system

Abstract

We provide the system. [Solution] A means for analyzing text data received from users using natural language processing technology and extracting information related to the issue from said text data, A means of obtaining a user's past purchase history and browsing information from a database, A means for selecting multiple products or services based on the extracted information and acquired information, and for generating a proposal that includes the reasons for the selection, A means for sending and displaying the generated proposal on the user's terminal, A means of receiving user feedback and learning from it to improve the quality of future suggestions, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Modern consumers often have difficulty selecting the optimal products and services from numerous options available on the Internet. In such a situation, there is a need for a means to easily receive proposals that match the preferences and needs of consumers. Also, it is necessary to alleviate the resistance to being automatically determined and improve the happiness level in the purchasing process. In the prior art, how to efficiently obtain relevant information and how to continuously improve the quality of proposals have not been solved either.

Means for Solving the Problems

[0005] This invention provides a system that understands user intent by analyzing text data received from users using natural language processing technology and extracting information related to the issue from the text data. Furthermore, it retrieves the user's past purchase history and browsing information from a database and generates suggestions that match the user's needs by selecting multiple products or services based on this information. In addition, it sends the generated suggestions to the user's terminal and continuously improves the quality of the suggestions by receiving and learning from user feedback. This system enables consumers to effectively choose from a complex set of options, thereby improving the purchasing experience.

[0006] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate natural language used by humans.

[0007] "Text data" refers to digital data containing character information, which is input to express the user's intentions and requests.

[0008] "Purchase history" refers to records of products or services acquired by a user in the past, and is data used to understand the user's preferences and trends.

[0009] "Browsing information" refers to a record of information a user has accessed on the internet in the past, and is data that indicates the user's interests and preferences.

[0010] A "database" is a storage system or software that efficiently stores, manages, and retrieves data.

[0011] "Products or services" refers to the general term for goods or services that consumers purchase or use.

[0012] A "suggestion" is a notification that includes information about recommended products or services for solving a user's problem, along with information about their selection.

[0013] "Feedback" refers to information about opinions and evaluations that users provide regarding proposals and services, and is data used to improve the system.

[0014] "Learning" is the process by which a system acquires information from past data and feedback, and uses that knowledge to improve its future behavior. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention begins with users interacting with the system using a terminal and inputting their challenges and needs. The terminal receives the user's input and sends the data to a server. The server analyzes the received data using natural language processing techniques. Through this analysis, the server identifies the user's challenges and extracts keywords and phrases relevant to their context.

[0037] Next, the server retrieves the user's past purchase history and browsing information from the database. This information helps in understanding the user's preferences and behavioral patterns. Based on this data, the server generates product and service suggestions that meet the user's needs.

[0038] A key feature of the suggestions is that they are presented from multiple perspectives. For example, a user aiming to organize their kitchen might be offered suggestions such as "tool storage boxes," "systematic organizing shelves," and "virtual organizing training." The server then explains, in natural language, how each of these suggestions contributes to solving the problem, providing justification for its application.

[0039] The terminal then displays the suggestions and explanations received from the server to the user. The user compares multiple suggestions via the terminal and makes a selection or provides feedback. The selected suggestion and feedback information are sent back to the server, and the system uses this information to learn and improve the quality of future suggestions.

[0040] For example, if a user enters "I want a new coffee maker," the server will refer to the user's past coffee-related purchase history and preferences, and generate suggestions such as "fast-boiling electric coffee maker," "portable drip coffee maker," and "premium coffee beans for regular delivery." Each suggestion will include explanations of how to use it and its benefits, tailored to the user's lifestyle.

[0041] In this way, the present invention constitutes a system that supports the user's purchasing process and promotes more satisfying choices.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users input information about the problems they want to solve or the products they are interested in using natural language via their device. This can include detailed conditions and expected results.

[0045] Step 2:

[0046] The terminal receives input data from the user and sends it to the server in text format. The input data is formatted according to the specified data format.

[0047] Step 3:

[0048] The server analyzes the received data using a natural language processing engine. Here, it understands the user's intent and identifies the category of the problem based on the extracted keywords and phrases.

[0049] Step 4:

[0050] The server connects to the database to retrieve the user's past purchase history and browsing information. This enables personalization based on the user's preferences and behavioral patterns.

[0051] Step 5:

[0052] Based on the information acquired and analyzed by the server, appropriate products and services are selected from the solution database. The selection process takes into account product characteristics, the user's past purchasing trends, and current trends.

[0053] Step 6:

[0054] The server generates information related to each product or service it proposes. The proposals include explanatory text that explains the reasons for selection, expected benefits, and how they address user needs.

[0055] Step 7:

[0056] The server generates suggestion data and sends it to the terminal, which then displays it to the user. The user can compare and consider the suggested options and view detailed information.

[0057] Step 8:

[0058] The user selects the product or service they are most interested in from the suggested options via their device, or provides feedback indicating that an alternative is needed.

[0059] Step 9:

[0060] The device sends the user's selections and feedback to the server. This information is used as data for future suggestions.

[0061] Step 10:

[0062] The server analyzes the feedback it receives, updates the proposed logic based on the learning algorithm, and aims to improve accuracy for the next attempt. This allows the system to continuously improve.

[0063] (Example 1)

[0064] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0065] In modern society, users often struggle to make the best choices from a wide variety of products and services to meet their specific needs. Therefore, there is a need for systems that support users in making appropriate choices tailored to their individual circumstances and preferences. Furthermore, technologies that allow these systems to incorporate user feedback and improve the quality of their recommendations are essential.

[0066] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0067] In this invention, the server includes means for analyzing character data received from a user using natural language processing technology and extracting information related to the request from the character data; means for obtaining the user's past purchase history and browsing information from a data storage device; means for selecting multiple items or offerings based on the extracted information and the obtained information and generating a proposal including the reasons for the selection; means for explaining how the generated proposal contributes to problem solving using a generative model; and means for receiving responses from the user and performing machine learning to improve the quality of future proposals. This enables the user to select the products and services that best suit their needs, and further improves the quality of the proposals through feedback.

[0068] A "user" is an individual or organization that uses the system to receive suggestions regarding products and services.

[0069] "Character data" refers to text information in natural language format entered by the user.

[0070] "Natural language processing technology" refers to the techniques and methods that enable computers to analyze, understand, and generate human language.

[0071] "Means of extracting information" refers to the process of identifying important keywords and phrases related to a request from text data.

[0072] A "data storage device" is a database or storage system used to store a user's past purchase history and browsing information.

[0073] A "generative model" is a computational model used to automatically generate suggestions in response to user requests, and is generally composed of machine learning algorithms.

[0074] "Response" refers to the user's choices and feedback information regarding suggestions.

[0075] "Machine learning" refers to algorithms and techniques that allow computers to continuously improve through data, and are used to enhance the quality of future suggestions.

[0076] The system in this invention begins with the user operating a terminal and inputting their needs and challenges. The user inputs information in text format into the terminal's interface. This information is used to identify the products or services the user is seeking.

[0077] The terminal sends the received text data to the server via a secure protocol. The server analyzes the text data sent by the user using natural language processing (NLP) technology. This analysis utilizes NLP libraries such as "spaCy" and "NLTK" to perform syntactic analysis and keyword extraction.

[0078] Next, the server retrieves the user's past purchase history and browsing information from the data storage device. This retrieval utilizes database systems such as MySQL® and PostgreSQL. Based on the analyzed and retrieved data, the server generates suggestions tailored to the user's needs. This involves using generative AI models such as GPT to select the most suitable items or services that can meet the user's specific requests.

[0079] The generated suggestions are accompanied by an explanation of how they contribute to solving the user's problem. The server sends this information to the terminal, which then presents it visually to the user.

[0080] For example, if a user enters "I want new running shoes," the server will refer to the user's past purchase history of sports equipment and generate suggestions that match their needs, such as shoes with high-performance cushioning or waterproof shoes for trail running. In addition, the AI ​​model used to generate these suggestions will explain the benefits, such as "quick-drying materials reduce fatigue" or "certain designs reduce strain on the feet."

[0081] In this way, suggestions are displayed to the user via their device, and the user can select or provide feedback. This feedback is sent back to the server and used as material for machine learning to improve the quality of future suggestions.

[0082] An example of a prompt to the generating AI model would be: "The user is looking for new running shoes. Please suggest suitable products based on their past purchase history of sports equipment." This system utilizes advanced artificial intelligence technology to efficiently support the user's decision-making.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user enters the request using a terminal.

[0086] Users input information about their needs and challenges in text format through the terminal's interface. This input data becomes the basis for subsequent processing. If a user inputs "I want new running shoes," that text data will be analyzed in the next step.

[0087] Step 2:

[0088] The terminal sends the user's input data to the server.

[0089] The terminal transfers the entered text data to the server as packets using a secure communication protocol. The input data is sent to the server in its original format and forms the basis of the data the server receives.

[0090] Step 3:

[0091] The server analyzes the received data using natural language processing technology.

[0092] The server uses tools such as "spaCy" and "NLTK" to tokenize the received text data and perform syntactic analysis. This extracts context-relevant keywords and phrases. This analysis process clarifies information directly relevant to the user's needs.

[0093] Step 4:

[0094] The server retrieves the user's purchase history from the database.

[0095] The server uses a database management system (e.g., MySQL, PostgreSQL) to query the user's past purchase history and browsing information. The retrieved data is used to understand the user's preferences. This information forms the basis for the data associated with the user's needs.

[0096] Step 5:

[0097] The server generates proposals using a generated AI model.

[0098] Based on the analyzed data and acquired historical information, the server uses a generative AI model to select products and services that best suit the user's needs. The generated suggestions include explanations of the reasons for selection and their benefits in natural language. An example of a prompt might be, "The user is looking for new running shoes. Please suggest suitable products based on their past sports equipment purchase history." The data obtained in this step forms the final output suggestions.

[0099] Step 6:

[0100] The server sends suggestion data to the terminal, and the terminal displays it.

[0101] The server sends the generated suggestions to the terminal, which converts them into a display format for the user and displays them on the interface. The user can review the suggested options and make a selection or provide feedback.

[0102] Step 7:

[0103] The device sends user feedback to the server, which then performs learning.

[0104] The device sends the information and feedback selected by the user to the server. The server then applies machine learning algorithms based on this information to improve the accuracy of future suggestions. Through learning, the system continuously improves, enabling more personalized suggestions.

[0105] (Application Example 1)

[0106] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0107] The present invention aims to solve the problem of difficulty in quickly and reliably proposing products and services that are tailored to the individual needs of users. In particular, it aims to provide a more satisfying purchasing experience by allowing users to receive highly relevant suggestions based on their search behavior and past purchase history.

[0108] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0109] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; means for selecting multiple products or services based on the extracted information and the obtained information and generating suggestions including the reasons for the selection; means for transmitting and displaying the generated suggestions on the user's terminal; means for receiving feedback from the user and learning to improve the quality of suggestions for future use; means for providing a portable information device that provides an interface for the user to input search behavior and purchase history; and means for generating and displaying a list of highly relevant products based on the information input through the interface. This makes it possible to propose optimized products and services to the user.

[0110] "Text data" refers to string information entered by the user via their device.

[0111] "Natural language processing technology" refers to computer program technology that analyzes human language and understands its meaning and intent.

[0112] "Information related to the issue" refers to data that includes content related to the user's requests and objectives.

[0113] "Purchase history" refers to a record of the products and services a user has acquired to date.

[0114] "Browsing information" refers to a log of the content that a user has viewed on a digital platform.

[0115] A "database" is a digital system that systematically organizes and stores information, making it searchable and retrievable.

[0116] "Product or service" refers to goods or benefits offered to the market.

[0117] A "proposal" refers to a selection of products or services that are chosen and recommended based on the user's needs.

[0118] A "terminal" is an electronic device used by users to input and receive information.

[0119] "Portable information devices" refer to portable digital devices that have a user interface function.

[0120] A "list of highly relevant products" is a list of products that are highly relevant based on the user's past behavior and input.

[0121] To implement this invention, it is fundamental for the server to analyze text data received from the user using natural language processing technology. The server first receives user input and uses a natural language processing engine (e.g., IBM Watson® NLP) to extract keywords related to the task from the text data.

[0122] Next, the server retrieves the user's past purchase history and browsing information from the database. This database is built using, for example, MySQL, allowing for efficient access to large amounts of user data.

[0123] Next, the server generates suggestions for relevant products or services based on the extracted information and historical data. This suggestion generation is achieved, for example, by using Node.js as the backend program, and by comparing the extracted keywords with the user's historical data.

[0124] The generated suggestions are then sent to the user's mobile device. The user's device has an interface developed using React Native where they can view the suggestions. This interface also provides a means to receive user input, allowing for the collection of user feedback.

[0125] For example, if a user enters "I'm looking for a party dress," the system will recommend relevant dresses based on their past browsing and purchase history, and explain the reasons for the selection. An example of a prompt to assist with this task would be, "Please suggest some dresses based on the user's purchase history for events last summer."

[0126] In this way, through the interaction between servers, terminals, and users, more optimized product and service suggestions are provided to users, resulting in an improved user experience.

[0127] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0128] Step 1:

[0129] The user uses a device to input specific needs or requests as text. The entered text data is received by the device and sent directly to the server. At this time, the input data is formatted for natural language processing.

[0130] Step 2:

[0131] The server analyzes the received text data using natural language processing techniques (e.g., IBM Watson NLP). The input is user text data, and the output extracts keywords and important phrases related to the issue. Specifically, it performs part-of-speech and semantic analysis of the text to identify words that indicate the user's needs.

