System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving information input by a user; means for analyzing the received information; means for recommending an optimal category based on the analyzed information using a generated AI; and means for automatically displaying the recommended category on a user device.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] When filling out a questionnaire or form, selecting an appropriate category from a vast number of options is time-consuming and reduces productivity. This problem is particularly pronounced when there are many options, placing a heavy burden on the user. As a result, the input process is inefficient and prone to errors, which detracts from the user's overall experience. The present invention aims to solve these problems and reduce the burden on the user. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving data entered by a user, a means for analyzing the received data, a means for generating and recommending optimal categories based on the analyzed data using AI, and a means for automatically displaying the recommended categories on the user's device. The system also includes a means for taking past input history into account in the analyzed data, thereby improving the accuracy and suitability of the categories. Furthermore, the system includes a means for displaying the recommended categories in a visually distinguishable color, preventing erroneous selection by the user and allowing for easy confirmation. In this way, a system is provided that increases user input efficiency, reduces input errors, and improves the overall user experience.

[0006] "Means for receiving data entered by a user" refers to a technical element that has the function of transmitting information entered by a user into a form via a browser or application to a server in real time and receiving it.

[0007] "Means for analyzing received data" refers to a technical element in which the server uses techniques such as natural language processing to interpret the content of the data received from the user and analyze it to identify the appropriate category.

[0008] "Means for recommending optimal categories using generative AI" refers to a technological element that uses artificial intelligence to automatically select and recommend the category that best suits the analyzed data.

[0009] The "means for automatically displaying on the user's terminal" is a technical element that transmits the recommended categories from the server to the user's terminal and automatically displays the information in the input field.

[0010] "Means for taking into account past input history" refers to a technical element that stores the user's past input data and selection history and uses this during analysis to recommend more suitable categories.

[0011] The "means of displaying in a visually identifiable color" is a technical element that visually emphasizes the recommended category by changing the display color so that the user can recognize it at a glance. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] The present invention is a system for automating category selection required when filling out a questionnaire or form. Specific embodiments are described below.

[0034] Program Structure

[0035] The program of this system consists of the following main components:

[0036] 1. Data receiving module

[0037] This module receives data entered by the user through a browser or application. It sends the data to the server in real time and receives it.

[0038] 2. Data Analysis Module

[0039] This module analyzes the data received by the server. This module uses natural language processing technology to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis, keyword extraction, semantic analysis, etc.

[0040] 3. Generative AI Module

[0041] This module utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset and recommends categories with high accuracy.

[0042] 4. Display module

[0043] This module automatically displays recommended categories on the user's device, highlighting them visually by changing the display color so that users can see them at a glance.

[0044] 5. History Keeping Module

[0045] This module saves the user's past input data and selection history and uses it during analysis. This allows it to recommend more appropriate categories when a similar input is made, by referring to past information.

[0046] Program processing explanation

[0047] 1. Data Reception

[0048] If a user types "Software Engineer" into the "Job Title" field, that data is sent to the server in real time.

[0049] The server receives the data sent by the user and records its contents.

[0050] 2. Data Analysis

[0051] The data received by the server is analyzed by the data analysis module, where the keyword "software engineer" is analyzed using natural language processing technology.

[0052] Based on the analysis results, the relevant category (for example, "technology" or "IT field") is extracted.

[0053] 3. Category recommendation using generative AI

[0054] The generative AI module selects the most appropriate category based on the analysis results. At this point, the generative AI model recommends categories such as "technology" and "AI technology" with a high probability.

[0055] If there is past input history, that will also be used as a reference when selecting a category.

[0056] 4. Category display

[0057] The recommended categories are transferred to the display module and automatically displayed on the user's device. For example, when "Software Engineer" is entered, "Technology" is automatically displayed in blue.

[0058] The user can review the displayed categories and manually correct them if necessary.

[0059] Specific examples

[0060] As an example, consider the case where a user enters the following information into a questionnaire form:

[0061] Job title: Software Engineer

[0062] Q: What do you think about recent advances in AI technology?

[0063] The server receives and analyzes the data for "software engineers" and "advances in AI technology." Based on the analysis results, the generative AI module recommends categories such as "technology" and "AI research," which are displayed in blue on the user's device. The user can then confirm the displayed categories and either proceed to the next input or modify them as necessary.

[0064] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[0068] Step 2:

[0069] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[0070] Step 3:

[0071] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[0072] Step 4:

[0073] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[0074] Step 5:

[0075] The parsed data is passed to a generative AI module, which uses a pre-trained model to recommend the best category based on the parsed results.

[0076] Step 6:

[0077] The generative AI module determines the recommended category, taking into account past input history and existing databases in the process.

[0078] Step 7:

[0079] The recommended categories are sent to a display module, which automatically displays the received category information on the user's device and visually emphasizes it by changing the color.

[0080] Step 8:

[0081] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0082] Step 9:

[0083] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[0084] Example 1

[0085] 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."

[0086] Conventional questionnaire and form entry systems require users to manually select categories, which is time-consuming and laborious. This manual category selection process is cumbersome for users and can lead to input errors and time-waste. Furthermore, because past input history is not taken into account, the system often produces low-accuracy category recommendations.

[0087] 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.

[0088] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for automatically displaying the recommended categories on the user terminal, and means for saving and referencing the user's past input history, thereby enabling the user to automatically select and display highly accurate categories without any effort on their part.

[0089] "User" refers to the person or end user who operates the system and inputs data.

[0090] "Means for receiving" refers to a hardware or software function that receives data sent from a user terminal and converts it into a processable format.

[0091] "Means for analyzing" refers to functions including natural language processing techniques and algorithms that process received data to understand and classify it.

[0092] "Generative AI" refers to an artificial intelligence model that processes data based on a pre-trained dataset and automatically generates or recommends optimal results.

[0093] "Recommendation means" refers to the function that allows the generative AI to select the most appropriate category based on the analyzed data and present it to the user.

[0094] "Means for automatic display" refers to a function for automatically displaying categories recommended by the system on the interface of the user terminal.

[0095] "Means for saving and referencing" refers to a function for saving the user's past input data and selection history and using it for subsequent data analysis and category recommendations.

[0096] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and is configured as follows. Specifically, this system is made up of the following main components:

[0097] 1. Data receiving module

[0098] This module receives data entered by users through a browser or application. It transmits data to a server in real time and receives it. The hardware used is a general server and a user terminal, and the software uses the HTTP protocol and WebSocket.

[0099] 2. Data Analysis Module

[0100] This module analyzes the data received by the server. It uses natural language processing techniques to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis such as Python's NLTK library, TF-IDF, and Word2Vec, keyword extraction, and semantic analysis.

[0101] 3. Generative AI Module

[0102] This system utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The generative AI model operates based on a pre-trained dataset and recommends categories with high accuracy. For example, a Transformer-based model is used. This enables highly accurate category recommendations based on the analysis results.

[0103] 4. Display module

[0104] This module automatically displays recommended categories on the user's device. It has a function to change the display color to emphasize them visually so that the user can check them at a glance. The display is made up of a user interface using HTML, CSS, and JavaScript.

[0105] 5. History Keeping Module

[0106] This is to store the user's past input data and selection history and use it during analysis. This allows us to refer to past information when there is similar input and recommend more appropriate categories. We efficiently manage history using a database system (e.g., MySQL or PostgreSQL).

[0107] Specific examples

[0108] Consider a case where a user enters the following information into a survey form in a browser:

[0109] Job title: Software Engineer

[0110] Q: What do you think about recent advances in AI technology?

[0111] The user enters "software engineer" and the input is sent from the device to the server. The server receives the data through the receiving module and analyzes the keyword "software engineer" in the data analysis module. Based on the analysis results, the generation AI module recommends categories such as "technology" or "AI research." The categories transferred from the server to the display module are displayed in blue on the user's device. The user checks the display and proceeds to the next input or makes corrections as necessary.

[0112] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] A user enters "Software Engineer" into the "Profession" field of a questionnaire form in a browser or application. The device sends the input data to the server in real time. The server receives the data through a receiving module and records the contents in a database. The input at this stage is text data from the user, which the server receives and stores.

[0116] Step 2:

[0117] The server analyzes the received data "Software Engineer" in the data analysis module. The analysis includes the following specific operations: First, the received text data is tokenized and each word is extracted. Then, important keywords are identified using TF-IDF and Word2Vec. Finally, semantic analysis is performed to identify the most appropriate category. The input here is the text data from step 1, and the output is a list of category candidates.

[0118] Step 3:

[0119] The generative AI module receives the list of candidate categories resulting from the analysis. The generative AI model (e.g., a Transformer-based model) selects the optimal category based on a pre-trained dataset. In this process, for example, a prompt sentence is generated to select a category with a high probability from the candidate list, and the AI ​​evaluates the result. The input here is the list of candidate categories from step 2, and the output is a category recommended with a high probability.

[0120] Step 4:

[0121] The server uses a history-keeping module to reference the user's past input data and influence the output of the generative AI module. This specifically involves retrieving the user's past selection history from the database and reprocessing it as input for the AI ​​model. The input here is the user's past input history and the category selected by the AI ​​in step 3, and the output is a final recommended category with further improved accuracy.

[0122] Step 5:

[0123] The final recommended category is transferred from the server to the display module and automatically displayed on the user's device. The display module uses HTML and CSS to display categories in different colors for easy visual identification. For example, for the input "software engineer," the "technology" category is displayed in blue. The user can check the displayed category and proceed to the next input or modify it as necessary. The input here is the final recommended category, and the output is the category displayed on the user's device.

[0124] (Application example 1)

[0125] 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."

[0126] In conventional input forms and surveys, users had to manually select the appropriate category when entering data, which increased the effort and time required for input. Furthermore, when entering product reviews or questions in physical stores, it was difficult to easily select the appropriate category, often resulting in a poor user experience. Furthermore, there was no system that could utilize past input history to recommend the most appropriate category, which sometimes resulted in inaccurate recommendations.

[0127] 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.

[0128] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending an optimal category based on the analyzed data using a generation AI, means for automatically displaying the recommended category on the user terminal, and means for recommending an optimal category in response to input of a review or question about a physical store. This allows the user to easily select an appropriate category, improving the user experience and reducing the effort required for input.

[0129] "User" refers to any individual or legal entity that uses the System.

[0130] "Data" refers to information such as text and numbers entered by the user.

[0131] "Receiving means" refers to a function for receiving data entered by a user in real time.

[0132] "Analysis means" refers to a function that analyzes received data using natural language processing technology.

[0133] "Category" refers to a category or classification item for classifying data.

[0134] "Generative AI" refers to artificial intelligence that automatically selects the most appropriate category based on a pre-trained dataset.

[0135] "Recommendation method" refers to the function of using generative AI to recommend categories to users based on analyzed data.

[0136] "Display means" refers to a function for displaying recommended categories on a user terminal.

[0137] "Brick and mortar store" refers to a commercial establishment located in a physical location.

[0138] A "review" refers to an evaluation or impression a user enters about a product or service.

[0139] "Question" refers to an inquiry or question that a user enters regarding a product or service.

[0140] "Input history" refers to a record of data that a user has previously entered and the results of their selections.

[0141] "Visually distinguishable color" refers to a color that allows a user to recognize the recommended category at a glance.

[0142] MODE FOR CARRYING OUT THE INVENTION

[0143] This invention is a system that aims to simplify the input of reviews and questions in physical stores and improve the user experience. This system analyzes the data entered by the user and automatically recommends and displays the most suitable category using generative AI.

[0144] System Program Overview

[0145] The system program is constructed mainly using the following hardware and software.

[0146] Hardware Configuration

[0147] Server: A central processing unit that handles the primary data processing and execution of generative AI models.

[0148] User device: A device used by users to enter reviews and questions in a physical store, such as a smartphone.

[0149] Software Configuration

[0150] Data receiving module: Provides a function for receiving input data from a user in real time.

[0151] Data Analysis Module: Analyzes the received data and interprets its contents using natural language processing techniques. Specifically, it uses the Hugging Face Transformer model.

[0152] Generative AI module: Recommends the most appropriate category based on the analyzed data, using a pre-trained generative AI model.

[0153] Display module: Visually displays the recommended categories on the user's device. The categories are displayed in easy-to-distinguish colors.

[0154] History keeping module: Saves the user's past input data and selected categories for future reference.

[0155] Processing flow

[0156] The server receives reviews and questions entered by users via the data reception module. The data analysis module analyzes this data using natural language processing technology to understand keywords and sentence structure. The generative AI module uses a pre-trained dataset to recommend the most appropriate category based on the analysis results. The display module visually displays the recommended category on the user's device. If the displayed category is appropriate, the user can proceed to the next input. The history retention module saves the user's past input data and the selection results, which can be used for future input.

[0157] Specific examples

[0158] For example, consider the case where a user enters the following information as a review:

[0159] Product Review: Review of the smartphone I recently bought

[0160] The server receives this data in real time and analyzes it using the data analysis module. As a result, the keyword "smartphone" is extracted, and the generation AI module recommends the category "electronic devices" based on this. The category is displayed in blue on the user's device. The user can check this recommended category and post a review right away.

[0161] In this way, the system reduces user input efforts and contributes to an improved overall user experience.

[0162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0163] Step 1:

[0164] The server receives reviews and questions entered by users on their devices in real time through a data receiving module. At this time, the specific data entered by the user (e.g., "Review of the smartphone I recently bought") is received as input. The received data is temporarily stored in the server's storage.

[0165] Step 2:

[0166] The server analyzes the received data using a data analysis module. This module uses natural language processing techniques (e.g., the Hugging Face Transformer model) to extract keywords and analyze sentence structure from the text data. The input text data (e.g., "Reviews of recently purchased smartphones") is analyzed, and extracted keywords (e.g., "smartphone") and contextual information are obtained as output.

[0167] Step 3:

[0168] The server then uses a generative AI module to recommend the most appropriate category based on the analysis results. At this stage, the analyzed keywords and contextual information (e.g., "smartphone") are used as input. The generative AI model leverages a pre-trained dataset to output the most appropriate category, such as "electronic devices," based on the input with high accuracy.

[0169] Step 4:

[0170] The server visually displays the recommended categories on the user device through a display module. The category information received from the generation AI module (e.g., "electronic devices") is input, and the output is displayed on the screen of the user device. The recommended categories are displayed in an easily identifiable color (e.g., blue).

[0171] Step 5:

[0172] The user can check the displayed categories and submit the review or question as is, or modify it. After the user confirms, the final input data and category selection are sent back to the server.

[0173] Step 6:

[0174] The server uses a history storage module to store the user's past input data and selected categories. At this time, the data confirmed and submitted by the user (e.g., "Review of the smartphone recently purchased," category "Electronic device") is used as input, and this history is accumulated in a database in the server as output.

[0175] Through the above processing steps, the system provides users with fast and accurate category recommendations and reduces input effort.

[0176] 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.

[0177] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[0178] Program Structure

[0179] The program of this system consists of the following main components:

[0180] 1. Data receiving module

[0181] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technology to receive data.

[0182] 2. Data Analysis Module

[0183] This module analyzes the data received by the server. It uses natural language processing technology to analyze the content of the data and extract keywords and related information.

[0184] 3. Generative AI Module

[0185] This module uses generative AI technology to recommend the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset.

[0186] 4. Emotion Engine

[0187] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes the user's typing speed, writing style, facial expressions (if a camera is available), etc.

[0188] 5. Display module

[0189] This module automatically displays recommended categories on the user's device. It dynamically changes the display color and format of the categories based on the results of the emotion engine.

[0190] 6. History Keeping Module

[0191] This module saves the user's past input data and selection history and uses it during analysis, allowing it to recommend more appropriate categories based on past input.

[0192] Program processing explanation

[0193] 1. Data Reception

[0194] If a user enters "Software Engineer" in the "Profession" field, the data is sent in real time to the server, which receives the data and passes it to the data receiving module.

[0195] 2. Data Analysis

[0196] The server passes the received data to a data analysis module, which uses natural language processing technology to extract and analyze keywords such as "software engineer."

