion.

[0225] "Input text" refers to textual information that a user inputs into a system.

[0226] "Emotional state" indicates the user's current psychological state, and includes joy, sadness, excitement, tension, and the like.

[0227] "Emotion engine" refers to a software means for analyzing collected emotion-related data and determining a user's emotional state.

[0228] "Server" refers to the computer system that receives information sent by users and analyzes it using a generative AI model.

[0229] "Generative AI model" refers to an algorithm that selects the optimal instrument based on a user's playing style, personal preferences, skill level, and emotional state.

[0230] "Recommendation Results" refers to the list of optimal instruments presented to the User based on the analysis of the Generative AI Model.

[0231] "Detailed information" refers to supplementary information required by the user to make a selection, such as the make, model, color, and features of the recommended instruments.

[0232] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[0233] First, a user accesses the system and inputs their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced) into the provided interface. This information is then saved on the device as a user profile.

[0234] The device then collects the user's facial expressions, tone of voice, and input text, and sends them to an emotion engine. The emotion engine analyzes this data and determines the user's current emotional state (e.g., happy, sad, excited, nervous). This process uses software such as Microsoft Azure Cognitive Services and IBM Watson.

[0235] The device then sends the user's input and the emotion engine's analysis results to the server, using secure communication protocols such as HTTPS to ensure that the user's data reaches the server safely.

[0236] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model, such as TensorFlow or PyTorch, which takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the optimal guitar.

[0237] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a subdued design for beginners will be recommended.

[0238] The server then sends the generated recommendation list to the device. The recommendation results are packaged in a format that is easy for the user to understand. The device receives the recommendation results and displays them to the user. The displayed information is easy to understand, and includes detailed descriptions and images. This allows the user to view detailed information about the recommended guitars and make an appropriate selection.

[0239] Specific examples

[0240] For example, consider a beginner rock player looking for a red guitar.

[0241] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0242] 2. The device sends the user's facial expressions and tone of voice to an emotion engine (e.g., Microsoft Azure Cognitive Services), which determines that the user is in an "excited" state.

[0243] 3. The device sends this information to the server.

[0244] 4. The server analyzes the received data using TensorFlow and then selects the appropriate guitar. In this case, because the user is excited, a guitar with a brighter and more active design is recommended.

[0245] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[0246] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0247] Prompt Sentence Examples

[0248] "Recommend the best guitar for the user based on the following information: playing style: rock, personal preference: red, skill level: beginner. emotional state: excited."

[0249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0250] Step 1:

[0251] A user accesses the system and enters their playing style, personal preferences, and skill level into the provided interface. The device receives this and stores it as a user profile. For example, if a user enters "rock," "red," and "beginner," the device formats and stores this data. The inputs are "playing style," "personal preferences," and "skill level." The output is the saved "user profile."

[0252] Step 2:

[0253] The device collects the user's facial expressions, tone of voice, input text, etc. This collection is done using hardware such as a camera and microphone. The collected data is sent to the emotion engine. For example, while a user is speaking in front of the camera, the device captures their facial expressions and tone of voice in real time and sends them to the emotion engine. The inputs are "facial expression data," "voice data," and "input text." The output is "collected data."

[0254] Step 3:

[0255] The emotion engine analyzes the received data and determines the user's current emotional state. The analysis is performed using Microsoft Azure Cognitive Services and IBM Watson. For example, the emotion engine analyzes the user's facial expression and tone of voice and determines that the user is in an "excited" state. The input is "collected data." The output is "emotional state."

[0256] Step 4:

[0257] The device sends the information entered by the user and the analysis results of the emotion engine to the server. In this process, data is transmitted using a secure communication protocol (e.g., HTTPS). The input is the "user profile" and "emotional state." The output is the "transmitted data."

[0258] Step 5:

[0259] The server validates the received data and ensures that it is in the correct format. It then analyzes it using a generative AI model such as TensorFlow or PyTorch. For example, the server validates the received data and inputs it into a generative AI model, which then analyzes it and outputs the best guitar candidates for the user. The input is the "transmitted data." The output is the "analysis results."

[0260] Step 6:

[0261] The server generates a list of optimal guitars from the analysis results. The list includes details of the instruments (e.g., manufacturer, model, color, features). For example, if the user is an excited rock-loving beginner, a guitar with a bright and active design is recommended. The input is the "analysis results." The output is the "recommendation list."

[0262] Step 7:

[0263] The server sends the generated recommendation list to the device. This process also uses a secure communication protocol (e.g., HTTPS) to transmit data. The input is the "recommendation list." The output is the "transmitted data."

[0264] Step 8:

[0265] The device receives the recommendation results and displays them to the user. The displayed information is in an easy-to-understand format, and includes detailed descriptions and images. For example, when the device receives a list of recommendations and displays it to the user, the user can view detailed information about the recommended guitar. The input is "transmitted data." The output is "displayed recommendation results."

[0266] (Application example 2)

[0267] 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."

[0268] Conventional instrument recommendation systems only consider fixed user information and are unable to reflect the user's emotional state or real-time feedback. As a result, it is difficult for users to choose the instrument that best suits their current mood and state, which can lead to lower satisfaction. Furthermore, when it comes to reward recommendations for electronic payment services, a personalized experience cannot be provided because the system does not consider the user's emotions, resulting in low reward usage rates.

[0269] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their playing style, personal preferences, and skill level; means for recognizing the user's facial expression and tone of voice and determining their current emotional state using an emotion engine; means for transmitting the input information and the analysis results of the emotion engine to the server; means for analyzing the received information using a generative AI model and recommending optimal instruments and benefits taking the user's emotional state into consideration; and means for displaying the recommendation results to the user. This enables more personalized recommendations of instruments and benefits that take the user's emotional state into consideration.

[0270] The "means for user input of playing style, personal preferences, and skill level" refers to an interface that allows a user to provide the system with their own musical playing style, personal preferences, and playing skill level.

[0271] "Means for recognizing a user's facial expressions and tone of voice and using an emotion engine to determine their current emotional state" refers to technology in which a user inputs facial expressions and tone of voice into the system via a smartphone or other device, and the data is analyzed to identify the user's emotional state.

[0272] The "means for transmitting input information and the analysis results by the emotion engine to the server" refers to a communication means for transmitting basic information collected from the user and data obtained by emotion recognition to the server via the Internet.

[0273] A "generative AI model" is an artificial intelligence algorithm that analyzes data obtained from users and generates optimal recommendations based on specific patterns and trends.

[0274] "Recommendation means" refers to the system's function of presenting the most suitable instruments and benefits to users based on information analyzed by the generative AI model.

[0275] The "means for displaying to the user" refers to a display or interface for visually presenting detailed information about the recommended instruments and special offers on the user's device.

[0276] An "emotion engine" is a software engine that analyzes the user's facial and voice data and identifies the user's current emotional state based on the results.

[0277] To put this invention into practice, a system is required for exchanging information between a terminal used by a user and a server. The specific configuration and operation of this system will now be described.

[0278] Enter user information

[0279] The user inputs their playing style, personal preferences, and skill level using a terminal. This information is saved in the system as a user profile. The input interface is a device such as a smartphone or tablet.

[0280] Emotion recognition

[0281] The device captures the user's facial expressions and tone of voice in real time and sends them to an emotion engine, which uses existing software such as Microsoft Azure Cognitive Services, to analyze the user's current emotional state (happiness, sadness, excitement, tension, etc.).

[0282] Sending information

[0283] The device sends the information entered by the user and the analysis results of the emotion engine to the server via secure HTTPS communication, ensuring the safety of the data.

[0284] Analysis of information

[0285] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model (such as TensorFlow or PyTorch) that takes into account the user's playing style, preferences, skill level, and emotional state to make optimal recommendations.

[0286] Recommending instruments and special offers

[0287] Based on the analysis results, the server recommends the most suitable musical instruments or special offers for electronic payment services. For example, if a user is feeling stressed, it will recommend relaxation-related offers (massage coupons, aroma candles, etc.). This also includes detailed information about specific products and services.

[0288] Sending and displaying recommendations

[0289] The server sends the generated recommendation list to the terminal, which displays this information in a format that is easy for the user to understand. The user can check the detailed information of the displayed instruments and benefits and make an appropriate selection.

[0290] Specific examples

[0291] For example, consider the case where a beginner rock player is looking for a red guitar and is currently in an "excited" state. First, the user inputs their playing style as "rock," their preference as "red," and their skill level as "beginner" into their device. Next, the device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state. This information is sent to the server, where the generative AI model analyzes it. As a result, it is determined that a guitar with an active design is suitable for the excited user, and a "red electric guitar from manufacturer ABC" is recommended, for example. The server sends this information to the device, which then displays the details to the user.

[0292] Prompt Sentence Examples

[0293] "If a user is stressed, what kind of reward would be appropriate? Consider past purchase history and basic information."

[0294] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0295] Step 1: Enter your user information

[0296] Users access the system using a device (smartphone or tablet) and input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced). The input information is temporarily stored on the device and organized as a user profile. This input data serves as the basis for all subsequent processing.

[0297] Step 2: Recognize emotions

[0298] The device captures the user's facial expressions and tone of voice in real time using a camera and microphone. The captured data is sent to an emotion engine (e.g., Microsoft Azure Cognitive Services) to determine the user's current emotional state (e.g., joy, sadness, excitement, or tension). The emotion engine analyzes facial expressions and voice tone to identify emotions from this data. The emotional state is output in text format.

[0299] Step 3: Submit your information

[0300] The device sends the information entered by the user (playing style, personal preferences, skill level) and the emotional state analyzed by the emotion engine to the server. The transmission uses the HTTPS protocol to ensure data security. The transmitted data is structured in JSON format or similar.

[0301] Step 4: Analyze the information

[0302] The server receives the data (user information and emotional state) sent from the device and verifies that the format is correct. Once the data is verified, the server analyzes it using a generative AI model (e.g., TensorFlow or PyTorch). The analysis takes into account the user's playing style, preferences, skill level, and emotional state to identify the most suitable instrument and rewards. The results of the data analysis are output.

[0303] Step 5: Recommend an instrument or benefit

[0304] The server generates a list of optimal instruments and rewards based on the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will include rewards related to relaxation (e.g., massage coupons, aroma candles, etc.). The recommendation list is configured with detailed information (e.g., manufacturer, model, features, etc.). The generated recommendation list is sent to the device in the next step.

[0305] Step 6: Submit your recommendation

[0306] The server sends the generated recommendation list to the device via secure communication. The recommendation list is packaged in a format that is easy for the user to understand (e.g., text and images). The sent data is structured in JSON format or similar.

[0307] Step 7: View Recommendations

[0308] The device analyzes the recommendation list received from the server and visually displays it to the user. The display includes detailed information about the recommended instruments and special offers, allowing the user to make a selection while looking at the screen. It is also possible to provide real-time user feedback.

[0309] Through this series of processes, the user can receive the optimal instrument or benefit that matches their emotional state, resulting in a high level of satisfaction.

[0310] 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.

[0311] 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.

[0312] 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.

[0313] [Second embodiment]

[0314] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0315] 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.

[0316] 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).

[0317] 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.

[0318] 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.

[0319] 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).

[0320] 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.

[0321] 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.

[0322] 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.

[0323] 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.

[0324] 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.

[0325] 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."

[0326] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the best instrument based on the input information, allowing users to easily find the guitar that best suits them. This system is implemented as follows.

[0327] Enter user information

[0328] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[0329] Sending information

[0330] The terminal sends the information entered by the user to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[0331] Analysis of information

[0332] The server analyzes the data received from the user. Using AI models, the server evaluates the user's playing style and preferences based on the information provided, and recommends the most suitable guitar model. This analysis also takes into account past data and other user information to make more accurate recommendations.

[0333] Guitar Recommendations

[0334] The server generates a list of suitable guitars from the analysis results and recommends them along with detailed information (manufacturer, model, features, etc.). For example, for a beginner who likes a rock style and red, "ABC model (red) from XYZ manufacturer" will be recommended.

[0335] Sending Recommendations

[0336] The server generates recommendations and sends them to the device, which include information customized based on the specific needs entered by the user.

[0337] Displaying the results

[0338] The device receives the recommendations from the server and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[0339] Specific examples

[0340] As a specific example, consider a beginner rock player looking for a red guitar.

[0341] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0342] 2. The device sends this information to the server.

[0343] 3. The server analyzes the received data using an AI model and then selects the appropriate guitar.

[0344] 4. The server recommends "XYZ manufacturer's ABC model (red)" and sends this information to the device.

[0345] 5. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0346] In this way, the system helps users find the perfect guitar for them.

[0347] The processing flow will be explained below.

[0348] Step 1:

[0349] Users access the system and enter their playing style, personal preferences, and skill level, providing detailed information via a web form or app interface.

[0350] Step 2:

[0351] The device collects user input information and converts it into a data format for sending to the server, for example, packaging the data in JSON format.

[0352] Step 3:

[0353] The device sends the converted data to the server using a secure communication protocol (e.g., HTTPS).