[0132] Step 3:

[0133] The server retrieves the user's past purchase history and browsing information from a database (e.g., MySQL). The input is identification information such as a user ID, and the output is historical record data related to that user. This allows the server to prepare a dataset to understand the user's preferences.

[0134] Step 4:

[0135] The server initiates a process to recommend relevant products or services based on the extracted information and historical data. The input is the output data from steps 2 and 3, and the output is the selected product or service and the reason for the recommendation. Here, a generative AI model is used to score data relevance and calculate recommendation accuracy.

[0136] Step 5:

[0137] The server sends the generated suggestions to the terminal and displays them to the user. At this time, it also sends information including the reasons for the suggestions. The input is the output from step 4, and the output is the list of suggestions received by the user.

[0138] Step 6:

[0139] Users review the suggestions and make selections and provide feedback via their device. After considering the details of the selected products and services, they enter their selections or feedback.

[0140] Step 7:

[0141] The server receives feedback from the user again and learns to improve the accuracy of its suggestions. The input is user feedback, and the output is the refined suggestion generation model. Specifically, it analyzes the feedback data and optimizes the parameters of the suggestion algorithm.

[0142] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0143] This invention is a system that provides a more user-centric service by combining an emotion engine with the analysis of user input data to generate personalized suggestions. When a user inputs their needs and desires through a terminal, the terminal sends this information to a server. The server analyzes the user's input using natural language processing technology to identify the nature of the problem. It also utilizes an emotion engine to recognize the user's emotions hidden within the text. This emotion information is used to adjust the suggestions, recommending appropriate products and services that match the user's emotions.

[0144] For example, if a user sends a text message expressing an emotion such as "frustrated," the server can use its emotion engine to identify that emotion and suggest products or services that can help them relax, such as an aroma diffuser or a relaxation massage. In this way, the system makes suggestions that take the user's emotional state into account.

[0145] The server also collects data based on the user's past purchase history and browsing information to further personalize suggestions. This allows the server to present options that match the user's preferences. The suggestions are displayed to the user through their device, and the user can review them, make a selection, or provide feedback.

[0146] User selections and feedback information are sent to the server and used as learning data to improve the quality of future suggestions. This process allows the system to continuously improve the user experience. By utilizing an emotion engine, a more human-like and meaningful interaction for the user is achieved compared to conventional suggestion systems.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] Users use their devices to input information about their current concerns and desired products in natural language. This input can optionally include emotions.

[0150] Step 2:

[0151] The terminal receives user input data and sends it to the server in text format. The input data is pre-formatted as needed.

[0152] Step 3:

[0153] The server analyzes the user's text data received by the server using a natural language processing engine. This analysis helps understand the user's intent and requests, and extracts relevant keywords and issues.

[0154] Step 4:

[0155] The server uses an emotion engine to recognize the user's emotions from text data. For example, it extracts emotions such as "tired" or "excited" and adds them to the analysis results.

[0156] Step 5:

[0157] The server connects to the database to retrieve the user's past purchase and browsing history. This gathers information to understand the user's preferences and interests.

[0158] Step 6:

[0159] The server selects relevant products and services from the solution database based on the analyzed text data, sentiment data, and acquired historical information. Sentiment information is given particular importance in selecting the products and services to propose.

[0160] Step 7:

[0161] The server generates product and service proposals, including explanations of the selection criteria and emotionally resonant benefits of the proposals. The proposals are presented from multiple perspectives.

[0162] Step 8:

[0163] The server sends the generated suggestion data to the terminal, which then displays it to the user. The user can then compare and view the provided options.

[0164] Step 9:

[0165] Users can use their devices to select suggested products or services, or provide feedback indicating their desire for further suggestions.

[0166] Step 10:

[0167] The device sends the user's selections and feedback to the server. The server receives this information and uses it as training data to improve future suggestions.

[0168] Step 11:

[0169] The server uses a learning algorithm to analyze feedback and improve the accuracy of future suggestions, including sentiment information. This continuous learning process makes the system's suggestions more appropriate for the user.

[0170] (Example 2)

[0171] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0172] Conventional suggestion systems have a problem in that they struggle to provide appropriate and personalized suggestions based on user input. In particular, because they make suggestions without considering the user's emotions, the suggested content often fails to meet the user's expectations. This problem needs to be solved.

[0173] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0174] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for recognizing the user's emotions using sentiment analysis technology; and means for obtaining the user's past behavioral history and digital information from information sources. This enables more appropriate and personalized suggestions based on the user's emotions.

[0175] "User" refers to an individual or organization that receives a system or service, and is the ultimate beneficiary.

[0176] "Text data" refers to string data containing information written in natural language, and is the content entered by the user.

[0177] "Natural language processing technology" refers to techniques that enable computers to understand, interpret, and generate human language, and is used in the analysis of text data.

[0178] An "information source" refers to a reference point from which information is retrieved, such as a database or external system, and stores past behavioral history and digital information.

[0179] "Emotional analysis technology" is an analytical technique that determines the emotional state of a user from text data, and is used to adjust the content of proposals.

[0180] "Proposal" refers to a selection of products or services presented based on the user's needs and feelings.

[0181] A "terminal" refers to an electronic device used by a user for inputting information or receiving information, and includes personal computers and smartphones.

[0182] "Feedback" refers to the opinions and responses that users provide in response to suggestions and other matters, and is used to improve the system.

[0183] A "learning algorithm" refers to a computational method that allows a system to grow based on data and make more accurate suggestions.

[0184] This invention begins with the user inputting their needs and feelings as text through a terminal. The terminal immediately sends the input data to a server. The server analyzes the received text data using natural language processing techniques. The software used here includes, for example, a "natural language processing library" and a "morphological analysis engine," which are utilized to structurally understand the text.

[0185] Next, the server applies sentiment analysis technology to identify the emotions contained in the text. Software used may include "sentiment analysis tools" or "text sentiment recognition APIs." This allows the user's emotional state to be quantified or categorized.

[0186] The server further retrieves the user's past behavioral history and digital information from various sources. This process utilizes a "customer data platform" and a "history management system," and data is collected based on individual content.

[0187] Based on this information and analysis results, the server suggests products and services that best suit the user's emotions and needs. A "suggestion generation algorithm" and a "product database system" are used for this suggestion generation. The suggestions are sent to the terminal and presented visually to the user. The user can review the suggestions and provide selections or feedback.

[0188] For example, if a user inputs a desire to "connect with nature" and an emotion representing "stress," the server will suggest products and services that have a relaxing effect. For instance, this could include admission tickets to a nature park or a gardening kit. Another example of a prompt for the generating AI model is, "List relaxation methods that should be suggested when a user is feeling stressed."

[0189] User feedback is used to inform future suggestions, and the server analyzes the feedback to improve the system. This functionality is achieved through a "learning model" and a "data analysis framework." As a result, the system can continuously adapt and provide users with a more satisfying experience.

[0190] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0191] Step 1:

[0192] The user uses a device to input text about their needs and feelings. This input data represents the user's desires and current emotional state. The device then performs the specific action of sending the entered text data to the server. The input is text data, and the output is the transmission of data to the server.

[0193] Step 2:

[0194] The server analyzes the received text data using natural language processing techniques. Specifically, the server uses a "natural language processing library" to tokenize and morphologically analyze the text, thereby understanding its structure. The input is text data sent from the terminal, and the output is the analysis results indicating user needs and preferences.

[0195] Step 3:

[0196] The server uses sentiment analysis technology to recognize the user's emotional state from the analyzed text data. Specifically, it uses a sentiment analysis tool to quantify emotions from the text and classify them into desirable emotion categories. The input is the result of natural language analysis, and the output is data indicating the user's emotions.

[0197] Step 4:

[0198] The server retrieves the user's past behavioral history and digital information from various sources. Specifically, it retrieves relevant information from the database through query processing and uses the user profile information to perform personalization. The input is user identification information, and the output is the behavioral history and digital information used for personalization.

[0199] Step 5:

[0200] The server generates appropriate product and service suggestions based on emotional information, needs analysis results, and past behavioral history. Specifically, it uses a suggestion generation algorithm to evaluate and select from multiple options. The input is emotional data and user profiles, and the output is a list of suggested products and services.

[0201] Step 6:

[0202] The generated suggestions are sent to the user's device and displayed visually on the device. Specifically, the server sends the generated suggestions to the device via push notification or in real time, and the device receives them and displays them in the user interface. The input is the generated suggestion data, and the output is the result displayed to the user.

[0203] Step 7:

[0204] Users make selections and provide feedback on the displayed suggestions. Specifically, users choose suggested products or services and enter their thoughts and suggestions for improvement through a feedback form. The input consists of the user's selections and feedback, and the output is the feedback data sent to the server.

[0205] Step 8:

[0206] The server analyzes the received feedback and uses it to improve future proposals. Specifically, the feedback data is used to train a learning algorithm, improving the system's proposal accuracy. The input is user feedback data, and the output is the improved proposal model.

[0207] (Application Example 2)

[0208] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0209] Conventional recommendation systems often recommended products and services based solely on past data, without considering the user's emotions. As a result, recommendations were not tailored to the user's current emotions and needs, leading to decreased satisfaction. This invention aims to solve this problem by analyzing the user's emotional state and providing more appropriate and personalized recommendations that respond to individual emotions.

[0210] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0211] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; and means for identifying the user's emotional state using an emotion engine, in addition to the extracted and obtained information, and generating suggestions that correspond to that emotion. This makes it possible to provide suggestions that match the user's current emotions.

[0212] "Natural language processing technology" is a technology that analyzes text data from users to understand its meaning and context.

[0213] An "emotion engine" is a system or method that identifies an emotional state from user input data and provides information corresponding to that emotion.

[0214] "Purchase history" refers to data that records information about products and services that a user has purchased in the past.

[0215] A "database" is an information system that systematically stores multiple pieces of data and allows access and management as needed.

[0216] "Feedback" refers to collecting evaluations and opinions from users regarding suggestions and services they have provided.

[0217] A "learning algorithm" is a computational method used to improve the performance of a system based on collected data.

[0218] To implement this invention, a system is needed that analyzes user input data and generates personalized suggestions based on emotions. First, the user inputs their needs and desires in natural language using a device such as a smartphone. This input data is sent from the device to a server, which uses natural language processing technology to analyze the text.

[0219] Here, "natural language processing technology" refers to the technology that analyzes text data from users and understands its meaning and context.

[0220] The server uses an emotion engine to identify the user's emotional state and, based on that information, generates product and service recommendations tailored to the user. An "emotion engine" is a system or method that identifies the user's emotional state from user input data and provides information corresponding to that emotion.

[0221] Next, the suggestions are sent to the device and displayed to the user. The user reviews the displayed suggestions and provides feedback by making selections. This feedback is sent to the server and used as training data to improve future suggestions.

[0222] As a concrete example, if a user provides input such as "I've been feeling stressed lately and want to refresh myself," the server uses its emotion engine to determine that the user is seeking relaxation. As a result, it generates suggestions for relaxation-related products and services, such as aroma diffusers or relaxation spas, and displays them on the user's device.

[0223] An example of a prompt message would be: "Analyze the user's emotions, and if the input is 'I've been feeling stressed lately,' recommend a relaxation item."

[0224] This process utilizes a smartphone as hardware and employs Python libraries such as TextBlob and Scikit-learn for analysis. This allows for the analysis of user input data and the provision of optimal suggestions. This system enables personalized product recommendations tailored to the user's current emotions, providing a more satisfying experience.

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The device receives input from the user. The user uses a smartphone to input their feelings and needs in natural language into a text box. For example, they might input something like, "I've been feeling stressed lately, so I want to relax." The entered data is then sent directly to the server.

[0228] Step 2:

[0229] The server analyzes the received user text data using natural language processing techniques. In this step, the Python library TextBlob is used to analyze the grammar and meaning of the text and identify the main point of what the user has entered. In this process, the user's problems and desires become clear. As a result, the analyzed text data is generated.

[0230] Step 3:

[0231] The server uses an emotion engine to identify the user's emotional state from the analyzed text data. For example, if the user uses the word "stress," the emotion engine recognizes it as a negative emotion. An SVM (Support Vector Machine) is used to calculate an emotion score, representing the user's emotional state numerically. The output here is the user's emotion score.

[0232] Step 4:

[0233] The server retrieves past purchase history and browsing information from the database. This data indicates the user's preferences and tendencies. Based on this, it combines the user's current emotional state with past behavioral patterns to generate more appropriate suggestions. In this step, historical data is retrieved and output.

[0234] Step 5:

[0235] The server selects products and services to suggest to the user based on their emotional score and historical data. Using a generative AI model, it proposes the product best suited to the user's state from the selected candidates. For example, relaxation goods and stress-reducing services may be presented. The selection results are output as suggestions.

[0236] Step 6:

[0237] The server sends the generated suggestions to the terminal and displays them to the user. The user can view the suggestions on their smartphone screen. After viewing the suggestions, the user selects products based on them and considers purchasing them. In this step, the suggestions are displayed visually.

[0238] Step 7:

[0239] The terminal receives user selections and feedback and sends that information to the server. Users contribute to system improvement by inputting how they felt about the suggestions and their satisfaction level. This data is then sent back to the server.

[0240] Step 8:

[0241] The server analyzes the received feedback and adjusts the system's learning algorithm based on the results. This process improves the accuracy and quality of subsequent suggestions, thereby achieving overall system optimization.