[0197] 3. Emotion recognition

[0198] The emotion engine analyzes the user's typing behavior and, if available, facial expressions to understand their emotional state. For example, if the user types slowly or writes in a rough style, the analysis results will reflect stress or frustration.

[0199] 4. Category recommendation using generative AI

[0200] Based on the results of the data analysis module and the sentiment engine, the generative AI module recommends the most appropriate category, taking into account past input history in the process.

[0201] 5. Category display

[0202] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[0203] 6. User Verification

[0204] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0205] 7. Data Transmission

[0206] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[0207] Specific examples

[0208] For example, consider the case where a user enters the following information into a questionnaire form:

[0209] Job title: Software Engineer

[0210] Q: What do you think about recent advances in AI technology?

[0211] The server receives data on "software engineers" and "AI technology advancements" and analyzes them using the data analysis module. The emotion engine analyzes the user's input speed and writing style to confirm that the user is interested. The generative AI module uses this data to recommend categories such as "technology" and "AI research," which are displayed in soft colors on the user's device. The user can then review the displayed categories and proceed to the next input or modify them as needed.

[0212] By taking user emotions into consideration, this system can provide more appropriate and personalized category recommendations, improving the user experience.

[0213] The processing flow will be explained below.

[0214] Step 1:

[0215] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[0216] Step 2:

[0217] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[0218] Step 3:

[0219] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[0220] Step 4:

[0221] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[0222] Step 5:

[0223] The server activates an emotion engine to analyze the user's typing behavior, writing style, and, if possible, facial expressions. For example, if the user types slowly or writes roughly, it may determine that the user is stressed or frustrated.

[0224] Step 6:

[0225] The analysis results of the data analysis module and the sentiment engine are passed to the generative AI module, which uses a pre-trained model to recommend the best category based on these results.

[0226] Step 7:

[0227] The generative AI module recommends the most appropriate category, taking into account past input history and emotional state. For example, based on the analysis results and emotional state, categories such as "technology" and "AI research" are highly likely to be recommended.

[0228] Step 8:

[0229] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[0230] Step 9:

[0231] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0232] Step 10:

[0233] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[0234] Example 2

[0235] 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."

[0236] In conventional survey and form entry systems, the task of selecting the appropriate category based on the data entered by the user is cumbersome, which can lead to a poor user experience. Furthermore, because the system does not take into account the user's emotional state, it can be even more difficult to enter data under stressful circumstances. This can lead to an increase in user input errors and a loss of data quality and accuracy.

[0237] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0238] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data using natural language processing technology, means for recognizing the user's emotional state, means for recommending optimal categories based on the analyzed data and the emotional state using generative AI technology, and means for automatically displaying the recommended categories on the user terminal. This makes it possible to streamline the user's input work and to recommend personalized categories that take the user's emotional state into consideration.

[0239] "User-entered data" refers to text data or information entered by a user into an input field on a questionnaire, form, or the like.

[0240] "Natural language processing technology" is a technology that allows computers to understand, analyze, and process the language that humans use on a daily basis.

[0241] The "emotional state" refers to the emotional state that is expressed when the user performs input actions, and includes factors such as input speed, character type, and facial expression.

[0242] "Generative AI technology" is a type of artificial intelligence technology that generates optimal output based on input data by learning from large amounts of data, and is used, for example, to recommend categories.

[0243] "Recommendation methods" refer to functions and technologies that automatically present the most appropriate category based on the analyzed data and the user's emotional state.

[0244] A "user terminal" is a device such as a computer, smartphone, or tablet used to enter data into a survey or form.

[0245] "Past input history" refers to a record of data that the user has previously entered and the categories they selected at that time, and is used for subsequent input data analysis and category recommendations.

[0246] "Visually distinguishable colors" are colors used to make categories easier to see, and are colors that are intuitively recognizable by users.

[0247] "Means for dynamic change" refers to a function that changes the color and format of the displayed categories in real time according to the user's emotional state.

[0248] The present invention is a system that automates the category selection required when a user fills out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[0249] Program Structure

[0250] The program of this system consists of the following main components:

[0251] 1. Data receiving module

[0252] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technologies such as Ajax and WebSocket to receive data.

[0253] 2. Data Analysis Module

[0254] This module analyzes the data received by the server. This module uses natural language processing techniques such as Python's NLTK library to extract keywords and related information from the input text.

[0255] 3. Emotion Engine

[0256] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes input speed, writing style, facial expressions (if a camera is available), and also uses image analysis software such as OpenCV.

[0257] 4. Generative AI Module

[0258] This module uses generative AI technology to recommend the most appropriate category based on the results of data analysis and an emotion engine. The AI ​​model uses a pre-trained dataset, such as the GPT-3 model.

[0259] 5. Display module

[0260] This module automatically displays recommended categories on the user's device. The display color and format of the recommended categories change dynamically based on the results of the emotion engine.

[0261] 6. History Keeping Module

[0262] This module stores the user's past input data and selection history and reuses it for data analysis and category recommendations, enabling more personalized suggestions.

[0263] Specific examples

[0264] Below is a concrete example of how this system works.

[0265] For example, consider the case where a user enters the following information into a questionnaire form:

[0266] Job title: Software Engineer

[0267] Q: What do you think about recent advances in AI technology?

[0268] The server receives the data "software engineer" entered in the "job title" field from the terminal via asynchronous communication and passes it to the data analysis module via the data reception module. The data analysis module uses Python's NLTK library to analyze this text and extract keywords such as "software engineer" and "advances in AI technology."

[0269] Next, the emotion engine analyzes the user's typing speed, writing style, and possibly facial expressions. For example, if the user types quickly in response to this question, it determines that the user has interest or positive emotions. These results are passed to a generative AI module, and an AI model such as GPT-3 recommends an appropriate category, such as "Technology" or "AI Research."

[0270] The recommended categories are displayed on the user's device through a display module. At this time, visual enhancements are made, such as changing the display color to light blue depending on the user's emotional state. The user can check the displayed categories and manually correct them if necessary.

[0271] In this way, the system automatically and appropriately selects categories while taking into account the user's emotions, improving the user experience. This reduces unnecessary input work and input errors, enabling efficient information collection.

[0272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0273] The flow of this system's program processing

[0274] Step 1:

[0275] When a user enters "Software Engineer" in the "Profession" field, the data is sent from the terminal to the server, which receives the data through the data receiving module.

[0276] Input: Data entered by the user, such as "Software Engineer"

[0277] Output: Preparing received data for passing to the data analysis module

[0278] Specific operation: The device's browser or application captures the input and sends the data to the server using asynchronous communication technology such as Ajax.

[0279] Step 2:

[0280] The server passes the received data to a data analysis module, which analyzes the data using natural language processing techniques.

[0281] Input: User input data received by the server

[0282] Output: Keywords and related information extracted as analysis results

[0283] Specific operation: Using Python's NLTK library, keywords are extracted from input data (such as "software engineer") and appropriate information is retrieved based on them.

[0284] Step 3:

[0285] The server passes the analysis results to the emotion engine, which analyzes the user's input speed, writing style, and, if possible, facial expressions to determine their emotional state.

[0286] Input: Analysis results of the data analysis module and user input behavior data collected from the terminal

[0287] Output: Information about the user's emotional state

[0288] Specific operation: Analyzes input speed and character type, and performs facial recognition using the device's camera if necessary. Performs image analysis using OpenCV and other tools to determine the user's stress level and emotions.

[0289] Step 4:

[0290] The server passes the results of the data analysis module and the emotion engine to the generative AI module, which uses a pre-trained dataset to recommend the best category.

[0291] Input: Results of the data analysis module and the sentiment engine

[0292] Output: Recommended categories

[0293] How it works: Using generative AI techniques such as the GPT-3 model, it recommends the most appropriate category (e.g., "Technology" or "AI Research") based on an input prompt (e.g., "Software Engineer" or "AI Technology Advancements").

[0294] Step 5:

[0295] The server passes the recommended categories to the display module, which automatically displays the recommended categories on the user's device.

[0296] Input: Categories recommended by the generative AI module

[0297] Output: Categories displayed on the user's device

[0298] Specific behavior: When the recommended categories are displayed on the web page, the background color and font color are dynamically changed taking into account the results of the emotion engine.

[0299] Step 6:

[0300] Users can check the displayed categories on their device and decide whether they are appropriate. If they are not, they can manually correct them.

[0301] Input: Viewed Categories

[0302] Output: Final categories after user review and correction

[0303] Specific operation: The user manually edits the displayed "Technology" category, for example, by changing it to "AI Research."

[0304] Step 7:

[0305] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[0306] Input: Form data that the user last confirmed

[0307] Output: Data stored on the server and any necessary subsequent processing performed

[0308] Specific operation: When you click the submit button on the form, all input data is sent to the server again via asynchronous communication. The server stores the data in a database (e.g., MySQL) and performs subsequent processing such as sending a confirmation email to the user.

[0309] (Application example 2)

[0310] 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."

[0311] While conventional online shopping sites have product recommendation systems that respond to users' search and purchasing behavior, they do not offer personalized product recommendations that take the user's emotions into account. As a result, they are unable to provide optimal products that reflect the user's momentary emotions and state, limiting the improvement of the user experience. Furthermore, users may feel frustrated because the recommended products and categories are not displayed appropriately based on the user's emotional state. A solution to these issues is needed.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0313] In this invention, the server includes means for receiving data entered by the user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for recognizing the user's emotions and reflecting the user's emotional state in the analysis and recommendation, and means for automatically displaying the recommended categories on the user's terminal. This enables personalized product recommendations that take the user's emotions into consideration. Furthermore, by further including means for considering the user's past input history in the analyzed data and means for dynamically changing the display according to the user's emotions, it is possible to recommend optimal products that correspond to the user's momentary emotions and to achieve a display that is less stressful.

[0314] The "means for receiving data entered by the user" is a function for receiving text, voice, image data, etc. entered by the user into the system in real time.

[0315] The "means for analyzing received data" is a function for processing received user data using natural language processing and image analysis technology to extract related keywords and information.

[0316] "Means of using AI to generate and recommend optimal categories based on analyzed data" is a function that uses a pre-trained AI model to recommend the most appropriate category to the user based on extracted keywords and information.

[0317] "Means for recognizing the user's emotions and reflecting their emotional state in the analysis and recommendations" refers to a function that uses sensor devices such as cameras and microphones to analyze the user's facial expressions and voice, and incorporates the results into category recommendations.

[0318] "Means for automatically displaying recommended categories on the user's device" refers to a function for automatically displaying categories recommended based on the results of generative AI or emotion recognition on the screen of the device used by the user.

[0319] "Means for taking past input history into account in analyzed data" refers to a function that refers to the user's past search history and purchase history and recommends the most appropriate category while taking this history into consideration.

[0320] The "means for dynamically changing the display in accordance with the user's emotions" is a function for dynamically changing the display content, color tone, layout, etc. of the screen in accordance with the user's emotional state.

[0321] The present invention provides a system for recognizing a user's emotions on an online shopping site and recommending the most suitable product category based on the emotions. Specific embodiments are described below.

[0322] System program configuration

[0323] Main components and processing explanation

[0324] The system consists of the following main components:

[0325] 1. Data Receiving Method

[0326] This function receives user-entered search keywords, purchase history, and browsing history in real time. Data is received from user devices using asynchronous communication technology. Examples of hardware that can be used include smartphones, tablets, and PCs.

[0327] 2. Data analysis methods

[0328] This function analyzes received data using natural language processing technology. Specifically, it extracts related information and keywords from keywords and text data entered by the user. The software used is an NLP library (e.g., spaCy, NLTK, etc.).

[0329] 3. Category recommendation method using generative AI

[0330] This function recommends the most appropriate category based on the analyzed data. A prompt sentence is input into a pre-trained generative AI model (such as GPT-3) to generate the most appropriate category. The software used is a generative AI model.

[0331] 4. Emotion recognition means

[0332] This function uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. The emotion recognition results are reflected in the analysis and category recommendations. The hardware used includes a camera and microphone, and the software includes an emotion analysis library (e.g., OpenCV, TensorFlow, etc.).

[0333] 5. Automatic Category Display Method

[0334] This function automatically displays recommended categories on the user's device. The display color and layout change dynamically depending on the user's emotional state. The software used is a front-end framework (e.g., React, Vue.js, etc.).

[0335] 6. History Consideration Methods

[0336] This function saves past input history and purchase history and uses them during analysis. This allows the system to recommend more appropriate categories based on the user's past behavior. The software used is a database management system (e.g., PostgreSQL, MongoDB, etc.).

[0337] 7. Dynamic display change methods

[0338] This function dynamically changes the content, color tone, and layout of the screen display according to the user's emotions. The display module dynamically updates the screen based on the results of emotion recognition.

[0339] Specific examples

[0340] If a user searches for "camping equipment" on an online shopping site and the camera detects an excited expression on the user's face, the following flow will occur:

[0341] 1. User Input and Data Reception

[0342] The user enters the search keyword "camping equipment." The search keyword is sent from the user's device to the server in real time.

[0343] 2. Data Analysis

[0344] The server analyzes the received search keywords using natural language processing technology and extracts keywords such as "camping" and "outdoors."

[0345] 3. Emotion recognition

[0346] The camera is used to analyze the user's facial expressions, and the emotion engine recognizes when the user is excited.

[0347] 4. Category Recommendation

[0348] Enter the following prompt into the generative AI model to generate the best category:

[0349] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[0350] Based on this prompt, the generative AI will recommend categories such as "New Camping Gear" or "Popular Outdoor Gear."

[0351] 5. Automatic category display

[0352] The recommended categories are automatically displayed on the user's device, and the display changes dynamically in bright colors depending on the emotion recognition results.

[0353] This system enables personalized product recommendations that take the user's emotions into consideration, providing an environment in which users can browse products with interest and without feeling stressed.

[0354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0355] Step 1:

[0356] A user enters the search keyword "camping equipment" into a device such as a smartphone or PC. This input data is sent from the device to the server in real time.

[0357] Step 2:

[0358] The server receives search keywords through the data receiving module. The input is "camping equipment," and the output is the keyword itself, which is stored on the server.

[0359] Step 3:

[0360] The server's data analysis means processes the received data. Specifically, it uses natural language processing technology (e.g., spaCy, NLTK) to analyze the keyword "camping equipment" and extract related keywords (e.g., "camping" and "outdoors"). The input is "camping equipment" and the output is a list of analyzed keywords.

[0361] Step 4:

[0362] The server's emotion recognition means uses a camera and microphone to acquire the user's emotional state. The camera captures the user's facial expressions, and the microphone captures their audio. An emotion analysis library (e.g., OpenCV, TensorFlow) is used to analyze the user's emotion and recognize that they are excited. The input is the camera video and audio data, and the output is the user's emotional state (excitement).

[0363] Step 5:

[0364] The server's generative AI-based category recommendation tool generates the most appropriate category based on the analyzed keywords and emotional state. The generative AI model (e.g., GPT-3) is given the following prompt:

[0365] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[0366] This allows the generative AI model to recommend categories such as "New Camping Equipment" or "Popular Outdoor Gear." The input is the prompt, analyzed keywords, and emotional state, and the output is a list of recommended categories.

[0367] Step 6:

[0368] The server's automatic category display means sends the recommended categories to the user's terminal. The user's terminal automatically displays the received category information and dynamically changes the display color tone and layout according to the user's emotional state. The input is a list of recommended categories, and the output is a dynamically updated user interface.

[0369] Step 7:

[0370] The server's history consideration means retrieves the user's past search history and purchase history from the database and analyzes them. This information is used for the next category recommendation and emotion recognition. The input is past history data, and the output is the analysis results that will be used for the next recommendation.

[0371] Step 8:

[0372] Once the server has completed all the processing, the user can view the recommended categories and products without any hassle.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] [Second embodiment]

[0377] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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."

[0389] The present invention is a system for automating category selection required when filling out a questionnaire or form. Specific embodiments are described below.

