system

Abstract

We provide the system. [Solution] A means of receiving user questions in natural language, An analytical tool that analyzes the input questions and searches for related data, A generation means for generating the optimal answer based on the searched data, A means for adding referenced supporting information to the generated response, A means of presenting the answer to the user, 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 persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In window consultations, it is often the case that the person in charge cannot immediately answer questions from applicants, resulting in a problem that it takes time to provide answers. Furthermore, there may be variations in the answer content depending on the person in charge, making it difficult to provide consistent information to applicants. In order to solve these problems, there is a demand for providing a system that can answer questions efficiently and accurately.

Means for Solving the Problems

[0005] This invention provides a system that receives user questions in natural language, analyzes them, searches for relevant information, and then generates the optimal answer using an AI model. The generated answer is accompanied by the legal basis from referenced laws and manuals and presented to the user. This system reduces the time to provide an answer, improves the quality and consistency of the answer, and enables the rapid and accurate provision of information to applicants.

[0006] A "reception method" is a means of receiving questions entered by users in natural language.

[0007] "Analysis tools" are means for analyzing the entered questions and retrieving relevant data.

[0008] "Generation means" refers to the means for generating the optimal response based on the retrieved data.

[0009] "Method of adding information" refers to a means of adding referenced supporting information to the generated response.

[0010] "Presentation method" refers to the means of presenting the generated answer to the user.

[0011] A "database" is a recording medium used to pre-register and store laws and manuals.

[0012] An "additional question" is a question that the user asks for further details based on the initial answer provided. [Brief explanation of the drawing]

[0013] [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] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example [1]. [Figure 12] It 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 Example [2] when an 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 an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] 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.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention begins with a user inputting a question in natural language through a terminal. The terminal functions as a receiving device, and once a question is entered, it is sent to a server. The server analyzes the received question using natural language processing technology as an analysis device. The information obtained from the analysis is used to quickly retrieve relevant data based on the content of the question.

[0035] The server searches the database for laws, past cases, and manual data, and constructs the optimal answer based on the information obtained using generation methods. The server then adds specific supporting information from the laws and manuals used to the generated answer using an annotation method, and presents it to the user based on that content. This presentation is again done via the terminal, providing the user with accurate and timely information.

[0036] As a concrete example, let's consider a scenario where a user asks, "Please tell me about the procedures required under the new Building Standards Act." The terminal receives this question, and the server analyzes it according to the means of the present invention. It searches the database for relevant legal data and generates the optimal answer using an AI model. The answer includes the details of the procedure, along with which law it is based on and the specific article number. In this way, the user can quickly obtain the necessary procedural information.

[0037] In addition, if a user requires further clarification of the information presented, they can ask additional questions. These additional questions are also entered in natural language, and the answers are generated through the same process. As described above, the embodiment of the present invention makes it possible to always provide accurate and prompt answers to questions at the counter, thereby achieving operational efficiency.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user accesses the device and enters a question in natural language. The entered data is sent from the device to the server.

[0041] Step 2:

[0042] The server receives the question sent from the terminal. Natural language processing techniques are used to analyze the question. Through analysis, keywords and context of the question are extracted, and the intent of the question is identified.

[0043] Step 3:

[0044] The server searches the database based on the analysis results. The database contains relevant laws, manuals, and past cases, allowing it to quickly identify data that matches the keywords of the query.

[0045] Step 4:

[0046] The server uses a generative AI model to construct the optimal answer based on the information obtained through the search. The answer includes not only direct information related to the question, but also supplementary information to present relevant evidence.

[0047] Step 5:

[0048] The server adds specific supporting information, such as the section and paragraph numbers of the laws and manuals it referenced, to the answers it generates. This supporting information allows users to verify the reliability of the answers.

[0049] Step 6:

[0050] The server sends the completed answer to the terminal, which then displays it to the user. The user can then review the answer on the screen and obtain information related to the question.

[0051] Step 7:

[0052] The user can ask additional questions about the provided answers as needed. These additional questions are sent again from the device, and a new answer is generated through the same processing steps.

[0053] (Example 1)

[0054] 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."

[0055] There is a need for a system that can provide users with quick and accurate answers to their questions regarding laws and guidelines. However, conventional systems have problems with reliability because they take time to analyze user questions, search for relevant information, and generate optimal answers, and often do not include specific supporting information in the answers.

[0056] 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.