[0354] Step 4:

[0355] Validate the data received by the server to ensure it is in the correct format and contains all required fields.

[0356] Step 5:

[0357] The server then inputs the verified data into an AI model for analysis, which then selects the best guitar for you based on your playing style, preferences, and skill level.

[0358] Step 6:

[0359] The server generates a list of suitable guitars based on the analysis results of the AI ​​model, including details about the instrument (e.g., manufacturer, model, color, features).

[0360] Step 7:

[0361] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[0362] Step 8:

[0363] The device receives the recommendation results and displays them to the user, who can then check the details and choose the best guitar based on the displayed information.

[0364] Example 1

[0365] 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."

[0366] Today's users are often overwhelmed by the sheer number of options available when choosing the perfect instrument for them, which can be a time-consuming and labor-intensive process. Another factor is the difficulty of obtaining recommendations that adequately reflect the user's personal preferences and skill level. In these circumstances, there is a need to efficiently and accurately find an instrument that meets the user's needs.

[0367] 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.

[0368] In this invention, the server includes means for a user to input their playing style, personal preferences, and skill level, means for transmitting the input information to a data processing device, means for the data processing device to analyze the received information using an artificial intelligence model, means for recommending an optimal instrument based on the analysis results, means for displaying the recommendation results to the user, means for using a communication protocol to encrypt and transmit the user's data, and means for including detailed descriptions and images in the recommendation results, thereby enabling optimal instrument recommendations based on the user's personal needs and preferences.

[0369] A "user" is an individual who accesses the system and inputs their playing style, personal preferences, and skill level.

[0370] "Performance style" refers to the type or genre of music (e.g., rock, jazz, classical) that a user inputs into the system.

[0371] "Personal preferences" refers to information that a user inputs into the system, such as preferred attributes of an instrument, such as color or material.

[0372] "Skill level" refers to the degree of skill a user has in playing a musical instrument (e.g., beginner, intermediate, advanced) that the user inputs into the system.

[0373] "Data processing device" refers to a server or computer system that receives and analyzes information sent by a user.

[0374] "Artificial intelligence model" refers to algorithms and programs that use machine learning and deep learning technologies to analyze user input and recommend the most suitable instrument.

[0375] A "communication protocol" is a data communication rule for securely transmitting user data, and refers to one that employs encryption technology (e.g., HTTPS).

[0376] "Analysis results" refers to the output information after the artificial intelligence model recommends the optimal instrument based on the user's input information.

[0377] "Detailed Description" refers to information about the recommended instrument, including the make, model, and features.

[0378] "Images" are visual information about the recommended musical instrument displayed as diagrams or photographs.

[0379] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the most suitable instrument based on the input information, allowing users to easily find the instrument that best suits them. This system is specifically implemented as follows.

[0380] A user accesses the system using a web browser or mobile application. First, the user uses the interface provided to input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., instrument color, material), and skill level (e.g., beginner, intermediate, advanced). This information is sent to a data processing device and stored in the system as a user profile.

[0381] The device automatically converts the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, which encrypts the data and ensures its security during transmission.

[0382] The server uses a generative AI model to analyze the received JSON data. For example, a generative AI model such as OpenAI's GPT-4 is used. This generative AI model receives the user's input information in the form of a prompt and analyzes it. An example of a specific prompt is as follows:

[0383] User Information:

[0384] Playing style: Rock

[0385] Favorite color: Red

[0386] Skill level: Beginner

[0387] Recommend the best instrument for this user.

[0388] The server generates a list of optimal instruments based on the analysis results from the generative AI model. This list includes detailed information about each instrument (manufacturer, model, features, etc.). For example, the analysis may recommend "Manufacturer ABC model (red)."

[0389] The generated instrument recommendation list is converted to JSON format and sent to the device using HTTPS. The device parses the received data and displays it in a user-friendly format, including detailed descriptions and images.

[0390] To give a specific example, if a beginner rock player is looking for a red instrument, the user accesses the system and enters the following information:

[0391] Playing style: Rock

[0392] Favorite color: Red

[0393] Skill level: Beginner

[0394] The device sends this information to the server, which then uses the generative AI model to analyze it and recommend "Manufacturer ABC Model (Red)." This information is then sent back to the device, where the user can finally view detailed information about the instrument.

[0395] The system recommends instruments based on the user's specific needs and provides useful assistance to help the user make an appropriate choice.

[0396] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0397] Step 1:

[0398] A user accesses the system and inputs their playing style, personal preferences, and skill level into the provided interface. For example, a user might input information such as "playing style: rock, preferences: red, skill level: beginner." After input, the device converts this information into JSON format. The input is information such as the user's preferences and skill level, and the output is user data in JSON format.

[0399] Step 2:

[0400] The terminal sends the JSON-formatted user data generated in step 1 to the server using the HTTPS protocol. The input is the JSON data generated in step 1, and the output is the data securely transferred to the server. Data encryption is performed during this process to ensure security.

[0401] Step 3:

[0402] The server parses the received JSON data using a generative AI model (e.g., GPT-4). The server converts the JSON data into a prompt and inputs it into the generative AI model. The specific prompt is as follows:

[0403] User Information:

[0404] Playing style: Rock

[0405] Favorite color: Red

[0406] Skill level: Beginner

[0407] Recommend the best instrument for this user.

[0408] The input is JSON data containing user information, and the output is the recommendation results generated by the generative AI model, which are returned as a list of optimal instruments.

[0409] Step 4:

[0410] The server further processes the recommendation results from the generative AI model and retrieves detailed instrument information (e.g., manufacturer, model, features, etc.), which may include retrieving information from an SQL database or other REST API. The input is the recommendation results from the generative AI model, and the output is data containing detailed instrument information.

[0411] Step 5:

[0412] The server converts the detailed instrument information it acquires into JSON format and sends it to the device using the HTTPS protocol. The input is data containing the detailed instrument information, and the output is the JSON-formatted data sent to the device. This data is also encrypted to ensure security.

[0413] Step 6:

[0414] The device analyzes the JSON format recommendation results received and displays them in a user-friendly format. Specifically, detailed information and images of the recommended instruments are displayed on the UI of a web page or mobile app. The input is JSON data containing detailed instrument information received from the server, and the output is a display format that the user can visually confirm. This allows the user to check detailed information about the recommended instruments and make a purchasing decision.

[0415] (Application example 1)

[0416] 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."

[0417] Conventional instrument recommendation systems have had the problem of making it difficult for users to find the instrument that best suits them. Furthermore, the information about the recommended instruments is insufficient, making them inadequate for users to use as a basis for making a final selection. Furthermore, it is difficult to provide recommendations that meet the specific needs of users, and the accuracy of recommendations is low, especially when multiple parameters need to be considered.

[0418] 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.

[0419] In this invention, the server includes: a means for a user to input their playing style, personal preferences, and skill level; a means for transmitting the input information to the server; a means for the server to analyze the received information using a generative AI model; a means for recommending an optimal instrument based on the analysis results; a means for displaying the recommendation results on the user's device; a means for transmitting the user's input information to the server in JSON format; and a means for the server to send a prompt to the generative AI model to obtain a recommendation result. This enables highly accurate instrument recommendations based on the user's specific needs. In addition, providing detailed information about the recommended instruments makes it easier for the user to make an appropriate selection.

[0420] "User" means any person or entity that accesses the System and inputs their playing style, preferences, and skill level.

[0421] "Performance style" refers to the musical genre or specific performance technique that a user prefers to play.

[0422] "Personal preference" refers to specific elements of the instrument that a user chooses, such as color, material, and design.

[0423] "Skill level" is an index that indicates the user's level of proficiency in playing technique, and is classified as beginner, intermediate, advanced, etc.

[0424] "Server" refers to the computer system that analyzes the information received from the user and recommends appropriate instruments using a generative AI model.

[0425] "Generative AI model" refers to an artificial intelligence model that analyzes user input information and takes into account past data and other user profiles to recommend the most suitable instrument.

[0426] "Input means" refers to an interface or device that allows a user to input playing style, personal preferences, and skill level.

[0427] "Transmission means" refers to a communication protocol and communication device for transmitting user input information to a server.

[0428] "Analysis means" refers to the computational process by which the server uses a generative AI model to recommend instruments based on information received from the user.

[0429] "Recommendation means" refers to the method and function of presenting the most suitable instrument to the user based on the results of analysis by the generative AI model.

[0430] "Display means" refers to an interface or device that visually presents the recommendation results sent from the server to the user.

[0431] "JSON format" is an abbreviation for JavaScript Object Notation and refers to a data exchange format that represents structured data in text format.

[0432] A "prompt sentence" refers to an input sentence that follows a specific format or rules to send instructions to a generative AI model.

[0433] The system for implementing this invention recommends the most suitable instrument to a user based on their playing style, preferences, and skill level. The system operates as follows:

[0434] First, a user accesses the system and inputs their playing style, personal preferences, and skill level through the user interface. The playing style input by the user can be, for example, rock, jazz, or classical. Personal preferences, on the other hand, include information about the color, material, and design of the instrument. Skill level indicates the user's level of proficiency in playing techniques, such as beginner, intermediate, or advanced.

[0435] The user's device then sends this input information in JSON format to the server, using a secure protocol such as HTTPS.

[0436] The server inputs the received user information into a generative AI model for analysis. This analysis takes into account past data and the profiles of other users, resulting in a highly accurate model that recommends the most suitable instrument for the user. Generative AI models are sometimes built using Python libraries such as TensorFlow and PyTorch.

[0437] Based on the analysis results, the server generates a list of suitable instruments and generates a recommendation result including detailed information (manufacturer, model, features, etc.). This recommendation result is obtained by sending instructions to the generative AI model using a prompt. For example, the prompt might be in the format "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner."

[0438] Finally, the server sends the recommendation results to the user's device, which displays them, including detailed information and images of the recommended instruments, allowing the user to visually confirm and select the instrument that best suits them.

[0439] As a concrete example, if a user inputs parameters such as "rock," "red," and "beginner" into the system, the server receives that information and analyzes it using a generative AI model. As a result of the analysis, a specific recommendation result such as "a certain model (red) from a certain manufacturer" is generated and sent to the user's device. As a result, the user can easily find the perfect guitar.

[0440] In this way, the system can recommend instruments with high accuracy according to the specific needs of the user, allowing a wide range of users, from beginners to advanced players, to reduce the effort required for choosing an instrument.

[0441] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0442] Step 1:

[0443] The user enters their playing style, personal preferences, and skill level into the interface. For example, the information entered by the user might be in the form of "playing style: rock," "preferences: red," or "skill level: beginner." This input data is then sent to the server in the next step.

[0444] Step 2:

[0445] The device sends the information entered by the user to the server in JSON format using a secure communication protocol such as HTTPS. The input data (playing style, preferences, skill level) is converted to JSON format and sent to the server.

[0446] Step 3:

[0447] The server parses the received JSON data and inputs it into a generative AI model. Based on the input data (playing style, preferences, skill level), the generative AI model analyzes the data and begins the process of recommending the most suitable instrument. The AI ​​models used here are often built using TensorFlow or PyTorch.

[0448] Step 4:

[0449] The generative AI model analyzes the incoming data, taking into account past data and other users' profiles. Instructions are sent to the generative AI model using prompts (e.g., "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner"). Data calculations are performed using the input data to generate the best instrument recommendation.

[0450] Step 5:

[0451] The server generates an optimal instrument list based on the analysis results from the generative AI model. The recommendation results include detailed information such as manufacturer, model, and features. This data is organized on the server and prepared for transmission to the user.

[0452] Step 6:

[0453] The server sends the generated recommendation results to the user's device. These recommendation results are converted back to JSON format and sent to the user's device. Examples of recommendation results include "Manufacturer: A," "Model: B," "Color: Red," and "Features: Rock guitar for beginners."

[0454] Step 7:

[0455] The device displays the recommendation results received from the server on the user interface. This allows the user to check detailed information and images of the recommended instruments. Based on the displayed information, the user can select and purchase the instrument of their choice.

[0456] These steps allow users to easily find the instrument that best suits their needs, significantly reducing the effort required to choose an instrument.

[0457] 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.

[0458] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[0459] Enter user information

[0460] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[0461] Emotion recognition

[0462] The device collects the user's facial expressions, tone of voice, input text, etc. and sends them to the emotion engine, which analyzes this data and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[0463] Sending information

[0464] The device sends the information entered by the user and the analysis results of the emotion engine to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[0465] Analysis of information

[0466] The server validates the received data to ensure it is in the correct format, then analyzes it using an AI model that takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the best guitar.

[0467] Guitar Recommendations

[0468] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a calm design for beginners will be recommended.

[0469] Sending Recommendations

[0470] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[0471] Displaying the results

[0472] The device receives the recommendations and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[0473] Specific examples

[0474] For example, consider a beginner rock player looking for a red guitar.

[0475] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0476] 2. The device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state.

[0477] 3. The device sends this information to the server.

[0478] 4. The server analyzes the received data using an AI model and then selects the next appropriate guitar. Because the user is excited, a guitar with a brighter, more active design is recommended.