[0390] Program Structure

[0391] The program of this system consists of the following main components:

[0392] 1. Data receiving module

[0393] This module receives data entered by the user through a browser or application. It sends the data to the server in real time and receives it.

[0394] 2. Data Analysis Module

[0395] This module analyzes the data received by the server. This module uses natural language processing technology to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis, keyword extraction, semantic analysis, etc.

[0396] 3. Generative AI Module

[0397] This module utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset and recommends categories with high accuracy.

[0398] 4. Display module

[0399] This module automatically displays recommended categories on the user's device, highlighting them visually by changing the display color so that users can see them at a glance.

[0400] 5. History Keeping Module

[0401] This module saves the user's past input data and selection history and uses it during analysis. This allows it to recommend more appropriate categories when a similar input is made, by referring to past information.

[0402] Program processing explanation

[0403] 1. Data Reception

[0404] If a user types "Software Engineer" into the "Job Title" field, that data is sent to the server in real time.

[0405] The server receives the data sent by the user and records its contents.

[0406] 2. Data Analysis

[0407] The data received by the server is analyzed by the data analysis module, where the keyword "software engineer" is analyzed using natural language processing technology.

[0408] Based on the analysis results, the relevant category (for example, "technology" or "IT field") is extracted.

[0409] 3. Category recommendation using generative AI

[0410] The generative AI module selects the most appropriate category based on the analysis results. At this point, the generative AI model recommends categories such as "technology" and "AI technology" with a high probability.

[0411] If there is past input history, that will also be used as a reference when selecting a category.

[0412] 4. Category display

[0413] The recommended categories are transferred to the display module and automatically displayed on the user's device. For example, when "Software Engineer" is entered, "Technology" is automatically displayed in blue.

[0414] The user can review the displayed categories and manually correct them if necessary.

[0415] Specific examples

[0416] As an example, consider the case where a user enters the following information into a questionnaire form:

[0417] Job title: Software Engineer

[0418] Q: What do you think about recent advances in AI technology?

[0419] The server receives and analyzes the data for "software engineers" and "advances in AI technology." Based on the analysis results, the generative AI module recommends categories such as "technology" and "AI research," which are displayed in blue on the user's device. The user can then confirm the displayed categories and either proceed to the next input or modify them as necessary.

[0420] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

[0421] The processing flow will be explained below.

[0422] Step 1:

[0423] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[0424] Step 2:

[0425] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[0426] Step 3:

[0427] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[0428] Step 4:

[0429] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[0430] Step 5:

[0431] The parsed data is passed to a generative AI module, which uses a pre-trained model to recommend the best category based on the parsed results.

[0432] Step 6:

[0433] The generative AI module determines the recommended category, taking into account past input history and existing databases in the process.

[0434] Step 7:

[0435] The recommended categories are sent to a display module, which automatically displays the received category information on the user's device and visually emphasizes it by changing the color.

[0436] Step 8:

[0437] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0438] Step 9:

[0439] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[0440] Example 1

[0441] 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."

[0442] Conventional questionnaire and form entry systems require users to manually select categories, which is time-consuming and laborious. This manual category selection process is cumbersome for users and can lead to input errors and time-waste. Furthermore, because past input history is not taken into account, the system often produces low-accuracy category recommendations.

[0443] 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.

[0444] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for automatically displaying the recommended categories on the user terminal, and means for saving and referencing the user's past input history, thereby enabling the user to automatically select and display highly accurate categories without any effort on their part.

[0445] "User" refers to the person or end user who operates the system and inputs data.

[0446] "Means for receiving" refers to a hardware or software function that receives data sent from a user terminal and converts it into a processable format.

[0447] "Means for analyzing" refers to functions including natural language processing techniques and algorithms that process received data to understand and classify it.

[0448] "Generative AI" refers to an artificial intelligence model that processes data based on a pre-trained dataset and automatically generates or recommends optimal results.

[0449] "Recommendation means" refers to the function that allows the generative AI to select the most appropriate category based on the analyzed data and present it to the user.

[0450] "Means for automatic display" refers to a function for automatically displaying categories recommended by the system on the interface of the user terminal.

[0451] "Means for saving and referencing" refers to a function for saving the user's past input data and selection history and using it for subsequent data analysis and category recommendations.

[0452] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and is configured as follows. Specifically, this system is made up of the following main components:

[0453] 1. Data receiving module

[0454] This module receives data entered by users through a browser or application. It transmits data to a server in real time and receives it. The hardware used is a general server and a user terminal, and the software uses the HTTP protocol and WebSocket.

[0455] 2. Data Analysis Module

[0456] This module analyzes the data received by the server. It uses natural language processing techniques to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis such as Python's NLTK library, TF-IDF, and Word2Vec, keyword extraction, and semantic analysis.

[0457] 3. Generative AI Module

[0458] This system utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The generative AI model operates based on a pre-trained dataset and recommends categories with high accuracy. For example, a Transformer-based model is used. This enables highly accurate category recommendations based on the analysis results.

[0459] 4. Display module

[0460] This module automatically displays recommended categories on the user's device. It has a function to change the display color to emphasize them visually so that the user can check them at a glance. The display is made up of a user interface using HTML, CSS, and JavaScript.

[0461] 5. History Keeping Module

[0462] This is to store the user's past input data and selection history and use it during analysis. This allows us to refer to past information when there is similar input and recommend more appropriate categories. We efficiently manage history using a database system (e.g., MySQL or PostgreSQL).

[0463] Specific examples

[0464] Consider a case where a user enters the following information into a survey form in a browser:

[0465] Job title: Software Engineer

[0466] Q: What do you think about recent advances in AI technology?

[0467] The user enters "software engineer" and the input is sent from the device to the server. The server receives the data through the receiving module and analyzes the keyword "software engineer" in the data analysis module. Based on the analysis results, the generation AI module recommends categories such as "technology" or "AI research." The categories transferred from the server to the display module are displayed in blue on the user's device. The user checks the display and proceeds to the next input or makes corrections as necessary.

[0468] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

[0469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0470] Step 1:

[0471] A user enters "Software Engineer" into the "Profession" field of a questionnaire form in a browser or application. The device sends the input data to the server in real time. The server receives the data through a receiving module and records the contents in a database. The input at this stage is text data from the user, which the server receives and stores.

[0472] Step 2:

[0473] The server analyzes the received data "Software Engineer" in the data analysis module. The analysis includes the following specific operations: First, the received text data is tokenized and each word is extracted. Then, important keywords are identified using TF-IDF and Word2Vec. Finally, semantic analysis is performed to identify the most appropriate category. The input here is the text data from step 1, and the output is a list of category candidates.

[0474] Step 3:

[0475] The generative AI module receives the list of candidate categories resulting from the analysis. The generative AI model (e.g., a Transformer-based model) selects the optimal category based on a pre-trained dataset. In this process, for example, a prompt sentence is generated to select a category with a high probability from the candidate list, and the AI ​​evaluates the result. The input here is the list of candidate categories from step 2, and the output is a category recommended with a high probability.

[0476] Step 4:

[0477] The server uses a history-keeping module to reference the user's past input data and influence the output of the generative AI module. This specifically involves retrieving the user's past selection history from the database and reprocessing it as input for the AI ​​model. The input here is the user's past input history and the category selected by the AI ​​in step 3, and the output is a final recommended category with further improved accuracy.

[0478] Step 5:

[0479] The final recommended category is transferred from the server to the display module and automatically displayed on the user's device. The display module uses HTML and CSS to display categories in different colors for easy visual identification. For example, for the input "software engineer," the "technology" category is displayed in blue. The user can check the displayed category and proceed to the next input or modify it as necessary. The input here is the final recommended category, and the output is the category displayed on the user's device.

[0480] (Application example 1)

[0481] 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."

[0482] In conventional input forms and surveys, users had to manually select the appropriate category when entering data, which increased the effort and time required for input. Furthermore, when entering product reviews or questions in physical stores, it was difficult to easily select the appropriate category, often resulting in a poor user experience. Furthermore, there was no system that could utilize past input history to recommend the most appropriate category, which sometimes resulted in inaccurate recommendations.

[0483] 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.

[0484] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending an optimal category based on the analyzed data using a generation AI, means for automatically displaying the recommended category on the user terminal, and means for recommending an optimal category in response to input of a review or question about a physical store. This allows the user to easily select an appropriate category, improving the user experience and reducing the effort required for input.

[0485] "User" refers to any individual or legal entity that uses the System.

[0486] "Data" refers to information such as text and numbers entered by the user.

[0487] "Receiving means" refers to a function for receiving data entered by a user in real time.

[0488] "Analysis means" refers to a function that analyzes received data using natural language processing technology.

[0489] "Category" refers to a category or classification item for classifying data.

[0490] "Generative AI" refers to artificial intelligence that automatically selects the most appropriate category based on a pre-trained dataset.

[0491] "Recommendation method" refers to the function of using generative AI to recommend categories to users based on analyzed data.

[0492] "Display means" refers to a function for displaying recommended categories on a user terminal.

[0493] "Brick and mortar store" refers to a commercial establishment located in a physical location.

[0494] A "review" refers to an evaluation or impression a user enters about a product or service.

[0495] "Question" refers to an inquiry or question that a user enters regarding a product or service.

[0496] "Input history" refers to a record of data that a user has previously entered and the results of their selections.

[0497] "Visually distinguishable color" refers to a color that allows a user to recognize the recommended category at a glance.

[0498] MODE FOR CARRYING OUT THE INVENTION

[0499] This invention is a system that aims to simplify the input of reviews and questions in physical stores and improve the user experience. This system analyzes the data entered by the user and automatically recommends and displays the most suitable category using generative AI.

[0500] System Program Overview

[0501] The system program is constructed mainly using the following hardware and software.

[0502] Hardware Configuration

[0503] Server: A central processing unit that handles the primary data processing and execution of generative AI models.

[0504] User device: A device used by users to enter reviews and questions in a physical store, such as a smartphone.

[0505] Software Configuration

[0506] Data receiving module: Provides a function for receiving input data from a user in real time.

[0507] Data Analysis Module: Analyzes the received data and interprets its contents using natural language processing techniques. Specifically, it uses the Hugging Face Transformer model.

[0508] Generative AI module: Recommends the most appropriate category based on the analyzed data, using a pre-trained generative AI model.

[0509] Display module: Visually displays the recommended categories on the user's device. The categories are displayed in easy-to-distinguish colors.

[0510] History keeping module: Saves the user's past input data and selected categories for future reference.

[0511] Processing flow

[0512] The server receives reviews and questions entered by users via the data reception module. The data analysis module analyzes this data using natural language processing technology to understand keywords and sentence structure. The generative AI module uses a pre-trained dataset to recommend the most appropriate category based on the analysis results. The display module visually displays the recommended category on the user's device. If the displayed category is appropriate, the user can proceed to the next input. The history retention module saves the user's past input data and the selection results, which can be used for future input.

[0513] Specific examples

[0514] For example, consider the case where a user enters the following information as a review:

[0515] Product Review: Review of the smartphone I recently bought

[0516] The server receives this data in real time and analyzes it using the data analysis module. As a result, the keyword "smartphone" is extracted, and the generation AI module recommends the category "electronic devices" based on this. The category is displayed in blue on the user's device. The user can check this recommended category and post a review right away.

[0517] In this way, the system reduces user input efforts and contributes to an improved overall user experience.

[0518] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0519] Step 1:

[0520] The server receives reviews and questions entered by users on their devices in real time through a data receiving module. At this time, the specific data entered by the user (e.g., "Review of the smartphone I recently bought") is received as input. The received data is temporarily stored in the server's storage.

[0521] Step 2:

[0522] The server analyzes the received data using a data analysis module. This module uses natural language processing techniques (e.g., the Hugging Face Transformer model) to extract keywords and analyze sentence structure from the text data. The input text data (e.g., "Reviews of recently purchased smartphones") is analyzed, and extracted keywords (e.g., "smartphone") and contextual information are obtained as output.

[0523] Step 3:

[0524] The server then uses a generative AI module to recommend the most appropriate category based on the analysis results. At this stage, the analyzed keywords and contextual information (e.g., "smartphone") are used as input. The generative AI model leverages a pre-trained dataset to output the most appropriate category, such as "electronic devices," based on the input with high accuracy.

[0525] Step 4:

[0526] The server visually displays the recommended categories on the user device through a display module. The category information received from the generation AI module (e.g., "electronic devices") is input, and the output is displayed on the screen of the user device. The recommended categories are displayed in an easily identifiable color (e.g., blue).

[0527] Step 5:

[0528] The user can check the displayed categories and submit the review or question as is, or modify it. After the user confirms, the final input data and category selection are sent back to the server.

[0529] Step 6:

[0530] The server uses a history storage module to store the user's past input data and selected categories. At this time, the data confirmed and submitted by the user (e.g., "Review of the smartphone recently purchased," category "Electronic device") is used as input, and this history is accumulated in a database in the server as output.

[0531] Through the above processing steps, the system provides users with fast and accurate category recommendations and reduces input effort.

[0532] 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.

[0533] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[0534] Program Structure

[0535] The program of this system consists of the following main components:

[0536] 1. Data receiving module

[0537] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technology to receive data.

[0538] 2. Data Analysis Module

[0539] This module analyzes the data received by the server. It uses natural language processing technology to analyze the content of the data and extract keywords and related information.

[0540] 3. Generative AI Module

[0541] This module uses generative AI technology to recommend the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset.

[0542] 4. Emotion Engine

[0543] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes the user's typing speed, writing style, facial expressions (if a camera is available), etc.

[0544] 5. Display module

[0545] This module automatically displays recommended categories on the user's device. It dynamically changes the display color and format of the categories based on the results of the emotion engine.

[0546] 6. History Keeping Module

[0547] This module saves the user's past input data and selection history and uses it during analysis, allowing it to recommend more appropriate categories based on past input.

[0548] Program processing explanation

[0549] 1. Data Reception

[0550] If a user enters "Software Engineer" in the "Profession" field, the data is sent in real time to the server, which receives the data and passes it to the data receiving module.

[0551] 2. Data Analysis

[0552] The server passes the received data to a data analysis module, which uses natural language processing technology to extract and analyze keywords such as "software engineer."

[0553] 3. Emotion recognition

[0554] The emotion engine analyzes the user's typing behavior and, if available, facial expressions to understand their emotional state. For example, if the user types slowly or writes in a rough style, the analysis results will reflect stress or frustration.

[0555] 4. Category recommendation using generative AI

[0556] Based on the results of the data analysis module and the sentiment engine, the generative AI module recommends the most appropriate category, taking into account past input history in the process.

[0557] 5. Category display

[0558] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[0559] 6. User Verification

[0560] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0561] 7. Data Transmission

[0562] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[0563] Specific examples

[0564] For example, consider the case where a user enters the following information into a questionnaire form:

[0565] Job title: Software Engineer

[0566] Q: What do you think about recent advances in AI technology?

[0567] The server receives data on "software engineers" and "AI technology advancements" and analyzes them using the data analysis module. The emotion engine analyzes the user's input speed and writing style to confirm that the user is interested. The generative AI module uses this data to recommend categories such as "technology" and "AI research," which are displayed in soft colors on the user's device. The user can then review the displayed categories and proceed to the next input or modify them as needed.

[0568] By taking user emotions into consideration, this system can provide more appropriate and personalized category recommendations, improving the user experience.

[0569] The processing flow will be explained below.

[0570] Step 1:

[0571] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[0572] Step 2:

[0573] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[0574] Step 3:

[0575] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[0576] Step 4:

[0577] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[0578] Step 5:

[0579] The server activates an emotion engine to analyze the user's typing behavior, writing style, and, if possible, facial expressions. For example, if the user types slowly or writes roughly, it may determine that the user is stressed or frustrated.

[0580] Step 6:

[0581] The analysis results of the data analysis module and the sentiment engine are passed to the generative AI module, which uses a pre-trained model to recommend the best category based on these results.