[0242] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0243] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0244] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0245] [Second Embodiment]

[0246] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0247] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0248] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0249] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0250] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0251] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0252] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0253] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0254] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0255] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0256] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0257] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0258] This invention begins with users interacting with the system using a terminal and inputting their challenges and needs. The terminal receives the user's input and sends the data to a server. The server analyzes the received data using natural language processing techniques. Through this analysis, the server identifies the user's challenges and extracts keywords and phrases relevant to their context.

[0259] Next, the server retrieves the user's past purchase history and browsing information from the database. This information helps in understanding the user's preferences and behavioral patterns. Based on this data, the server generates product and service suggestions that meet the user's needs.

[0260] A key feature of the suggestions is that they are presented from multiple perspectives. For example, a user aiming to organize their kitchen might be offered suggestions such as "tool storage boxes," "systematic organizing shelves," and "virtual organizing training." The server then explains, in natural language, how each of these suggestions contributes to solving the problem, providing justification for its application.

[0261] The terminal then displays the suggestions and explanations received from the server to the user. The user compares multiple suggestions via the terminal and makes a selection or provides feedback. The selected suggestion and feedback information are sent back to the server, and the system uses this information to learn and improve the quality of future suggestions.

[0262] For example, if a user enters "I want a new coffee maker," the server will refer to the user's past coffee-related purchase history and preferences, and generate suggestions such as "fast-boiling electric coffee maker," "portable drip coffee maker," and "premium coffee beans for regular delivery." Each suggestion will include explanations of how to use it and its benefits, tailored to the user's lifestyle.

[0263] In this way, the present invention constitutes a system that supports the user's purchasing process and promotes more satisfying choices.

[0264] The following describes the processing flow.

[0265] Step 1:

[0266] Users input information about the problems they want to solve or the products they are interested in using natural language via their device. This can include detailed conditions and expected results.

[0267] Step 2:

[0268] The terminal receives input data from the user and sends it to the server in text format. The input data is formatted according to the specified data format.

[0269] Step 3:

[0270] The server analyzes the received data using a natural language processing engine. Here, it understands the user's intent and identifies the category of the problem based on the extracted keywords and phrases.

[0271] Step 4:

[0272] The server connects to the database to retrieve the user's past purchase history and browsing information. This enables personalization based on the user's preferences and behavioral patterns.

[0273] Step 5:

[0274] Based on the information acquired and analyzed by the server, appropriate products and services are selected from the solution database. The selection process takes into account product characteristics, the user's past purchasing trends, and current trends.

[0275] Step 6:

[0276] The server generates information related to each product or service it proposes. The proposals include explanatory text that explains the reasons for selection, expected benefits, and how they address user needs.

[0277] Step 7:

[0278] The server generates suggestion data and sends it to the terminal, which then displays it to the user. The user can compare and consider the suggested options and view detailed information.

[0279] Step 8:

[0280] The user selects the most interesting product or service from the proposed ones via the terminal, or inputs feedback indicating that an alternative is needed.

[0281] Step 9:

[0282] The terminal sends the user's selection result and feedback to the server. This information is utilized as data for future proposals.

[0283] Step 10:

[0284] The server analyzes the received feedback, updates the proposal logic based on the learning algorithm, and aims to improve the accuracy next time. As a result, the system is continuously improved.

[0285] (Example 1)

[0286] Next, Example ① will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0287] In modern society, it is difficult for users to make the optimal choice for their needs from a variety of products and services. Therefore, there is a demand for a system that supports appropriate selections according to individual situations and preferences. Also, a technology that enables the proposed system to reflect the user's feedback and improve the quality of the proposals is essential.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Example ① is realized by the following means.

[0289] In this invention, the server includes means for analyzing character data received from a user using natural language processing technology and extracting information related to the request from the character data; means for obtaining the user's past purchase history and browsing information from a data storage device; means for selecting multiple items or offerings based on the extracted information and the obtained information and generating a proposal including the reasons for the selection; means for explaining how the generated proposal contributes to problem solving using a generative model; and means for receiving responses from the user and performing machine learning to improve the quality of future proposals. This enables the user to select the products and services that best suit their needs, and further improves the quality of the proposals through feedback.

[0290] A "user" is an individual or organization that uses the system to receive suggestions regarding products and services.

[0291] "Character data" refers to text information in natural language format entered by the user.

[0292] "Natural language processing technology" refers to the techniques and methods that enable computers to analyze, understand, and generate human language.

[0293] "Means of extracting information" refers to the process of identifying important keywords and phrases related to a request from text data.

[0294] A "data storage device" is a database or storage system used to store a user's past purchase history and browsing information.

[0295] A "generative model" is a computational model used to automatically generate suggestions in response to user requests, and is generally composed of machine learning algorithms.

[0296] "Response" refers to the user's choices and feedback information regarding suggestions.

[0297] "Machine learning" refers to algorithms and techniques that allow computers to continuously improve through data, and are used to enhance the quality of future suggestions.

[0298] The system in this invention begins with the user operating a terminal and inputting their needs and challenges. The user inputs information in text format into the terminal's interface. This information is used to identify the products or services the user is seeking.

[0299] The terminal sends the received text data to the server via a secure protocol. The server analyzes the text data sent by the user using natural language processing (NLP) technology. This analysis utilizes NLP libraries such as "spaCy" and "NLTK" to perform syntactic analysis and keyword extraction.

[0300] Next, the server retrieves the user's past purchase history and browsing information from the data storage device. This retrieval utilizes database systems such as MySQL and PostgreSQL. Based on the analyzed and retrieved data, the server generates suggestions tailored to the user's needs. This involves using generative AI models such as GPT to select the most suitable items or services that can meet the user's specific requests.

[0301] The generated suggestions are accompanied by an explanation of how they contribute to solving the user's problem. The server sends this information to the terminal, which then presents it visually to the user.

[0302] For example, if a user enters "I want new running shoes," the server will refer to the user's past purchase history of sports equipment and generate suggestions that match their needs, such as shoes with high-performance cushioning or waterproof shoes for trail running. In addition, the AI ​​model used to generate these suggestions will explain the benefits, such as "quick-drying materials reduce fatigue" or "certain designs reduce strain on the feet."

[0303] In this way, the proposal is displayed to the user via the terminal, and the user can make a selection or provide feedback. This feedback is sent back to the server and serves as material for machine learning to improve the quality of proposals in subsequent times.

[0304] Examples of prompt sentences for the generative AI model are in the form of "The user is looking for new running shoes. Please propose appropriate products based on the user's past sports equipment purchase history." This system utilizes advanced artificial intelligence technology to efficiently support the user's decision-making.

[0305] The flow of the specific process in Example 1 will be described using FIG. 11.

[0306] Step 1:

[0307] The user inputs a request using the terminal.

[0308] The user inputs information about their needs and issues in text form through the terminal interface. This input data becomes the basic data in subsequent processing. If the user inputs "I want new running shoes", the text data will be the object to be analyzed in the next step.

[0309] Step 2:

[0310] The terminal sends the user's input data to the server.

[0311] The terminal transfers the input text data to the server as packets using a secure communication protocol. The input data is sent to the server in its original form and serves as the basis for the data received by the server.

[0312] Step 3:

[0313] The server analyzes the received data using natural language processing technology.

[0314] The server uses tools such as "spaCy" and "NLTK" to tokenize the received text data and perform syntactic analysis. This extracts context-relevant keywords and phrases. This analysis process clarifies information directly relevant to the user's needs.

[0315] Step 4:

[0316] The server retrieves the user's purchase history from the database.

[0317] The server uses a database management system (e.g., MySQL, PostgreSQL) to query the user's past purchase history and browsing information. The retrieved data is used to understand the user's preferences. This information forms the basis for the data associated with the user's needs.

[0318] Step 5:

[0319] The server generates proposals using a generated AI model.

[0320] Based on the analyzed data and acquired historical information, the server uses a generative AI model to select products and services that best suit the user's needs. The generated suggestions include explanations of the reasons for selection and their benefits in natural language. An example of a prompt might be, "The user is looking for new running shoes. Please suggest suitable products based on their past sports equipment purchase history." The data obtained in this step forms the final output suggestions.

[0321] Step 6:

[0322] The server sends suggestion data to the terminal, and the terminal displays it.

[0323] The server sends the generated suggestions to the terminal, which converts them into a display format for the user and displays them on the interface. The user can review the suggested options and make a selection or provide feedback.

[0324] Step 7:

[0325] The device sends user feedback to the server, which then performs learning.

[0326] The device sends the information and feedback selected by the user to the server. The server then applies machine learning algorithms based on this information to improve the accuracy of future suggestions. Through learning, the system continuously improves, enabling more personalized suggestions.

[0327] (Application Example 1)

[0328] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0329] The present invention aims to solve the problem of difficulty in quickly and reliably proposing products and services that are tailored to the individual needs of users. In particular, it aims to provide a more satisfying purchasing experience by allowing users to receive highly relevant suggestions based on their search behavior and past purchase history.

[0330] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0331] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; means for selecting multiple products or services based on the extracted information and the obtained information and generating suggestions including the reasons for the selection; means for transmitting and displaying the generated suggestions on the user's terminal; means for receiving feedback from the user and learning to improve the quality of suggestions for future use; means for providing a portable information device that provides an interface for the user to input search behavior and purchase history; and means for generating and displaying a list of highly relevant products based on the information input through the interface. This makes it possible to propose optimized products and services to the user.

[0332] "Text data" refers to string information entered by the user via their device.

[0333] "Natural language processing technology" refers to computer program technology that analyzes human language and understands its meaning and intent.

[0334] "Information related to the issue" refers to data that includes content related to the user's requests and objectives.

[0335] "Purchase history" refers to a record of the products and services a user has acquired to date.

[0336] "Browsing information" refers to a log of the content that a user has viewed on a digital platform.

[0337] A "database" is a digital system that systematically organizes and stores information, making it searchable and retrievable.

[0338] "Product or service" refers to goods or benefits offered to the market.

[0339] A "proposal" refers to a selection of products or services that are chosen and recommended based on the user's needs.

[0340] A "terminal" is an electronic device used by users to input and receive information.

[0341] "Portable information devices" refer to portable digital devices that have a user interface function.

[0342] A "list of highly relevant products" is a list of products that are highly relevant based on the user's past behavior and input.

[0343] To implement this invention, it is fundamental for the server to analyze text data received from the user using natural language processing technology. The server first receives user input and uses a natural language processing engine (e.g., IBM Watson NLP) to extract keywords related to the task from the text data.

[0344] Next, the server retrieves the user's past purchase history and browsing information from the database. This database is built using, for example, MySQL, allowing for efficient access to large amounts of user data.

[0345] Next, the server generates suggestions for relevant products or services based on the extracted information and historical data. This suggestion generation is achieved, for example, by using Node.js as the backend program, and by comparing the extracted keywords with the user's historical data.

[0346] The generated suggestions are then sent to the user's mobile device. The user's device has an interface developed using React Native where they can view the suggestions. This interface also provides a means to receive user input, allowing for the collection of user feedback.

[0347] For example, if a user enters "I'm looking for a party dress," the system will recommend relevant dresses based on their past browsing and purchase history, and explain the reasons for the selection. An example of a prompt to assist with this task would be, "Please suggest some dresses based on the user's purchase history for events last summer."

[0348] In this way, through the interaction between servers, terminals, and users, more optimized product and service suggestions are provided to users, resulting in an improved user experience.

[0349] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0350] Step 1:

[0351] The user uses a device to input specific needs or requests as text. The entered text data is received by the device and sent directly to the server. At this time, the input data is formatted for natural language processing.

[0352] Step 2:

[0353] The server analyzes the received text data using natural language processing techniques (e.g., IBM Watson NLP). The input is user text data, and the output extracts keywords and important phrases related to the issue. Specifically, it performs part-of-speech and semantic analysis of the text to identify words that indicate the user's needs.

[0354] Step 3:

[0355] The server retrieves the user's past purchase history and browsing information from a database (e.g., MySQL). The input is identification information such as a user ID, and the output is historical record data related to that user. This allows the server to prepare a dataset to understand the user's preferences.

[0356] Step 4:

[0357] The server initiates a process to recommend relevant products or services based on the extracted information and historical data. The input is the output data from steps 2 and 3, and the output is the selected product or service and the reason for the recommendation. Here, a generative AI model is used to score data relevance and calculate recommendation accuracy.

[0358] Step 5:

[0359] The server sends the generated suggestions to the terminal and displays them to the user. At this time, it also sends information including the reasons for the suggestions. The input is the output from step 4, and the output is the list of suggestions received by the user.

[0360] Step 6:

[0361] Users review the suggestions and make selections and provide feedback via their device. After considering the details of the selected products and services, they enter their selections or feedback.

[0362] Step 7:

[0363] The server receives feedback from the user again and learns to improve the accuracy of its suggestions. The input is user feedback, and the output is the refined suggestion generation model. Specifically, it analyzes the feedback data and optimizes the parameters of the suggestion algorithm.

[0364] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0365] This invention is a system that provides a more user-centric service by combining an emotion engine with the analysis of user input data to generate personalized suggestions. When a user inputs their needs and desires through a terminal, the terminal sends this information to a server. The server analyzes the user's input using natural language processing technology to identify the nature of the problem. It also utilizes an emotion engine to recognize the user's emotions hidden within the text. This emotion information is used to adjust the suggestions, recommending appropriate products and services that match the user's emotions.

[0366] For example, if a user sends a text message expressing an emotion such as "frustrated," the server can use its emotion engine to identify that emotion and suggest products or services that can help them relax, such as an aroma diffuser or a relaxation massage. In this way, the system makes suggestions that take the user's emotional state into account.