[0479] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[0480] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0481] In this way, the system makes more personalized guitar recommendations that take into account the user's emotional state.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] Users access the system and input their playing style, personal preferences, and skill level through a web form or application interface.

[0485] Step 2:

[0486] The device collects user input information and sends it to the emotion engine. The user's facial expressions and tone of voice are provided to the emotion engine via the camera and microphone.

[0487] Step 3:

[0488] The terminal receives the analysis results of the emotion engine and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[0489] Step 4:

[0490] The device packages the user's emotional state and input information into a single data packet and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0491] Step 5:

[0492] The server validates the data packet it receives to ensure that it contains all required fields in the correct format, including verifying the integrity of the data.

[0493] Step 6:

[0494] The server inputs the verified data into an AI model for analysis, which then selects the best guitar for the user, taking into account their playing style, preferences, skill level, and emotional state.

[0495] Step 7:

[0496] The server uses the AI ​​model's analysis to generate a list of optimal guitars, including details about the instrument (e.g., make, model, color, features), and adjusts recommendations based on the user's emotional state.

[0497] Step 8:

[0498] The server generates a recommendation list and sends it to the terminal as a data packet. It is important that the criteria for selecting recommended guitars are adjusted according to the user's emotional state.

[0499] Step 9:

[0500] The device receives the recommendation list and displays it to the user, including detailed descriptions and images, allowing the user to learn more about the recommended guitars.

[0501] Step 10:

[0502] The user then selects from the recommended guitars based on the displayed information, and the user is provided with an easy-to-understand interface to help them choose the guitar that best suits them.

[0503] Example 2

[0504] 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."

[0505] Current instrument recommendation systems make recommendations based on a user's playing style, personal preferences, and skill level, but they are unable to take into account the user's emotional state, making personalized recommendations difficult. Furthermore, detailed information about the recommended instruments is often lacking, making it difficult for users to make informed decisions.

[0506] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for the user to input the playing style, personal preferences, and skill level; means for saving the input information; means for collecting the user's facial expression, tone of voice, and input text; means for recognizing the user's emotional state based on the collected information; means for transmitting the input information and the emotional state to the server; means for performing analysis using a generative AI model based on the information received by the server; means for recommending an optimal instrument based on the analysis results; and means for displaying the recommendation results to the user. This enables personalized instrument recommendations that take the user's emotional state into consideration, and by providing recommendation results that include detailed information and images, the user can make appropriate decisions with sufficient information.

[0507] "User" refers to a person who uses the instrument recommendation system.

[0508] "Performance style" refers to the genre of music the user prefers, such as rock, jazz, or classical.

[0509] "Personal preferences" refers to a user's particular preferences for musical instruments, such as guitar color, material, etc.

[0510] "Skill level" indicates the user's technical proficiency in playing a musical instrument, and includes categories such as beginner, intermediate, and advanced.

[0511] "Facial expressions" refer to the movements and expressions of a user's face and are used to read emotions.

[0512] "Tone of voice" refers to the tone of a user's speech that indicates their tone and emotion.

[0513] "Input text" refers to textual information that a user inputs into a system.

[0514] "Emotional state" indicates the user's current psychological state, and includes joy, sadness, excitement, tension, and the like.

[0515] "Emotion engine" refers to a software means for analyzing collected emotion-related data and determining a user's emotional state.

[0516] "Server" refers to the computer system that receives information sent by users and analyzes it using a generative AI model.

[0517] "Generative AI model" refers to an algorithm that selects the optimal instrument based on a user's playing style, personal preferences, skill level, and emotional state.

[0518] "Recommendation Results" refers to the list of optimal instruments presented to the User based on the analysis of the Generative AI Model.

[0519] "Detailed information" refers to supplementary information required by the user to make a selection, such as the make, model, color, and features of the recommended instruments.

[0520] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[0521] First, a user accesses the system and inputs their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced) into the provided interface. This information is then saved on the device as a user profile.

[0522] The device then collects the user's facial expressions, tone of voice, and input text, and sends them to an emotion engine. The emotion engine analyzes this data and determines the user's current emotional state (e.g., happy, sad, excited, nervous). This process uses software such as Microsoft Azure Cognitive Services and IBM Watson.

[0523] The device then sends the user's input and the emotion engine's analysis results to the server, using secure communication protocols such as HTTPS to ensure that the user's data reaches the server safely.

[0524] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model, such as TensorFlow or PyTorch, which takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the optimal guitar.

[0525] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a subdued design for beginners will be recommended.

[0526] The server then sends the generated recommendation list to the device. The recommendation results are packaged in a format that is easy for the user to understand. The device receives the recommendation results and displays them to the user. The displayed information is easy to understand, and includes detailed descriptions and images. This allows the user to view detailed information about the recommended guitars and make an appropriate selection.

[0527] Specific examples

[0528] For example, consider a beginner rock player looking for a red guitar.

[0529] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0530] 2. The device sends the user's facial expressions and tone of voice to an emotion engine (e.g., Microsoft Azure Cognitive Services), which determines that the user is in an "excited" state.

[0531] 3. The device sends this information to the server.

[0532] 4. The server analyzes the received data using TensorFlow and then selects the appropriate guitar. In this case, because the user is excited, a guitar with a brighter and more active design is recommended.

[0533] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[0534] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0535] Prompt Sentence Examples

[0536] "Recommend the best guitar for the user based on the following information: playing style: rock, personal preference: red, skill level: beginner. emotional state: excited."

[0537] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0538] Step 1:

[0539] A user accesses the system and enters their playing style, personal preferences, and skill level into the provided interface. The device receives this and stores it as a user profile. For example, if a user enters "rock," "red," and "beginner," the device formats and stores this data. The inputs are "playing style," "personal preferences," and "skill level." The output is the saved "user profile."

[0540] Step 2:

[0541] The device collects the user's facial expressions, tone of voice, input text, etc. This collection is done using hardware such as a camera and microphone. The collected data is sent to the emotion engine. For example, while a user is speaking in front of the camera, the device captures their facial expressions and tone of voice in real time and sends them to the emotion engine. The inputs are "facial expression data," "voice data," and "input text." The output is "collected data."

[0542] Step 3:

[0543] The emotion engine analyzes the received data and determines the user's current emotional state. The analysis is performed using Microsoft Azure Cognitive Services and IBM Watson. For example, the emotion engine analyzes the user's facial expression and tone of voice and determines that the user is in an "excited" state. The input is "collected data." The output is "emotional state."

[0544] Step 4:

[0545] The device sends the information entered by the user and the analysis results of the emotion engine to the server. In this process, data is transmitted using a secure communication protocol (e.g., HTTPS). The input is the "user profile" and "emotional state." The output is the "transmitted data."

[0546] Step 5:

[0547] The server validates the received data and ensures that it is in the correct format. It then analyzes it using a generative AI model such as TensorFlow or PyTorch. For example, the server validates the received data and inputs it into a generative AI model, which then analyzes it and outputs the best guitar candidates for the user. The input is the "transmitted data." The output is the "analysis results."

[0548] Step 6:

[0549] The server generates a list of optimal guitars from the analysis results. The list includes details of the instruments (e.g., manufacturer, model, color, features). For example, if the user is an excited rock-loving beginner, a guitar with a bright and active design is recommended. The input is the "analysis results." The output is the "recommendation list."

[0550] Step 7:

[0551] The server sends the generated recommendation list to the device. This process also uses a secure communication protocol (e.g., HTTPS) to transmit data. The input is the "recommendation list." The output is the "transmitted data."

[0552] Step 8:

[0553] The device receives the recommendation results and displays them to the user. The displayed information is in an easy-to-understand format, and includes detailed descriptions and images. For example, when the device receives a list of recommendations and displays it to the user, the user can view detailed information about the recommended guitar. The input is "transmitted data." The output is "displayed recommendation results."

[0554] (Application example 2)

[0555] 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."

[0556] Conventional instrument recommendation systems only consider fixed user information and are unable to reflect the user's emotional state or real-time feedback. As a result, it is difficult for users to choose the instrument that best suits their current mood and state, which can lead to lower satisfaction. Furthermore, when it comes to reward recommendations for electronic payment services, a personalized experience cannot be provided because the system does not consider the user's emotions, resulting in low reward usage rates.

[0557] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their playing style, personal preferences, and skill level; means for recognizing the user's facial expression and tone of voice and determining their current emotional state using an emotion engine; means for transmitting the input information and the analysis results of the emotion engine to the server; means for analyzing the received information using a generative AI model and recommending optimal instruments and benefits taking the user's emotional state into consideration; and means for displaying the recommendation results to the user. This enables more personalized recommendations of instruments and benefits that take the user's emotional state into consideration.

[0558] The "means for user input of playing style, personal preferences, and skill level" refers to an interface that allows a user to provide the system with their own musical playing style, personal preferences, and playing skill level.

[0559] "Means for recognizing a user's facial expressions and tone of voice and using an emotion engine to determine their current emotional state" refers to technology in which a user inputs facial expressions and tone of voice into the system via a smartphone or other device, and the data is analyzed to identify the user's emotional state.

[0560] The "means for transmitting input information and the analysis results by the emotion engine to the server" refers to a communication means for transmitting basic information collected from the user and data obtained by emotion recognition to the server via the Internet.

[0561] A "generative AI model" is an artificial intelligence algorithm that analyzes data obtained from users and generates optimal recommendations based on specific patterns and trends.

[0562] "Recommendation means" refers to the system's function of presenting the most suitable instruments and benefits to users based on information analyzed by the generative AI model.

[0563] The "means for displaying to the user" refers to a display or interface for visually presenting detailed information about the recommended instruments and special offers on the user's device.

[0564] An "emotion engine" is a software engine that analyzes the user's facial and voice data and identifies the user's current emotional state based on the results.

[0565] To put this invention into practice, a system is required for exchanging information between a terminal used by a user and a server. The specific configuration and operation of this system will now be described.

[0566] Enter user information

[0567] The user inputs their playing style, personal preferences, and skill level using a terminal. This information is saved in the system as a user profile. The input interface is a device such as a smartphone or tablet.

[0568] Emotion recognition

[0569] The device captures the user's facial expressions and tone of voice in real time and sends them to an emotion engine, which uses existing software such as Microsoft Azure Cognitive Services, to analyze the user's current emotional state (happiness, sadness, excitement, tension, etc.).

[0570] Sending information

[0571] The device sends the information entered by the user and the analysis results of the emotion engine to the server via secure HTTPS communication, ensuring the safety of the data.

[0572] Analysis of information

[0573] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model (such as TensorFlow or PyTorch) that takes into account the user's playing style, preferences, skill level, and emotional state to make optimal recommendations.

[0574] Recommending instruments and special offers

[0575] Based on the analysis results, the server recommends the most suitable musical instruments or special offers for electronic payment services. For example, if a user is feeling stressed, it will recommend relaxation-related offers (massage coupons, aroma candles, etc.). This also includes detailed information about specific products and services.

[0576] Sending and displaying recommendations

[0577] The server sends the generated recommendation list to the terminal, which displays this information in a format that is easy for the user to understand. The user can check the detailed information of the displayed instruments and benefits and make an appropriate selection.

[0578] Specific examples

[0579] For example, consider the case where a beginner rock player is looking for a red guitar and is currently in an "excited" state. First, the user inputs their playing style as "rock," their preference as "red," and their skill level as "beginner" into their device. Next, the device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state. This information is sent to the server, where the generative AI model analyzes it. As a result, it is determined that a guitar with an active design is suitable for the excited user, and a "red electric guitar from manufacturer ABC" is recommended, for example. The server sends this information to the device, which then displays the details to the user.

[0580] Prompt Sentence Examples

[0581] "If a user is stressed, what kind of reward would be appropriate? Consider past purchase history and basic information."

[0582] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0583] Step 1: Enter your user information

[0584] Users access the system using a device (smartphone or tablet) and input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced). The input information is temporarily stored on the device and organized as a user profile. This input data serves as the basis for all subsequent processing.

[0585] Step 2: Recognize emotions

[0586] The device captures the user's facial expressions and tone of voice in real time using a camera and microphone. The captured data is sent to an emotion engine (e.g., Microsoft Azure Cognitive Services) to determine the user's current emotional state (e.g., joy, sadness, excitement, or tension). The emotion engine analyzes facial expressions and voice tone to identify emotions from this data. The emotional state is output in text format.

[0587] Step 3: Submit your information

[0588] The device sends the information entered by the user (playing style, personal preferences, skill level) and the emotional state analyzed by the emotion engine to the server. The transmission uses the HTTPS protocol to ensure data security. The transmitted data is structured in JSON format or similar.

[0589] Step 4: Analyze the information

[0590] The server receives the data (user information and emotional state) sent from the device and verifies that the format is correct. Once the data is verified, the server analyzes it using a generative AI model (e.g., TensorFlow or PyTorch). The analysis takes into account the user's playing style, preferences, skill level, and emotional state to identify the most suitable instrument and rewards. The results of the data analysis are output.