[0582] Step 7:

[0583] The generative AI module recommends the most appropriate category, taking into account past input history and emotional state. For example, based on the analysis results and emotional state, categories such as "technology" and "AI research" are highly likely to be recommended.

[0584] Step 8:

[0585] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[0586] Step 9:

[0587] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0588] Step 10:

[0589] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[0590] Example 2

[0591] 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."

[0592] In conventional survey and form entry systems, the task of selecting the appropriate category based on the data entered by the user is cumbersome, which can lead to a poor user experience. Furthermore, because the system does not take into account the user's emotional state, it can be even more difficult to enter data under stressful circumstances. This can lead to an increase in user input errors and a loss of data quality and accuracy.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0594] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data using natural language processing technology, means for recognizing the user's emotional state, means for recommending optimal categories based on the analyzed data and the emotional state using generative AI technology, and means for automatically displaying the recommended categories on the user terminal. This makes it possible to streamline the user's input work and to recommend personalized categories that take the user's emotional state into consideration.

[0595] "User-entered data" refers to text data or information entered by a user into an input field on a questionnaire, form, or the like.

[0596] "Natural language processing technology" is a technology that allows computers to understand, analyze, and process the language that humans use on a daily basis.

[0597] The "emotional state" refers to the emotional state that is expressed when the user performs input actions, and includes factors such as input speed, character type, and facial expression.

[0598] "Generative AI technology" is a type of artificial intelligence technology that generates optimal output based on input data by learning from large amounts of data, and is used, for example, to recommend categories.

[0599] "Recommendation methods" refer to functions and technologies that automatically present the most appropriate category based on the analyzed data and the user's emotional state.

[0600] A "user terminal" is a device such as a computer, smartphone, or tablet used to enter data into a survey or form.

[0601] "Past input history" refers to a record of data that the user has previously entered and the categories they selected at that time, and is used for subsequent input data analysis and category recommendations.

[0602] "Visually distinguishable colors" are colors used to make categories easier to see, and are colors that are intuitively recognizable by users.

[0603] "Means for dynamic change" refers to a function that changes the color and format of the displayed categories in real time according to the user's emotional state.

[0604] The present invention is a system that automates the category selection required when a user fills out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[0605] Program Structure

[0606] The program of this system consists of the following main components:

[0607] 1. Data receiving module

[0608] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technologies such as Ajax and WebSocket to receive data.

[0609] 2. Data Analysis Module

[0610] This module analyzes the data received by the server. This module uses natural language processing techniques such as Python's NLTK library to extract keywords and related information from the input text.

[0611] 3. Emotion Engine

[0612] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes input speed, writing style, facial expressions (if a camera is available), and also uses image analysis software such as OpenCV.

[0613] 4. Generative AI Module

[0614] This module uses generative AI technology to recommend the most appropriate category based on the results of data analysis and an emotion engine. The AI ​​model uses a pre-trained dataset, such as the GPT-3 model.

[0615] 5. Display module

[0616] This module automatically displays recommended categories on the user's device. The display color and format of the recommended categories change dynamically based on the results of the emotion engine.

[0617] 6. History Keeping Module

[0618] This module stores the user's past input data and selection history and reuses it for data analysis and category recommendations, enabling more personalized suggestions.

[0619] Specific examples

[0620] Below is a concrete example of how this system works.

[0621] For example, consider the case where a user enters the following information into a questionnaire form:

[0622] Job title: Software Engineer

[0623] Q: What do you think about recent advances in AI technology?

[0624] The server receives the data "software engineer" entered in the "job title" field from the terminal via asynchronous communication and passes it to the data analysis module via the data reception module. The data analysis module uses Python's NLTK library to analyze this text and extract keywords such as "software engineer" and "advances in AI technology."

[0625] Next, the emotion engine analyzes the user's typing speed, writing style, and possibly facial expressions. For example, if the user types quickly in response to this question, it determines that the user has interest or positive emotions. These results are passed to a generative AI module, and an AI model such as GPT-3 recommends an appropriate category, such as "Technology" or "AI Research."

[0626] The recommended categories are displayed on the user's device through a display module. At this time, visual enhancements are made, such as changing the display color to light blue depending on the user's emotional state. The user can check the displayed categories and manually correct them if necessary.

[0627] In this way, the system automatically and appropriately selects categories while taking into account the user's emotions, improving the user experience. This reduces unnecessary input work and input errors, enabling efficient information collection.

[0628] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0629] The flow of this system's program processing

[0630] Step 1:

[0631] When a user enters "Software Engineer" in the "Profession" field, the data is sent from the terminal to the server, which receives the data through the data receiving module.

[0632] Input: Data entered by the user, such as "Software Engineer"

[0633] Output: Preparing received data for passing to the data analysis module

[0634] Specific operation: The device's browser or application captures the input and sends the data to the server using asynchronous communication technology such as Ajax.

[0635] Step 2:

[0636] The server passes the received data to a data analysis module, which analyzes the data using natural language processing techniques.

[0637] Input: User input data received by the server

[0638] Output: Keywords and related information extracted as analysis results

[0639] Specific operation: Using Python's NLTK library, keywords are extracted from input data (such as "software engineer") and appropriate information is retrieved based on them.

[0640] Step 3:

[0641] The server passes the analysis results to the emotion engine, which analyzes the user's input speed, writing style, and, if possible, facial expressions to determine their emotional state.

[0642] Input: Analysis results of the data analysis module and user input behavior data collected from the terminal

[0643] Output: Information about the user's emotional state

[0644] Specific operation: Analyzes input speed and character type, and performs facial recognition using the device's camera if necessary. Performs image analysis using OpenCV and other tools to determine the user's stress level and emotions.

[0645] Step 4:

[0646] The server passes the results of the data analysis module and the emotion engine to the generative AI module, which uses a pre-trained dataset to recommend the best category.

[0647] Input: Results of the data analysis module and the sentiment engine

[0648] Output: Recommended categories

[0649] How it works: Using generative AI techniques such as the GPT-3 model, it recommends the most appropriate category (e.g., "Technology" or "AI Research") based on an input prompt (e.g., "Software Engineer" or "AI Technology Advancements").

[0650] Step 5:

[0651] The server passes the recommended categories to the display module, which automatically displays the recommended categories on the user's device.

[0652] Input: Categories recommended by the generative AI module

[0653] Output: Categories displayed on the user's device

[0654] Specific behavior: When the recommended categories are displayed on the web page, the background color and font color are dynamically changed taking into account the results of the emotion engine.

[0655] Step 6:

[0656] Users can check the displayed categories on their device and decide whether they are appropriate. If they are not, they can manually correct them.

[0657] Input: Viewed Categories

[0658] Output: Final categories after user review and correction

[0659] Specific operation: The user manually edits the displayed "Technology" category, for example, by changing it to "AI Research."

[0660] Step 7:

[0661] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[0662] Input: Form data that the user last confirmed

[0663] Output: Data stored on the server and any necessary subsequent processing performed

[0664] Specific operation: When you click the submit button on the form, all input data is sent to the server again via asynchronous communication. The server stores the data in a database (e.g., MySQL) and performs subsequent processing such as sending a confirmation email to the user.

[0665] (Application example 2)

[0666] 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."

[0667] While conventional online shopping sites have product recommendation systems that respond to users' search and purchasing behavior, they do not offer personalized product recommendations that take the user's emotions into account. As a result, they are unable to provide optimal products that reflect the user's momentary emotions and state, limiting the improvement of the user experience. Furthermore, users may feel frustrated because the recommended products and categories are not displayed appropriately based on the user's emotional state. A solution to these issues is needed.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0669] In this invention, the server includes means for receiving data entered by the user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for recognizing the user's emotions and reflecting the user's emotional state in the analysis and recommendation, and means for automatically displaying the recommended categories on the user's terminal. This enables personalized product recommendations that take the user's emotions into consideration. Furthermore, by further including means for considering the user's past input history in the analyzed data and means for dynamically changing the display according to the user's emotions, it is possible to recommend optimal products that correspond to the user's momentary emotions and to achieve a display that is less stressful.

[0670] The "means for receiving data entered by the user" is a function for receiving text, voice, image data, etc. entered by the user into the system in real time.

[0671] The "means for analyzing received data" is a function for processing received user data using natural language processing and image analysis technology to extract related keywords and information.

[0672] "Means of using AI to generate and recommend optimal categories based on analyzed data" is a function that uses a pre-trained AI model to recommend the most appropriate category to the user based on extracted keywords and information.

[0673] "Means for recognizing the user's emotions and reflecting their emotional state in the analysis and recommendations" refers to a function that uses sensor devices such as cameras and microphones to analyze the user's facial expressions and voice, and incorporates the results into category recommendations.

[0674] "Means for automatically displaying recommended categories on the user's device" refers to a function for automatically displaying categories recommended based on the results of generative AI or emotion recognition on the screen of the device used by the user.

[0675] "Means for taking past input history into account in analyzed data" refers to a function that refers to the user's past search history and purchase history and recommends the most appropriate category while taking this history into consideration.

[0676] The "means for dynamically changing the display in accordance with the user's emotions" is a function for dynamically changing the display content, color tone, layout, etc. of the screen in accordance with the user's emotional state.

[0677] The present invention provides a system for recognizing a user's emotions on an online shopping site and recommending the most suitable product category based on the emotions. Specific embodiments are described below.

[0678] System program configuration

[0679] Main components and processing explanation

[0680] The system consists of the following main components:

[0681] 1. Data Receiving Method

[0682] This function receives user-entered search keywords, purchase history, and browsing history in real time. Data is received from user devices using asynchronous communication technology. Examples of hardware that can be used include smartphones, tablets, and PCs.

[0683] 2. Data analysis methods

[0684] This function analyzes received data using natural language processing technology. Specifically, it extracts related information and keywords from keywords and text data entered by the user. The software used is an NLP library (e.g., spaCy, NLTK, etc.).

[0685] 3. Category recommendation method using generative AI

[0686] This function recommends the most appropriate category based on the analyzed data. A prompt sentence is input into a pre-trained generative AI model (such as GPT-3) to generate the most appropriate category. The software used is a generative AI model.

[0687] 4. Emotion recognition means

[0688] This function uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. The emotion recognition results are reflected in the analysis and category recommendations. The hardware used includes a camera and microphone, and the software includes an emotion analysis library (e.g., OpenCV, TensorFlow, etc.).

[0689] 5. Automatic Category Display Method

[0690] This function automatically displays recommended categories on the user's device. The display color and layout change dynamically depending on the user's emotional state. The software used is a front-end framework (e.g., React, Vue.js, etc.).

[0691] 6. History Consideration Methods

[0692] This function saves past input history and purchase history and uses them during analysis. This allows the system to recommend more appropriate categories based on the user's past behavior. The software used is a database management system (e.g., PostgreSQL, MongoDB, etc.).

[0693] 7. Dynamic display change methods

[0694] This function dynamically changes the content, color tone, and layout of the screen display according to the user's emotions. The display module dynamically updates the screen based on the results of emotion recognition.

[0695] Specific examples

[0696] If a user searches for "camping equipment" on an online shopping site and the camera detects an excited expression on the user's face, the following flow will occur:

[0697] 1. User Input and Data Reception

[0698] The user enters the search keyword "camping equipment." The search keyword is sent from the user's device to the server in real time.

[0699] 2. Data Analysis

[0700] The server analyzes the received search keywords using natural language processing technology and extracts keywords such as "camping" and "outdoors."

[0701] 3. Emotion recognition

[0702] The camera is used to analyze the user's facial expressions, and the emotion engine recognizes when the user is excited.

[0703] 4. Category Recommendation

[0704] Enter the following prompt into the generative AI model to generate the best category:

[0705] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[0706] Based on this prompt, the generative AI will recommend categories such as "New Camping Gear" or "Popular Outdoor Gear."

[0707] 5. Automatic category display

[0708] The recommended categories are automatically displayed on the user's device, and the display changes dynamically in bright colors depending on the emotion recognition results.

[0709] This system enables personalized product recommendations that take the user's emotions into consideration, providing an environment in which users can browse products with interest and without feeling stressed.

[0710] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0711] Step 1:

[0712] A user enters the search keyword "camping equipment" into a device such as a smartphone or PC. This input data is sent from the device to the server in real time.

[0713] Step 2:

[0714] The server receives search keywords through the data receiving module. The input is "camping equipment," and the output is the keyword itself, which is stored on the server.

[0715] Step 3:

[0716] The server's data analysis means processes the received data. Specifically, it uses natural language processing technology (e.g., spaCy, NLTK) to analyze the keyword "camping equipment" and extract related keywords (e.g., "camping" and "outdoors"). The input is "camping equipment" and the output is a list of analyzed keywords.

[0717] Step 4:

[0718] The server's emotion recognition means uses a camera and microphone to acquire the user's emotional state. The camera captures the user's facial expressions, and the microphone captures their audio. An emotion analysis library (e.g., OpenCV, TensorFlow) is used to analyze the user's emotion and recognize that they are excited. The input is the camera video and audio data, and the output is the user's emotional state (excitement).

[0719] Step 5:

[0720] The server's generative AI-based category recommendation tool generates the most appropriate category based on the analyzed keywords and emotional state. The generative AI model (e.g., GPT-3) is given the following prompt:

[0721] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[0722] This allows the generative AI model to recommend categories such as "New Camping Equipment" or "Popular Outdoor Gear." The input is the prompt, analyzed keywords, and emotional state, and the output is a list of recommended categories.

[0723] Step 6:

[0724] The server's automatic category display means sends the recommended categories to the user's terminal. The user's terminal automatically displays the received category information and dynamically changes the display color tone and layout according to the user's emotional state. The input is a list of recommended categories, and the output is a dynamically updated user interface.

[0725] Step 7:

[0726] The server's history consideration means retrieves the user's past search history and purchase history from the database and analyzes them. This information is used for the next category recommendation and emotion recognition. The input is past history data, and the output is the analysis results that will be used for the next recommendation.

[0727] Step 8:

[0728] Once the server has completed all the processing, the user can view the recommended categories and products without any hassle.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] [Third embodiment]

[0733] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0734] 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.

[0735] 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).

[0736] 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.

[0737] 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.

[0738] 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).

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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."

[0745] The present invention is a system for automating category selection required when filling out a questionnaire or form. Specific embodiments are described below.

[0746] Program Structure

[0747] The program of this system consists of the following main components:

[0748] 1. Data receiving module

[0749] This module receives data entered by the user through a browser or application. It sends the data to the server in real time and receives it.

[0750] 2. Data Analysis Module

[0751] This module analyzes the data received by the server. This module uses natural language processing technology to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis, keyword extraction, semantic analysis, etc.

[0752] 3. Generative AI Module

[0753] This module utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset and recommends categories with high accuracy.

[0754] 4. Display module

[0755] This module automatically displays recommended categories on the user's device, highlighting them visually by changing the display color so that users can see them at a glance.

[0756] 5. History Keeping Module

[0757] This module saves the user's past input data and selection history and uses it during analysis. This allows it to recommend more appropriate categories when a similar input is made, by referring to past information.

[0758] Program processing explanation

[0759] 1. Data Reception

[0760] If a user types "Software Engineer" into the "Job Title" field, that data is sent to the server in real time.

[0761] The server receives the data sent by the user and records its contents.

[0762] 2. Data Analysis

[0763] The data received by the server is analyzed by the data analysis module, where the keyword "software engineer" is analyzed using natural language processing technology.

[0764] Based on the analysis results, the relevant category (for example, "technology" or "IT field") is extracted.

[0765] 3. Category recommendation using generative AI

[0766] The generative AI module selects the most appropriate category based on the analysis results. At this point, the generative AI model recommends categories such as "technology" and "AI technology" with a high probability.

[0767] If there is past input history, that will also be used as a reference when selecting a category.

[0768] 4. Category display

[0769] The recommended categories are transferred to the display module and automatically displayed on the user's device. For example, when "Software Engineer" is entered, "Technology" is automatically displayed in blue.

[0770] The user can review the displayed categories and manually correct them if necessary.