[0057] In this invention, the server includes means for analyzing the user's question using natural language processing technology, means for retrieving relevant information from a data store based on the analysis results, and means for using a generative model to construct the optimal answer based on the search results. This enables the user to obtain a quick, accurate answer with specific supporting information.

[0058] A "user" refers to someone who uses the system to input questions and receive answers.

[0059] "Language" refers to natural language, and is the format of information input via a terminal.

[0060] A "terminal" refers to a device that allows a user to input a question and receive an answer from a server.

[0061] A "server" is a computing unit that receives information sent from a terminal and performs analysis, retrieval, and generation.

[0062] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0063] "Analysis" refers to the process of understanding the linguistic information received from the user and clarifying its intent.

[0064] "Related information" refers to data related to the user's question, identified based on the analysis results.

[0065] A "data store" is an information aggregation location where relevant information such as laws and guidelines are registered in advance.

[0066] "Searching" refers to the process of finding specific, relevant information from a data store.

[0067] A "generative model" refers to an algorithm that generates the most appropriate sentence or response based on the input information.

[0068] "Supporting information" refers to specific references added to a generated response to support its accuracy and reliability.

[0069] The user first inputs a question in natural language using a terminal. The terminal formats this user input appropriately and sends it to the server using a communication protocol. The server analyzes the received input data using one of several natural language processing technologies. The analysis uses a generative AI model (for example, a model for natural language processing) to understand the intent of the input question.

[0070] Next, the server searches a data store containing pre-registered laws and guidelines based on the analysis results. This search process executes database queries to quickly extract relevant items.

[0071] After the search is complete, the server uses a generative AI model to generate the most suitable answer based on the searched information. Before providing the generated answer to the user, supporting information is added and the format is edited to include legal codes and relevant guideline sections.

[0072] The server then sends the completed response to the terminal, which displays the result to the user. The display format is designed to be easily understood by the user.

[0073] As a concrete example, if a user enters "Please tell me about the procedures required under the new Building Standards Act" into their terminal, the system will begin analysis. It will then extract relevant legal data from its data store and use a generating AI model to create detailed procedural guidance based on that information. The final response will include the details of the procedure, along with the specific legal provision and article number. In this way, users can quickly obtain the necessary procedural information.

[0074] This embodiment of the invention enables users to immediately access the information they need, thereby achieving efficient and effective response provision.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1: The user enters the question in natural language through the terminal. The entered data is stored on the terminal as text. This text will serve as the basic input for subsequent processes. The terminal appropriately encodes this input and prepares it to be sent to the server.

[0077] Step 2: The terminal uses a communication protocol to send the entered text data to the server, delivering the encoded data over the network to the server. The output here is the question data that has been accurately transmitted to the server.

[0078] Step 3: The server uses natural language processing techniques to analyze the received input data. A generative AI model is activated to understand the intent of the question, breaking down the text data into tokens and extracting relevant keywords and phrases. The output of this step is the analyzed tokenized data and its intent.

[0079] Step 4: Based on the analysis results, the server searches the data store for relevant information. The server generates database queries to quickly extract information related to laws and guidelines. The output obtained here is a dataset related to the user's question.

[0080] Step 5: The server uses the information obtained from the search and constructs the optimal answer using a generative AI model. It integrates multiple data points to generate a logical and consistent answer. The output of this process is the answer text that should be provided to the user.

[0081] Step 6: The server adds supporting information to the generated response. It adds legal code numbers and relevant guideline sections to the response to increase its reliability. This step outputs a final response with supporting information added.

[0082] Step 7: The server sends the completed answer to the terminal. The terminal displays the received data in a format suitable for the user interface, presenting it visually to the user. The user reviews the answer on the screen and considers additional questions as needed. The output of this step is the answer information that the user can view directly.

[0083] (Application Example 1)

[0084] 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."

[0085] In recent years, with the advancement of information technology, companies and organizations are required to acquire information quickly and accurately. However, information such as laws and guidelines is vast, and security-related information in particular is updated frequently, making it difficult to reliably grasp its contents. Therefore, a system is needed that allows employees to easily obtain the latest information and take appropriate action quickly.

[0086] 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.

[0087] In this invention, the server includes an information processing means for inputting information requests from users in natural language, an analysis means for analyzing the input information requests and searching for relevant information, and a response formation means for generating an optimal response based on the retrieved information. This enables employees to request information in natural language and quickly obtain accurate information based on the latest laws and guidelines.

[0088] An "information request" is a natural language query submitted by a user to obtain specific information.