[0591] Step 5: Recommend an instrument or benefit

[0592] The server generates a list of optimal instruments and rewards based on the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will include rewards related to relaxation (e.g., massage coupons, aroma candles, etc.). The recommendation list is configured with detailed information (e.g., manufacturer, model, features, etc.). The generated recommendation list is sent to the device in the next step.

[0593] Step 6: Submit your recommendation

[0594] The server sends the generated recommendation list to the device via secure communication. The recommendation list is packaged in a format that is easy for the user to understand (e.g., text and images). The sent data is structured in JSON format or similar.

[0595] Step 7: View Recommendations

[0596] The device analyzes the recommendation list received from the server and visually displays it to the user. The display includes detailed information about the recommended instruments and special offers, allowing the user to make a selection while looking at the screen. It is also possible to provide real-time user feedback.

[0597] Through this series of processes, the user can receive the optimal instrument or benefit that matches their emotional state, resulting in a high level of satisfaction.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] [Third embodiment]

[0602] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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."

[0614] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the best instrument based on the input information, allowing users to easily find the guitar that best suits them. This system is implemented as follows.

[0615] Enter user information

[0616] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[0617] Sending information

[0618] The terminal sends the information entered by the user to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[0619] Analysis of information

[0620] The server analyzes the data received from the user. Using AI models, the server evaluates the user's playing style and preferences based on the information provided, and recommends the most suitable guitar model. This analysis also takes into account past data and other user information to make more accurate recommendations.

[0621] Guitar Recommendations

[0622] The server generates a list of suitable guitars from the analysis results and recommends them along with detailed information (manufacturer, model, features, etc.). For example, for a beginner who likes a rock style and red, "ABC model (red) from XYZ manufacturer" will be recommended.

[0623] Sending Recommendations

[0624] The server generates recommendations and sends them to the device, which include information customized based on the specific needs entered by the user.

[0625] Displaying the results

[0626] The device receives the recommendations from the server and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[0627] Specific examples

[0628] As a specific example, consider a beginner rock player looking for a red guitar.

[0629] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0630] 2. The device sends this information to the server.

[0631] 3. The server analyzes the received data using an AI model and then selects the appropriate guitar.

[0632] 4. The server recommends "XYZ manufacturer's ABC model (red)" and sends this information to the device.

[0633] 5. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0634] In this way, the system helps users find the perfect guitar for them.

[0635] The processing flow will be explained below.

[0636] Step 1:

[0637] Users access the system and enter their playing style, personal preferences, and skill level, providing detailed information via a web form or app interface.

[0638] Step 2:

[0639] The device collects user input information and converts it into a data format for sending to the server, for example, packaging the data in JSON format.

[0640] Step 3:

[0641] The device sends the converted data to the server using a secure communication protocol (e.g., HTTPS).

[0642] Step 4:

[0643] Validate the data received by the server to ensure it is in the correct format and contains all required fields.

[0644] Step 5:

[0645] The server then inputs the verified data into an AI model for analysis, which then selects the best guitar for you based on your playing style, preferences, and skill level.

[0646] Step 6:

[0647] The server generates a list of suitable guitars based on the analysis results of the AI ​​model, including details about the instrument (e.g., manufacturer, model, color, features).

[0648] Step 7:

[0649] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[0650] Step 8:

[0651] The device receives the recommendation results and displays them to the user, who can then check the details and choose the best guitar based on the displayed information.

[0652] Example 1

[0653] 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."

[0654] Today's users are often overwhelmed by the sheer number of options available when choosing the perfect instrument for them, which can be a time-consuming and labor-intensive process. Another factor is the difficulty of obtaining recommendations that adequately reflect the user's personal preferences and skill level. In these circumstances, there is a need to efficiently and accurately find an instrument that meets the user's needs.

[0655] 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.

[0656] In this invention, the server includes means for a user to input their playing style, personal preferences, and skill level, means for transmitting the input information to a data processing device, means for the data processing device to analyze the received information using an artificial intelligence model, means for recommending an optimal instrument based on the analysis results, means for displaying the recommendation results to the user, means for using a communication protocol to encrypt and transmit the user's data, and means for including detailed descriptions and images in the recommendation results, thereby enabling optimal instrument recommendations based on the user's personal needs and preferences.

[0657] A "user" is an individual who accesses the system and inputs their playing style, personal preferences, and skill level.

[0658] "Performance style" refers to the type or genre of music (e.g., rock, jazz, classical) that a user inputs into the system.

[0659] "Personal preferences" refers to information that a user inputs into the system, such as preferred attributes of an instrument, such as color or material.

[0660] "Skill level" refers to the degree of skill a user has in playing a musical instrument (e.g., beginner, intermediate, advanced) that the user inputs into the system.

[0661] "Data processing device" refers to a server or computer system that receives and analyzes information sent by a user.

[0662] "Artificial intelligence model" refers to algorithms and programs that use machine learning and deep learning technologies to analyze user input and recommend the most suitable instrument.

[0663] A "communication protocol" is a data communication rule for securely transmitting user data, and refers to one that employs encryption technology (e.g., HTTPS).

[0664] "Analysis results" refers to the output information after the artificial intelligence model recommends the optimal instrument based on the user's input information.

[0665] "Detailed Description" refers to information about the recommended instrument, including the make, model, and features.

[0666] "Images" are visual information about the recommended musical instrument displayed as diagrams or photographs.

[0667] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the most suitable instrument based on the input information, allowing users to easily find the instrument that best suits them. This system is specifically implemented as follows.

[0668] A user accesses the system using a web browser or mobile application. First, the user uses the interface provided to input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., instrument color, material), and skill level (e.g., beginner, intermediate, advanced). This information is sent to a data processing device and stored in the system as a user profile.

[0669] The device automatically converts the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, which encrypts the data and ensures its security during transmission.

[0670] The server uses a generative AI model to analyze the received JSON data. For example, a generative AI model such as OpenAI's GPT-4 is used. This generative AI model receives the user's input information in the form of a prompt and analyzes it. An example of a specific prompt is as follows:

[0671] User Information:

[0672] Playing style: Rock

[0673] Favorite color: Red

[0674] Skill level: Beginner

[0675] Recommend the best instrument for this user.

[0676] The server generates a list of optimal instruments based on the analysis results from the generative AI model. This list includes detailed information about each instrument (manufacturer, model, features, etc.). For example, the analysis may recommend "Manufacturer ABC model (red)."

[0677] The generated instrument recommendation list is converted to JSON format and sent to the device using HTTPS. The device parses the received data and displays it in a user-friendly format, including detailed descriptions and images.

[0678] To give a specific example, if a beginner rock player is looking for a red instrument, the user accesses the system and enters the following information:

[0679] Playing style: Rock

[0680] Favorite color: Red

[0681] Skill level: Beginner

[0682] The device sends this information to the server, which then uses the generative AI model to analyze it and recommend "Manufacturer ABC Model (Red)." This information is then sent back to the device, where the user can finally view detailed information about the instrument.

[0683] The system recommends instruments based on the user's specific needs and provides useful assistance to help the user make an appropriate choice.

[0684] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0685] Step 1:

[0686] A user accesses the system and inputs their playing style, personal preferences, and skill level into the provided interface. For example, a user might input information such as "playing style: rock, preferences: red, skill level: beginner." After input, the device converts this information into JSON format. The input is information such as the user's preferences and skill level, and the output is user data in JSON format.

[0687] Step 2:

[0688] The terminal sends the JSON-formatted user data generated in step 1 to the server using the HTTPS protocol. The input is the JSON data generated in step 1, and the output is the data securely transferred to the server. Data encryption is performed during this process to ensure security.

[0689] Step 3:

[0690] The server parses the received JSON data using a generative AI model (e.g., GPT-4). The server converts the JSON data into a prompt and inputs it into the generative AI model. The specific prompt is as follows:

[0691] User Information:

[0692] Playing style: Rock

[0693] Favorite color: Red

[0694] Skill level: Beginner

[0695] Recommend the best instrument for this user.

[0696] The input is JSON data containing user information, and the output is the recommendation results generated by the generative AI model, which are returned as a list of optimal instruments.

[0697] Step 4:

[0698] The server further processes the recommendation results from the generative AI model and retrieves detailed instrument information (e.g., manufacturer, model, features, etc.), which may include retrieving information from an SQL database or other REST API. The input is the recommendation results from the generative AI model, and the output is data containing detailed instrument information.

[0699] Step 5:

[0700] The server converts the detailed instrument information it acquires into JSON format and sends it to the device using the HTTPS protocol. The input is data containing the detailed instrument information, and the output is the JSON-formatted data sent to the device. This data is also encrypted to ensure security.

[0701] Step 6:

[0702] The device analyzes the JSON format recommendation results received and displays them in a user-friendly format. Specifically, detailed information and images of the recommended instruments are displayed on the UI of a web page or mobile app. The input is JSON data containing detailed instrument information received from the server, and the output is a display format that the user can visually confirm. This allows the user to check detailed information about the recommended instruments and make a purchasing decision.

[0703] (Application example 1)

[0704] 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."

[0705] Conventional instrument recommendation systems have had the problem of making it difficult for users to find the instrument that best suits them. Furthermore, the information about the recommended instruments is insufficient, making them inadequate for users to use as a basis for making a final selection. Furthermore, it is difficult to provide recommendations that meet the specific needs of users, and the accuracy of recommendations is low, especially when multiple parameters need to be considered.

[0706] 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.

[0707] In this invention, the server includes: a means for a user to input their playing style, personal preferences, and skill level; a means for transmitting the input information to the server; a means for the server to analyze the received information using a generative AI model; a means for recommending an optimal instrument based on the analysis results; a means for displaying the recommendation results on the user's device; a means for transmitting the user's input information to the server in JSON format; and a means for the server to send a prompt to the generative AI model to obtain a recommendation result. This enables highly accurate instrument recommendations based on the user's specific needs. In addition, providing detailed information about the recommended instruments makes it easier for the user to make an appropriate selection.

[0708] "User" means any person or entity that accesses the System and inputs their playing style, preferences, and skill level.

[0709] "Performance style" refers to the musical genre or specific performance technique that a user prefers to play.

[0710] "Personal preference" refers to specific elements of the instrument that a user chooses, such as color, material, and design.

[0711] "Skill level" is an index that indicates the user's level of proficiency in playing technique, and is classified as beginner, intermediate, advanced, etc.

[0712] "Server" refers to the computer system that analyzes the information received from the user and recommends appropriate instruments using a generative AI model.

[0713] "Generative AI model" refers to an artificial intelligence model that analyzes user input information and takes into account past data and other user profiles to recommend the most suitable instrument.

[0714] "Input means" refers to an interface or device that allows a user to input playing style, personal preferences, and skill level.

[0715] "Transmission means" refers to a communication protocol and communication device for transmitting user input information to a server.

[0716] "Analysis means" refers to the computational process by which the server uses a generative AI model to recommend instruments based on information received from the user.

[0717] "Recommendation means" refers to the method and function of presenting the most suitable instrument to the user based on the results of analysis by the generative AI model.

[0718] "Display means" refers to an interface or device that visually presents the recommendation results sent from the server to the user.

[0719] "JSON format" is an abbreviation for JavaScript Object Notation and refers to a data exchange format that represents structured data in text format.

[0720] A "prompt sentence" refers to an input sentence that follows a specific format or rules to send instructions to a generative AI model.

[0721] The system for implementing this invention recommends the most suitable instrument to a user based on their playing style, preferences, and skill level. The system operates as follows:

[0722] First, a user accesses the system and inputs their playing style, personal preferences, and skill level through the user interface. The playing style input by the user can be, for example, rock, jazz, or classical. Personal preferences, on the other hand, include information about the color, material, and design of the instrument. Skill level indicates the user's level of proficiency in playing techniques, such as beginner, intermediate, or advanced.

[0723] The user's device then sends this input information in JSON format to the server, using a secure protocol such as HTTPS.

[0724] The server inputs the received user information into a generative AI model for analysis. This analysis takes into account past data and the profiles of other users, resulting in a highly accurate model that recommends the most suitable instrument for the user. Generative AI models are sometimes built using Python libraries such as TensorFlow and PyTorch.

[0725] Based on the analysis results, the server generates a list of suitable instruments and generates a recommendation result including detailed information (manufacturer, model, features, etc.). This recommendation result is obtained by sending instructions to the generative AI model using a prompt. For example, the prompt might be in the format "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner."

[0726] Finally, the server sends the recommendation results to the user's device, which displays them, including detailed information and images of the recommended instruments, allowing the user to visually confirm and select the instrument that best suits them.

[0727] As a concrete example, if a user inputs parameters such as "rock," "red," and "beginner" into the system, the server receives that information and analyzes it using a generative AI model. As a result of the analysis, a specific recommendation result such as "a certain model (red) from a certain manufacturer" is generated and sent to the user's device. As a result, the user can easily find the perfect guitar.

[0728] In this way, the system can recommend instruments with high accuracy according to the specific needs of the user, allowing a wide range of users, from beginners to advanced players, to reduce the effort required for choosing an instrument.