[0771] Specific examples

[0772] As an example, consider the case where a user enters the following information into a questionnaire form:

[0773] Job title: Software Engineer

[0774] Q: What do you think about recent advances in AI technology?

[0775] The server receives and analyzes the data for "software engineers" and "advances in AI technology." Based on the analysis results, the generative AI module recommends categories such as "technology" and "AI research," which are displayed in blue on the user's device. The user can then confirm the displayed categories and either proceed to the next input or modify them as necessary.

[0776] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

[0777] The processing flow will be explained below.

[0778] Step 1:

[0779] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[0780] Step 2:

[0781] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[0782] Step 3:

[0783] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[0784] Step 4:

[0785] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[0786] Step 5:

[0787] The parsed data is passed to a generative AI module, which uses a pre-trained model to recommend the best category based on the parsed results.

[0788] Step 6:

[0789] The generative AI module determines the recommended category, taking into account past input history and existing databases in the process.

[0790] Step 7:

[0791] The recommended categories are sent to a display module, which automatically displays the received category information on the user's device and visually emphasizes it by changing the color.

[0792] Step 8:

[0793] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0794] Step 9:

[0795] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[0796] Example 1

[0797] 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."

[0798] Conventional questionnaire and form entry systems require users to manually select categories, which is time-consuming and laborious. This manual category selection process is cumbersome for users and can lead to input errors and time-waste. Furthermore, because past input history is not taken into account, the system often produces low-accuracy category recommendations.

[0799] 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.

[0800] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for automatically displaying the recommended categories on the user terminal, and means for saving and referencing the user's past input history, thereby enabling the user to automatically select and display highly accurate categories without any effort on their part.

[0801] "User" refers to the person or end user who operates the system and inputs data.

[0802] "Means for receiving" refers to a hardware or software function that receives data sent from a user terminal and converts it into a processable format.

[0803] "Means for analyzing" refers to functions including natural language processing techniques and algorithms that process received data to understand and classify it.

[0804] "Generative AI" refers to an artificial intelligence model that processes data based on a pre-trained dataset and automatically generates or recommends optimal results.

[0805] "Recommendation means" refers to the function that allows the generative AI to select the most appropriate category based on the analyzed data and present it to the user.

[0806] "Means for automatic display" refers to a function for automatically displaying categories recommended by the system on the interface of the user terminal.

[0807] "Means for saving and referencing" refers to a function for saving the user's past input data and selection history and using it for subsequent data analysis and category recommendations.

[0808] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and is configured as follows. Specifically, this system is made up of the following main components:

[0809] 1. Data receiving module

[0810] This module receives data entered by users through a browser or application. It transmits data to a server in real time and receives it. The hardware used is a general server and a user terminal, and the software uses the HTTP protocol and WebSocket.

[0811] 2. Data Analysis Module

[0812] This module analyzes the data received by the server. It uses natural language processing techniques to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis such as Python's NLTK library, TF-IDF, and Word2Vec, keyword extraction, and semantic analysis.

[0813] 3. Generative AI Module

[0814] This system utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The generative AI model operates based on a pre-trained dataset and recommends categories with high accuracy. For example, a Transformer-based model is used. This enables highly accurate category recommendations based on the analysis results.

[0815] 4. Display module

[0816] This module automatically displays recommended categories on the user's device. It has a function to change the display color to emphasize them visually so that the user can check them at a glance. The display is made up of a user interface using HTML, CSS, and JavaScript.

[0817] 5. History Keeping Module

[0818] This is to store the user's past input data and selection history and use it during analysis. This allows us to refer to past information when there is similar input and recommend more appropriate categories. We efficiently manage history using a database system (e.g., MySQL or PostgreSQL).

[0819] Specific examples

[0820] Consider a case where a user enters the following information into a survey form in a browser:

[0821] Job title: Software Engineer

[0822] Q: What do you think about recent advances in AI technology?

[0823] The user enters "software engineer" and the input is sent from the device to the server. The server receives the data through the receiving module and analyzes the keyword "software engineer" in the data analysis module. Based on the analysis results, the generation AI module recommends categories such as "technology" or "AI research." The categories transferred from the server to the display module are displayed in blue on the user's device. The user checks the display and proceeds to the next input or makes corrections as necessary.

[0824] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

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

[0826] Step 1:

[0827] A user enters "Software Engineer" into the "Profession" field of a questionnaire form in a browser or application. The device sends the input data to the server in real time. The server receives the data through a receiving module and records the contents in a database. The input at this stage is text data from the user, which the server receives and stores.

[0828] Step 2:

[0829] The server analyzes the received data "Software Engineer" in the data analysis module. The analysis includes the following specific operations: First, the received text data is tokenized and each word is extracted. Then, important keywords are identified using TF-IDF and Word2Vec. Finally, semantic analysis is performed to identify the most appropriate category. The input here is the text data from step 1, and the output is a list of category candidates.

[0830] Step 3:

[0831] The generative AI module receives the list of candidate categories resulting from the analysis. The generative AI model (e.g., a Transformer-based model) selects the optimal category based on a pre-trained dataset. In this process, for example, a prompt sentence is generated to select a category with a high probability from the candidate list, and the AI ​​evaluates the result. The input here is the list of candidate categories from step 2, and the output is a category recommended with a high probability.

[0832] Step 4:

[0833] The server uses a history-keeping module to reference the user's past input data and influence the output of the generative AI module. This specifically involves retrieving the user's past selection history from the database and reprocessing it as input for the AI ​​model. The input here is the user's past input history and the category selected by the AI ​​in step 3, and the output is a final recommended category with further improved accuracy.

[0834] Step 5:

[0835] The final recommended category is transferred from the server to the display module and automatically displayed on the user's device. The display module uses HTML and CSS to display categories in different colors for easy visual identification. For example, for the input "software engineer," the "technology" category is displayed in blue. The user can check the displayed category and proceed to the next input or modify it as necessary. The input here is the final recommended category, and the output is the category displayed on the user's device.

[0836] (Application example 1)

[0837] 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."

[0838] In conventional input forms and surveys, users had to manually select the appropriate category when entering data, which increased the effort and time required for input. Furthermore, when entering product reviews or questions in physical stores, it was difficult to easily select the appropriate category, often resulting in a poor user experience. Furthermore, there was no system that could utilize past input history to recommend the most appropriate category, which sometimes resulted in inaccurate recommendations.

[0839] 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.

[0840] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending an optimal category based on the analyzed data using a generation AI, means for automatically displaying the recommended category on the user terminal, and means for recommending an optimal category in response to input of a review or question about a physical store. This allows the user to easily select an appropriate category, improving the user experience and reducing the effort required for input.

[0841] "User" refers to any individual or legal entity that uses the System.

[0842] "Data" refers to information such as text and numbers entered by the user.

[0843] "Receiving means" refers to a function for receiving data entered by a user in real time.

[0844] "Analysis means" refers to a function that analyzes received data using natural language processing technology.

[0845] "Category" refers to a category or classification item for classifying data.

[0846] "Generative AI" refers to artificial intelligence that automatically selects the most appropriate category based on a pre-trained dataset.

[0847] "Recommendation method" refers to the function of using generative AI to recommend categories to users based on analyzed data.

[0848] "Display means" refers to a function for displaying recommended categories on a user terminal.

[0849] "Brick and mortar store" refers to a commercial establishment located in a physical location.

[0850] A "review" refers to an evaluation or impression a user enters about a product or service.

[0851] "Question" refers to an inquiry or question that a user enters regarding a product or service.

[0852] "Input history" refers to a record of data that a user has previously entered and the results of their selections.

[0853] "Visually distinguishable color" refers to a color that allows a user to recognize the recommended category at a glance.

[0854] MODE FOR CARRYING OUT THE INVENTION

[0855] This invention is a system that aims to simplify the input of reviews and questions in physical stores and improve the user experience. This system analyzes the data entered by the user and automatically recommends and displays the most suitable category using generative AI.

[0856] System Program Overview

[0857] The system program is constructed mainly using the following hardware and software.

[0858] Hardware Configuration

[0859] Server: A central processing unit that handles the primary data processing and execution of generative AI models.

[0860] User device: A device used by users to enter reviews and questions in a physical store, such as a smartphone.

[0861] Software Configuration

[0862] Data receiving module: Provides a function for receiving input data from a user in real time.

[0863] Data Analysis Module: Analyzes the received data and interprets its contents using natural language processing techniques. Specifically, it uses the Hugging Face Transformer model.

[0864] Generative AI module: Recommends the most appropriate category based on the analyzed data, using a pre-trained generative AI model.

[0865] Display module: Visually displays the recommended categories on the user's device. The categories are displayed in easy-to-distinguish colors.

[0866] History keeping module: Saves the user's past input data and selected categories for future reference.

[0867] Processing flow

[0868] The server receives reviews and questions entered by users via the data reception module. The data analysis module analyzes this data using natural language processing technology to understand keywords and sentence structure. The generative AI module uses a pre-trained dataset to recommend the most appropriate category based on the analysis results. The display module visually displays the recommended category on the user's device. If the displayed category is appropriate, the user can proceed to the next input. The history retention module saves the user's past input data and the selection results, which can be used for future input.

[0869] Specific examples

[0870] For example, consider the case where a user enters the following information as a review:

[0871] Product Review: Review of the smartphone I recently bought

[0872] The server receives this data in real time and analyzes it using the data analysis module. As a result, the keyword "smartphone" is extracted, and the generation AI module recommends the category "electronic devices" based on this. The category is displayed in blue on the user's device. The user can check this recommended category and post a review right away.

[0873] In this way, the system reduces user input efforts and contributes to an improved overall user experience.

[0874] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0875] Step 1:

[0876] The server receives reviews and questions entered by users on their devices in real time through a data receiving module. At this time, the specific data entered by the user (e.g., "Review of the smartphone I recently bought") is received as input. The received data is temporarily stored in the server's storage.

[0877] Step 2:

[0878] The server analyzes the received data using a data analysis module. This module uses natural language processing techniques (e.g., the Hugging Face Transformer model) to extract keywords and analyze sentence structure from the text data. The input text data (e.g., "Reviews of recently purchased smartphones") is analyzed, and extracted keywords (e.g., "smartphone") and contextual information are obtained as output.

[0879] Step 3:

[0880] The server then uses a generative AI module to recommend the most appropriate category based on the analysis results. At this stage, the analyzed keywords and contextual information (e.g., "smartphone") are used as input. The generative AI model leverages a pre-trained dataset to output the most appropriate category, such as "electronic devices," based on the input with high accuracy.

[0881] Step 4:

[0882] The server visually displays the recommended categories on the user device through a display module. The category information received from the generation AI module (e.g., "electronic devices") is input, and the output is displayed on the screen of the user device. The recommended categories are displayed in an easily identifiable color (e.g., blue).

[0883] Step 5:

[0884] The user can check the displayed categories and submit the review or question as is, or modify it. After the user confirms, the final input data and category selection are sent back to the server.

[0885] Step 6:

[0886] The server uses a history storage module to store the user's past input data and selected categories. At this time, the data confirmed and submitted by the user (e.g., "Review of the smartphone recently purchased," category "Electronic device") is used as input, and this history is accumulated in a database in the server as output.

[0887] Through the above processing steps, the system provides users with fast and accurate category recommendations and reduces input effort.

[0888] 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.

[0889] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[0890] Program Structure

[0891] The program of this system consists of the following main components:

[0892] 1. Data receiving module

[0893] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technology to receive data.

[0894] 2. Data Analysis Module

[0895] This module analyzes the data received by the server. It uses natural language processing technology to analyze the content of the data and extract keywords and related information.

[0896] 3. Generative AI Module

[0897] This module uses generative AI technology to recommend the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset.

[0898] 4. Emotion Engine

[0899] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes the user's typing speed, writing style, facial expressions (if a camera is available), etc.

[0900] 5. Display module

[0901] This module automatically displays recommended categories on the user's device. It dynamically changes the display color and format of the categories based on the results of the emotion engine.

[0902] 6. History Keeping Module

[0903] This module saves the user's past input data and selection history and uses it during analysis, allowing it to recommend more appropriate categories based on past input.

[0904] Program processing explanation

[0905] 1. Data Reception

[0906] If a user enters "Software Engineer" in the "Profession" field, the data is sent in real time to the server, which receives the data and passes it to the data receiving module.

[0907] 2. Data Analysis

[0908] The server passes the received data to a data analysis module, which uses natural language processing technology to extract and analyze keywords such as "software engineer."

[0909] 3. Emotion recognition

[0910] The emotion engine analyzes the user's typing behavior and, if available, facial expressions to understand their emotional state. For example, if the user types slowly or writes in a rough style, the analysis results will reflect stress or frustration.

[0911] 4. Category recommendation using generative AI

[0912] Based on the results of the data analysis module and the sentiment engine, the generative AI module recommends the most appropriate category, taking into account past input history in the process.

[0913] 5. Category display

[0914] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[0915] 6. User Verification

[0916] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0917] 7. Data Transmission

[0918] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[0919] Specific examples

[0920] For example, consider the case where a user enters the following information into a questionnaire form:

[0921] Job title: Software Engineer

[0922] Q: What do you think about recent advances in AI technology?

[0923] The server receives data on "software engineers" and "AI technology advancements" and analyzes them using the data analysis module. The emotion engine analyzes the user's input speed and writing style to confirm that the user is interested. The generative AI module uses this data to recommend categories such as "technology" and "AI research," which are displayed in soft colors on the user's device. The user can then review the displayed categories and proceed to the next input or modify them as needed.

[0924] By taking user emotions into consideration, this system can provide more appropriate and personalized category recommendations, improving the user experience.

[0925] The processing flow will be explained below.

[0926] Step 1:

[0927] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[0928] Step 2:

[0929] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[0930] Step 3:

[0931] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[0932] Step 4:

[0933] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[0934] Step 5:

[0935] The server activates an emotion engine to analyze the user's typing behavior, writing style, and, if possible, facial expressions. For example, if the user types slowly or writes roughly, it may determine that the user is stressed or frustrated.

[0936] Step 6:

[0937] The analysis results of the data analysis module and the sentiment engine are passed to the generative AI module, which uses a pre-trained model to recommend the best category based on these results.

[0938] Step 7:

[0939] The generative AI module recommends the most appropriate category, taking into account past input history and emotional state. For example, based on the analysis results and emotional state, categories such as "technology" and "AI research" are highly likely to be recommended.

[0940] Step 8:

[0941] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[0942] Step 9:

[0943] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[0944] Step 10:

[0945] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[0946] Example 2

[0947] 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."

[0948] In conventional survey and form entry systems, the task of selecting the appropriate category based on the data entered by the user is cumbersome, which can lead to a poor user experience. Furthermore, because the system does not take into account the user's emotional state, it can be even more difficult to enter data under stressful circumstances. This can lead to an increase in user input errors and a loss of data quality and accuracy.

[0949] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0950] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data using natural language processing technology, means for recognizing the user's emotional state, means for recommending optimal categories based on the analyzed data and the emotional state using generative AI technology, and means for automatically displaying the recommended categories on the user terminal. This makes it possible to streamline the user's input work and to recommend personalized categories that take the user's emotional state into consideration.

[0951] "User-entered data" refers to text data or information entered by a user into an input field on a questionnaire, form, or the like.

[0952] "Natural language processing technology" is a technology that allows computers to understand, analyze, and process the language that humans use on a daily basis.

[0953] The "emotional state" refers to the emotional state that is expressed when the user performs input actions, and includes factors such as input speed, character type, and facial expression.

[0954] "Generative AI technology" is a type of artificial intelligence technology that generates optimal output based on input data by learning from large amounts of data, and is used, for example, to recommend categories.

[0955] "Recommendation methods" refer to functions and technologies that automatically present the most appropriate category based on the analyzed data and the user's emotional state.

[0956] A "user terminal" is a device such as a computer, smartphone, or tablet used to enter data into a survey or form.

[0957] "Past input history" refers to a record of data that the user has previously entered and the categories they selected at that time, and is used for subsequent input data analysis and category recommendations.