[0367] The server also collects data based on the user's past purchase history and browsing information to further personalize suggestions. This allows the server to present options that match the user's preferences. The suggestions are displayed to the user through their device, and the user can review them, make a selection, or provide feedback.

[0368] User selections and feedback information are sent to the server and used as learning data to improve the quality of future suggestions. This process allows the system to continuously improve the user experience. By utilizing an emotion engine, a more human-like and meaningful interaction for the user is achieved compared to conventional suggestion systems.

[0369] The following describes the processing flow.

[0370] Step 1:

[0371] Users use their devices to input information about their current concerns and desired products in natural language. This input can optionally include emotions.

[0372] Step 2:

[0373] The terminal receives user input data and sends it to the server in text format. The input data is pre-formatted as needed.

[0374] Step 3:

[0375] The server analyzes the user's text data received by the server using a natural language processing engine. This analysis helps understand the user's intent and requests, and extracts relevant keywords and issues.

[0376] Step 4:

[0377] The server uses an emotion engine to recognize the user's emotions from text data. For example, it extracts emotions such as "tired" or "excited" and adds them to the analysis results.

[0378] Step 5:

[0379] The server connects to the database to retrieve the user's past purchase and browsing history. This gathers information to understand the user's preferences and interests.

[0380] Step 6:

[0381] The server selects relevant products and services from the solution database based on the analyzed text data, sentiment data, and acquired historical information. Sentiment data is given particular importance in selecting the products and services to propose.

[0382] Step 7:

[0383] The server generates product and service proposals, including explanations of the selection criteria and emotionally resonant benefits of the proposals. The proposals are presented from multiple perspectives.

[0384] Step 8:

[0385] The server sends the generated suggestion data to the terminal, which then displays it to the user. The user can then compare and view the provided options.

[0386] Step 9:

[0387] Users can use their devices to select suggested products or services, or provide feedback indicating their desire for further suggestions.

[0388] Step 10:

[0389] The device sends the user's selections and feedback to the server. The server receives this information and uses it as training data to improve future suggestions.

[0390] Step 11:

[0391] The server uses a learning algorithm to analyze feedback and improve the accuracy of future suggestions, including sentiment information. This continuous learning process makes the system's suggestions more appropriate for the user.

[0392] (Example 2)

[0393] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0394] Conventional suggestion systems have a problem in that they struggle to provide appropriate and personalized suggestions based on user input. In particular, because they make suggestions without considering the user's emotions, the suggested content often fails to meet the user's expectations. This problem needs to be solved.

[0395] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0396] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for recognizing the user's emotions using sentiment analysis technology; and means for obtaining the user's past behavioral history and digital information from information sources. This enables more appropriate and personalized suggestions based on the user's emotions.

[0397] "User" refers to an individual or organization that receives a system or service, and is the ultimate beneficiary.

[0398] "Text data" refers to string data containing information written in natural language, and is the content entered by the user.

[0399] "Natural language processing technology" refers to techniques that enable computers to understand, interpret, and generate human language, and is used in the analysis of text data.

[0400] An "information source" refers to a reference point from which information is retrieved, such as a database or external system, and stores past behavioral history and digital information.

[0401] "Emotional analysis technology" is an analytical technique that determines the emotional state of a user from text data, and is used to adjust the content of proposals.

[0402] "Proposal" refers to a selection of products or services presented based on the user's needs and feelings.

[0403] A "terminal" refers to an electronic device used by a user for inputting information or receiving information, and includes personal computers and smartphones.

[0404] "Feedback" refers to the opinions and responses that users provide in response to suggestions and other matters, and is used to improve the system.

[0405] A "learning algorithm" refers to a computational method that allows a system to grow based on data and make more accurate suggestions.

[0406] This invention begins with the user inputting their needs and feelings as text through a terminal. The terminal immediately sends the input data to a server. The server analyzes the received text data using natural language processing techniques. The software used here includes, for example, a "natural language processing library" and a "morphological analysis engine," which are utilized to structurally understand the text.

[0407] Next, the server applies sentiment analysis technology to identify the emotions contained in the text. Software used may include "sentiment analysis tools" or "text sentiment recognition APIs." This allows the user's emotional state to be quantified or categorized.

[0408] The server further retrieves the user's past behavioral history and digital information from various sources. This process utilizes a "customer data platform" and a "history management system," and data is collected based on individual content.

[0409] Based on this information and analysis results, the server suggests products and services that best suit the user's emotions and needs. A "suggestion generation algorithm" and a "product database system" are used for this suggestion generation. The suggestions are sent to the terminal and presented visually to the user. The user can review the suggestions and provide selections or feedback.

[0410] For example, if a user inputs a desire to "connect with nature" and an emotion representing "stress," the server will suggest products and services that have a relaxing effect. For instance, this could include admission tickets to a nature park or a gardening kit. Another example of a prompt for the generating AI model is, "List relaxation methods that should be suggested when a user is feeling stressed."

[0411] User feedback is used to inform future suggestions, and the server analyzes the feedback to improve the system. This functionality is achieved through a "learning model" and a "data analysis framework." As a result, the system can continuously adapt and provide users with a more satisfying experience.

[0412] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0413] Step 1:

[0414] The user uses a device to input text about their needs and feelings. This input data represents the user's desires and current emotional state. The device then performs the specific action of sending the entered text data to the server. The input is text data, and the output is the transmission of data to the server.

[0415] Step 2:

[0416] The server analyzes the received text data using natural language processing techniques. Specifically, the server uses a "natural language processing library" to tokenize and morphologically analyze the text, thereby understanding its structure. The input is text data sent from the terminal, and the output is the analysis results indicating user needs and preferences.

[0417] Step 3:

[0418] The server uses sentiment analysis technology to recognize the user's emotional state from the analyzed text data. Specifically, it uses a sentiment analysis tool to quantify emotions from the text and classify them into desirable emotional categories. The input is the result of natural language analysis, and the output is data indicating the user's emotions.

[0419] Step 4:

[0420] The server retrieves the user's past behavioral history and digital information from various sources. Specifically, it retrieves relevant information from the database through query processing and uses the user profile information to perform personalization. The input is user identification information, and the output is the behavioral history and digital information used for personalization.

[0421] Step 5:

[0422] The server generates appropriate product and service suggestions based on emotional information, needs analysis results, and past behavioral history. Specifically, it uses a suggestion generation algorithm to evaluate and select from multiple options. The input is emotional data and user profiles, and the output is a list of suggested products and services.

[0423] Step 6:

[0424] The generated suggestions are sent to the user's device and displayed visually on the device. Specifically, the server sends the generated suggestions to the device via push notification or in real time, and the device receives them and displays them in the user interface. The input is the generated suggestion data, and the output is the result displayed to the user.

[0425] Step 7:

[0426] Users make selections and provide feedback on the displayed suggestions. Specifically, users choose suggested products or services and enter their thoughts and suggestions for improvement through a feedback form. The input consists of the user's selections and feedback, and the output is the feedback data sent to the server.

[0427] Step 8:

[0428] The server analyzes the received feedback and uses it to improve future proposals. Specifically, the feedback data is used to train a learning algorithm, improving the system's proposal accuracy. The input is user feedback data, and the output is the improved proposal model.

[0429] (Application Example 2)

[0430] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0431] Conventional recommendation systems often recommended products and services based solely on past data, without considering the user's emotions. As a result, recommendations were not tailored to the user's current emotions and needs, leading to decreased satisfaction. This invention aims to solve this problem by analyzing the user's emotional state and providing more appropriate and personalized recommendations that respond to individual emotions.

[0432] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0433] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; and means for identifying the user's emotional state using an emotion engine, in addition to the extracted and obtained information, and generating suggestions that correspond to that emotion. This makes it possible to provide suggestions that match the user's current emotions.

[0434] "Natural language processing technology" is a technology that analyzes text data from users to understand its meaning and context.

[0435] An "emotion engine" is a system or method that identifies an emotional state from user input data and provides information corresponding to that emotion.

[0436] "Purchase history" refers to data that records information about products and services that a user has purchased in the past.

[0437] A "database" is an information system that systematically stores multiple pieces of data and allows access and management as needed.

[0438] "Feedback" refers to collecting evaluations and opinions from users regarding suggestions and services they have provided.

[0439] A "learning algorithm" is a computational method used to improve the performance of a system based on collected data.

[0440] To implement this invention, a system is needed that analyzes user input data and generates personalized suggestions based on emotions. First, the user inputs their needs and desires in natural language using a device such as a smartphone. This input data is sent from the device to a server, which uses natural language processing technology to analyze the text.

[0441] Here, "natural language processing technology" refers to the technology that analyzes text data from users and understands its meaning and context.

[0442] The server uses an emotion engine to identify the user's emotional state and, based on that information, generates product and service recommendations tailored to the user. An "emotion engine" is a system or method that identifies the user's emotional state from user input data and provides information corresponding to that emotion.

[0443] Next, the suggestions are sent to the device and displayed to the user. The user reviews the displayed suggestions and provides feedback by making selections. This feedback is sent to the server and used as training data to improve future suggestions.

[0444] As a concrete example, if a user provides input such as "I've been feeling stressed lately and want to refresh myself," the server uses its emotion engine to determine that the user is seeking relaxation. As a result, it generates suggestions for relaxation-related products and services, such as aroma diffusers or relaxation spas, and displays them on the user's device.

[0445] An example of a prompt message would be: "Analyze the user's emotions, and if the input is 'I've been feeling stressed lately,' recommend a relaxation item."

[0446] This process utilizes a smartphone as hardware and employs Python libraries such as TextBlob and Scikit-learn for analysis. This allows for the analysis of user input data and the provision of optimal suggestions. This system enables personalized product recommendations tailored to the user's current emotions, providing a more satisfying experience.

[0447] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0448] Step 1:

[0449] The device receives input from the user. The user uses a smartphone to input their feelings and needs in natural language into a text box. For example, they might input something like, "I've been feeling stressed lately, so I want to relax." The entered data is then sent directly to the server.

[0450] Step 2:

[0451] The server analyzes the received user text data using natural language processing techniques. In this step, the Python library TextBlob is used to analyze the grammar and meaning of the text and identify the main point of what the user has entered. In this process, the user's problems and desires become clear. As a result, the analyzed text data is generated.

[0452] Step 3:

[0453] The server uses an emotion engine to identify the user's emotional state from the analyzed text data. For example, if the user uses the word "stress," the emotion engine recognizes it as a negative emotion. An SVM (Support Vector Machine) is used to calculate an emotion score, representing the user's emotional state numerically. The output here is the user's emotion score.

[0454] Step 4:

[0455] The server retrieves past purchase history and browsing information from the database. This data indicates the user's preferences and tendencies. Based on this, it combines the user's current emotional state with past behavioral patterns to generate more appropriate suggestions. In this step, historical data is retrieved and output.

[0456] Step 5:

[0457] The server selects products and services to suggest to the user based on their emotional score and historical data. Using a generative AI model, it proposes the product best suited to the user's state from the selected candidates. For example, relaxation goods and stress-reducing services may be presented. The selection results are output as suggestions.

[0458] Step 6:

[0459] The server sends the generated suggestions to the terminal and displays them to the user. The user can view the suggestions on their smartphone screen. After viewing the suggestions, the user selects products based on them and considers purchasing them. In this step, the suggestions are displayed visually.

[0460] Step 7:

[0461] The terminal receives user selections and feedback and sends that information to the server. Users contribute to system improvement by inputting how they felt about the suggestions and their satisfaction level. This data is then sent back to the server.

[0462] Step 8:

[0463] The server analyzes the received feedback and adjusts the system's learning algorithm based on the results. This process improves the accuracy and quality of subsequent suggestions, thereby achieving overall system optimization.

[0464] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0465] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0466] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0467] [Third Embodiment]

[0468] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0469] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0470] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0471] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0472] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0473] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0474] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0475] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0476] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0477] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0478] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0479] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0480] This invention begins with users interacting with the system using a terminal and inputting their challenges and needs. The terminal receives the user's input and sends the data to a server. The server analyzes the received data using natural language processing techniques. Through this analysis, the server identifies the user's challenges and extracts keywords and phrases relevant to their context.

[0481] Next, the server retrieves the user's past purchase history and browsing information from the database. This information helps in understanding the user's preferences and behavioral patterns. Based on this data, the server generates product and service suggestions that meet the user's needs.

[0482] A key feature of the suggestions is that they are presented from multiple perspectives. For example, a user aiming to organize their kitchen might be offered suggestions such as "tool storage boxes," "systematic organizing shelves," and "virtual organizing training." The server then explains, in natural language, how each of these suggestions contributes to solving the problem, providing justification for its application.

[0483] The terminal then displays the suggestions and explanations received from the server to the user. The user compares multiple suggestions via the terminal and makes a selection or provides feedback. The selected suggestion and feedback information are sent back to the server, and the system uses this information to learn and improve the quality of future suggestions.

[0484] For example, if a user enters "I want a new coffee maker," the server will refer to the user's past coffee-related purchase history and preferences, and generate suggestions such as "fast-boiling electric coffee maker," "portable drip coffee maker," and "premium coffee beans for regular delivery." Each suggestion will include explanations of how to use it and its benefits, tailored to the user's lifestyle.

[0485] In this way, the present invention constitutes a system that supports the user's purchasing process and promotes more satisfying choices.

[0486] The following describes the processing flow.

[0487] Step 1:

[0488] Users input information about the problems they want to solve or the products they are interested in using natural language via their device. This can include detailed conditions and expected results.