[0729] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0730] Step 1:

[0731] The user enters their playing style, personal preferences, and skill level into the interface. For example, the information entered by the user might be in the form of "playing style: rock," "preferences: red," or "skill level: beginner." This input data is then sent to the server in the next step.

[0732] Step 2:

[0733] The device sends the information entered by the user to the server in JSON format using a secure communication protocol such as HTTPS. The input data (playing style, preferences, skill level) is converted to JSON format and sent to the server.

[0734] Step 3:

[0735] The server parses the received JSON data and inputs it into a generative AI model. Based on the input data (playing style, preferences, skill level), the generative AI model analyzes the data and begins the process of recommending the most suitable instrument. The AI ​​models used here are often built using TensorFlow or PyTorch.

[0736] Step 4:

[0737] The generative AI model analyzes the incoming data, taking into account past data and other users' profiles. Instructions are sent to the generative AI model using prompts (e.g., "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner"). Data calculations are performed using the input data to generate the best instrument recommendation.

[0738] Step 5:

[0739] The server generates an optimal instrument list based on the analysis results from the generative AI model. The recommendation results include detailed information such as manufacturer, model, and features. This data is organized on the server and prepared for transmission to the user.

[0740] Step 6:

[0741] The server sends the generated recommendation results to the user's device. These recommendation results are converted back to JSON format and sent to the user's device. Examples of recommendation results include "Manufacturer: A," "Model: B," "Color: Red," and "Features: Rock guitar for beginners."

[0742] Step 7:

[0743] The device displays the recommendation results received from the server on the user interface. This allows the user to check detailed information and images of the recommended instruments. Based on the displayed information, the user can select and purchase the instrument of their choice.

[0744] These steps allow users to easily find the instrument that best suits their needs, significantly reducing the effort required to choose an instrument.

[0745] 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.

[0746] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[0747] Enter user information

[0748] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[0749] Emotion recognition

[0750] The device collects the user's facial expressions, tone of voice, input text, etc. and sends them to the emotion engine, which analyzes this data and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[0751] Sending information

[0752] The device sends the information entered by the user and the analysis results of the emotion engine to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[0753] Analysis of information

[0754] The server validates the received data to ensure it is in the correct format, then analyzes it using an AI model that takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the best guitar.

[0755] Guitar Recommendations

[0756] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a calm design for beginners will be recommended.

[0757] Sending Recommendations

[0758] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[0759] Displaying the results

[0760] The device receives the recommendations and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[0761] Specific examples

[0762] For example, consider a beginner rock player looking for a red guitar.

[0763] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0764] 2. The device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state.

[0765] 3. The device sends this information to the server.

[0766] 4. The server analyzes the received data using an AI model and then selects the next appropriate guitar. Because the user is excited, a guitar with a brighter, more active design is recommended.

[0767] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[0768] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0769] In this way, the system makes more personalized guitar recommendations that take into account the user's emotional state.

[0770] The processing flow will be explained below.

[0771] Step 1:

[0772] Users access the system and input their playing style, personal preferences, and skill level through a web form or application interface.

[0773] Step 2:

[0774] The device collects user input information and sends it to the emotion engine. The user's facial expressions and tone of voice are provided to the emotion engine via the camera and microphone.

[0775] Step 3:

[0776] The terminal receives the analysis results of the emotion engine and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[0777] Step 4:

[0778] The device packages the user's emotional state and input information into a single data packet and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0779] Step 5:

[0780] The server validates the data packet it receives to ensure that it contains all required fields in the correct format, including verifying the integrity of the data.

[0781] Step 6:

[0782] The server inputs the verified data into an AI model for analysis, which then selects the best guitar for the user, taking into account their playing style, preferences, skill level, and emotional state.

[0783] Step 7:

[0784] The server uses the AI ​​model's analysis to generate a list of optimal guitars, including details about the instrument (e.g., make, model, color, features), and adjusts recommendations based on the user's emotional state.

[0785] Step 8:

[0786] The server generates a recommendation list and sends it to the terminal as a data packet. It is important that the criteria for selecting recommended guitars are adjusted according to the user's emotional state.

[0787] Step 9:

[0788] The device receives the recommendation list and displays it to the user, including detailed descriptions and images, allowing the user to learn more about the recommended guitars.

[0789] Step 10:

[0790] The user then selects from the recommended guitars based on the displayed information, and the user is provided with an easy-to-understand interface to help them choose the guitar that best suits them.

[0791] Example 2

[0792] 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."

[0793] Current instrument recommendation systems make recommendations based on a user's playing style, personal preferences, and skill level, but they are unable to take into account the user's emotional state, making personalized recommendations difficult. Furthermore, detailed information about the recommended instruments is often lacking, making it difficult for users to make informed decisions.

[0794] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for the user to input the playing style, personal preferences, and skill level; means for saving the input information; means for collecting the user's facial expression, tone of voice, and input text; means for recognizing the user's emotional state based on the collected information; means for transmitting the input information and the emotional state to the server; means for performing analysis using a generative AI model based on the information received by the server; means for recommending an optimal instrument based on the analysis results; and means for displaying the recommendation results to the user. This enables personalized instrument recommendations that take the user's emotional state into consideration, and by providing recommendation results that include detailed information and images, the user can make appropriate decisions with sufficient information.

[0795] "User" refers to a person who uses the instrument recommendation system.

[0796] "Performance style" refers to the genre of music the user prefers, such as rock, jazz, or classical.

[0797] "Personal preferences" refers to a user's particular preferences for musical instruments, such as guitar color, material, etc.

[0798] "Skill level" indicates the user's technical proficiency in playing a musical instrument, and includes categories such as beginner, intermediate, and advanced.

[0799] "Facial expressions" refer to the movements and expressions of a user's face and are used to read emotions.

[0800] "Tone of voice" refers to the tone of a user's speech that indicates their tone and emotion.

[0801] "Input text" refers to textual information that a user inputs into a system.

[0802] "Emotional state" indicates the user's current psychological state, and includes joy, sadness, excitement, tension, and the like.

[0803] "Emotion engine" refers to a software means for analyzing collected emotion-related data and determining a user's emotional state.

[0804] "Server" refers to the computer system that receives information sent by users and analyzes it using a generative AI model.

[0805] "Generative AI model" refers to an algorithm that selects the optimal instrument based on a user's playing style, personal preferences, skill level, and emotional state.

[0806] "Recommendation Results" refers to the list of optimal instruments presented to the User based on the analysis of the Generative AI Model.

[0807] "Detailed information" refers to supplementary information required by the user to make a selection, such as the make, model, color, and features of the recommended instruments.

[0808] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[0809] First, a user accesses the system and inputs their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced) into the provided interface. This information is then saved on the device as a user profile.

[0810] The device then collects the user's facial expressions, tone of voice, and input text, and sends them to an emotion engine. The emotion engine analyzes this data and determines the user's current emotional state (e.g., happy, sad, excited, nervous). This process uses software such as Microsoft Azure Cognitive Services and IBM Watson.

[0811] The device then sends the user's input and the emotion engine's analysis results to the server, using secure communication protocols such as HTTPS to ensure that the user's data reaches the server safely.

[0812] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model, such as TensorFlow or PyTorch, which takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the optimal guitar.

[0813] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a subdued design for beginners will be recommended.

[0814] The server then sends the generated recommendation list to the device. The recommendation results are packaged in a format that is easy for the user to understand. The device receives the recommendation results and displays them to the user. The displayed information is easy to understand, and includes detailed descriptions and images. This allows the user to view detailed information about the recommended guitars and make an appropriate selection.

[0815] Specific examples

[0816] For example, consider a beginner rock player looking for a red guitar.

[0817] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0818] 2. The device sends the user's facial expressions and tone of voice to an emotion engine (e.g., Microsoft Azure Cognitive Services), which determines that the user is in an "excited" state.

[0819] 3. The device sends this information to the server.

[0820] 4. The server analyzes the received data using TensorFlow and then selects the appropriate guitar. In this case, because the user is excited, a guitar with a brighter and more active design is recommended.

[0821] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[0822] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0823] Prompt Sentence Examples

[0824] "Recommend the best guitar for the user based on the following information: playing style: rock, personal preference: red, skill level: beginner. emotional state: excited."

[0825] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0826] Step 1:

[0827] A user accesses the system and enters their playing style, personal preferences, and skill level into the provided interface. The device receives this and stores it as a user profile. For example, if a user enters "rock," "red," and "beginner," the device formats and stores this data. The inputs are "playing style," "personal preferences," and "skill level." The output is the saved "user profile."

[0828] Step 2:

[0829] The device collects the user's facial expressions, tone of voice, input text, etc. This collection is done using hardware such as a camera and microphone. The collected data is sent to the emotion engine. For example, while a user is speaking in front of the camera, the device captures their facial expressions and tone of voice in real time and sends them to the emotion engine. The inputs are "facial expression data," "voice data," and "input text." The output is "collected data."

[0830] Step 3:

[0831] The emotion engine analyzes the received data and determines the user's current emotional state. The analysis is performed using Microsoft Azure Cognitive Services and IBM Watson. For example, the emotion engine analyzes the user's facial expression and tone of voice and determines that the user is in an "excited" state. The input is "collected data." The output is "emotional state."

[0832] Step 4:

[0833] The device sends the information entered by the user and the analysis results of the emotion engine to the server. In this process, data is transmitted using a secure communication protocol (e.g., HTTPS). The input is the "user profile" and "emotional state." The output is the "transmitted data."

[0834] Step 5:

[0835] The server validates the received data and ensures that it is in the correct format. It then analyzes it using a generative AI model such as TensorFlow or PyTorch. For example, the server validates the received data and inputs it into a generative AI model, which then analyzes it and outputs the best guitar candidates for the user. The input is the "transmitted data." The output is the "analysis results."

[0836] Step 6:

[0837] The server generates a list of optimal guitars from the analysis results. The list includes details of the instruments (e.g., manufacturer, model, color, features). For example, if the user is an excited rock-loving beginner, a guitar with a bright and active design is recommended. The input is the "analysis results." The output is the "recommendation list."

[0838] Step 7:

[0839] The server sends the generated recommendation list to the device. This process also uses a secure communication protocol (e.g., HTTPS) to transmit data. The input is the "recommendation list." The output is the "transmitted data."

[0840] Step 8:

[0841] The device receives the recommendation results and displays them to the user. The displayed information is in an easy-to-understand format, and includes detailed descriptions and images. For example, when the device receives a list of recommendations and displays it to the user, the user can view detailed information about the recommended guitar. The input is "transmitted data." The output is "displayed recommendation results."

[0842] (Application example 2)

[0843] 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."

[0844] Conventional instrument recommendation systems only consider fixed user information and are unable to reflect the user's emotional state or real-time feedback. As a result, it is difficult for users to choose the instrument that best suits their current mood and state, which can lead to lower satisfaction. Furthermore, when it comes to reward recommendations for electronic payment services, a personalized experience cannot be provided because the system does not consider the user's emotions, resulting in low reward usage rates.

[0845] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their playing style, personal preferences, and skill level; means for recognizing the user's facial expression and tone of voice and determining their current emotional state using an emotion engine; means for transmitting the input information and the analysis results of the emotion engine to the server; means for analyzing the received information using a generative AI model and recommending optimal instruments and benefits taking the user's emotional state into consideration; and means for displaying the recommendation results to the user. This enables more personalized recommendations of instruments and benefits that take the user's emotional state into consideration.

[0846] The "means for user input of playing style, personal preferences, and skill level" refers to an interface that allows a user to provide the system with their own musical playing style, personal preferences, and playing skill level.

[0847] "Means for recognizing a user's facial expressions and tone of voice and using an emotion engine to determine their current emotional state" refers to technology in which a user inputs facial expressions and tone of voice into the system via a smartphone or other device, and the data is analyzed to identify the user's emotional state.

[0848] The "means for transmitting input information and the analysis results by the emotion engine to the server" refers to a communication means for transmitting basic information collected from the user and data obtained by emotion recognition to the server via the Internet.

[0849] A "generative AI model" is an artificial intelligence algorithm that analyzes data obtained from users and generates optimal recommendations based on specific patterns and trends.

[0850] "Recommendation means" refers to the system's function of presenting the most suitable instruments and benefits to users based on information analyzed by the generative AI model.

[0851] The "means for displaying to the user" refers to a display or interface for visually presenting detailed information about the recommended instruments and special offers on the user's device.

[0852] An "emotion engine" is a software engine that analyzes the user's facial and voice data and identifies the user's current emotional state based on the results.

[0853] To put this invention into practice, a system is required for exchanging information between a terminal used by a user and a server. The specific configuration and operation of this system will now be described.

[0854] Enter user information

[0855] The user inputs their playing style, personal preferences, and skill level using a terminal. This information is saved in the system as a user profile. The input interface is a device such as a smartphone or tablet.

[0856] Emotion recognition

[0857] The device captures the user's facial expressions and tone of voice in real time and sends them to an emotion engine, which uses existing software such as Microsoft Azure Cognitive Services, to analyze the user's current emotional state (happiness, sadness, excitement, tension, etc.).