[0958] "Visually distinguishable colors" are colors used to make categories easier to see, and are colors that are intuitively recognizable by users.

[0959] "Means for dynamic change" refers to a function that changes the color and format of the displayed categories in real time according to the user's emotional state.

[0960] The present invention is a system that automates the category selection required when a user fills out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[0961] Program Structure

[0962] The program of this system consists of the following main components:

[0963] 1. Data receiving module

[0964] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technologies such as Ajax and WebSocket to receive data.

[0965] 2. Data Analysis Module

[0966] This module analyzes the data received by the server. This module uses natural language processing techniques such as Python's NLTK library to extract keywords and related information from the input text.

[0967] 3. Emotion Engine

[0968] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes input speed, writing style, facial expressions (if a camera is available), and also uses image analysis software such as OpenCV.

[0969] 4. Generative AI Module

[0970] This module uses generative AI technology to recommend the most appropriate category based on the results of data analysis and an emotion engine. The AI ​​model uses a pre-trained dataset, such as the GPT-3 model.

[0971] 5. Display module

[0972] This module automatically displays recommended categories on the user's device. The display color and format of the recommended categories change dynamically based on the results of the emotion engine.

[0973] 6. History Keeping Module

[0974] This module stores the user's past input data and selection history and reuses it for data analysis and category recommendations, enabling more personalized suggestions.

[0975] Specific examples

[0976] Below is a concrete example of how this system works.

[0977] For example, consider the case where a user enters the following information into a questionnaire form:

[0978] Job title: Software Engineer

[0979] Q: What do you think about recent advances in AI technology?

[0980] The server receives the data "software engineer" entered in the "job title" field from the terminal via asynchronous communication and passes it to the data analysis module via the data reception module. The data analysis module uses Python's NLTK library to analyze this text and extract keywords such as "software engineer" and "advances in AI technology."

[0981] Next, the emotion engine analyzes the user's typing speed, writing style, and possibly facial expressions. For example, if the user types quickly in response to this question, it determines that the user has interest or positive emotions. These results are passed to a generative AI module, and an AI model such as GPT-3 recommends an appropriate category, such as "Technology" or "AI Research."

[0982] The recommended categories are displayed on the user's device through a display module. At this time, visual enhancements are made, such as changing the display color to light blue depending on the user's emotional state. The user can check the displayed categories and manually correct them if necessary.

[0983] In this way, the system automatically and appropriately selects categories while taking into account the user's emotions, improving the user experience. This reduces unnecessary input work and input errors, enabling efficient information collection.

[0984] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0985] The flow of this system's program processing

[0986] Step 1:

[0987] When a user enters "Software Engineer" in the "Profession" field, the data is sent from the terminal to the server, which receives the data through the data receiving module.

[0988] Input: Data entered by the user, such as "Software Engineer"

[0989] Output: Preparing received data for passing to the data analysis module

[0990] Specific operation: The device's browser or application captures the input and sends the data to the server using asynchronous communication technology such as Ajax.

[0991] Step 2:

[0992] The server passes the received data to a data analysis module, which analyzes the data using natural language processing techniques.

[0993] Input: User input data received by the server

[0994] Output: Keywords and related information extracted as analysis results

[0995] Specific operation: Using Python's NLTK library, keywords are extracted from input data (such as "software engineer") and appropriate information is retrieved based on them.

[0996] Step 3:

[0997] The server passes the analysis results to the emotion engine, which analyzes the user's input speed, writing style, and, if possible, facial expressions to determine their emotional state.

[0998] Input: Analysis results of the data analysis module and user input behavior data collected from the terminal

[0999] Output: Information about the user's emotional state

[1000] Specific operation: Analyzes input speed and character type, and performs facial recognition using the device's camera if necessary. Performs image analysis using OpenCV and other tools to determine the user's stress level and emotions.

[1001] Step 4:

[1002] The server passes the results of the data analysis module and the emotion engine to the generative AI module, which uses a pre-trained dataset to recommend the best category.

[1003] Input: Results of the data analysis module and the sentiment engine

[1004] Output: Recommended categories

[1005] How it works: Using generative AI techniques such as the GPT-3 model, it recommends the most appropriate category (e.g., "Technology" or "AI Research") based on an input prompt (e.g., "Software Engineer" or "AI Technology Advancements").

[1006] Step 5:

[1007] The server passes the recommended categories to the display module, which automatically displays the recommended categories on the user's device.

[1008] Input: Categories recommended by the generative AI module

[1009] Output: Categories displayed on the user's device

[1010] Specific behavior: When the recommended categories are displayed on the web page, the background color and font color are dynamically changed taking into account the results of the emotion engine.

[1011] Step 6:

[1012] Users can check the displayed categories on their device and decide whether they are appropriate. If they are not, they can manually correct them.

[1013] Input: Viewed Categories

[1014] Output: Final categories after user review and correction

[1015] Specific operation: The user manually edits the displayed "Technology" category, for example, by changing it to "AI Research."

[1016] Step 7:

[1017] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[1018] Input: Form data that the user last confirmed

[1019] Output: Data stored on the server and any necessary subsequent processing performed

[1020] Specific operation: When you click the submit button on the form, all input data is sent to the server again via asynchronous communication. The server stores the data in a database (e.g., MySQL) and performs subsequent processing such as sending a confirmation email to the user.

[1021] (Application example 2)

[1022] 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."

[1023] While conventional online shopping sites have product recommendation systems that respond to users' search and purchasing behavior, they do not offer personalized product recommendations that take the user's emotions into account. As a result, they are unable to provide optimal products that reflect the user's momentary emotions and state, limiting the improvement of the user experience. Furthermore, users may feel frustrated because the recommended products and categories are not displayed appropriately based on the user's emotional state. A solution to these issues is needed.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1025] In this invention, the server includes means for receiving data entered by the user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for recognizing the user's emotions and reflecting the user's emotional state in the analysis and recommendation, and means for automatically displaying the recommended categories on the user's terminal. This enables personalized product recommendations that take the user's emotions into consideration. Furthermore, by further including means for considering the user's past input history in the analyzed data and means for dynamically changing the display according to the user's emotions, it is possible to recommend optimal products that correspond to the user's momentary emotions and to achieve a display that is less stressful.

[1026] The "means for receiving data entered by the user" is a function for receiving text, voice, image data, etc. entered by the user into the system in real time.

[1027] The "means for analyzing received data" is a function for processing received user data using natural language processing and image analysis technology to extract related keywords and information.

[1028] "Means of using AI to generate and recommend optimal categories based on analyzed data" is a function that uses a pre-trained AI model to recommend the most appropriate category to the user based on extracted keywords and information.

[1029] "Means for recognizing the user's emotions and reflecting their emotional state in the analysis and recommendations" refers to a function that uses sensor devices such as cameras and microphones to analyze the user's facial expressions and voice, and incorporates the results into category recommendations.

[1030] "Means for automatically displaying recommended categories on the user's device" refers to a function for automatically displaying categories recommended based on the results of generative AI or emotion recognition on the screen of the device used by the user.

[1031] "Means for taking past input history into account in analyzed data" refers to a function that refers to the user's past search history and purchase history and recommends the most appropriate category while taking this history into consideration.

[1032] The "means for dynamically changing the display in accordance with the user's emotions" is a function for dynamically changing the display content, color tone, layout, etc. of the screen in accordance with the user's emotional state.

[1033] The present invention provides a system for recognizing a user's emotions on an online shopping site and recommending the most suitable product category based on the emotions. Specific embodiments are described below.

[1034] System program configuration

[1035] Main components and processing explanation

[1036] The system consists of the following main components:

[1037] 1. Data Receiving Method

[1038] This function receives user-entered search keywords, purchase history, and browsing history in real time. Data is received from user devices using asynchronous communication technology. Examples of hardware that can be used include smartphones, tablets, and PCs.

[1039] 2. Data analysis methods

[1040] This function analyzes received data using natural language processing technology. Specifically, it extracts related information and keywords from keywords and text data entered by the user. The software used is an NLP library (e.g., spaCy, NLTK, etc.).

[1041] 3. Category recommendation method using generative AI

[1042] This function recommends the most appropriate category based on the analyzed data. A prompt sentence is input into a pre-trained generative AI model (such as GPT-3) to generate the most appropriate category. The software used is a generative AI model.

[1043] 4. Emotion recognition means

[1044] This function uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. The emotion recognition results are reflected in the analysis and category recommendations. The hardware used includes a camera and microphone, and the software includes an emotion analysis library (e.g., OpenCV, TensorFlow, etc.).

[1045] 5. Automatic Category Display Method

[1046] This function automatically displays recommended categories on the user's device. The display color and layout change dynamically depending on the user's emotional state. The software used is a front-end framework (e.g., React, Vue.js, etc.).

[1047] 6. History Consideration Methods

[1048] This function saves past input history and purchase history and uses them during analysis. This allows the system to recommend more appropriate categories based on the user's past behavior. The software used is a database management system (e.g., PostgreSQL, MongoDB, etc.).

[1049] 7. Dynamic display change methods

[1050] This function dynamically changes the content, color tone, and layout of the screen display according to the user's emotions. The display module dynamically updates the screen based on the results of emotion recognition.

[1051] Specific examples

[1052] If a user searches for "camping equipment" on an online shopping site and the camera detects an excited expression on the user's face, the following flow will occur:

[1053] 1. User Input and Data Reception

[1054] The user enters the search keyword "camping equipment." The search keyword is sent from the user's device to the server in real time.

[1055] 2. Data Analysis

[1056] The server analyzes the received search keywords using natural language processing technology and extracts keywords such as "camping" and "outdoors."

[1057] 3. Emotion recognition

[1058] The camera is used to analyze the user's facial expressions, and the emotion engine recognizes when the user is excited.

[1059] 4. Category Recommendation

[1060] Enter the following prompt into the generative AI model to generate the best category:

[1061] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[1062] Based on this prompt, the generative AI will recommend categories such as "New Camping Gear" or "Popular Outdoor Gear."

[1063] 5. Automatic category display

[1064] The recommended categories are automatically displayed on the user's device, and the display changes dynamically in bright colors depending on the emotion recognition results.

[1065] This system enables personalized product recommendations that take the user's emotions into consideration, providing an environment in which users can browse products with interest and without feeling stressed.

[1066] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1067] Step 1:

[1068] A user enters the search keyword "camping equipment" into a device such as a smartphone or PC. This input data is sent from the device to the server in real time.

[1069] Step 2:

[1070] The server receives search keywords through the data receiving module. The input is "camping equipment," and the output is the keyword itself, which is stored on the server.

[1071] Step 3:

[1072] The server's data analysis means processes the received data. Specifically, it uses natural language processing technology (e.g., spaCy, NLTK) to analyze the keyword "camping equipment" and extract related keywords (e.g., "camping" and "outdoors"). The input is "camping equipment" and the output is a list of analyzed keywords.

[1073] Step 4:

[1074] The server's emotion recognition means uses a camera and microphone to acquire the user's emotional state. The camera captures the user's facial expressions, and the microphone captures their audio. An emotion analysis library (e.g., OpenCV, TensorFlow) is used to analyze the user's emotion and recognize that they are excited. The input is the camera video and audio data, and the output is the user's emotional state (excitement).

[1075] Step 5:

[1076] The server's generative AI-based category recommendation tool generates the most appropriate category based on the analyzed keywords and emotional state. The generative AI model (e.g., GPT-3) is given the following prompt:

[1077] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[1078] This allows the generative AI model to recommend categories such as "New Camping Equipment" or "Popular Outdoor Gear." The input is the prompt, analyzed keywords, and emotional state, and the output is a list of recommended categories.

[1079] Step 6:

[1080] The server's automatic category display means sends the recommended categories to the user's terminal. The user's terminal automatically displays the received category information and dynamically changes the display color tone and layout according to the user's emotional state. The input is a list of recommended categories, and the output is a dynamically updated user interface.

[1081] Step 7:

[1082] The server's history consideration means retrieves the user's past search history and purchase history from the database and analyzes them. This information is used for the next category recommendation and emotion recognition. The input is past history data, and the output is the analysis results that will be used for the next recommendation.

[1083] Step 8:

[1084] Once the server has completed all the processing, the user can view the recommended categories and products without any hassle.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] [Fourth embodiment]

[1089] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1090] 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.

[1091] 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).

[1092] 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.

[1093] 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.

[1094] 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).

[1095] 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.

[1096] 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.

[1097] 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.

[1098] 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.

[1099] 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.

[1100] 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.

[1101] 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."

[1102] The present invention is a system for automating category selection required when filling out a questionnaire or form. Specific embodiments are described below.

[1103] Program Structure

[1104] The program of this system consists of the following main components:

[1105] 1. Data receiving module

[1106] This module receives data entered by the user through a browser or application. It sends the data to the server in real time and receives it.

[1107] 2. Data Analysis Module

[1108] This module analyzes the data received by the server. This module uses natural language processing technology to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis, keyword extraction, semantic analysis, etc.

[1109] 3. Generative AI Module

[1110] This module utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset and recommends categories with high accuracy.

[1111] 4. Display module

[1112] This module automatically displays recommended categories on the user's device, highlighting them visually by changing the display color so that users can see them at a glance.

[1113] 5. History Keeping Module

[1114] This module saves the user's past input data and selection history and uses it during analysis. This allows it to recommend more appropriate categories when a similar input is made, by referring to past information.

[1115] Program processing explanation

[1116] 1. Data Reception

[1117] If a user types "Software Engineer" into the "Job Title" field, that data is sent to the server in real time.

[1118] The server receives the data sent by the user and records its contents.

[1119] 2. Data Analysis

[1120] The data received by the server is analyzed by the data analysis module, where the keyword "software engineer" is analyzed using natural language processing technology.

[1121] Based on the analysis results, the relevant category (for example, "technology" or "IT field") is extracted.

[1122] 3. Category recommendation using generative AI

[1123] The generative AI module selects the most appropriate category based on the analysis results. At this point, the generative AI model recommends categories such as "technology" and "AI technology" with a high probability.

[1124] If there is past input history, that will also be used as a reference when selecting a category.

[1125] 4. Category display

[1126] The recommended categories are transferred to the display module and automatically displayed on the user's device. For example, when "Software Engineer" is entered, "Technology" is automatically displayed in blue.

[1127] The user can review the displayed categories and manually correct them if necessary.

[1128] Specific examples

[1129] As an example, consider the case where a user enters the following information into a questionnaire form:

[1130] Job title: Software Engineer

[1131] Q: What do you think about recent advances in AI technology?

[1132] The server receives and analyzes the data for "software engineers" and "advances in AI technology." Based on the analysis results, the generative AI module recommends categories such as "technology" and "AI research," which are displayed in blue on the user's device. The user can then confirm the displayed categories and either proceed to the next input or modify them as necessary.

[1133] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

[1134] The processing flow will be explained below.

[1135] Step 1:

[1136] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[1137] Step 2:

[1138] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[1139] Step 3:

[1140] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[1141] Step 4:

[1142] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[1143] Step 5:

[1144] The parsed data is passed to a generative AI module, which uses a pre-trained model to recommend the best category based on the parsed results.

[1145] Step 6:

[1146] The generative AI module determines the recommended category, taking into account past input history and existing databases in the process.

[1147] Step 7:

[1148] The recommended categories are sent to a display module, which automatically displays the received category information on the user's device and visually emphasizes it by changing the color.

[1149] Step 8:

[1150] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[1151] Step 9:

[1152] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[1153] Example 1

[1154] 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."

[1155] Conventional questionnaire and form entry systems require users to manually select categories, which is time-consuming and laborious. This manual category selection process is cumbersome for users and can lead to input errors and time-waste. Furthermore, because past input history is not taken into account, the system often produces low-accuracy category recommendations.

[1156] 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.

[1157] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for automatically displaying the recommended categories on the user terminal, and means for saving and referencing the user's past input history, thereby enabling the user to automatically select and display highly accurate categories without any effort on their part.

[1158] "User" refers to the person or end user who operates the system and inputs data.