[0089] "Information processing means" refers to technology for receiving and appropriately processing information requests from users.

[0090] "Analysis means" refers to a technology that analyzes input information requests using natural language processing techniques and retrieves relevant information.

[0091] "Response formation means" refers to a technology for generating an optimal response based on analyzed information.

[0092] "Element addition means" refers to a technique for adding supplementary information, such as supporting information, to a generated response.

[0093] "Communication methods" refer to technologies for appropriately conveying the generated response to the user.

[0094] An "information processing device" is a device that includes the means described above and provides predetermined information in response to a user's information request.

[0095] A "data storage device" is a device used to register and store information such as laws and guidelines in advance.

[0096] The system for implementing this invention consists of a terminal that receives information requests from users in natural language and a server that analyzes the information and generates a response. The terminal functions as a mobile device such as a smartphone and is designed to receive user information requests via an interface. Once the user enters an information request, the terminal sends it to the server.

[0097] The server uses natural language processing (NLP) tools such as BERT and spaCy to analyze information requests and quickly retrieve relevant information from the database. This analysis allows the server to understand the context and accurately extract information such as laws and guidelines.

[0098] Next, the server generates the optimal response based on the analysis results. Utilizing a generative AI model, a comprehensive answer is created from the collected data. This response includes relevant supporting information, such as references to specific legal norms or provisions. The generated response helps the user take appropriate action.

[0099] The response generated by the server is presented to the user via the terminal. This allows the user to obtain information quickly and accurately. For example, if an employee enters a prompt such as "Please tell me about the latest security protocol changes," the server can provide information on the latest regulations and protocols.

[0100] This system enables rapid information sharing within companies and organizations, making compliance and adherence to guidelines, particularly in the security field, much smoother.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The user enters information requests in natural language using a terminal. This input data is in text format and is sent to the terminal as a prompt. The terminal converts this input into the appropriate format and prepares it for transmission to the server.

[0104] Step 2:

[0105] When a terminal receives an information request from a user, it sends it to the server. The server first receives this input data and preprocesses it into a format suitable for database querying. This preprocessing includes text tokenization and tagging as needed.

[0106] Step 3:

[0107] The server uses natural language processing tools (e.g., spaCy, BERT) to analyze the received information request. It extracts relevant keywords and phrases from the analyzed data and generates a database search query based on these. The query is then generated as output.

[0108] Step 4:

[0109] The server executes the generated query against the database to retrieve relevant information. This database contains laws and guidelines that have been pre-registered, and the relevant information is output as a search result.

[0110] Step 5:

[0111] The server uses a generative AI model to generate responses based on search results. The generative model collects necessary information from the input query and creates a comprehensive answer. The output includes the answer along with relevant supporting information.

[0112] Step 6:

[0113] The generated response is sent from the server to the terminal, which then displays it to the user. The user then uses this information to take specific actions or make decisions. For example, the terminal displays a response to the prompt, "Please tell me about the latest security protocol changes."

[0114] 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.

[0115] This invention is a system that combines user emotion recognition with user inquiry handling. When a user inputs a question in natural language using a terminal, the input data is first analyzed by an emotion engine to determine the user's emotion. The emotion engine analyzes the context and expression of the question to identify whether the user is, for example, angry, irritated, or confused.

[0116] The server receives the results from the emotion engine and uses analysis tools to search for relevant data, taking into account both the content of the question and the user's emotions. The server then uses the obtained information to construct the optimal answer through a generation tool. In this generation process, the answer is adjusted according to the emotion. For example, if the user is expressing dissatisfaction, the answer will be written using more polite and reassuring language.

[0117] The answers are accompanied by supporting information, increasing their reliability. This information is added through various means, such as specifically citing laws, manuals, and relevant chapters.

[0118] The user receives the presented answers through their device. The server uses a presentation method to display the answers in a format that matches the user's emotions. Based on the presented information, the user can input additional information if they have further questions. Similarly, emotions are recognized and a corresponding process is performed for these additional questions.

[0119] As a concrete example, suppose a user asks an irritated question such as, "Why is this procedure so complicated?" The emotion engine recognizes this irritation, and the server analyzes it using analytical tools and retrieves appropriate information from the database. In the generated response, the server conveys a message that takes the user's feelings into consideration, such as, "Each step of the procedure is based on Law XX and is in order to protect the user's safety and rights. We apologize for the inconvenience, but we will do our best to respond as quickly as possible."