[0858] Sending information

[0859] The device sends the information entered by the user and the analysis results of the emotion engine to the server via secure HTTPS communication, ensuring the safety of the data.

[0860] Analysis of information

[0861] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model (such as TensorFlow or PyTorch) that takes into account the user's playing style, preferences, skill level, and emotional state to make optimal recommendations.

[0862] Recommending instruments and special offers

[0863] Based on the analysis results, the server recommends the most suitable musical instruments or special offers for electronic payment services. For example, if a user is feeling stressed, it will recommend relaxation-related offers (massage coupons, aroma candles, etc.). This also includes detailed information about specific products and services.

[0864] Sending and displaying recommendations

[0865] The server sends the generated recommendation list to the terminal, which displays this information in a format that is easy for the user to understand. The user can check the detailed information of the displayed instruments and benefits and make an appropriate selection.

[0866] Specific examples

[0867] For example, consider the case where a beginner rock player is looking for a red guitar and is currently in an "excited" state. First, the user inputs their playing style as "rock," their preference as "red," and their skill level as "beginner" into their device. Next, the device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state. This information is sent to the server, where the generative AI model analyzes it. As a result, it is determined that a guitar with an active design is suitable for the excited user, and a "red electric guitar from manufacturer ABC" is recommended, for example. The server sends this information to the device, which then displays the details to the user.

[0868] Prompt Sentence Examples

[0869] "If a user is stressed, what kind of reward would be appropriate? Consider past purchase history and basic information."

[0870] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0871] Step 1: Enter your user information

[0872] Users access the system using a device (smartphone or tablet) and input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced). The input information is temporarily stored on the device and organized as a user profile. This input data serves as the basis for all subsequent processing.

[0873] Step 2: Recognize emotions

[0874] The device captures the user's facial expressions and tone of voice in real time using a camera and microphone. The captured data is sent to an emotion engine (e.g., Microsoft Azure Cognitive Services) to determine the user's current emotional state (e.g., joy, sadness, excitement, or tension). The emotion engine analyzes facial expressions and voice tone to identify emotions from this data. The emotional state is output in text format.

[0875] Step 3: Submit your information

[0876] The device sends the information entered by the user (playing style, personal preferences, skill level) and the emotional state analyzed by the emotion engine to the server. The transmission uses the HTTPS protocol to ensure data security. The transmitted data is structured in JSON format or similar.

[0877] Step 4: Analyze the information

[0878] The server receives the data (user information and emotional state) sent from the device and verifies that the format is correct. Once the data is verified, the server analyzes it using a generative AI model (e.g., TensorFlow or PyTorch). The analysis takes into account the user's playing style, preferences, skill level, and emotional state to identify the most suitable instrument and rewards. The results of the data analysis are output.

[0879] Step 5: Recommend an instrument or benefit

[0880] The server generates a list of optimal instruments and rewards based on the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will include rewards related to relaxation (e.g., massage coupons, aroma candles, etc.). The recommendation list is configured with detailed information (e.g., manufacturer, model, features, etc.). The generated recommendation list is sent to the device in the next step.

[0881] Step 6: Submit your recommendation

[0882] The server sends the generated recommendation list to the device via secure communication. The recommendation list is packaged in a format that is easy for the user to understand (e.g., text and images). The sent data is structured in JSON format or similar.

[0883] Step 7: View Recommendations

[0884] The device analyzes the recommendation list received from the server and visually displays it to the user. The display includes detailed information about the recommended instruments and special offers, allowing the user to make a selection while looking at the screen. It is also possible to provide real-time user feedback.

[0885] Through this series of processes, the user can receive the optimal instrument or benefit that matches their emotional state, resulting in a high level of satisfaction.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] [Fourth embodiment]

[0890] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0891] 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.

[0892] 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).

[0893] 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.

[0894] 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.

[0895] 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).

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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."

[0903] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the best instrument based on the input information, allowing users to easily find the guitar that best suits them. This system is implemented as follows.

[0904] Enter user information

[0905] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[0906] Sending information

[0907] The terminal sends the information entered by the user to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[0908] Analysis of information

[0909] The server analyzes the data received from the user. Using AI models, the server evaluates the user's playing style and preferences based on the information provided, and recommends the most suitable guitar model. This analysis also takes into account past data and other user information to make more accurate recommendations.

[0910] Guitar Recommendations

[0911] The server generates a list of suitable guitars from the analysis results and recommends them along with detailed information (manufacturer, model, features, etc.). For example, for a beginner who likes a rock style and red, "ABC model (red) from XYZ manufacturer" will be recommended.

[0912] Sending Recommendations

[0913] The server generates recommendations and sends them to the device, which include information customized based on the specific needs entered by the user.

[0914] Displaying the results

[0915] The device receives the recommendations from the server and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[0916] Specific examples

[0917] As a specific example, consider a beginner rock player looking for a red guitar.

[0918] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[0919] 2. The device sends this information to the server.

[0920] 3. The server analyzes the received data using an AI model and then selects the appropriate guitar.

[0921] 4. The server recommends "XYZ manufacturer's ABC model (red)" and sends this information to the device.

[0922] 5. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[0923] In this way, the system helps users find the perfect guitar for them.

[0924] The processing flow will be explained below.

[0925] Step 1:

[0926] Users access the system and enter their playing style, personal preferences, and skill level, providing detailed information via a web form or app interface.

[0927] Step 2:

[0928] The device collects user input information and converts it into a data format for sending to the server, for example, packaging the data in JSON format.

[0929] Step 3:

[0930] The device sends the converted data to the server using a secure communication protocol (e.g., HTTPS).

[0931] Step 4:

[0932] Validate the data received by the server to ensure it is in the correct format and contains all required fields.

[0933] Step 5:

[0934] The server then inputs the verified data into an AI model for analysis, which then selects the best guitar for you based on your playing style, preferences, and skill level.

[0935] Step 6:

[0936] The server generates a list of suitable guitars based on the analysis results of the AI ​​model, including details about the instrument (e.g., manufacturer, model, color, features).

[0937] Step 7:

[0938] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[0939] Step 8:

[0940] The device receives the recommendation results and displays them to the user, who can then check the details and choose the best guitar based on the displayed information.

[0941] Example 1

[0942] 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."

[0943] Today's users are often overwhelmed by the sheer number of options available when choosing the perfect instrument for them, which can be a time-consuming and labor-intensive process. Another factor is the difficulty of obtaining recommendations that adequately reflect the user's personal preferences and skill level. In these circumstances, there is a need to efficiently and accurately find an instrument that meets the user's needs.

[0944] 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.

[0945] In this invention, the server includes means for a user to input their playing style, personal preferences, and skill level, means for transmitting the input information to a data processing device, means for the data processing device to analyze the received information using an artificial intelligence model, means for recommending an optimal instrument based on the analysis results, means for displaying the recommendation results to the user, means for using a communication protocol to encrypt and transmit the user's data, and means for including detailed descriptions and images in the recommendation results, thereby enabling optimal instrument recommendations based on the user's personal needs and preferences.

[0946] A "user" is an individual who accesses the system and inputs their playing style, personal preferences, and skill level.

[0947] "Performance style" refers to the type or genre of music (e.g., rock, jazz, classical) that a user inputs into the system.

[0948] "Personal preferences" refers to information that a user inputs into the system, such as preferred attributes of an instrument, such as color or material.

[0949] "Skill level" refers to the degree of skill a user has in playing a musical instrument (e.g., beginner, intermediate, advanced) that the user inputs into the system.

[0950] "Data processing device" refers to a server or computer system that receives and analyzes information sent by a user.

[0951] "Artificial intelligence model" refers to algorithms and programs that use machine learning and deep learning technologies to analyze user input and recommend the most suitable instrument.

[0952] A "communication protocol" is a data communication rule for securely transmitting user data, and refers to one that employs encryption technology (e.g., HTTPS).

[0953] "Analysis results" refers to the output information after the artificial intelligence model recommends the optimal instrument based on the user's input information.

[0954] "Detailed Description" refers to information about the recommended instrument, including the make, model, and features.

[0955] "Images" are visual information about the recommended musical instrument displayed as diagrams or photographs.

[0956] This invention is a system that allows users to input their playing style, preferences, and skill level, and recommends the most suitable instrument based on the input information, allowing users to easily find the instrument that best suits them. This system is specifically implemented as follows.

[0957] A user accesses the system using a web browser or mobile application. First, the user uses the interface provided to input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., instrument color, material), and skill level (e.g., beginner, intermediate, advanced). This information is sent to a data processing device and stored in the system as a user profile.

[0958] The device automatically converts the information entered by the user into JSON format and sends it to the server using the HTTPS protocol, which encrypts the data and ensures its security during transmission.

[0959] The server uses a generative AI model to analyze the received JSON data. For example, a generative AI model such as OpenAI's GPT-4 is used. This generative AI model receives the user's input information in the form of a prompt and analyzes it. An example of a specific prompt is as follows:

[0960] User Information:

[0961] Playing style: Rock

[0962] Favorite color: Red

[0963] Skill level: Beginner

[0964] Recommend the best instrument for this user.

[0965] The server generates a list of optimal instruments based on the analysis results from the generative AI model. This list includes detailed information about each instrument (manufacturer, model, features, etc.). For example, the analysis may recommend "Manufacturer ABC model (red)."

[0966] The generated instrument recommendation list is converted to JSON format and sent to the device using HTTPS. The device parses the received data and displays it in a user-friendly format, including detailed descriptions and images.

[0967] To give a specific example, if a beginner rock player is looking for a red instrument, the user accesses the system and enters the following information:

[0968] Playing style: Rock

[0969] Favorite color: Red

[0970] Skill level: Beginner

[0971] The device sends this information to the server, which then uses the generative AI model to analyze it and recommend "Manufacturer ABC Model (Red)." This information is then sent back to the device, where the user can finally view detailed information about the instrument.

[0972] The system recommends instruments based on the user's specific needs and provides useful assistance to help the user make an appropriate choice.

[0973] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0974] Step 1:

[0975] A user accesses the system and inputs their playing style, personal preferences, and skill level into the provided interface. For example, a user might input information such as "playing style: rock, preferences: red, skill level: beginner." After input, the device converts this information into JSON format. The input is information such as the user's preferences and skill level, and the output is user data in JSON format.

[0976] Step 2:

[0977] The terminal sends the JSON-formatted user data generated in step 1 to the server using the HTTPS protocol. The input is the JSON data generated in step 1, and the output is the data securely transferred to the server. Data encryption is performed during this process to ensure security.

[0978] Step 3:

[0979] The server parses the received JSON data using a generative AI model (e.g., GPT-4). The server converts the JSON data into a prompt and inputs it into the generative AI model. The specific prompt is as follows:

[0980] User Information:

[0981] Playing style: Rock

[0982] Favorite color: Red

[0983] Skill level: Beginner

[0984] Recommend the best instrument for this user.

[0985] The input is JSON data containing user information, and the output is the recommendation results generated by the generative AI model, which are returned as a list of optimal instruments.

[0986] Step 4:

[0987] The server further processes the recommendation results from the generative AI model and retrieves detailed instrument information (e.g., manufacturer, model, features, etc.), which may include retrieving information from an SQL database or other REST API. The input is the recommendation results from the generative AI model, and the output is data containing detailed instrument information.

[0988] Step 5:

[0989] The server converts the detailed instrument information it acquires into JSON format and sends it to the device using the HTTPS protocol. The input is data containing the detailed instrument information, and the output is the JSON-formatted data sent to the device. This data is also encrypted to ensure security.

[0990] Step 6:

[0991] The device analyzes the JSON format recommendation results received and displays them in a user-friendly format. Specifically, detailed information and images of the recommended instruments are displayed on the UI of a web page or mobile app. The input is JSON data containing detailed instrument information received from the server, and the output is a display format that the user can visually confirm. This allows the user to check detailed information about the recommended instruments and make a purchasing decision.

[0992] (Application example 1)

[0993] 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."

[0994] Conventional instrument recommendation systems have had the problem of making it difficult for users to find the instrument that best suits them. Furthermore, the information about the recommended instruments is insufficient, making them inadequate for users to use as a basis for making a final selection. Furthermore, it is difficult to provide recommendations that meet the specific needs of users, and the accuracy of recommendations is low, especially when multiple parameters need to be considered.

[0995] 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.

[0996] In this invention, the server includes: a means for a user to input their playing style, personal preferences, and skill level; a means for transmitting the input information to the server; a means for the server to analyze the received information using a generative AI model; a means for recommending an optimal instrument based on the analysis results; a means for displaying the recommendation results on the user's device; a means for transmitting the user's input information to the server in JSON format; and a means for the server to send a prompt to the generative AI model to obtain a recommendation result. This enables highly accurate instrument recommendations based on the user's specific needs. In addition, providing detailed information about the recommended instruments makes it easier for the user to make an appropriate selection.

[0997] "User" means any person or entity that accesses the System and inputs their playing style, preferences, and skill level.

[0998] "Performance style" refers to the musical genre or specific performance technique that a user prefers to play.