[0489] Step 2:

[0490] The terminal receives input data from the user and sends it to the server in text format. The input data is formatted according to the specified data format.

[0491] Step 3:

[0492] The server analyzes the received data using a natural language processing engine. Here, it understands the user's intent and identifies the category of the problem based on the extracted keywords and phrases.

[0493] Step 4:

[0494] The server connects to the database to retrieve the user's past purchase history and browsing information. This enables personalization based on the user's preferences and behavioral patterns.

[0495] Step 5:

[0496] Based on the information acquired and analyzed by the server, appropriate products and services are selected from the solution database. The selection process takes into account product characteristics, the user's past purchasing trends, and current trends.

[0497] Step 6:

[0498] The server generates information related to each product or service it proposes. The proposals include explanatory text that explains the reasons for selection, expected benefits, and how they address user needs.

[0499] Step 7:

[0500] The server generates suggestion data and sends it to the terminal, which then displays it to the user. The user can compare and consider the suggested options and view detailed information.

[0501] Step 8:

[0502] The user selects the product or service they are most interested in from the suggested options via their device, or provides feedback indicating that an alternative is needed.

[0503] Step 9:

[0504] The device sends the user's selections and feedback to the server. This information is used as data for future suggestions.

[0505] Step 10:

[0506] The server analyzes the feedback it receives, updates the proposed logic based on the learning algorithm, and aims to improve accuracy for the next attempt. This allows the system to continuously improve.

[0507] (Example 1)

[0508] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0509] In modern society, users often struggle to make the best choices from a wide variety of products and services to meet their specific needs. Therefore, there is a need for systems that support users in making appropriate choices tailored to their individual circumstances and preferences. Furthermore, technologies that allow these systems to incorporate user feedback and improve the quality of their recommendations are essential.

[0510] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0511] In this invention, the server includes means for analyzing character data received from a user using natural language processing technology and extracting information related to the request from the character data; means for obtaining the user's past purchase history and browsing information from a data storage device; means for selecting multiple items or offerings based on the extracted information and the obtained information and generating a proposal including the reasons for the selection; means for explaining how the generated proposal contributes to problem solving using a generative model; and means for receiving responses from the user and performing machine learning to improve the quality of future proposals. This enables the user to select the products and services that best suit their needs, and further improves the quality of the proposals through feedback.

[0512] A "user" is an individual or organization that uses the system to receive suggestions regarding products and services.

[0513] "Character data" refers to text information in natural language format entered by the user.

[0514] "Natural language processing technology" refers to the techniques and methods that enable computers to analyze, understand, and generate human language.

[0515] "Means of extracting information" refers to the process of identifying important keywords and phrases related to a request from text data.

[0516] A "data storage device" is a database or storage system used to store a user's past purchase history and browsing information.

[0517] A "generative model" is a computational model used to automatically generate suggestions in response to user requests, and is generally composed of machine learning algorithms.

[0518] "Response" refers to the user's choices and feedback information regarding suggestions.

[0519] "Machine learning" refers to algorithms and techniques that allow computers to continuously improve through data, and are used to enhance the quality of future suggestions.

[0520] The system in this invention begins with the user operating a terminal and inputting their needs and challenges. The user inputs information in text format into the terminal's interface. This information is used to identify the products or services the user is seeking.

[0521] The terminal sends the received text data to the server via a secure protocol. The server analyzes the text data sent by the user using natural language processing (NLP) technology. This analysis utilizes NLP libraries such as "spaCy" and "NLTK" to perform syntactic analysis and keyword extraction.

[0522] Next, the server retrieves the user's past purchase history and browsing information from the data storage device. This retrieval utilizes database systems such as MySQL and PostgreSQL. Based on the analyzed and retrieved data, the server generates suggestions tailored to the user's needs. This involves using generative AI models such as GPT to select the most suitable items or services that can meet the user's specific requests.

[0523] The generated suggestions are accompanied by an explanation of how they contribute to solving the user's problem. The server sends this information to the terminal, which then presents it visually to the user.

[0524] For example, if a user enters "I want new running shoes," the server will refer to the user's past purchase history of sports equipment and generate suggestions that match their needs, such as shoes with high-performance cushioning or waterproof shoes for trail running. In addition, the AI ​​model used to generate these suggestions will explain the benefits, such as "quick-drying materials reduce fatigue" or "certain designs reduce strain on the feet."

[0525] In this way, suggestions are displayed to the user via their device, and the user can select or provide feedback. This feedback is sent back to the server and used as material for machine learning to improve the quality of future suggestions.

[0526] An example of a prompt to the generating AI model would be: "The user is looking for new running shoes. Please suggest suitable products based on their past purchase history of sports equipment." This system utilizes advanced artificial intelligence technology to efficiently support the user's decision-making.

[0527] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0528] Step 1:

[0529] The user enters the request using a terminal.

[0530] Users input information about their needs and challenges in text format through the terminal's interface. This input data becomes the basis for subsequent processing. If a user inputs "I want new running shoes," that text data will be analyzed in the next step.

[0531] Step 2:

[0532] The terminal sends the user's input data to the server.

[0533] The terminal transfers the entered text data to the server as packets using a secure communication protocol. The input data is sent to the server in its original format and forms the basis of the data the server receives.

[0534] Step 3:

[0535] The server analyzes the received data using natural language processing technology.

[0536] The server uses tools such as "spaCy" and "NLTK" to tokenize the received text data and perform syntactic analysis. This extracts context-relevant keywords and phrases. This analysis process clarifies information directly relevant to the user's needs.

[0537] Step 4:

[0538] The server retrieves the user's purchase history from the database.

[0539] The server uses a database management system (e.g., MySQL, PostgreSQL) to query the user's past purchase history and browsing information. The retrieved data is used to understand the user's preferences. This information forms the basis for the data associated with the user's needs.

[0540] Step 5:

[0541] The server generates proposals using a generated AI model.

[0542] Based on the analyzed data and acquired historical information, the server uses a generative AI model to select products and services that best suit the user's needs. The generated suggestions include explanations of the reasons for selection and their benefits in natural language. An example of a prompt might be, "The user is looking for new running shoes. Please suggest suitable products based on their past sports equipment purchase history." The data obtained in this step forms the final output suggestions.

[0543] Step 6:

[0544] The server sends suggestion data to the terminal, and the terminal displays it.

[0545] The server sends the generated suggestions to the terminal, which converts them into a display format for the user and displays them on the interface. The user can review the suggested options and make a selection or provide feedback.

[0546] Step 7:

[0547] The device sends user feedback to the server, which then performs learning.

[0548] The device sends the information and feedback selected by the user to the server. The server then applies machine learning algorithms based on this information to improve the accuracy of future suggestions. Through learning, the system continuously improves, enabling more personalized suggestions.

[0549] (Application Example 1)

[0550] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] The present invention aims to solve the problem of difficulty in quickly and reliably proposing products and services that are tailored to the individual needs of users. In particular, it aims to provide a more satisfying purchasing experience by allowing users to receive highly relevant suggestions based on their search behavior and past purchase history.

[0552] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0553] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; means for selecting multiple products or services based on the extracted information and the obtained information and generating suggestions including the reasons for the selection; means for transmitting and displaying the generated suggestions on the user's terminal; means for receiving feedback from the user and learning to improve the quality of suggestions for future use; means for providing a portable information device that provides an interface for the user to input search behavior and purchase history; and means for generating and displaying a list of highly relevant products based on the information input through the interface. This makes it possible to propose optimized products and services to the user.

[0554] "Text data" refers to string information entered by the user via their device.

[0555] "Natural language processing technology" refers to computer program technology that analyzes human language and understands its meaning and intent.

[0556] "Information related to the issue" refers to data that includes content related to the user's requests and objectives.

[0557] "Purchase history" refers to a record of the products and services a user has acquired to date.

[0558] "Browsing information" refers to a log of the content that a user has viewed on a digital platform.

[0559] A "database" is a digital system that systematically organizes and stores information, making it searchable and retrievable.

[0560] "Product or service" refers to goods or benefits offered to the market.

[0561] A "proposal" refers to a selection of products or services that are chosen and recommended based on the user's needs.

[0562] A "terminal" is an electronic device used by users to input and receive information.

[0563] "Portable information devices" refer to portable digital devices that have a user interface function.

[0564] A "list of highly relevant products" is a list of products that are highly relevant based on the user's past behavior and input.

[0565] To implement this invention, it is fundamental for the server to analyze text data received from the user using natural language processing technology. The server first receives user input and uses a natural language processing engine (e.g., IBM Watson NLP) to extract keywords related to the task from the text data.

[0566] Next, the server retrieves the user's past purchase history and browsing information from the database. This database is built using, for example, MySQL, allowing for efficient access to large amounts of user data.

[0567] Next, the server generates suggestions for relevant products or services based on the extracted information and historical data. This suggestion generation is achieved, for example, by using Node.js as the backend program, and by comparing the extracted keywords with the user's historical data.

[0568] The generated suggestions are then sent to the user's mobile device. The user's device has an interface developed using React Native where they can view the suggestions. This interface also provides a means to receive user input, allowing for the collection of user feedback.

[0569] For example, if a user enters "I'm looking for a party dress," the system will recommend relevant dresses based on their past browsing and purchase history, and explain the reasons for the selection. An example of a prompt to assist with this task would be, "Please suggest some dresses based on the user's purchase history for events last summer."

[0570] In this way, through the interaction between servers, terminals, and users, more optimized product and service suggestions are provided to users, resulting in an improved user experience.

[0571] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0572] Step 1:

[0573] The user uses a device to input specific needs or requests as text. The entered text data is received by the device and sent directly to the server. At this time, the input data is formatted for natural language processing.

[0574] Step 2:

[0575] The server analyzes the received text data using natural language processing techniques (e.g., IBM Watson NLP). The input is user text data, and the output extracts keywords and important phrases related to the issue. Specifically, it performs part-of-speech and semantic analysis of the text to identify words that indicate the user's needs.

[0576] Step 3:

[0577] The server retrieves the user's past purchase history and browsing information from a database (e.g., MySQL). The input is identification information such as a user ID, and the output is historical record data related to that user. This allows the server to prepare a dataset to understand the user's preferences.

[0578] Step 4:

[0579] The server initiates a process to recommend relevant products or services based on the extracted information and historical data. The input is the output data from steps 2 and 3, and the output is the selected product or service and the reason for the recommendation. Here, a generative AI model is used to score data relevance and calculate recommendation accuracy.

[0580] Step 5:

[0581] The server sends the generated suggestions to the terminal and displays them to the user. At this time, it also sends information including the reasons for the suggestions. The input is the output from step 4, and the output is the list of suggestions received by the user.

[0582] Step 6:

[0583] Users review the suggestions and make selections and provide feedback via their device. After considering the details of the selected products and services, they enter their selections or feedback.

[0584] Step 7:

[0585] The server receives feedback from the user again and learns to improve the accuracy of its suggestions. The input is user feedback, and the output is the refined suggestion generation model. Specifically, it analyzes the feedback data and optimizes the parameters of the suggestion algorithm.

[0586] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0587] This invention is a system that provides a more user-centric service by combining an emotion engine with the analysis of user input data to generate personalized suggestions. When a user inputs their needs and desires through a terminal, the terminal sends this information to a server. The server analyzes the user's input using natural language processing technology to identify the nature of the problem. It also utilizes an emotion engine to recognize the user's emotions hidden within the text. This emotion information is used to adjust the suggestions, recommending appropriate products and services that match the user's emotions.

[0588] For example, if a user sends a text message expressing an emotion such as "frustrated," the server can use its emotion engine to identify that emotion and suggest products or services that can help them relax, such as an aroma diffuser or a relaxation massage. In this way, the system makes suggestions that take the user's emotional state into account.

[0589] The server also collects data based on the user's past purchase history and browsing information to further personalize suggestions. This allows the server to present options that match the user's preferences. The suggestions are displayed to the user through their device, and the user can review them, make a selection, or provide feedback.

[0590] User selections and feedback information are sent to the server and used as learning data to improve the quality of future suggestions. This process allows the system to continuously improve the user experience. By utilizing an emotion engine, a more human-like and meaningful interaction for the user is achieved compared to conventional suggestion systems.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] Users use their devices to input information about their current concerns and desired products in natural language. This input can optionally include emotions.

[0594] Step 2:

[0595] The terminal receives user input data and sends it to the server in text format. The input data is pre-formatted as needed.

[0596] Step 3:

[0597] The server analyzes the user's text data received by the server using a natural language processing engine. This analysis helps understand the user's intent and requests, and extracts relevant keywords and issues.

[0598] Step 4:

[0599] The server uses an emotion engine to recognize the user's emotions from text data. For example, it extracts emotions such as "tired" or "excited" and adds them to the analysis results.

[0600] Step 5:

[0601] The server connects to the database to retrieve the user's past purchase and browsing history. This gathers information to understand the user's preferences and interests.

[0602] Step 6:

[0603] The server selects relevant products and services from the solution database based on the analyzed text data, sentiment data, and acquired historical information. Sentiment data is given particular importance in selecting the products and services to propose.

[0604] Step 7:

[0605] The server generates product and service proposals, including explanations of the selection criteria and emotionally resonant benefits of the proposals. The proposals are presented from multiple perspectives.

[0606] Step 8:

[0607] The server sends the generated suggestion data to the terminal, which then displays it to the user. The user can then compare and view the provided options.

[0608] Step 9:

[0609] Users can use their devices to select suggested products or services, or provide feedback indicating their desire for further suggestions.