[0120] This form goes beyond mere information provision, enabling communication that responds to the user's emotions and achieving higher customer satisfaction.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The user enters the question in natural language using a terminal. The terminal processes the input as a means of reception and sends it to the server.

[0124] Step 2:

[0125] The server inputs the question received from the terminal into the emotion engine. The emotion engine analyzes the content of the question and detects the user's emotions. For example, it identifies emotional states such as joy, anger, and anxiety.

[0126] Step 3:

[0127] The server receives the results from the sentiment engine and uses analytical tools to analyze the question content and detected sentiment. It understands the intent of the question and extracts relevant keywords.

[0128] Step 4:

[0129] Based on the analysis results, the server searches the database and extracts relevant information. The database includes laws, manuals, and past case data.

[0130] Step 5:

[0131] The server uses a generation mechanism to construct a response based on the retrieved information. During this process, the response is adjusted according to the emotions recognized by the emotion engine. For example, careful and empathetic language is selected to reflect the user's feelings.

[0132] Step 6:

[0133] The server uses an annotation mechanism to add referenced supporting information, such as the article number of a law or a detailed explanation, to the generated response.

[0134] Step 7:

[0135] The server sends the completed answer to the terminal via a presentation device, and the terminal displays it to the user. The displayed answer is presented in a format that takes the user's feelings into consideration.

[0136] Step 8:

[0137] The user can ask additional questions about the provided answers as needed. These additional questions are also accepted by the terminal, and the same processing flow is repeated.

[0138] (Example 2)

[0139] 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".

[0140] Traditional information delivery systems lack personalized responses that cater to user emotions, leading to decreased user satisfaction. Furthermore, there is a need to improve the reliability of the responses provided.

[0141] 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.

[0142] In this invention, the server includes an input means, an emotion recognition means, an information retrieval means, a generation means, an information addition means, and a display means. This enables the provision of personalized responses that correspond to the user's emotions and the presentation of highly reliable information.

[0143] An "input device" is a device that has the function of receiving questions from the user in natural language and transmitting them to the analysis device.

[0144] An "emotion recognition device" is a device that analyzes the context of an input question and has the function of identifying the user's emotional state.

[0145] An "information retrieval device" is a device that has the function of retrieving relevant information based on the user's question and perceived emotions.

[0146] A "generation means" is a device that has the function of constructing the optimal answer using a generation AI model based on the retrieved information.

[0147] An "information-adding device" is a device that has the function of adding supporting information to the generated response to increase its reliability.

[0148] A "display means" is a device that has the function of presenting the generated response to the user in a format appropriate to the user's emotions.

[0149] This invention is a system that utilizes natural language processing and emotion recognition technologies to respond to user inquiries. When a user inputs a question in natural language using a terminal, the system analyzes the question and identifies the user's emotions.

[0150] The server uses a natural language processing library as its emotion recognition engine. Specifically, it can utilize tools such as the Natural Language Processing Toolkit (NLTK) and TextBlob to analyze the context of the input text and determine the user's emotional state (e.g., anger, frustration, confusion).

[0151] The server considers the content and emotional state of the user's question and uses an information search engine to retrieve relevant information from the database. For database management, relational database management systems (RDBMS) such as MySQL® and PostgreSQL are used.

[0152] Subsequently, the server uses a generative AI model to generate the optimal response. By using generative AI such as the OpenAI® API, it adjusts the tone according to specific emotions, constructing a response that is considerate of the user's feelings. In this process, supporting information from laws and manuals is added to ensure the reliability of the response, and it is presented to the user in an easy-to-understand manner.

[0153] For example, if a user enters a question expressing frustration, such as "Why is this procedure so complicated?", the system recognizes this emotion, the server retrieves relevant information from the database, and the AI ​​model generates a response such as, "Each step of the procedure is based on Law XX and is designed to protect the user's safety and rights. We apologize for any inconvenience, but we will do our best to respond promptly." This allows for a response that is appropriate to the user's emotions.

[0154] An example of a prompt message to input into a generative AI model might be: "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure."

[0155] This system enables more personalized communication that responds to user emotions, which is expected to improve customer satisfaction.

[0156] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0157] Step 1:

[0158] The user inputs questions using natural language through the terminal. This input process generates unstructured text data. The terminal then sends this text data to a server for analysis.