[0999] "Personal preference" refers to specific elements of the instrument that a user chooses, such as color, material, and design.

[1000] "Skill level" is an index that indicates the user's level of proficiency in playing technique, and is classified as beginner, intermediate, advanced, etc.

[1001] "Server" refers to the computer system that analyzes the information received from the user and recommends appropriate instruments using a generative AI model.

[1002] "Generative AI model" refers to an artificial intelligence model that analyzes user input information and takes into account past data and other user profiles to recommend the most suitable instrument.

[1003] "Input means" refers to an interface or device that allows a user to input playing style, personal preferences, and skill level.

[1004] "Transmission means" refers to a communication protocol and communication device for transmitting user input information to a server.

[1005] "Analysis means" refers to the computational process by which the server uses a generative AI model to recommend instruments based on information received from the user.

[1006] "Recommendation means" refers to the method and function of presenting the most suitable instrument to the user based on the results of analysis by the generative AI model.

[1007] "Display means" refers to an interface or device that visually presents the recommendation results sent from the server to the user.

[1008] "JSON format" is an abbreviation for JavaScript Object Notation and refers to a data exchange format that represents structured data in text format.

[1009] A "prompt sentence" refers to an input sentence that follows a specific format or rules to send instructions to a generative AI model.

[1010] The system for implementing this invention recommends the most suitable instrument to a user based on their playing style, preferences, and skill level. The system operates as follows:

[1011] First, a user accesses the system and inputs their playing style, personal preferences, and skill level through the user interface. The playing style input by the user can be, for example, rock, jazz, or classical. Personal preferences, on the other hand, include information about the color, material, and design of the instrument. Skill level indicates the user's level of proficiency in playing techniques, such as beginner, intermediate, or advanced.

[1012] The user's device then sends this input information in JSON format to the server, using a secure protocol such as HTTPS.

[1013] The server inputs the received user information into a generative AI model for analysis. This analysis takes into account past data and the profiles of other users, resulting in a highly accurate model that recommends the most suitable instrument for the user. Generative AI models are sometimes built using Python libraries such as TensorFlow and PyTorch.

[1014] Based on the analysis results, the server generates a list of suitable instruments and generates a recommendation result including detailed information (manufacturer, model, features, etc.). This recommendation result is obtained by sending instructions to the generative AI model using a prompt. For example, the prompt might be in the format "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner."

[1015] Finally, the server sends the recommendation results to the user's device, which displays them, including detailed information and images of the recommended instruments, allowing the user to visually confirm and select the instrument that best suits them.

[1016] As a concrete example, if a user inputs parameters such as "rock," "red," and "beginner" into the system, the server receives that information and analyzes it using a generative AI model. As a result of the analysis, a specific recommendation result such as "a certain model (red) from a certain manufacturer" is generated and sent to the user's device. As a result, the user can easily find the perfect guitar.

[1017] In this way, the system can recommend instruments with high accuracy according to the specific needs of the user, allowing a wide range of users, from beginners to advanced players, to reduce the effort required for choosing an instrument.

[1018] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1019] Step 1:

[1020] The user enters their playing style, personal preferences, and skill level into the interface. For example, the information entered by the user might be in the form of "playing style: rock," "preferences: red," or "skill level: beginner." This input data is then sent to the server in the next step.

[1021] Step 2:

[1022] The device sends the information entered by the user to the server in JSON format using a secure communication protocol such as HTTPS. The input data (playing style, preferences, skill level) is converted to JSON format and sent to the server.

[1023] Step 3:

[1024] The server parses the received JSON data and inputs it into a generative AI model. Based on the input data (playing style, preferences, skill level), the generative AI model analyzes the data and begins the process of recommending the most suitable instrument. The AI ​​models used here are often built using TensorFlow or PyTorch.

[1025] Step 4:

[1026] The generative AI model analyzes the incoming data, taking into account past data and other users' profiles. Instructions are sent to the generative AI model using prompts (e.g., "Recommend the best guitar based on the following information: playing style: rock, preference: red, skill level: beginner"). Data calculations are performed using the input data to generate the best instrument recommendation.

[1027] Step 5:

[1028] The server generates an optimal instrument list based on the analysis results from the generative AI model. The recommendation results include detailed information such as manufacturer, model, and features. This data is organized on the server and prepared for transmission to the user.

[1029] Step 6:

[1030] The server sends the generated recommendation results to the user's device. These recommendation results are converted back to JSON format and sent to the user's device. Examples of recommendation results include "Manufacturer: A," "Model: B," "Color: Red," and "Features: Rock guitar for beginners."

[1031] Step 7:

[1032] The device displays the recommendation results received from the server on the user interface. This allows the user to check detailed information and images of the recommended instruments. Based on the displayed information, the user can select and purchase the instrument of their choice.

[1033] These steps allow users to easily find the instrument that best suits their needs, significantly reducing the effort required to choose an instrument.

[1034] 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.

[1035] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[1036] Enter user information

[1037] A user accesses the system and enters their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color, material), and skill level (e.g., beginner, intermediate, advanced) into the interface provided. This information is then stored in the system as a user profile.

[1038] Emotion recognition

[1039] The device collects the user's facial expressions, tone of voice, input text, etc. and sends them to the emotion engine, which analyzes this data and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[1040] Sending information

[1041] The device sends the information entered by the user and the analysis results of the emotion engine to the server. This process uses a communication protocol to ensure that the user's data reaches the server safely.

[1042] Analysis of information

[1043] The server validates the received data to ensure it is in the correct format, then analyzes it using an AI model that takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the best guitar.

[1044] Guitar Recommendations

[1045] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a calm design for beginners will be recommended.

[1046] Sending Recommendations

[1047] The server generates a recommendation list and sends it to the terminal. The recommendation results are packaged in a format that is easy for the user to understand.

[1048] Displaying the results

[1049] The device receives the recommendations and displays them to the user in an easy-to-understand format, including detailed descriptions and images, allowing the user to view detailed information about the recommended guitars and make an appropriate selection.

[1050] Specific examples

[1051] For example, consider a beginner rock player looking for a red guitar.

[1052] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[1053] 2. The device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state.

[1054] 3. The device sends this information to the server.

[1055] 4. The server analyzes the received data using an AI model and then selects the next appropriate guitar. Because the user is excited, a guitar with a brighter, more active design is recommended.

[1056] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[1057] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[1058] In this way, the system makes more personalized guitar recommendations that take into account the user's emotional state.

[1059] The processing flow will be explained below.

[1060] Step 1:

[1061] Users access the system and input their playing style, personal preferences, and skill level through a web form or application interface.

[1062] Step 2:

[1063] The device collects user input information and sends it to the emotion engine. The user's facial expressions and tone of voice are provided to the emotion engine via the camera and microphone.

[1064] Step 3:

[1065] The terminal receives the analysis results of the emotion engine and determines the user's current emotional state (e.g., joy, sadness, excitement, tension).

[1066] Step 4:

[1067] The device packages the user's emotional state and input information into a single data packet and sends it to the server using a secure communication protocol (e.g., HTTPS).

[1068] Step 5:

[1069] The server validates the data packet it receives to ensure that it contains all required fields in the correct format, including verifying the integrity of the data.

[1070] Step 6:

[1071] The server inputs the verified data into an AI model for analysis, which then selects the best guitar for the user, taking into account their playing style, preferences, skill level, and emotional state.

[1072] Step 7:

[1073] The server uses the AI ​​model's analysis to generate a list of optimal guitars, including details about the instrument (e.g., make, model, color, features), and adjusts recommendations based on the user's emotional state.

[1074] Step 8:

[1075] The server generates a recommendation list and sends it to the terminal as a data packet. It is important that the criteria for selecting recommended guitars are adjusted according to the user's emotional state.

[1076] Step 9:

[1077] The device receives the recommendation list and displays it to the user, including detailed descriptions and images, allowing the user to learn more about the recommended guitars.

[1078] Step 10:

[1079] The user then selects from the recommended guitars based on the displayed information, and the user is provided with an easy-to-understand interface to help them choose the guitar that best suits them.

[1080] Example 2

[1081] 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."

[1082] Current instrument recommendation systems make recommendations based on a user's playing style, personal preferences, and skill level, but they are unable to take into account the user's emotional state, making personalized recommendations difficult. Furthermore, detailed information about the recommended instruments is often lacking, making it difficult for users to make informed decisions.

[1083] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for the user to input the playing style, personal preferences, and skill level; means for saving the input information; means for collecting the user's facial expression, tone of voice, and input text; means for recognizing the user's emotional state based on the collected information; means for transmitting the input information and the emotional state to the server; means for performing analysis using a generative AI model based on the information received by the server; means for recommending an optimal instrument based on the analysis results; and means for displaying the recommendation results to the user. This enables personalized instrument recommendations that take the user's emotional state into consideration, and by providing recommendation results that include detailed information and images, the user can make appropriate decisions with sufficient information.

[1084] "User" refers to a person who uses the instrument recommendation system.

[1085] "Performance style" refers to the genre of music the user prefers, such as rock, jazz, or classical.

[1086] "Personal preferences" refers to a user's particular preferences for musical instruments, such as guitar color, material, etc.

[1087] "Skill level" indicates the user's technical proficiency in playing a musical instrument, and includes categories such as beginner, intermediate, and advanced.

[1088] "Facial expressions" refer to the movements and expressions of a user's face and are used to read emotions.

[1089] "Tone of voice" refers to the tone of a user's speech that indicates their tone and emotion.

[1090] "Input text" refers to textual information that a user inputs into a system.

[1091] "Emotional state" indicates the user's current psychological state, and includes joy, sadness, excitement, tension, and the like.

[1092] "Emotion engine" refers to a software means for analyzing collected emotion-related data and determining a user's emotional state.

[1093] "Server" refers to the computer system that receives information sent by users and analyzes it using a generative AI model.

[1094] "Generative AI model" refers to an algorithm that selects the optimal instrument based on a user's playing style, personal preferences, skill level, and emotional state.

[1095] "Recommendation Results" refers to the list of optimal instruments presented to the User based on the analysis of the Generative AI Model.

[1096] "Detailed information" refers to supplementary information required by the user to make a selection, such as the make, model, color, and features of the recommended instruments.

[1097] This invention is a system that allows users to input their playing style, personal preferences, and skill level, and combines it with an emotion engine that recognizes the user's emotions to provide a more personalized instrument recommendation system. This system is implemented as follows.

[1098] First, a user accesses the system and inputs their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced) into the provided interface. This information is then saved on the device as a user profile.

[1099] The device then collects the user's facial expressions, tone of voice, and input text, and sends them to an emotion engine. The emotion engine analyzes this data and determines the user's current emotional state (e.g., happy, sad, excited, nervous). This process uses software such as Microsoft Azure Cognitive Services and IBM Watson.

[1100] The device then sends the user's input and the emotion engine's analysis results to the server, using secure communication protocols such as HTTPS to ensure that the user's data reaches the server safely.

[1101] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model, such as TensorFlow or PyTorch, which takes into account the user's playing style, preferences, skill level, and emotional state as recognized by the emotion engine to select the optimal guitar.

[1102] The server generates a list of suitable guitars based on the analysis results. The list includes details about the instrument (e.g., manufacturer, model, color, and features). The type and features of the recommended guitar are adjusted based on the user's emotional state. For example, if the user is nervous, a guitar that is easy to handle and has a subdued design for beginners will be recommended.

[1103] The server then sends the generated recommendation list to the device. The recommendation results are packaged in a format that is easy for the user to understand. The device receives the recommendation results and displays them to the user. The displayed information is easy to understand, and includes detailed descriptions and images. This allows the user to view detailed information about the recommended guitars and make an appropriate selection.

[1104] Specific examples

[1105] For example, consider a beginner rock player looking for a red guitar.

[1106] 1. A user accesses the system and enters their playing style as "Rock," their preference as "Red," and their skill level as "Beginner."

[1107] 2. The device sends the user's facial expressions and tone of voice to an emotion engine (e.g., Microsoft Azure Cognitive Services), which determines that the user is in an "excited" state.

[1108] 3. The device sends this information to the server.

[1109] 4. The server analyzes the received data using TensorFlow and then selects the appropriate guitar. In this case, because the user is excited, a guitar with a brighter and more active design is recommended.

[1110] 5. The server recommends "ABC manufacturer's XYZ model (red)" and sends this information to the device.

[1111] 6. The device displays the recommendation results to the user, and the user can check detailed information about the guitar.

[1112] Prompt Sentence Examples

[1113] "Recommend the best guitar for the user based on the following information: playing style: rock, personal preference: red, skill level: beginner. emotional state: excited."

[1114] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1115] Step 1:

[1116] A user accesses the system and enters their playing style, personal preferences, and skill level into the provided interface. The device receives this and stores it as a user profile. For example, if a user enters "rock," "red," and "beginner," the device formats and stores this data. The inputs are "playing style," "personal preferences," and "skill level." The output is the saved "user profile."