[0610] Step 10:

[0611] The device sends the user's selections and feedback to the server. The server receives this information and uses it as training data to improve future suggestions.

[0612] Step 11:

[0613] The server uses a learning algorithm to analyze feedback and improve the accuracy of future suggestions, including sentiment information. This continuous learning process makes the system's suggestions more appropriate for the user.

[0614] (Example 2)

[0615] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0616] Conventional suggestion systems have a problem in that they struggle to provide appropriate and personalized suggestions based on user input. In particular, because they make suggestions without considering the user's emotions, the suggested content often fails to meet the user's expectations. This problem needs to be solved.

[0617] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0618] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for recognizing the user's emotions using sentiment analysis technology; and means for obtaining the user's past behavioral history and digital information from information sources. This enables more appropriate and personalized suggestions based on the user's emotions.

[0619] "User" refers to an individual or organization that receives a system or service, and is the ultimate beneficiary.

[0620] "Text data" refers to string data containing information written in natural language, and is the content entered by the user.

[0621] "Natural language processing technology" refers to techniques that enable computers to understand, interpret, and generate human language, and is used in the analysis of text data.

[0622] An "information source" refers to a reference point from which information is retrieved, such as a database or external system, and stores past behavioral history and digital information.

[0623] "Emotional analysis technology" is an analytical technique that determines the emotional state of a user from text data, and is used to adjust the content of proposals.

[0624] "Proposal" refers to a selection of products or services presented based on the user's needs and feelings.

[0625] A "terminal" refers to an electronic device used by a user for inputting information or receiving information, and includes personal computers and smartphones.

[0626] "Feedback" refers to the opinions and responses that users provide in response to suggestions and other matters, and is used to improve the system.

[0627] A "learning algorithm" refers to a computational method that allows a system to grow based on data and make more accurate suggestions.

[0628] This invention begins with the user inputting their needs and feelings as text through a terminal. The terminal immediately sends the input data to a server. The server analyzes the received text data using natural language processing techniques. The software used here includes, for example, a "natural language processing library" and a "morphological analysis engine," which are utilized to structurally understand the text.

[0629] Next, the server applies sentiment analysis technology to identify the emotions contained in the text. Software used may include "sentiment analysis tools" or "text sentiment recognition APIs." This allows the user's emotional state to be quantified or categorized.

[0630] The server further retrieves the user's past behavioral history and digital information from various sources. This process utilizes a "customer data platform" and a "history management system," and data is collected based on individual content.

[0631] Based on this information and analysis results, the server suggests products and services that best suit the user's emotions and needs. A "suggestion generation algorithm" and a "product database system" are used for this suggestion generation. The suggestions are sent to the terminal and presented visually to the user. The user can review the suggestions and provide selections or feedback.

[0632] For example, if a user inputs a desire to "connect with nature" and an emotion representing "stress," the server will suggest products and services that have a relaxing effect. For instance, this could include admission tickets to a nature park or a gardening kit. Another example of a prompt for the generating AI model is, "List relaxation methods that should be suggested when a user is feeling stressed."

[0633] User feedback is used to inform future suggestions, and the server analyzes the feedback to improve the system. This functionality is achieved through a "learning model" and a "data analysis framework." As a result, the system can continuously adapt and provide users with a more satisfying experience.

[0634] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0635] Step 1:

[0636] The user uses a device to input text about their needs and feelings. This input data represents the user's desires and current emotional state. The device then performs the specific action of sending the entered text data to the server. The input is text data, and the output is the transmission of data to the server.

[0637] Step 2:

[0638] The server analyzes the received text data using natural language processing techniques. Specifically, the server uses a "natural language processing library" to tokenize and morphologically analyze the text, thereby understanding its structure. The input is text data sent from the terminal, and the output is the analysis results indicating user needs and preferences.

[0639] Step 3:

[0640] The server uses sentiment analysis technology to recognize the user's emotional state from the analyzed text data. Specifically, it uses a sentiment analysis tool to quantify emotions from the text and classify them into desirable emotional categories. The input is the result of natural language analysis, and the output is data indicating the user's emotions.

[0641] Step 4:

[0642] The server retrieves the user's past behavioral history and digital information from various sources. Specifically, it retrieves relevant information from the database through query processing and uses the user profile information to perform personalization. The input is user identification information, and the output is the behavioral history and digital information used for personalization.

[0643] Step 5:

[0644] The server generates appropriate product and service suggestions based on emotional information, needs analysis results, and past behavioral history. Specifically, it uses a suggestion generation algorithm to evaluate and select from multiple options. The input is emotional data and user profiles, and the output is a list of suggested products and services.

[0645] Step 6:

[0646] The generated suggestions are sent to the user's device and displayed visually on the device. Specifically, the server sends the generated suggestions to the device via push notification or in real time, and the device receives them and displays them in the user interface. The input is the generated suggestion data, and the output is the result displayed to the user.

[0647] Step 7:

[0648] Users make selections and provide feedback on the displayed suggestions. Specifically, users choose suggested products or services and enter their thoughts and suggestions for improvement through a feedback form. The input consists of the user's selections and feedback, and the output is the feedback data sent to the server.

[0649] Step 8:

[0650] The server analyzes the received feedback and uses it to improve future proposals. Specifically, the feedback data is used to train a learning algorithm, improving the system's proposal accuracy. The input is user feedback data, and the output is the improved proposal model.

[0651] (Application Example 2)

[0652] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0653] Conventional recommendation systems often recommended products and services based solely on past data, without considering the user's emotions. As a result, recommendations were not tailored to the user's current emotions and needs, leading to decreased satisfaction. This invention aims to solve this problem by analyzing the user's emotional state and providing more appropriate and personalized recommendations that respond to individual emotions.

[0654] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0655] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; and means for identifying the user's emotional state using an emotion engine, in addition to the extracted and obtained information, and generating suggestions that correspond to that emotion. This makes it possible to provide suggestions that match the user's current emotions.

[0656] "Natural language processing technology" is a technology that analyzes text data from users to understand its meaning and context.

[0657] An "emotion engine" is a system or method that identifies an emotional state from user input data and provides information corresponding to that emotion.

[0658] "Purchase history" refers to data that records information about products and services that a user has purchased in the past.

[0659] A "database" is an information system that systematically stores multiple pieces of data and allows access and management as needed.

[0660] "Feedback" refers to collecting evaluations and opinions from users regarding suggestions and services they have provided.

[0661] A "learning algorithm" is a computational method used to improve the performance of a system based on collected data.

[0662] To implement this invention, a system is needed that analyzes user input data and generates personalized suggestions based on emotions. First, the user inputs their needs and desires in natural language using a device such as a smartphone. This input data is sent from the device to a server, which uses natural language processing technology to analyze the text.

[0663] Here, "natural language processing technology" refers to the technology that analyzes text data from users and understands its meaning and context.

[0664] The server uses an emotion engine to identify the user's emotional state and, based on that information, generates product and service recommendations tailored to the user. An "emotion engine" is a system or method that identifies the user's emotional state from user input data and provides information corresponding to that emotion.

[0665] Next, the suggestions are sent to the device and displayed to the user. The user reviews the displayed suggestions and provides feedback by making selections. This feedback is sent to the server and used as training data to improve future suggestions.

[0666] As a concrete example, if a user provides input such as "I've been feeling stressed lately and want to refresh myself," the server uses its emotion engine to determine that the user is seeking relaxation. As a result, it generates suggestions for relaxation-related products and services, such as aroma diffusers or relaxation spas, and displays them on the user's device.

[0667] An example of a prompt message would be: "Analyze the user's emotions, and if the input is 'I've been feeling stressed lately,' recommend a relaxation item."

[0668] This process utilizes a smartphone as hardware and employs Python libraries such as TextBlob and Scikit-learn for analysis. This allows for the analysis of user input data and the provision of optimal suggestions. This system enables personalized product recommendations tailored to the user's current emotions, providing a more satisfying experience.

[0669] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0670] Step 1:

[0671] The device receives input from the user. The user uses a smartphone to input their feelings and needs in natural language into a text box. For example, they might input something like, "I've been feeling stressed lately, so I want to relax." The entered data is then sent directly to the server.

[0672] Step 2:

[0673] The server analyzes the received user text data using natural language processing techniques. In this step, the Python library TextBlob is used to analyze the grammar and meaning of the text and identify the main point of what the user has entered. In this process, the user's problems and desires become clear. As a result, the analyzed text data is generated.

[0674] Step 3:

[0675] The server uses an emotion engine to identify the user's emotional state from the analyzed text data. For example, if the user uses the word "stress," the emotion engine recognizes it as a negative emotion. An SVM (Support Vector Machine) is used to calculate an emotion score, representing the user's emotional state numerically. The output here is the user's emotion score.

[0676] Step 4:

[0677] The server retrieves past purchase history and browsing information from the database. This data indicates the user's preferences and tendencies. Based on this, it combines the user's current emotional state with past behavioral patterns to generate more appropriate suggestions. In this step, historical data is retrieved and output.

[0678] Step 5:

[0679] The server selects products and services to suggest to the user based on their emotional score and historical data. Using a generative AI model, it proposes the product best suited to the user's state from the selected candidates. For example, relaxation goods and stress-reducing services may be presented. The selection results are output as suggestions.

[0680] Step 6:

[0681] The server sends the generated suggestions to the terminal and displays them to the user. The user can view the suggestions on their smartphone screen. After viewing the suggestions, the user selects products based on them and considers purchasing them. In this step, the suggestions are displayed visually.

[0682] Step 7:

[0683] The terminal receives user selections and feedback and sends that information to the server. Users contribute to system improvement by inputting how they felt about the suggestions and their satisfaction level. This data is then sent back to the server.

[0684] Step 8:

[0685] The server analyzes the received feedback and adjusts the system's learning algorithm based on the results. This process improves the accuracy and quality of subsequent suggestions, thereby achieving overall system optimization.

[0686] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0687] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0688] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0689] [Fourth Embodiment]

[0690] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0691] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0692] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0693] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0694] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0695] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0696] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0697] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0698] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0699] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0700] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0701] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0702] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] This invention begins with users interacting with the system using a terminal and inputting their challenges and needs. The terminal receives the user's input and sends the data to a server. The server analyzes the received data using natural language processing techniques. Through this analysis, the server identifies the user's challenges and extracts keywords and phrases relevant to their context.

[0704] Next, the server retrieves the user's past purchase history and browsing information from the database. This information helps in understanding the user's preferences and behavioral patterns. Based on this data, the server generates product and service suggestions that meet the user's needs.

[0705] A key feature of the suggestions is that they are presented from multiple perspectives. For example, a user aiming to organize their kitchen might be offered suggestions such as "tool storage boxes," "systematic organizing shelves," and "virtual organizing training." The server then explains, in natural language, how each of these suggestions contributes to solving the problem, providing justification for its application.

[0706] The terminal then displays the suggestions and explanations received from the server to the user. The user compares multiple suggestions via the terminal and makes a selection or provides feedback. The selected suggestion and feedback information are sent back to the server, and the system uses this information to learn and improve the quality of future suggestions.

[0707] For example, if a user enters "I want a new coffee maker," the server will refer to the user's past coffee-related purchase history and preferences, and generate suggestions such as "fast-boiling electric coffee maker," "portable drip coffee maker," and "premium coffee beans for regular delivery." Each suggestion will include explanations of how to use it and its benefits, tailored to the user's lifestyle.

[0708] In this way, the present invention constitutes a system that supports the user's purchasing process and promotes more satisfying choices.

[0709] The following describes the processing flow.

[0710] Step 1:

[0711] Users input information about the problems they want to solve or the products they are interested in using natural language via their device. This can include detailed conditions and expected results.

[0712] Step 2:

[0713] The terminal receives input data from the user and sends it to the server in text format. The input data is formatted according to the specified data format.

[0714] Step 3:

[0715] The server analyzes the received data using a natural language processing engine. Here, it understands the user's intent and identifies the category of the problem based on the extracted keywords and phrases.

[0716] Step 4:

[0717] The server connects to the database to retrieve the user's past purchase history and browsing information. This enables personalization based on the user's preferences and behavioral patterns.

[0718] Step 5:

[0719] Based on the information acquired and analyzed by the server, appropriate products and services are selected from the solution database. The selection process takes into account product characteristics, the user's past purchasing trends, and current trends.

[0720] Step 6:

[0721] The server generates information related to each product or service it proposes. The proposals include explanatory text that explains the reasons for selection, expected benefits, and how they address user needs.

[0722] Step 7:

[0723] The server generates suggestion data and sends it to the terminal, which then displays it to the user. The user can compare and consider the suggested options and view detailed information.

[0724] Step 8:

[0725] The user selects the product or service they are most interested in from the suggested options via their device, or provides feedback indicating that an alternative is needed.

[0726] Step 9:

[0727] The device sends the user's selections and feedback to the server. This information is used as data for future suggestions.

[0728] Step 10:

[0729] The server analyzes the feedback it receives, updates the proposed logic based on the learning algorithm, and aims to improve accuracy for the next attempt. This allows the system to continuously improve.

[0730] (Example 1)

[0731] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0732] In modern society, users often struggle to make the best choices from a wide variety of products and services to meet their specific needs. Therefore, there is a need for systems that support users in making appropriate choices tailored to their individual circumstances and preferences. Furthermore, technologies that allow these systems to incorporate user feedback and improve the quality of their recommendations are essential.