[0159] Step 2:

[0160] The server analyzes the received text data using natural language processing libraries (e.g., NLTK or TextBlob) as a means of sentiment recognition. This analysis extracts the emotional characteristics of the text. Specifically, it determines the user's emotional state (e.g., anger, frustration, confusion) from the text and outputs the result as sentiment data.

[0161] Step 3:

[0162] The server uses information retrieval methods based on the user's question content and sentiment data, and searches for relevant information using a data management system (e.g., MySQL or PostgreSQL). By executing SQL queries, the server extracts appropriate information from the database that matches the user's question and outputs it as search result data.

[0163] Step 4:

[0164] The server uses a generative AI model (e.g., OpenAI API) to generate responses appropriate to the user's emotions based on search result data. During this process, prompt text (e.g., "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure.") is input, and the generated text is tone-adjusted. The generated answer is then output as response data.

[0165] Step 5:

[0166] The server uses information enhancement tools to incorporate supporting information such as laws and manuals to add reliability to the response data. This supplementary process results in more reliable responses, which are then output as presented data.

[0167] Step 6:

[0168] The server sends the final presentation data to the terminal. The terminal displays the response to the user in a format that is appropriate to their emotions. Based on this information, the user can ask further questions if necessary.

[0169] (Application Example 2)

[0170] 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".

[0171] Conventional user inquiry systems typically provide impersonal responses without considering the user's emotions, and are particularly incapable of adequately addressing emotionally charged inquiries, thus posing a challenge to improving customer satisfaction. When users contact an e-commerce site with anxieties or dissatisfactions, it is necessary to understand their emotions and respond appropriately, but this has not been adequately achieved with current technologies.

[0172] 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.

[0173] In this invention, the server includes emotion analysis means for analyzing user questions and their context and recognizing emotions; analysis means for searching for relevant information based on the analyzed questions and emotions; and providing means for attaching referenced supporting information to the generated answers. This enables flexible and appropriate responses in accordance with the user's emotions, thereby improving customer satisfaction.

[0174] A "reception mechanism" is an interface for receiving questions from users in natural language.

[0175] An "emotion analysis device" is a processing device that analyzes an input question and its context to recognize the user's emotions.

[0176] "Analysis tools" refer to devices and software used to retrieve relevant information based on the sentiment analysis results and the content of the questions.

[0177] A "generation means" is a device that has the function of constructing the optimal response based on retrieved information and recognized emotions.

[0178] "Methods for adding information" refer to techniques for adding supporting evidence to generated responses to enhance their reliability.

[0179] A "presentation method" is an interface for presenting answers in a format that responds to the user's emotions.

[0180] This system aims to automatically process user inquiries based on their sentiment. The entire system consists of a server, user terminals, sentiment analyzers, a database, and an interface.

[0181] When a user enters a query in natural language using a terminal, that data is sent to the server. The server analyzes the input data using sentiment analysis tools to identify the user's emotions. This process utilizes a sentiment analysis engine. The sentiment engine analyzes the context and expression of the user's question to determine whether the user is angry, confused, or otherwise feeling something.

[0182] Next, the server uses analytical tools to search for relevant information in the database based on the analysis results. After collecting the information, a generation tool generates a response based on this information and in a manner that is appropriate to the user's emotions. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite in order to provide reassurance.

[0183] Supporting information is provided with the response. This supporting information, such as laws and operating procedures, is obtained from a database and attached to the response using a designated method. This increases the reliability of the response.

[0184] Ultimately, the server uses a presentation mechanism to display the answer to the user in an emotionally appropriate format. This display allows the user to be satisfied with the information provided and to enter further questions if necessary. In this case, the further questions are also processed.

[0185] As a concrete example, consider a scenario where a user becomes frustrated because their order hasn't arrived on an online shopping site and contacts customer support. The emotion engine identifies the emotion as "frustration," and the server analyzes the situation using analytical tools to obtain appropriate information regarding delivery. Then, a generation tool constructs an emotionally sensitive response such as, "We apologize for the delay. We will investigate immediately and take appropriate action."

[0186] An example of a prompt message would be: "I want to design an AI assistant that can determine the user's emotions in response to their inquiries and consider an appropriate response. If the user inputs 'I'm frustrated because the delivery is late,' I want it to analyze their emotions and generate a response that shows empathy while promising prompt support."

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The user enters a query in natural language using a terminal. This input data is then prepared for processing by the sentiment analysis engine. In this process, the input is the user's natural language text, and the output is text data ready for analysis.