[1117] Step 2:

[1118] The device collects the user's facial expressions, tone of voice, input text, etc. This collection is done using hardware such as a camera and microphone. The collected data is sent to the emotion engine. For example, while a user is speaking in front of the camera, the device captures their facial expressions and tone of voice in real time and sends them to the emotion engine. The inputs are "facial expression data," "voice data," and "input text." The output is "collected data."

[1119] Step 3:

[1120] The emotion engine analyzes the received data and determines the user's current emotional state. The analysis is performed using Microsoft Azure Cognitive Services and IBM Watson. For example, the emotion engine analyzes the user's facial expression and tone of voice and determines that the user is in an "excited" state. The input is "collected data." The output is "emotional state."

[1121] Step 4:

[1122] The device sends the information entered by the user and the analysis results of the emotion engine to the server. In this process, data is transmitted using a secure communication protocol (e.g., HTTPS). The input is the "user profile" and "emotional state." The output is the "transmitted data."

[1123] Step 5:

[1124] The server validates the received data and ensures that it is in the correct format. It then analyzes it using a generative AI model such as TensorFlow or PyTorch. For example, the server validates the received data and inputs it into a generative AI model, which then analyzes it and outputs the best guitar candidates for the user. The input is the "transmitted data." The output is the "analysis results."

[1125] Step 6:

[1126] The server generates a list of optimal guitars from the analysis results. The list includes details of the instruments (e.g., manufacturer, model, color, features). For example, if the user is an excited rock-loving beginner, a guitar with a bright and active design is recommended. The input is the "analysis results." The output is the "recommendation list."

[1127] Step 7:

[1128] The server sends the generated recommendation list to the device. This process also uses a secure communication protocol (e.g., HTTPS) to transmit data. The input is the "recommendation list." The output is the "transmitted data."

[1129] Step 8:

[1130] The device receives the recommendation results and displays them to the user. The displayed information is in an easy-to-understand format, and includes detailed descriptions and images. For example, when the device receives a list of recommendations and displays it to the user, the user can view detailed information about the recommended guitar. The input is "transmitted data." The output is "displayed recommendation results."

[1131] (Application example 2)

[1132] 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."

[1133] Conventional instrument recommendation systems only consider fixed user information and are unable to reflect the user's emotional state or real-time feedback. As a result, it is difficult for users to choose the instrument that best suits their current mood and state, which can lead to lower satisfaction. Furthermore, when it comes to reward recommendations for electronic payment services, a personalized experience cannot be provided because the system does not consider the user's emotions, resulting in low reward usage rates.

[1134] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for the user to input their playing style, personal preferences, and skill level; means for recognizing the user's facial expression and tone of voice and determining their current emotional state using an emotion engine; means for transmitting the input information and the analysis results of the emotion engine to the server; means for analyzing the received information using a generative AI model and recommending optimal instruments and benefits taking the user's emotional state into consideration; and means for displaying the recommendation results to the user. This enables more personalized recommendations of instruments and benefits that take the user's emotional state into consideration.

[1135] The "means for user input of playing style, personal preferences, and skill level" refers to an interface that allows a user to provide the system with their own musical playing style, personal preferences, and playing skill level.

[1136] "Means for recognizing a user's facial expressions and tone of voice and using an emotion engine to determine their current emotional state" refers to technology in which a user inputs facial expressions and tone of voice into the system via a smartphone or other device, and the data is analyzed to identify the user's emotional state.

[1137] The "means for transmitting input information and the analysis results by the emotion engine to the server" refers to a communication means for transmitting basic information collected from the user and data obtained by emotion recognition to the server via the Internet.

[1138] A "generative AI model" is an artificial intelligence algorithm that analyzes data obtained from users and generates optimal recommendations based on specific patterns and trends.

[1139] "Recommendation means" refers to the system's function of presenting the most suitable instruments and benefits to users based on information analyzed by the generative AI model.

[1140] The "means for displaying to the user" refers to a display or interface for visually presenting detailed information about the recommended instruments and special offers on the user's device.

[1141] An "emotion engine" is a software engine that analyzes the user's facial and voice data and identifies the user's current emotional state based on the results.

[1142] To put this invention into practice, a system is required for exchanging information between a terminal used by a user and a server. The specific configuration and operation of this system will now be described.

[1143] Enter user information

[1144] The user inputs their playing style, personal preferences, and skill level using a terminal. This information is saved in the system as a user profile. The input interface is a device such as a smartphone or tablet.

[1145] Emotion recognition

[1146] The device captures the user's facial expressions and tone of voice in real time and sends them to an emotion engine, which uses existing software such as Microsoft Azure Cognitive Services, to analyze the user's current emotional state (happiness, sadness, excitement, tension, etc.).

[1147] Sending information

[1148] The device sends the information entered by the user and the analysis results of the emotion engine to the server via secure HTTPS communication, ensuring the safety of the data.

[1149] Analysis of information

[1150] The server validates the received data to ensure it is in the correct format, then analyzes it using a generative AI model (such as TensorFlow or PyTorch) that takes into account the user's playing style, preferences, skill level, and emotional state to make optimal recommendations.

[1151] Recommending instruments and special offers

[1152] Based on the analysis results, the server recommends the most suitable musical instruments or special offers for electronic payment services. For example, if a user is feeling stressed, it will recommend relaxation-related offers (massage coupons, aroma candles, etc.). This also includes detailed information about specific products and services.

[1153] Sending and displaying recommendations

[1154] The server sends the generated recommendation list to the terminal, which displays this information in a format that is easy for the user to understand. The user can check the detailed information of the displayed instruments and benefits and make an appropriate selection.

[1155] Specific examples

[1156] For example, consider the case where a beginner rock player is looking for a red guitar and is currently in an "excited" state. First, the user inputs their playing style as "rock," their preference as "red," and their skill level as "beginner" into their device. Next, the device sends the user's facial expression and tone of voice to the emotion engine, which determines that the user is in an "excited" state. This information is sent to the server, where the generative AI model analyzes it. As a result, it is determined that a guitar with an active design is suitable for the excited user, and a "red electric guitar from manufacturer ABC" is recommended, for example. The server sends this information to the device, which then displays the details to the user.

[1157] Prompt Sentence Examples

[1158] "If a user is stressed, what kind of reward would be appropriate? Consider past purchase history and basic information."

[1159] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1160] Step 1: Enter your user information

[1161] Users access the system using a device (smartphone or tablet) and input their playing style (e.g., rock, jazz, classical), personal preferences (e.g., guitar color and material), and skill level (e.g., beginner, intermediate, advanced). The input information is temporarily stored on the device and organized as a user profile. This input data serves as the basis for all subsequent processing.

[1162] Step 2: Recognize emotions

[1163] The device captures the user's facial expressions and tone of voice in real time using a camera and microphone. The captured data is sent to an emotion engine (e.g., Microsoft Azure Cognitive Services) to determine the user's current emotional state (e.g., joy, sadness, excitement, or tension). The emotion engine analyzes facial expressions and voice tone to identify emotions from this data. The emotional state is output in text format.

[1164] Step 3: Submit your information

[1165] The device sends the information entered by the user (playing style, personal preferences, skill level) and the emotional state analyzed by the emotion engine to the server. The transmission uses the HTTPS protocol to ensure data security. The transmitted data is structured in JSON format or similar.

[1166] Step 4: Analyze the information

[1167] The server receives the data (user information and emotional state) sent from the device and verifies that the format is correct. Once the data is verified, the server analyzes it using a generative AI model (e.g., TensorFlow or PyTorch). The analysis takes into account the user's playing style, preferences, skill level, and emotional state to identify the most suitable instrument and rewards. The results of the data analysis are output.

[1168] Step 5: Recommend an instrument or benefit

[1169] The server generates a list of optimal instruments and rewards based on the analysis results of the generative AI model. For example, if the user is feeling stressed, the server will include rewards related to relaxation (e.g., massage coupons, aroma candles, etc.). The recommendation list is configured with detailed information (e.g., manufacturer, model, features, etc.). The generated recommendation list is sent to the device in the next step.

[1170] Step 6: Submit your recommendation

[1171] The server sends the generated recommendation list to the device via secure communication. The recommendation list is packaged in a format that is easy for the user to understand (e.g., text and images). The sent data is structured in JSON format or similar.

[1172] Step 7: View Recommendations

[1173] The device analyzes the recommendation list received from the server and visually displays it to the user. The display includes detailed information about the recommended instruments and special offers, allowing the user to make a selection while looking at the screen. It is also possible to provide real-time user feedback.

[1174] Through this series of processes, the user can receive the optimal instrument or benefit that matches their emotional state, resulting in a high level of satisfaction.

[1175] 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.

[1176] 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.

[1177] 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.

[1178] 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.

[1179] 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.

[1180] 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.

[1181] 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).

[1182] 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.

[1183] 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."

[1184] 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.

[1185] 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).

[1186] 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.

[1187] 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.

[1188] 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.

[1189] 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.

[1190] 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.

[1191] 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.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] 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.

[1196] The following is further disclosed regarding the above embodiment.

[1197] (Claim 1)

[1198] a means for the user to input playing style, personal preferences, and skill level;

[1199] means for transmitting the input information to a server;

[1200] A means for the server to analyze the received information using an AI model;

[1201] A means of recommending the most suitable instrument based on the analysis results;

[1202] The system includes a means for displaying the recommendation results to the user.

[1203] (Claim 2)

[1204] The system of claim 1, wherein the AI ​​model performs analysis taking into account past data and user profile.

[1205] (Claim 3)

[1206] 10. The system of claim 1, wherein the recommended instruments include detailed information.

[1207] "Example 1"

[1208] (Claim 1)

[1209] a means for the user to input playing style, personal preferences, and skill level;

[1210] means for transmitting the input information to a data processing device;

[1211] means for performing an analysis using an artificial intelligence model based on the information received by the data processing device;

[1212] A means of recommending the most suitable instrument based on the analysis results;

[1213] means for displaying the recommendation results to the user;

[1214] means for using a communication protocol that encrypts and transmits user data;

[1215] A system that includes a means to include detailed descriptions and images in recommendation results.

[1216] (Claim 2)

[1217] 2. The system of claim 1, wherein the artificial intelligence model performs analysis taking into account past data and user profile.

[1218] (Claim 3)

[1219] 10. The system of claim 1, wherein the recommended instruments include a manufacturer, a model, and characteristics.

[1220] "Application Example 1"

[1221] (Claim 1)

[1222] a means for the user to input playing style, personal preferences, and skill level;

[1223] means for transmitting the input information to a server;

[1224] A means for the server to analyze the received information using a generative AI model;

[1225] A means of recommending the most suitable instrument based on the analysis results;

[1226] A means for displaying the recommendation results on a user terminal;

[1227] A means of sending user input information to the server in JSON format;

[1228] A means for the server to send prompt sentences to the generative AI model to obtain recommendation results;

[1229] A system including:

[1230] (Claim 2)

[1231] The system of claim 1, wherein the generative AI model performs analysis taking into account past data and the user's profile.

[1232] (Claim 3)

[1233] 10. The system of claim 1, wherein the recommended instruments include detailed information.

[1234] "Example 2: Combining Emotion Engines"

[1235] (Claim 1)

[1236] a means for the user to input playing style, personal preferences, and skill level;

[1237] means for storing the entered information;

[1238] a means for collecting a user's facial expression, tone of voice, and input text;

[1239] means for recognizing the emotional state of the user based on the collected information;

[1240] means for transmitting the input information and emotional state to a server;

[1241] A means for the server to analyze the received information using a generative AI model;

[1242] A means of recommending the most suitable instrument based on the analysis results;

[1243] The system includes a means for displaying the recommendation results to the user.

[1244] (Claim 2)

[1245] The system of claim 1, wherein the generative AI model also takes into account the user's emotional state when performing analysis.

[1246] (Claim 3)

[1247] 10. The system of claim 1, wherein the recommended instruments include detailed information and images.

[1248] "Application example 2 when combining emotion engines"

[1249] (Claim 1)

[1250] a means for the user to input playing style, personal preferences, and skill level;

[1251] means for recognizing a user's facial expression and tone of voice and determining their current emotional state using an emotion engine;

[1252] A means for transmitting the input information and the analysis results by the emotion engine to a server;

[1253] The server analyzes the received information using a generative AI model and recommends the most suitable instruments and benefits, taking into account the user's emotional state.

[1254] The system includes a means for displaying the recommendation results to the user.

[1255] (Claim 2)

[1256] The system of claim 1, wherein the generative AI model performs analysis taking into account past data, the user's profile, and emotional state.

[1257] (Claim 3)

[1258] 10. The system of claim 1, wherein the recommended instruments and rewards include detailed information. [Explanation of symbols]

[1259] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for the user to input playing style, personal preferences, and skill level; means for transmitting the input information to a server; A means for the server to analyze the received information using an AI model; A means of recommending the most suitable instrument based on the analysis results; The system includes a means for displaying the recommendation results to the user.

2. The system of claim 1, wherein the AI ​​model performs analysis taking into account past data and user profiles.

3. The system of claim 1 , wherein the recommended instruments include detailed information.

Images