[0733] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0734] In this invention, the server includes means for analyzing character data received from a user using natural language processing technology and extracting information related to the request from the character data; means for obtaining the user's past purchase history and browsing information from a data storage device; means for selecting multiple items or offerings based on the extracted information and the obtained information and generating a proposal including the reasons for the selection; means for explaining how the generated proposal contributes to problem solving using a generative model; and means for receiving responses from the user and performing machine learning to improve the quality of future proposals. This enables the user to select the products and services that best suit their needs, and further improves the quality of the proposals through feedback.

[0735] A "user" is an individual or organization that uses the system to receive suggestions regarding products and services.

[0736] "Character data" refers to text information in natural language format entered by the user.

[0737] "Natural language processing technology" refers to the techniques and methods that enable computers to analyze, understand, and generate human language.

[0738] "Means of extracting information" refers to the process of identifying important keywords and phrases related to a request from text data.

[0739] A "data storage device" is a database or storage system used to store a user's past purchase history and browsing information.

[0740] A "generative model" is a computational model used to automatically generate suggestions in response to user requests, and is generally composed of machine learning algorithms.

[0741] "Response" refers to the user's choices and feedback information regarding suggestions.

[0742] "Machine learning" refers to algorithms and techniques that allow computers to continuously improve through data, and are used to enhance the quality of future suggestions.

[0743] The system in this invention begins with the user operating a terminal and inputting their needs and challenges. The user inputs information in text format into the terminal's interface. This information is used to identify the products or services the user is seeking.

[0744] The terminal sends the received text data to the server via a secure protocol. The server analyzes the text data sent by the user using natural language processing (NLP) technology. This analysis utilizes NLP libraries such as "spaCy" and "NLTK" to perform syntactic analysis and keyword extraction.

[0745] Next, the server retrieves the user's past purchase history and browsing information from the data storage device. This retrieval utilizes database systems such as MySQL and PostgreSQL. Based on the analyzed and retrieved data, the server generates suggestions tailored to the user's needs. This involves using generative AI models such as GPT to select the most suitable items or services that can meet the user's specific requests.

[0746] The generated suggestions are accompanied by an explanation of how they contribute to solving the user's problem. The server sends this information to the terminal, which then presents it visually to the user.

[0747] For example, if a user enters "I want new running shoes," the server will refer to the user's past purchase history of sports equipment and generate suggestions that match their needs, such as shoes with high-performance cushioning or waterproof shoes for trail running. In addition, the AI ​​model used to generate these suggestions will explain the benefits, such as "quick-drying materials reduce fatigue" or "certain designs reduce strain on the feet."

[0748] In this way, suggestions are displayed to the user via their device, and the user can select or provide feedback. This feedback is sent back to the server and used as material for machine learning to improve the quality of future suggestions.

[0749] An example of a prompt to the generating AI model would be: "The user is looking for new running shoes. Please suggest suitable products based on their past purchase history of sports equipment." This system utilizes advanced artificial intelligence technology to efficiently support the user's decision-making.

[0750] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0751] Step 1:

[0752] The user enters the request using a terminal.

[0753] Users input information about their needs and challenges in text format through the terminal's interface. This input data becomes the basis for subsequent processing. If a user inputs "I want new running shoes," that text data will be analyzed in the next step.

[0754] Step 2:

[0755] The terminal sends the user's input data to the server.

[0756] The terminal transfers the entered text data to the server as packets using a secure communication protocol. The input data is sent to the server in its original format and forms the basis of the data the server receives.

[0757] Step 3:

[0758] The server analyzes the received data using natural language processing technology.

[0759] The server uses tools such as "spaCy" and "NLTK" to tokenize the received text data and perform syntactic analysis. This extracts context-relevant keywords and phrases. This analysis process clarifies information directly relevant to the user's needs.

[0760] Step 4:

[0761] The server retrieves the user's purchase history from the database.

[0762] The server uses a database management system (e.g., MySQL, PostgreSQL) to query the user's past purchase history and browsing information. The retrieved data is used to understand the user's preferences. This information forms the basis for the data associated with the user's needs.

[0763] Step 5:

[0764] The server generates proposals using a generated AI model.

[0765] Based on the analyzed data and acquired historical information, the server uses a generative AI model to select products and services that best suit the user's needs. The generated suggestions include explanations of the reasons for selection and their benefits in natural language. An example of a prompt might be, "The user is looking for new running shoes. Please suggest suitable products based on their past sports equipment purchase history." The data obtained in this step forms the final output suggestions.

[0766] Step 6:

[0767] The server sends suggestion data to the terminal, and the terminal displays it.

[0768] The server sends the generated suggestions to the terminal, which converts them into a display format for the user and displays them on the interface. The user can review the suggested options and make a selection or provide feedback.

[0769] Step 7:

[0770] The device sends user feedback to the server, which then performs learning.

[0771] The device sends the information and feedback selected by the user to the server. The server then applies machine learning algorithms based on this information to improve the accuracy of future suggestions. Through learning, the system continuously improves, enabling more personalized suggestions.

[0772] (Application Example 1)

[0773] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0774] The present invention aims to solve the problem of difficulty in quickly and reliably proposing products and services that are tailored to the individual needs of users. In particular, it aims to provide a more satisfying purchasing experience by allowing users to receive highly relevant suggestions based on their search behavior and past purchase history.

[0775] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0776] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; means for selecting multiple products or services based on the extracted information and the obtained information and generating suggestions including the reasons for the selection; means for transmitting and displaying the generated suggestions on the user's terminal; means for receiving feedback from the user and learning to improve the quality of suggestions for future use; means for providing a portable information device that provides an interface for the user to input search behavior and purchase history; and means for generating and displaying a list of highly relevant products based on the information input through the interface. This makes it possible to propose optimized products and services to the user.

[0777] "Text data" refers to string information entered by the user via their device.

[0778] "Natural language processing technology" refers to computer program technology that analyzes human language and understands its meaning and intent.

[0779] "Information related to the issue" refers to data that includes content related to the user's requests and objectives.

[0780] "Purchase history" refers to a record of the products and services a user has acquired to date.

[0781] "Browsing information" refers to a log of the content that a user has viewed on a digital platform.

[0782] A "database" is a digital system that systematically organizes and stores information, making it searchable and retrievable.

[0783] "Product or service" refers to goods or benefits offered to the market.

[0784] A "proposal" refers to a selection of products or services that are chosen and recommended based on the user's needs.

[0785] A "terminal" is an electronic device used by users to input and receive information.

[0786] "Portable information devices" refer to portable digital devices that have a user interface function.

[0787] A "list of highly relevant products" is a list of products that are highly relevant based on the user's past behavior and input.

[0788] To implement this invention, it is fundamental for the server to analyze text data received from the user using natural language processing technology. The server first receives user input and uses a natural language processing engine (e.g., IBM Watson NLP) to extract keywords related to the task from the text data.

[0789] Next, the server retrieves the user's past purchase history and browsing information from the database. This database is built using, for example, MySQL, allowing for efficient access to large amounts of user data.

[0790] Next, the server generates suggestions for relevant products or services based on the extracted information and historical data. This suggestion generation is achieved, for example, by using Node.js as the backend program, and by comparing the extracted keywords with the user's historical data.

[0791] The generated suggestions are then sent to the user's mobile device. The user's device has an interface developed using React Native where they can view the suggestions. This interface also provides a means to receive user input, allowing for the collection of user feedback.

[0792] For example, if a user enters "I'm looking for a party dress," the system will recommend relevant dresses based on their past browsing and purchase history, and explain the reasons for the selection. An example of a prompt to assist with this task would be, "Please suggest some dresses based on the user's purchase history for events last summer."

[0793] In this way, through the interaction between servers, terminals, and users, more optimized product and service suggestions are provided to users, resulting in an improved user experience.

[0794] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0795] Step 1:

[0796] The user uses a device to input specific needs or requests as text. The entered text data is received by the device and sent directly to the server. At this time, the input data is formatted for natural language processing.

[0797] Step 2:

[0798] The server analyzes the received text data using natural language processing techniques (e.g., IBM Watson NLP). The input is user text data, and the output extracts keywords and important phrases related to the issue. Specifically, it performs part-of-speech and semantic analysis of the text to identify words that indicate the user's needs.

[0799] Step 3:

[0800] The server retrieves the user's past purchase history and browsing information from a database (e.g., MySQL). The input is identification information such as a user ID, and the output is historical record data related to that user. This allows the server to prepare a dataset to understand the user's preferences.

[0801] Step 4:

[0802] The server initiates a process to recommend relevant products or services based on the extracted information and historical data. The input is the output data from steps 2 and 3, and the output is the selected product or service and the reason for the recommendation. Here, a generative AI model is used to score data relevance and calculate recommendation accuracy.

[0803] Step 5:

[0804] The server sends the generated suggestions to the terminal and displays them to the user. At this time, it also sends information including the reasons for the suggestions. The input is the output from step 4, and the output is the list of suggestions received by the user.

[0805] Step 6:

[0806] Users review the suggestions and make selections and provide feedback via their device. After considering the details of the selected products and services, they enter their selections or feedback.

[0807] Step 7:

[0808] The server receives feedback from the user again and learns to improve the accuracy of its suggestions. The input is user feedback, and the output is the refined suggestion generation model. Specifically, it analyzes the feedback data and optimizes the parameters of the suggestion algorithm.

[0809] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0810] This invention is a system that provides a more user-centric service by combining an emotion engine with the analysis of user input data to generate personalized suggestions. When a user inputs their needs and desires through a terminal, the terminal sends this information to a server. The server analyzes the user's input using natural language processing technology to identify the nature of the problem. It also utilizes an emotion engine to recognize the user's emotions hidden within the text. This emotion information is used to adjust the suggestions, recommending appropriate products and services that match the user's emotions.

[0811] For example, if a user sends a text message expressing an emotion such as "frustrated," the server can use its emotion engine to identify that emotion and suggest products or services that can help them relax, such as an aroma diffuser or a relaxation massage. In this way, the system makes suggestions that take the user's emotional state into account.

[0812] The server also collects data based on the user's past purchase history and browsing information to further personalize suggestions. This allows the server to present options that match the user's preferences. The suggestions are displayed to the user through their device, and the user can review them, make a selection, or provide feedback.

[0813] User selections and feedback information are sent to the server and used as learning data to improve the quality of future suggestions. This process allows the system to continuously improve the user experience. By utilizing an emotion engine, a more human-like and meaningful interaction for the user is achieved compared to conventional suggestion systems.

[0814] The following describes the processing flow.

[0815] Step 1:

[0816] Users use their devices to input information about their current concerns and desired products in natural language. This input can optionally include emotions.

[0817] Step 2:

[0818] The terminal receives user input data and sends it to the server in text format. The input data is pre-formatted as needed.

[0819] Step 3:

[0820] The server analyzes the user's text data received by the server using a natural language processing engine. This analysis helps understand the user's intent and requests, and extracts relevant keywords and issues.

[0821] Step 4:

[0822] The server uses an emotion engine to recognize the user's emotions from text data. For example, it extracts emotions such as "tired" or "excited" and adds them to the analysis results.

[0823] Step 5:

[0824] The server connects to the database to retrieve the user's past purchase and browsing history. This gathers information to understand the user's preferences and interests.

[0825] Step 6:

[0826] The server selects relevant products and services from the solution database based on the analyzed text data, sentiment data, and acquired historical information. Sentiment data is given particular importance in selecting the products and services to propose.

[0827] Step 7:

[0828] The server generates product and service proposals, including explanations of the selection criteria and emotionally resonant benefits of the proposals. The proposals are presented from multiple perspectives.

[0829] Step 8:

[0830] The server sends the generated suggestion data to the terminal, which then displays it to the user. The user can then compare and view the provided options.

[0831] Step 9:

[0832] Users can use their devices to select suggested products or services, or provide feedback indicating their desire for further suggestions.

[0833] Step 10:

[0834] The device sends the user's selections and feedback to the server. The server receives this information and uses it as training data to improve future suggestions.

[0835] Step 11:

[0836] The server uses a learning algorithm to analyze feedback and improve the accuracy of future suggestions, including sentiment information. This continuous learning process makes the system's suggestions more appropriate for the user.

[0837] (Example 2)

[0838] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0839] Conventional suggestion systems have a problem in that they struggle to provide appropriate and personalized suggestions based on user input. In particular, because they make suggestions without considering the user's emotions, the suggested content often fails to meet the user's expectations. This problem needs to be solved.

[0840] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0841] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for recognizing the user's emotions using sentiment analysis technology; and means for obtaining the user's past behavioral history and digital information from information sources. This enables more appropriate and personalized suggestions based on the user's emotions.

[0842] "User" refers to an individual or organization that receives a system or service, and is the ultimate beneficiary.

[0843] "Text data" refers to string data containing information written in natural language, and is the content entered by the user.

[0844] "Natural language processing technology" refers to techniques that enable computers to understand, interpret, and generate human language, and is used in the analysis of text data.

[0845] An "information source" refers to a reference point from which information is retrieved, such as a database or external system, and stores past behavioral history and digital information.

[0846] "Emotional analysis technology" is an analytical technique that determines the emotional state of a user from text data, and is used to adjust the content of proposals.

[0847] "Proposal" refers to a selection of products or services presented based on the user's needs and feelings.

[0848] A "terminal" refers to an electronic device used by a user for inputting information or receiving information, and includes personal computers and smartphones.

[0849] "Feedback" refers to the opinions and responses that users provide in response to suggestions and other matters, and is used to improve the system.

[0850] A "learning algorithm" refers to a computational method that allows a system to grow based on data and make more accurate suggestions.