[0190] Step 2:

[0191] The server uses an emotion analysis engine to analyze the user's input data and recognize their emotions. The input is the text data prepared in step 1, and the output is the user's emotion information. As part of the data processing, contextual analysis and expression analysis are performed on the input text, and an emotion determination algorithm is applied.

[0192] Step 3:

[0193] The server uses analytical tools to retrieve relevant information based on sentiment information. The input is the sentiment information obtained in step 2 and the original query text, and the output is data related to the query content. This data is retrieved from a database. Sentiment-intensive search queries are used for data calculation.

[0194] Step 4:

[0195] The generation mechanism generates the optimal response based on the data and sentiment information retrieved by the server. The input is the search results and sentiment information from step 3, and the output is the optimized response text. Specifically, the generation AI model constructs a unique response.

[0196] Step 5:

[0197] The annotation method attaches supporting information to the generated response. The input is the response generated in step 4, and the output is the response text with the supporting information attached. Specifically, a process is executed to attach reference information from relevant laws and procedures.

[0198] Step 6:

[0199] The server uses a presentation mechanism to display the answer to the user. The input is the answer text formatted in step 5, and the output is the final answer displayed on the user's terminal. Specifically, the message is displayed in a tone that corresponds to the user's emotions.

[0200] Step 7:

[0201] The user can enter additional questions, which are then processed again through a similar process. The input is a newly entered natural language question, and the process restarts from step 1. The server performs a new analysis, taking into account the previous sentiment analysis.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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".

[0218] This invention begins with a user inputting a question in natural language through a terminal. The terminal functions as a receiving device, and once a question is entered, it is sent to a server. The server analyzes the received question using natural language processing technology as an analysis device. The information obtained from the analysis is used to quickly retrieve relevant data based on the content of the question.

[0219] The server searches the database for laws, past cases, and manual data, and constructs the optimal answer based on the information obtained using generation methods. The server then adds specific supporting information from the laws and manuals used to the generated answer using an annotation method, and presents it to the user based on that content. This presentation is again done via the terminal, providing the user with accurate and timely information.

[0220] As a concrete example, let's consider a scenario where a user asks, "Please tell me about the procedures required under the new Building Standards Act." The terminal receives this question, and the server analyzes it according to the means of the present invention. It searches the database for relevant legal data and generates the optimal answer using an AI model. The answer includes the details of the procedure, along with which law it is based on and the specific article number. In this way, the user can quickly obtain the necessary procedural information.

[0221] In addition, if a user requires further clarification of the information presented, they can ask additional questions. These additional questions are also entered in natural language, and the answers are generated through the same process. As described above, the embodiment of the present invention makes it possible to always provide accurate and prompt answers to questions at the counter, thereby achieving operational efficiency.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user accesses the device and enters a question in natural language. The entered data is sent from the device to the server.

[0225] Step 2:

[0226] The server receives the question sent from the terminal. Natural language processing techniques are used to analyze the question. Through analysis, keywords and context of the question are extracted, and the intent of the question is identified.

[0227] Step 3:

[0228] The server searches the database based on the analysis results. The database contains relevant laws, manuals, and past cases, allowing it to quickly identify data that matches the keywords of the query.

[0229] Step 4:

[0230] The server uses a generative AI model to construct the optimal answer based on the information obtained through the search. The answer includes not only direct information related to the question, but also supplementary information to present relevant evidence.

[0231] Step 5:

[0232] The server adds specific supporting information, such as the section and paragraph numbers of the laws and manuals it referenced, to the answers it generates. This supporting information allows users to verify the reliability of the answers.

[0233] Step 6:

[0234] The server sends the completed answer to the terminal, which then displays it to the user. The user can then review the answer on the screen and obtain information related to the question.

[0235] Step 7:

[0236] The user can ask additional questions about the provided answers as needed. These additional questions are sent again from the device, and a new answer is generated through the same processing steps.

[0237] (Example 1)

[0238] 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 glasses 214 will be referred to as the "terminal."

[0239] There is a need for a system that can provide users with quick and accurate answers to their questions regarding laws and guidelines. However, conventional systems have problems with reliability because they take time to analyze user questions, search for relevant information, and generate optimal answers, and often do not include specific supporting information in the answers.

[0240] 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.

[0241] In this invention, the server includes means for analyzing the user's question using natural language processing technology, means for retrieving relevant information from a data store based on the analysis results, and means for using a generative model to construct the optimal answer based on the search results. This enables the user to obtain a quick, accurate answer with specific supporting information.