[1159] "Means for receiving" refers to a hardware or software function that receives data sent from a user terminal and converts it into a processable format.

[1160] "Means for analyzing" refers to functions including natural language processing techniques and algorithms that process received data to understand and classify it.

[1161] "Generative AI" refers to an artificial intelligence model that processes data based on a pre-trained dataset and automatically generates or recommends optimal results.

[1162] "Recommendation means" refers to the function that allows the generative AI to select the most appropriate category based on the analyzed data and present it to the user.

[1163] "Means for automatic display" refers to a function for automatically displaying categories recommended by the system on the interface of the user terminal.

[1164] "Means for saving and referencing" refers to a function for saving the user's past input data and selection history and using it for subsequent data analysis and category recommendations.

[1165] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and is configured as follows. Specifically, this system is made up of the following main components:

[1166] 1. Data receiving module

[1167] This module receives data entered by users through a browser or application. It transmits data to a server in real time and receives it. The hardware used is a general server and a user terminal, and the software uses the HTTP protocol and WebSocket.

[1168] 2. Data Analysis Module

[1169] This module analyzes the data received by the server. It uses natural language processing techniques to interpret the content of the data and perform analysis to identify the most appropriate category. Analysis includes text analysis such as Python's NLTK library, TF-IDF, and Word2Vec, keyword extraction, and semantic analysis.

[1170] 3. Generative AI Module

[1171] This system utilizes generative AI to automatically select the most appropriate category based on the analyzed data. The generative AI model operates based on a pre-trained dataset and recommends categories with high accuracy. For example, a Transformer-based model is used. This enables highly accurate category recommendations based on the analysis results.

[1172] 4. Display module

[1173] This module automatically displays recommended categories on the user's device. It has a function to change the display color to emphasize them visually so that the user can check them at a glance. The display is made up of a user interface using HTML, CSS, and JavaScript.

[1174] 5. History Keeping Module

[1175] This is to store the user's past input data and selection history and use it during analysis. This allows us to refer to past information when there is similar input and recommend more appropriate categories. We efficiently manage history using a database system (e.g., MySQL or PostgreSQL).

[1176] Specific examples

[1177] Consider a case where a user enters the following information into a survey form in a browser:

[1178] Job title: Software Engineer

[1179] Q: What do you think about recent advances in AI technology?

[1180] The user enters "software engineer" and the input is sent from the device to the server. The server receives the data through the receiving module and analyzes the keyword "software engineer" in the data analysis module. Based on the analysis results, the generation AI module recommends categories such as "technology" or "AI research." The categories transferred from the server to the display module are displayed in blue on the user's device. The user checks the display and proceeds to the next input or makes corrections as necessary.

[1181] This allows users to complete the form efficiently without having to select categories, reducing the burden on users and improving the overall input experience.

[1182] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1183] Step 1:

[1184] A user enters "Software Engineer" into the "Profession" field of a questionnaire form in a browser or application. The device sends the input data to the server in real time. The server receives the data through a receiving module and records the contents in a database. The input at this stage is text data from the user, which the server receives and stores.

[1185] Step 2:

[1186] The server analyzes the received data "Software Engineer" in the data analysis module. The analysis includes the following specific operations: First, the received text data is tokenized and each word is extracted. Then, important keywords are identified using TF-IDF and Word2Vec. Finally, semantic analysis is performed to identify the most appropriate category. The input here is the text data from step 1, and the output is a list of category candidates.

[1187] Step 3:

[1188] The generative AI module receives the list of candidate categories resulting from the analysis. The generative AI model (e.g., a Transformer-based model) selects the optimal category based on a pre-trained dataset. In this process, for example, a prompt sentence is generated to select a category with a high probability from the candidate list, and the AI ​​evaluates the result. The input here is the list of candidate categories from step 2, and the output is a category recommended with a high probability.

[1189] Step 4:

[1190] The server uses a history-keeping module to reference the user's past input data and influence the output of the generative AI module. This specifically involves retrieving the user's past selection history from the database and reprocessing it as input for the AI ​​model. The input here is the user's past input history and the category selected by the AI ​​in step 3, and the output is a final recommended category with further improved accuracy.

[1191] Step 5:

[1192] The final recommended category is transferred from the server to the display module and automatically displayed on the user's device. The display module uses HTML and CSS to display categories in different colors for easy visual identification. For example, for the input "software engineer," the "technology" category is displayed in blue. The user can check the displayed category and proceed to the next input or modify it as necessary. The input here is the final recommended category, and the output is the category displayed on the user's device.

[1193] (Application example 1)

[1194] 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."

[1195] In conventional input forms and surveys, users had to manually select the appropriate category when entering data, which increased the effort and time required for input. Furthermore, when entering product reviews or questions in physical stores, it was difficult to easily select the appropriate category, often resulting in a poor user experience. Furthermore, there was no system that could utilize past input history to recommend the most appropriate category, which sometimes resulted in inaccurate recommendations.

[1196] 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.

[1197] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data, means for recommending an optimal category based on the analyzed data using a generation AI, means for automatically displaying the recommended category on the user terminal, and means for recommending an optimal category in response to input of a review or question about a physical store. This allows the user to easily select an appropriate category, improving the user experience and reducing the effort required for input.

[1198] "User" refers to any individual or legal entity that uses the System.

[1199] "Data" refers to information such as text and numbers entered by the user.

[1200] "Receiving means" refers to a function for receiving data entered by a user in real time.

[1201] "Analysis means" refers to a function that analyzes received data using natural language processing technology.

[1202] "Category" refers to a category or classification item for classifying data.

[1203] "Generative AI" refers to artificial intelligence that automatically selects the most appropriate category based on a pre-trained dataset.

[1204] "Recommendation method" refers to the function of using generative AI to recommend categories to users based on analyzed data.

[1205] "Display means" refers to a function for displaying recommended categories on a user terminal.

[1206] "Brick and mortar store" refers to a commercial establishment located in a physical location.

[1207] A "review" refers to an evaluation or impression a user enters about a product or service.

[1208] "Question" refers to an inquiry or question that a user enters regarding a product or service.

[1209] "Input history" refers to a record of data that a user has previously entered and the results of their selections.

[1210] "Visually distinguishable color" refers to a color that allows a user to recognize the recommended category at a glance.

[1211] MODE FOR CARRYING OUT THE INVENTION

[1212] This invention is a system that aims to simplify the input of reviews and questions in physical stores and improve the user experience. This system analyzes the data entered by the user and automatically recommends and displays the most suitable category using generative AI.

[1213] System Program Overview

[1214] The system program is constructed mainly using the following hardware and software.

[1215] Hardware Configuration

[1216] Server: A central processing unit that handles the primary data processing and execution of generative AI models.

[1217] User device: A device used by users to enter reviews and questions in a physical store, such as a smartphone.

[1218] Software Configuration

[1219] Data receiving module: Provides a function for receiving input data from a user in real time.

[1220] Data Analysis Module: Analyzes the received data and interprets its contents using natural language processing techniques. Specifically, it uses the Hugging Face Transformer model.

[1221] Generative AI module: Recommends the most appropriate category based on the analyzed data, using a pre-trained generative AI model.

[1222] Display module: Visually displays the recommended categories on the user's device. The categories are displayed in easy-to-distinguish colors.

[1223] History keeping module: Saves the user's past input data and selected categories for future reference.

[1224] Processing flow

[1225] The server receives reviews and questions entered by users via the data reception module. The data analysis module analyzes this data using natural language processing technology to understand keywords and sentence structure. The generative AI module uses a pre-trained dataset to recommend the most appropriate category based on the analysis results. The display module visually displays the recommended category on the user's device. If the displayed category is appropriate, the user can proceed to the next input. The history retention module saves the user's past input data and the selection results, which can be used for future input.

[1226] Specific examples

[1227] For example, consider the case where a user enters the following information as a review:

[1228] Product Review: Review of the smartphone I recently bought

[1229] The server receives this data in real time and analyzes it using the data analysis module. As a result, the keyword "smartphone" is extracted, and the generation AI module recommends the category "electronic devices" based on this. The category is displayed in blue on the user's device. The user can check this recommended category and post a review right away.

[1230] In this way, the system reduces user input efforts and contributes to an improved overall user experience.

[1231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1232] Step 1:

[1233] The server receives reviews and questions entered by users on their devices in real time through a data receiving module. At this time, the specific data entered by the user (e.g., "Review of the smartphone I recently bought") is received as input. The received data is temporarily stored in the server's storage.

[1234] Step 2:

[1235] The server analyzes the received data using a data analysis module. This module uses natural language processing techniques (e.g., the Hugging Face Transformer model) to extract keywords and analyze sentence structure from the text data. The input text data (e.g., "Reviews of recently purchased smartphones") is analyzed, and extracted keywords (e.g., "smartphone") and contextual information are obtained as output.

[1236] Step 3:

[1237] The server then uses a generative AI module to recommend the most appropriate category based on the analysis results. At this stage, the analyzed keywords and contextual information (e.g., "smartphone") are used as input. The generative AI model leverages a pre-trained dataset to output the most appropriate category, such as "electronic devices," based on the input with high accuracy.

[1238] Step 4:

[1239] The server visually displays the recommended categories on the user device through a display module. The category information received from the generation AI module (e.g., "electronic devices") is input, and the output is displayed on the screen of the user device. The recommended categories are displayed in an easily identifiable color (e.g., blue).

[1240] Step 5:

[1241] The user can check the displayed categories and submit the review or question as is, or modify it. After the user confirms, the final input data and category selection are sent back to the server.

[1242] Step 6:

[1243] The server uses a history storage module to store the user's past input data and selected categories. At this time, the data confirmed and submitted by the user (e.g., "Review of the smartphone recently purchased," category "Electronic device") is used as input, and this history is accumulated in a database in the server as output.

[1244] Through the above processing steps, the system provides users with fast and accurate category recommendations and reduces input effort.

[1245] 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.

[1246] The present invention is a system that automates the category selection required when filling out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[1247] Program Structure

[1248] The program of this system consists of the following main components:

[1249] 1. Data receiving module

[1250] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technology to receive data.

[1251] 2. Data Analysis Module

[1252] This module analyzes the data received by the server. It uses natural language processing technology to analyze the content of the data and extract keywords and related information.

[1253] 3. Generative AI Module

[1254] This module uses generative AI technology to recommend the most appropriate category based on the analyzed data. The AI ​​model operates based on a pre-trained dataset.

[1255] 4. Emotion Engine

[1256] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes the user's typing speed, writing style, facial expressions (if a camera is available), etc.

[1257] 5. Display module

[1258] This module automatically displays recommended categories on the user's device. It dynamically changes the display color and format of the categories based on the results of the emotion engine.

[1259] 6. History Keeping Module

[1260] This module saves the user's past input data and selection history and uses it during analysis, allowing it to recommend more appropriate categories based on past input.

[1261] Program processing explanation

[1262] 1. Data Reception

[1263] If a user enters "Software Engineer" in the "Profession" field, the data is sent in real time to the server, which receives the data and passes it to the data receiving module.

[1264] 2. Data Analysis

[1265] The server passes the received data to a data analysis module, which uses natural language processing technology to extract and analyze keywords such as "software engineer."

[1266] 3. Emotion recognition

[1267] The emotion engine analyzes the user's typing behavior and, if available, facial expressions to understand their emotional state. For example, if the user types slowly or writes in a rough style, the analysis results will reflect stress or frustration.

[1268] 4. Category recommendation using generative AI

[1269] Based on the results of the data analysis module and the sentiment engine, the generative AI module recommends the most appropriate category, taking into account past input history in the process.

[1270] 5. Category display

[1271] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[1272] 6. User Verification

[1273] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[1274] 7. Data Transmission

[1275] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[1276] Specific examples

[1277] For example, consider the case where a user enters the following information into a questionnaire form:

[1278] Job title: Software Engineer

[1279] Q: What do you think about recent advances in AI technology?

[1280] The server receives data on "software engineers" and "AI technology advancements" and analyzes them using the data analysis module. The emotion engine analyzes the user's input speed and writing style to confirm that the user is interested. The generative AI module uses this data to recommend categories such as "technology" and "AI research," which are displayed in soft colors on the user's device. The user can then review the displayed categories and proceed to the next input or modify them as needed.

[1281] By taking user emotions into consideration, this system can provide more appropriate and personalized category recommendations, improving the user experience.

[1282] The processing flow will be explained below.

[1283] Step 1:

[1284] A user opens a form screen through a browser or application, and each input field is displayed on the screen.

[1285] Step 2:

[1286] The user begins entering information into each field, for example, "Software Engineer" into the "Job Title" field.

[1287] Step 3:

[1288] The entered data is sent to the server in real time using asynchronous communication technologies such as AJAX and WebSocket.

[1289] Step 4:

[1290] The server passes the received data to a data analysis module, which uses natural language processing technology to analyze the input and extract keywords and related information.

[1291] Step 5:

[1292] The server activates an emotion engine to analyze the user's typing behavior, writing style, and, if possible, facial expressions. For example, if the user types slowly or writes roughly, it may determine that the user is stressed or frustrated.

[1293] Step 6:

[1294] The analysis results of the data analysis module and the sentiment engine are passed to the generative AI module, which uses a pre-trained model to recommend the best category based on these results.

[1295] Step 7:

[1296] The generative AI module recommends the most appropriate category, taking into account past input history and emotional state. For example, based on the analysis results and emotional state, categories such as "technology" and "AI research" are highly likely to be recommended.

[1297] Step 8:

[1298] The recommended categories are sent to the display module and automatically displayed on the user's device. The display color and format are dynamically changed based on the results of the emotion engine. For example, if the user is feeling stressed, the display will be changed to a calmer color tone.

[1299] Step 9:

[1300] The user checks the automatically displayed category. If the displayed category is appropriate, the user can continue inputting. If it is inappropriate, the user can manually correct the category.

[1301] Step 10:

[1302] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and handles further processing as needed.

[1303] Example 2

[1304] 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."

[1305] In conventional survey and form entry systems, the task of selecting the appropriate category based on the data entered by the user is cumbersome, which can lead to a poor user experience. Furthermore, because the system does not take into account the user's emotional state, it can be even more difficult to enter data under stressful circumstances. This can lead to an increase in user input errors and a loss of data quality and accuracy.

[1306] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1307] In this invention, the server includes means for receiving data entered by a user, means for analyzing the received data using natural language processing technology, means for recognizing the user's emotional state, means for recommending optimal categories based on the analyzed data and the emotional state using generative AI technology, and means for automatically displaying the recommended categories on the user terminal. This makes it possible to streamline the user's input work and to recommend personalized categories that take the user's emotional state into consideration.

[1308] "User-entered data" refers to text data or information entered by a user into an input field on a questionnaire, form, or the like.

[1309] "Natural language processing technology" is a technology that allows computers to understand, analyze, and process the language that humans use on a daily basis.

[1310] The "emotional state" refers to the emotional state that is expressed when the user performs input actions, and includes factors such as input speed, character type, and facial expression.

[1311] "Generative AI technology" is a type of artificial intelligence technology that generates optimal output based on input data by learning from large amounts of data, and is used, for example, to recommend categories.

[1312] "Recommendation methods" refer to functions and technologies that automatically present the most appropriate category based on the analyzed data and the user's emotional state.

[1313] A "user terminal" is a device such as a computer, smartphone, or tablet used to enter data into a survey or form.

[1314] "Past input history" refers to a record of data that the user has previously entered and the categories they selected at that time, and is used for subsequent input data analysis and category recommendations.

[1315] "Visually distinguishable colors" are colors used to make categories easier to see, and are colors that are intuitively recognizable by users.

[1316] "Means for dynamic change" refers to a function that changes the color and format of the displayed categories in real time according to the user's emotional state.

[1317] The present invention is a system that automates the category selection required when a user fills out a questionnaire or form, and further recognizes the user's emotions by combining it with an emotion engine, and makes recommendations that take these emotions into consideration. Specific embodiments are described below.