[0851] This invention begins with the user inputting their needs and feelings as text through a terminal. The terminal immediately sends the input data to a server. The server analyzes the received text data using natural language processing techniques. The software used here includes, for example, a "natural language processing library" and a "morphological analysis engine," which are utilized to structurally understand the text.

[0852] Next, the server applies sentiment analysis technology to identify the emotions contained in the text. Software used may include "sentiment analysis tools" or "text sentiment recognition APIs." This allows the user's emotional state to be quantified or categorized.

[0853] The server further retrieves the user's past behavioral history and digital information from various sources. This process utilizes a "customer data platform" and a "history management system," and data is collected based on individual content.

[0854] Based on this information and analysis results, the server suggests products and services that best suit the user's emotions and needs. A "suggestion generation algorithm" and a "product database system" are used for this suggestion generation. The suggestions are sent to the terminal and presented visually to the user. The user can review the suggestions and provide selections or feedback.

[0855] For example, if a user inputs a desire to "connect with nature" and an emotion representing "stress," the server will suggest products and services that have a relaxing effect. For instance, this could include admission tickets to a nature park or a gardening kit. Another example of a prompt for the generating AI model is, "List relaxation methods that should be suggested when a user is feeling stressed."

[0856] User feedback is used to inform future suggestions, and the server analyzes the feedback to improve the system. This functionality is achieved through a "learning model" and a "data analysis framework." As a result, the system can continuously adapt and provide users with a more satisfying experience.

[0857] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0858] Step 1:

[0859] The user uses a device to input text about their needs and feelings. This input data represents the user's desires and current emotional state. The device then performs the specific action of sending the entered text data to the server. The input is text data, and the output is the transmission of data to the server.

[0860] Step 2:

[0861] The server analyzes the received text data using natural language processing techniques. Specifically, the server uses a "natural language processing library" to tokenize and morphologically analyze the text, thereby understanding its structure. The input is text data sent from the terminal, and the output is the analysis results indicating user needs and preferences.

[0862] Step 3:

[0863] The server uses sentiment analysis technology to recognize the user's emotional state from the analyzed text data. Specifically, it uses a sentiment analysis tool to quantify emotions from the text and classify them into desirable emotional categories. The input is the result of natural language analysis, and the output is data indicating the user's emotions.

[0864] Step 4:

[0865] The server retrieves the user's past behavioral history and digital information from various sources. Specifically, it retrieves relevant information from the database through query processing and uses the user profile information to perform personalization. The input is user identification information, and the output is the behavioral history and digital information used for personalization.

[0866] Step 5:

[0867] The server generates appropriate product and service suggestions based on emotional information, needs analysis results, and past behavioral history. Specifically, it uses a suggestion generation algorithm to evaluate and select from multiple options. The input is emotional data and user profiles, and the output is a list of suggested products and services.

[0868] Step 6:

[0869] The generated suggestions are sent to the user's device and displayed visually on the device. Specifically, the server sends the generated suggestions to the device via push notification or in real time, and the device receives them and displays them in the user interface. The input is the generated suggestion data, and the output is the result displayed to the user.

[0870] Step 7:

[0871] Users make selections and provide feedback on the displayed suggestions. Specifically, users choose suggested products or services and enter their thoughts and suggestions for improvement through a feedback form. The input consists of the user's selections and feedback, and the output is the feedback data sent to the server.

[0872] Step 8:

[0873] The server analyzes the received feedback and uses it to improve future proposals. Specifically, the feedback data is used to train a learning algorithm, improving the system's proposal accuracy. The input is user feedback data, and the output is the improved proposal model.

[0874] (Application Example 2)

[0875] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0876] Conventional recommendation systems often recommended products and services based solely on past data, without considering the user's emotions. As a result, recommendations were not tailored to the user's current emotions and needs, leading to decreased satisfaction. This invention aims to solve this problem by analyzing the user's emotional state and providing more appropriate and personalized recommendations that respond to individual emotions.

[0877] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0878] In this invention, the server includes means for analyzing text data received from a user using natural language processing technology and extracting information related to the task from the text data; means for obtaining the user's past purchase history and browsing information from a database; and means for identifying the user's emotional state using an emotion engine, in addition to the extracted and obtained information, and generating suggestions that correspond to that emotion. This makes it possible to provide suggestions that match the user's current emotions.

[0879] "Natural language processing technology" is a technology that analyzes text data from users to understand its meaning and context.

[0880] An "emotion engine" is a system or method that identifies an emotional state from user input data and provides information corresponding to that emotion.

[0881] "Purchase history" refers to data that records information about products and services that a user has purchased in the past.

[0882] A "database" is an information system that systematically stores multiple pieces of data and allows access and management as needed.

[0883] "Feedback" refers to collecting evaluations and opinions from users regarding suggestions and services they have provided.

[0884] A "learning algorithm" is a computational method used to improve the performance of a system based on collected data.

[0885] To implement this invention, a system is needed that analyzes user input data and generates personalized suggestions based on emotions. First, the user inputs their needs and desires in natural language using a device such as a smartphone. This input data is sent from the device to a server, which uses natural language processing technology to analyze the text.

[0886] Here, "natural language processing technology" refers to the technology that analyzes text data from users and understands its meaning and context.

[0887] The server uses an emotion engine to identify the user's emotional state and, based on that information, generates product and service recommendations tailored to the user. An "emotion engine" is a system or method that identifies the user's emotional state from user input data and provides information corresponding to that emotion.

[0888] Next, the suggestions are sent to the device and displayed to the user. The user reviews the displayed suggestions and provides feedback by making selections. This feedback is sent to the server and used as training data to improve future suggestions.

[0889] As a concrete example, if a user provides input such as "I've been feeling stressed lately and want to refresh myself," the server uses its emotion engine to determine that the user is seeking relaxation. As a result, it generates suggestions for relaxation-related products and services, such as aroma diffusers or relaxation spas, and displays them on the user's device.

[0890] An example of a prompt message would be: "Analyze the user's emotions, and if the input is 'I've been feeling stressed lately,' recommend a relaxation item."

[0891] This process utilizes a smartphone as hardware and employs Python libraries such as TextBlob and Scikit-learn for analysis. This allows for the analysis of user input data and the provision of optimal suggestions. This system enables personalized product recommendations tailored to the user's current emotions, providing a more satisfying experience.

[0892] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0893] Step 1:

[0894] The device receives input from the user. The user uses a smartphone to input their feelings and needs in natural language into a text box. For example, they might input something like, "I've been feeling stressed lately, so I want to relax." The entered data is then sent directly to the server.

[0895] Step 2:

[0896] The server analyzes the received user text data using natural language processing techniques. In this step, the Python library TextBlob is used to analyze the grammar and meaning of the text and identify the main point of what the user has entered. In this process, the user's problems and desires become clear. As a result, the analyzed text data is generated.

[0897] Step 3:

[0898] The server uses an emotion engine to identify the user's emotional state from the analyzed text data. For example, if the user uses the word "stress," the emotion engine recognizes it as a negative emotion. An SVM (Support Vector Machine) is used to calculate an emotion score, representing the user's emotional state numerically. The output here is the user's emotion score.

[0899] Step 4:

[0900] The server retrieves past purchase history and browsing information from the database. This data indicates the user's preferences and tendencies. Based on this, it combines the user's current emotional state with past behavioral patterns to generate more appropriate suggestions. In this step, historical data is retrieved and output.

[0901] Step 5:

[0902] The server selects products and services to suggest to the user based on their emotional score and historical data. Using a generative AI model, it proposes the product best suited to the user's state from the selected candidates. For example, relaxation goods and stress-reducing services may be presented. The selection results are output as suggestions.

[0903] Step 6:

[0904] The server sends the generated suggestions to the terminal and displays them to the user. The user can view the suggestions on their smartphone screen. After viewing the suggestions, the user selects products based on them and considers purchasing them. In this step, the suggestions are displayed visually.

[0905] Step 7:

[0906] The terminal receives user selections and feedback and sends that information to the server. Users contribute to system improvement by inputting how they felt about the suggestions and their satisfaction level. This data is then sent back to the server.

[0907] Step 8:

[0908] The server analyzes the received feedback and adjusts the system's learning algorithm based on the results. This process improves the accuracy and quality of subsequent suggestions, thereby achieving overall system optimization.

[0909] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0910] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0911] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0912] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0913] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0914] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0915] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0916] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0917] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0918] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0919] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0920] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0921] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0922] 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.

[0923] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0924] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0925] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0926] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0927] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0928] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0929] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0930] The following is further disclosed regarding the embodiments described above.

[0931] (Claim 1)

[0932] A means for analyzing text data received from users using natural language processing technology and extracting information related to the issue from said text data,

[0933] A means of obtaining a user's past purchase history and browsing information from a database,

[0934] A means for selecting multiple products or services based on the extracted information and acquired information, and for generating a proposal that includes the reasons for the selection,

[0935] A means for sending and displaying the generated proposal on the user's terminal,

[0936] A means of receiving user feedback and learning from it to improve the quality of future suggestions,

[0937] A system that includes this.

[0938] (Claim 2)

[0939] The system according to claim 1, wherein the proposal is a product or service from three different perspectives.

[0940] (Claim 3)

[0941] The system according to claim 1, further comprising analyzing user feedback and adjusting the learning algorithm based on the analysis results.

[0942] "Example 1"

[0943] (Claim 1)

[0944] A means for analyzing text data received from a user using natural language processing technology and extracting information related to the request from said text data,

[0945] A means for obtaining the user's past purchase history and browsing information from a data storage device,

[0946] A means for selecting multiple items or offerings based on the extracted information and the acquired information, and for generating a proposal that includes the reasons for the selection,

[0947] Regarding the generated proposals, a means to explain how they contribute to problem solving using the generative model,

[0948] A means for transmitting and displaying the generated proposal on the user's communication device,

[0949] A means of receiving responses from users and using machine learning to improve the quality of future suggestions,

[0950] A system that includes this.

[0951] (Claim 2)

[0952] The system according to claim 1, wherein the proposal is an item or offering from three different perspectives.

[0953] (Claim 3)

[0954] The system according to claim 1, comprising analyzing the user's response and adjusting the learning method based on the analysis results.

[0955] "Application Example 1"

[0956] (Claim 1)

[0957] A means for analyzing text data received from users using natural language processing technology and extracting information related to the issue from said text data,

[0958] A means of obtaining a user's past purchase history and browsing information from a database,

[0959] A means for selecting multiple products or services based on the extracted information and acquired information, and for generating a proposal that includes the reasons for the selection,

[0960] A means for sending and displaying the generated proposal on the user's terminal,

[0961] A means of receiving user feedback and learning from it to improve the quality of future suggestions,

[0962] A portable information device that provides an interface for users to input search behavior and purchase history,

[0963] A means for generating and displaying a list of highly relevant products based on the information entered through the interface,

[0964] A system that includes this.

[0965] (Claim 2)

[0966] The system according to claim 1, wherein the proposal is a product or service from three different perspectives.

[0967] (Claim 3)

[0968] The system according to claim 1, further comprising analyzing user feedback and adjusting the learning algorithm based on the analysis results.

[0969] "Example 2 of combining an emotion engine"

[0970] (Claim 1)

[0971] A means for analyzing text data received from users using natural language processing technology and extracting information related to the issue from said text data,

[0972] A means of recognizing a user's emotions using emotion analysis technology,

[0973] Means for obtaining the user's past behavioral history and digital information from information sources,

[0974] A means for generating suggestions corresponding to the user's emotions based on the extracted information, the emotion information, and the acquired information,

[0975] A means for sending and displaying the generated proposal on the user's terminal,

[0976] A means of receiving user feedback and learning from it to improve the quality of future suggestions,

[0977] A system that includes this.

[0978] (Claim 2)

[0979] The proposed system according to claim 1, comprising products or services from different perspectives and based on the emotional state of the user.

[0980] (Claim 3)

[0981] The system according to claim 1, further comprising analyzing the user's feedback and emotion recognition results, and adjusting the learning algorithm based on the analysis results.

[0982] "Application example 2 when combining with an emotional engine"

[0983] (Claim 1)

[0984] A means for analyzing text data received from users using natural language processing technology and extracting information related to the issue from said text data,

[0985] A means of obtaining a user's past purchase history and browsing information from a database,

[0986] In addition to the extracted information and acquired information, the means for identifying the user's emotional state using an emotion engine and generating suggestions corresponding to that emotion,

[0987] A means for sending and displaying the generated proposal on the user's terminal,

[0988] A means of receiving user feedback and learning from it to improve the quality of future suggestions,

[0989] A system that includes this.

[0990] (Claim 2)

[0991] The system according to claim 1, wherein the proposed solution is a product or service from multiple perspectives that take into account the emotional state of the user.

[0992] (Claim 3)

[0993] The system according to claim 1, further comprising analyzing the user's feedback and emotional state, and adjusting the learning algorithm based on the analysis results. [Explanation of Symbols]

[0994] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing text data received from users using natural language processing technology and extracting information related to the issue from said text data, A means of obtaining a user's past purchase history and browsing information from a database, A means for selecting multiple products or services based on the extracted information and acquired information, and for generating a proposal that includes the reasons for the selection, A means for sending and displaying the generated proposal on the user's terminal, A means of receiving user feedback and learning from it to improve the quality of future suggestions, A system that includes this.

2. The system according to claim 1, wherein the proposal is a product or service from three different perspectives.

3. The system according to claim 1, further comprising analyzing user feedback and adjusting the learning algorithm based on the analysis results.

Images