[0242] A "user" refers to someone who uses the system to input questions and receive answers.

[0243] "Language" refers to natural language, and is the format of information input via a terminal.

[0244] A "terminal" refers to a device that allows a user to input a question and receive an answer from a server.

[0245] A "server" is a computing unit that receives information sent from a terminal and performs analysis, retrieval, and generation.

[0246] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0247] "Analysis" refers to the process of understanding the linguistic information received from the user and clarifying its intent.

[0248] "Related information" refers to data related to the user's question, identified based on the analysis results.

[0249] A "data store" is an information aggregation location where relevant information such as laws and guidelines are registered in advance.

[0250] "Searching" refers to the process of finding specific, relevant information from a data store.

[0251] A "generative model" refers to an algorithm that generates the most appropriate sentence or response based on the input information.

[0252] "Supporting information" refers to specific references added to a generated response to support its accuracy and reliability.

[0253] The user first inputs a question in natural language using a terminal. The terminal formats this user input appropriately and sends it to the server using a communication protocol. The server analyzes the received input data using one of several natural language processing technologies. The analysis uses a generative AI model (for example, a model for natural language processing) to understand the intent of the input question.

[0254] Next, the server searches a data store containing pre-registered laws and guidelines based on the analysis results. This search process executes database queries to quickly extract relevant items.

[0255] After the search is complete, the server uses a generative AI model to generate the most suitable answer based on the searched information. Before providing the generated answer to the user, supporting information is added and the format is edited to include legal codes and relevant guideline sections.

[0256] The server then sends the completed response to the terminal, which displays the result to the user. The display format is designed to be easily understood by the user.

[0257] As a concrete example, if a user enters "Please tell me about the procedures required under the new Building Standards Act" into their terminal, the system will begin analysis. It will then extract relevant legal data from its data store and use a generating AI model to create detailed procedural guidance based on that information. The final response will include the details of the procedure, along with the specific legal provision and article number. In this way, users can quickly obtain the necessary procedural information.

[0258] This embodiment of the invention enables users to immediately access the information they need, thereby achieving efficient and effective response provision.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1: The user enters the question in natural language through the terminal. The entered data is stored on the terminal as text. This text will serve as the basic input for subsequent processes. The terminal appropriately encodes this input and prepares it to be sent to the server.

[0261] Step 2: The terminal uses a communication protocol to send the entered text data to the server, delivering the encoded data over the network to the server. The output here is the question data that has been accurately transmitted to the server.

[0262] Step 3: The server uses natural language processing techniques to analyze the received input data. A generative AI model is activated to understand the intent of the question, breaking down the text data into tokens and extracting relevant keywords and phrases. The output of this step is the analyzed tokenized data and its intent.

[0263] Step 4: Based on the analysis results, the server searches the data store for relevant information. The server generates database queries to quickly extract information related to laws and guidelines. The output obtained here is a dataset related to the user's question.

[0264] Step 5: The server uses the information obtained from the search and constructs the optimal answer using a generative AI model. It integrates multiple data points to generate a logical and consistent answer. The output of this process is the answer text that should be provided to the user.

[0265] Step 6: The server adds supporting information to the generated response. It adds legal code numbers and relevant guideline sections to the response to increase its reliability. This step outputs a final response with supporting information added.

[0266] Step 7: The server sends the completed answer to the terminal. The terminal displays the received data in a format suitable for the user interface, presenting it visually to the user. The user reviews the answer on the screen and considers additional questions as needed. The output of this step is the answer information that the user can view directly.

[0267] (Application Example 1)

[0268] 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."

[0269] In recent years, with the advancement of information technology, companies and organizations are required to acquire information quickly and accurately. However, information such as laws and guidelines is vast, and security-related information in particular is updated frequently, making it difficult to reliably grasp its contents. Therefore, a system is needed that allows employees to easily obtain the latest information and take appropriate action quickly.

[0270] 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.

[0271] In this invention, the server includes an information processing means for inputting information requests from users in natural language, an analysis means for analyzing the input information requests and searching for relevant information, and a response formation means for generating an optimal response based on the retrieved information. This enables employees to request information in natural language and quickly obtain accurate information based on the latest laws and guidelines.

[0272] An "information request" is a natural language query submitted by a user to obtain specific information.

[0273] "Information processing means" refers to technology for receiving and appropriately processing information requests from users.