[1318] Program Structure

[1319] The program of this system consists of the following main components:

[1320] 1. Data receiving module

[1321] This module receives data entered by the user through a browser or application in real time. It uses asynchronous communication technologies such as Ajax and WebSocket to receive data.

[1322] 2. Data Analysis Module

[1323] This module analyzes the data received by the server. This module uses natural language processing techniques such as Python's NLTK library to extract keywords and related information from the input text.

[1324] 3. Emotion Engine

[1325] This module recognizes the user's emotions in real time and reflects their emotional state in data analysis and category recommendations. The emotion engine analyzes input speed, writing style, facial expressions (if a camera is available), and also uses image analysis software such as OpenCV.

[1326] 4. Generative AI Module

[1327] This module uses generative AI technology to recommend the most appropriate category based on the results of data analysis and an emotion engine. The AI ​​model uses a pre-trained dataset, such as the GPT-3 model.

[1328] 5. Display module

[1329] This module automatically displays recommended categories on the user's device. The display color and format of the recommended categories change dynamically based on the results of the emotion engine.

[1330] 6. History Keeping Module

[1331] This module stores the user's past input data and selection history and reuses it for data analysis and category recommendations, enabling more personalized suggestions.

[1332] Specific examples

[1333] Below is a concrete example of how this system works.

[1334] For example, consider the case where a user enters the following information into a questionnaire form:

[1335] Job title: Software Engineer

[1336] Q: What do you think about recent advances in AI technology?

[1337] The server receives the data "software engineer" entered in the "job title" field from the terminal via asynchronous communication and passes it to the data analysis module via the data reception module. The data analysis module uses Python's NLTK library to analyze this text and extract keywords such as "software engineer" and "advances in AI technology."

[1338] Next, the emotion engine analyzes the user's typing speed, writing style, and possibly facial expressions. For example, if the user types quickly in response to this question, it determines that the user has interest or positive emotions. These results are passed to a generative AI module, and an AI model such as GPT-3 recommends an appropriate category, such as "Technology" or "AI Research."

[1339] The recommended categories are displayed on the user's device through a display module. At this time, visual enhancements are made, such as changing the display color to light blue depending on the user's emotional state. The user can check the displayed categories and manually correct them if necessary.

[1340] In this way, the system automatically and appropriately selects categories while taking into account the user's emotions, improving the user experience. This reduces unnecessary input work and input errors, enabling efficient information collection.

[1341] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1342] The flow of this system's program processing

[1343] Step 1:

[1344] When a user enters "Software Engineer" in the "Profession" field, the data is sent from the terminal to the server, which receives the data through the data receiving module.

[1345] Input: Data entered by the user, such as "Software Engineer"

[1346] Output: Preparing received data for passing to the data analysis module

[1347] Specific operation: The device's browser or application captures the input and sends the data to the server using asynchronous communication technology such as Ajax.

[1348] Step 2:

[1349] The server passes the received data to a data analysis module, which analyzes the data using natural language processing techniques.

[1350] Input: User input data received by the server

[1351] Output: Keywords and related information extracted as analysis results

[1352] Specific operation: Using Python's NLTK library, keywords are extracted from input data (such as "software engineer") and appropriate information is retrieved based on them.

[1353] Step 3:

[1354] The server passes the analysis results to the emotion engine, which analyzes the user's input speed, writing style, and, if possible, facial expressions to determine their emotional state.

[1355] Input: Analysis results of the data analysis module and user input behavior data collected from the terminal

[1356] Output: Information about the user's emotional state

[1357] Specific operation: Analyzes input speed and character type, and performs facial recognition using the device's camera if necessary. Performs image analysis using OpenCV and other tools to determine the user's stress level and emotions.

[1358] Step 4:

[1359] The server passes the results of the data analysis module and the emotion engine to the generative AI module, which uses a pre-trained dataset to recommend the best category.

[1360] Input: Results of the data analysis module and the sentiment engine

[1361] Output: Recommended categories

[1362] How it works: Using generative AI techniques such as the GPT-3 model, it recommends the most appropriate category (e.g., "Technology" or "AI Research") based on an input prompt (e.g., "Software Engineer" or "AI Technology Advancements").

[1363] Step 5:

[1364] The server passes the recommended categories to the display module, which automatically displays the recommended categories on the user's device.

[1365] Input: Categories recommended by the generative AI module

[1366] Output: Categories displayed on the user's device

[1367] Specific behavior: When the recommended categories are displayed on the web page, the background color and font color are dynamically changed taking into account the results of the emotion engine.

[1368] Step 6:

[1369] Users can check the displayed categories on their device and decide whether they are appropriate. If they are not, they can manually correct them.

[1370] Input: Viewed Categories

[1371] Output: Final categories after user review and correction

[1372] Specific operation: The user manually edits the displayed "Technology" category, for example, by changing it to "AI Research."

[1373] Step 7:

[1374] Once all fields have been filled in and the user has given a final confirmation, the entire form is submitted to the server, which stores the submitted data and performs further processing as needed.

[1375] Input: Form data that the user last confirmed

[1376] Output: Data stored on the server and any necessary subsequent processing performed

[1377] Specific operation: When you click the submit button on the form, all input data is sent to the server again via asynchronous communication. The server stores the data in a database (e.g., MySQL) and performs subsequent processing such as sending a confirmation email to the user.

[1378] (Application example 2)

[1379] 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."

[1380] While conventional online shopping sites have product recommendation systems that respond to users' search and purchasing behavior, they do not offer personalized product recommendations that take the user's emotions into account. As a result, they are unable to provide optimal products that reflect the user's momentary emotions and state, limiting the improvement of the user experience. Furthermore, users may feel frustrated because the recommended products and categories are not displayed appropriately based on the user's emotional state. A solution to these issues is needed.

[1381] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1382] In this invention, the server includes means for receiving data entered by the user, means for analyzing the received data, means for recommending optimal categories based on the analyzed data using a generation AI, means for recognizing the user's emotions and reflecting the user's emotional state in the analysis and recommendation, and means for automatically displaying the recommended categories on the user's terminal. This enables personalized product recommendations that take the user's emotions into consideration. Furthermore, by further including means for considering the user's past input history in the analyzed data and means for dynamically changing the display according to the user's emotions, it is possible to recommend optimal products that correspond to the user's momentary emotions and to achieve a display that is less stressful.

[1383] The "means for receiving data entered by the user" is a function for receiving text, voice, image data, etc. entered by the user into the system in real time.

[1384] The "means for analyzing received data" is a function for processing received user data using natural language processing and image analysis technology to extract related keywords and information.

[1385] "Means of using AI to generate and recommend optimal categories based on analyzed data" is a function that uses a pre-trained AI model to recommend the most appropriate category to the user based on extracted keywords and information.

[1386] "Means for recognizing the user's emotions and reflecting their emotional state in the analysis and recommendations" refers to a function that uses sensor devices such as cameras and microphones to analyze the user's facial expressions and voice, and incorporates the results into category recommendations.

[1387] "Means for automatically displaying recommended categories on the user's device" refers to a function for automatically displaying categories recommended based on the results of generative AI or emotion recognition on the screen of the device used by the user.

[1388] "Means for taking past input history into account in analyzed data" refers to a function that refers to the user's past search history and purchase history and recommends the most appropriate category while taking this history into consideration.

[1389] The "means for dynamically changing the display in accordance with the user's emotions" is a function for dynamically changing the display content, color tone, layout, etc. of the screen in accordance with the user's emotional state.

[1390] The present invention provides a system for recognizing a user's emotions on an online shopping site and recommending the most suitable product category based on the emotions. Specific embodiments are described below.

[1391] System program configuration

[1392] Main components and processing explanation

[1393] The system consists of the following main components:

[1394] 1. Data Receiving Method

[1395] This function receives user-entered search keywords, purchase history, and browsing history in real time. Data is received from user devices using asynchronous communication technology. Examples of hardware that can be used include smartphones, tablets, and PCs.

[1396] 2. Data analysis methods

[1397] This function analyzes received data using natural language processing technology. Specifically, it extracts related information and keywords from keywords and text data entered by the user. The software used is an NLP library (e.g., spaCy, NLTK, etc.).

[1398] 3. Category recommendation method using generative AI

[1399] This function recommends the most appropriate category based on the analyzed data. A prompt sentence is input into a pre-trained generative AI model (such as GPT-3) to generate the most appropriate category. The software used is a generative AI model.

[1400] 4. Emotion recognition means

[1401] This function uses a camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. The emotion recognition results are reflected in the analysis and category recommendations. The hardware used includes a camera and microphone, and the software includes an emotion analysis library (e.g., OpenCV, TensorFlow, etc.).

[1402] 5. Automatic Category Display Method

[1403] This function automatically displays recommended categories on the user's device. The display color and layout change dynamically depending on the user's emotional state. The software used is a front-end framework (e.g., React, Vue.js, etc.).

[1404] 6. History Consideration Methods

[1405] This function saves past input history and purchase history and uses them during analysis. This allows the system to recommend more appropriate categories based on the user's past behavior. The software used is a database management system (e.g., PostgreSQL, MongoDB, etc.).

[1406] 7. Dynamic display change methods

[1407] This function dynamically changes the content, color tone, and layout of the screen display according to the user's emotions. The display module dynamically updates the screen based on the results of emotion recognition.

[1408] Specific examples

[1409] If a user searches for "camping equipment" on an online shopping site and the camera detects an excited expression on the user's face, the following flow will occur:

[1410] 1. User Input and Data Reception

[1411] The user enters the search keyword "camping equipment." The search keyword is sent from the user's device to the server in real time.

[1412] 2. Data Analysis

[1413] The server analyzes the received search keywords using natural language processing technology and extracts keywords such as "camping" and "outdoors."

[1414] 3. Emotion recognition

[1415] The camera is used to analyze the user's facial expressions, and the emotion engine recognizes when the user is excited.

[1416] 4. Category Recommendation

[1417] Enter the following prompt into the generative AI model to generate the best category:

[1418] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[1419] Based on this prompt, the generative AI will recommend categories such as "New Camping Gear" or "Popular Outdoor Gear."

[1420] 5. Automatic category display

[1421] The recommended categories are automatically displayed on the user's device, and the display changes dynamically in bright colors depending on the emotion recognition results.

[1422] This system enables personalized product recommendations that take the user's emotions into consideration, providing an environment in which users can browse products with interest and without feeling stressed.

[1423] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1424] Step 1:

[1425] A user enters the search keyword "camping equipment" into a device such as a smartphone or PC. This input data is sent from the device to the server in real time.

[1426] Step 2:

[1427] The server receives search keywords through the data receiving module. The input is "camping equipment," and the output is the keyword itself, which is stored on the server.

[1428] Step 3:

[1429] The server's data analysis means processes the received data. Specifically, it uses natural language processing technology (e.g., spaCy, NLTK) to analyze the keyword "camping equipment" and extract related keywords (e.g., "camping" and "outdoors"). The input is "camping equipment" and the output is a list of analyzed keywords.

[1430] Step 4:

[1431] The server's emotion recognition means uses a camera and microphone to acquire the user's emotional state. The camera captures the user's facial expressions, and the microphone captures their audio. An emotion analysis library (e.g., OpenCV, TensorFlow) is used to analyze the user's emotion and recognize that they are excited. The input is the camera video and audio data, and the output is the user's emotional state (excitement).

[1432] Step 5:

[1433] The server's generative AI-based category recommendation tool generates the most appropriate category based on the analyzed keywords and emotional state. The generative AI model (e.g., GPT-3) is given the following prompt:

[1434] If a user searches for "camping equipment" and gets excited, suggest categories and products to recommend.

[1435] This allows the generative AI model to recommend categories such as "New Camping Equipment" or "Popular Outdoor Gear." The input is the prompt, analyzed keywords, and emotional state, and the output is a list of recommended categories.

[1436] Step 6:

[1437] The server's automatic category display means sends the recommended categories to the user's terminal. The user's terminal automatically displays the received category information and dynamically changes the display color tone and layout according to the user's emotional state. The input is a list of recommended categories, and the output is a dynamically updated user interface.

[1438] Step 7:

[1439] The server's history consideration means retrieves the user's past search history and purchase history from the database and analyzes them. This information is used for the next category recommendation and emotion recognition. The input is past history data, and the output is the analysis results that will be used for the next recommendation.

[1440] Step 8:

[1441] Once the server has completed all the processing, the user can view the recommended categories and products without any hassle.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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).

[1449] 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.

[1450] 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."

[1451] 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.

[1452] 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).

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] The following is further disclosed regarding the above embodiment.

[1464] (Claim 1)

[1465] means for receiving user-entered data;

[1466] means for analyzing the received data;

[1467] A method to recommend the best category using AI based on the analyzed data, and

[1468] A means for automatically displaying the recommended categories on a user terminal;

[1469] A system including:

[1470] (Claim 2)

[1471] 10. The system of claim 1, further comprising means for taking into account past input history in the analyzed data.

[1472] (Claim 3)

[1473] 10. The system of claim 1, further comprising means for displaying the recommended categories in a visually distinguishable color.

[1474] "Example 1"

[1475] (Claim 1)

[1476] means for receiving user-entered data;

[1477] means for analyzing the received data;

[1478] A method to recommend the best category using AI based on the analyzed data, and

[1479] A means for automatically displaying the recommended categories on a user terminal;

[1480] A means for storing and referencing a user's past input history;

[1481] A system including:

[1482] (Claim 2)

[1483] 10. The system of claim 1, further comprising means for taking into account past input history in the analyzed data.

[1484] (Claim 3)

[1485] 10. The system of claim 1, further comprising means for displaying the recommended categories in a visually distinguishable color.

[1486] "Application Example 1"

[1487] (Claim 1)

[1488] means for receiving user-entered data;

[1489] means for analyzing the received data;

[1490] A method to recommend the best category using AI based on the analyzed data, and

[1491] A means for automatically displaying the recommended categories on a user terminal;

[1492] A system that includes a means to recommend the most appropriate category based on input of reviews and questions about physical stores.

[1493] (Claim 2)

[1494] 10. The system of claim 1, further comprising means for taking into account past input history in the analyzed data.

[1495] (Claim 3)

[1496] 10. The system of claim 1, further comprising means for displaying the recommended categories in a visually distinguishable color.

[1497] "Example 2: Combining Emotion Engines"

[1498] (Claim 1)

[1499] means for receiving user-entered data;

[1500] means for analyzing the received data using natural language processing technology;

[1501] means for recognizing the emotional state of a user;

[1502] A means for recommending the most appropriate category based on the analyzed data and emotional state using AI technology;

[1503] A means for automatically displaying the recommended categories on a user terminal;

[1504] A system including:

[1505] (Claim 2)

[1506] 10. The system of claim 1, further comprising means for taking into account past input history in the analyzed data.

[1507] (Claim 3)

[1508] 10. The system of claim 1, further comprising means for displaying the recommended categories in a visually distinguishable color and dynamically changing the color based on the user's emotional state.

[1509] "Application example 2 when combining emotion engines"

[1510] (Claim 1)

[1511] means for receiving user-entered data;

[1512] means for analyzing the received data;

[1513] A method to recommend the best category using AI based on the analyzed data, and

[1514] means for recognizing a user's emotions and incorporating the emotional state into the analysis and recommendations;

[1515] A means for automatically displaying the recommended categories on a user terminal;

[1516] A system including:

[1517] (Claim 2)

[1518] 10. The system of claim 1, further comprising: means for taking into account past input history in the analyzed data; and means for dynamically changing the display in response to a user's emotions.

[1519] (Claim 3)

[1520] 10. The system of claim 1, further comprising means for displaying the recommended categories in a visually distinguishable color and for changing the color based on the emotional state. [Explanation of symbols]

[1521] 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. means for receiving user-entered data; means for analyzing the received data; A method to recommend the best category using AI based on the analyzed data, and A means for automatically displaying the recommended categories on a user terminal; A system including:

2. 10. The system of claim 1, further comprising means for taking into account past input history in the analyzed data.

3. 10. The system of claim 1, further comprising means for displaying the recommended categories in visually distinguishable colors.

Images