[0274] "Analysis means" refers to a technology that analyzes input information requests using natural language processing techniques and retrieves relevant information.

[0275] "Response formation means" refers to a technology for generating an optimal response based on analyzed information.

[0276] "Element addition means" refers to a technique for adding supplementary information, such as supporting information, to a generated response.

[0277] "Communication methods" refer to technologies for appropriately conveying the generated response to the user.

[0278] An "information processing device" is a device that includes the means described above and provides predetermined information in response to a user's information request.

[0279] A "data storage device" is a device used to register and store information such as laws and guidelines in advance.

[0280] The system for implementing this invention consists of a terminal that receives information requests from users in natural language and a server that analyzes the information and generates responses. The terminal functions as a mobile device such as a smartphone and is designed to input the user's information request via an interface. When the user inputs an information request, the terminal sends it to the server.

[0281] The server analyzes the information request using natural language processing technology and quickly retrieves relevant information from the database. For analysis, NLP (Natural Language Processing) tools such as BERT or spaCy are used. This enables the server to understand the context and accurately extract information such as laws and regulations.

[0282] Next, the server generates an optimal response based on the analysis results. Utilizing a generative AI model, a comprehensive answer is created from the collected data. This response includes relevant reference information, such as references to specific laws and regulations. The generated response helps the user to take appropriate actions.

[0283] The response generated by the server is presented to the user through the terminal. This allows the user to obtain information quickly and accurately. As a specific example, when an employee inputs a prompt sentence such as "Please tell me the changes in the latest security protocols", the server can present information regarding the latest regulations and protocols.

[0284] This system enables rapid information sharing in enterprises and organizations, and particularly makes compliance with security regulations and guidelines smoother.

[0285] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0286] Step 1:

[0287] The user enters information requests in natural language using a terminal. This input data is in text format and is sent to the terminal as a prompt. The terminal converts this input into the appropriate format and prepares it for transmission to the server.

[0288] Step 2:

[0289] When a terminal receives an information request from a user, it sends it to the server. The server first receives this input data and preprocesses it into a format suitable for database querying. This preprocessing includes text tokenization and tagging as needed.

[0290] Step 3:

[0291] The server uses natural language processing tools (e.g., spaCy, BERT) to analyze the received information request. It extracts relevant keywords and phrases from the analyzed data and generates a database search query based on these. The query is then generated as output.

[0292] Step 4:

[0293] The server executes the generated query against the database to retrieve relevant information. This database contains laws and guidelines that have been pre-registered, and the relevant information is output as a search result.

[0294] Step 5:

[0295] The server uses a generative AI model to generate responses based on search results. The generative model collects necessary information from the input query and creates a comprehensive answer. The output includes the answer along with relevant supporting information.

[0296] Step 6:

[0297] The generated response is sent from the server to the terminal, which then displays it to the user. The user then uses this information to take specific actions or make decisions. For example, the terminal displays a response to the prompt, "Please tell me about the latest security protocol changes."

[0298] 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.

[0299] This invention is a system that combines user emotion recognition with user inquiry handling. When a user inputs a question in natural language using a terminal, the input data is first analyzed by an emotion engine to determine the user's emotion. The emotion engine analyzes the context and expression of the question to identify whether the user is, for example, angry, irritated, or confused.

[0300] The server receives the results from the emotion engine and uses analysis tools to search for relevant data, taking into account both the content of the question and the user's emotions. The server then uses the obtained information to construct the optimal answer through a generation tool. In this generation process, the answer is adjusted according to the emotion. For example, if the user is expressing dissatisfaction, the answer will be written using more polite and reassuring language.

[0301] The answers are accompanied by supporting information, increasing their reliability. This information is added through various means, such as specifically citing laws, manuals, and relevant chapters.

[0302] The user receives the presented answers through their device. The server uses a presentation method to display the answers in a format that matches the user's emotions. Based on the presented information, the user can input additional information if they have further questions. Similarly, emotions are recognized and a corresponding process is performed for these additional questions.

[0303] As a specific example, suppose a user asks a frustrated question like "Why is this procedure so cumbersome?" The emotion engine recognizes this frustration, and the server analyzes it using analysis means and retrieves appropriate information from the database. In the generated response, the server conveys content that takes into account the user's emotions, such as "Each step of the procedure is based on Statute XX and is for the protection of the user's safety and rights. It may be inconvenient, but we will strive to respond promptly."

[0304] In this form, the present invention goes beyond mere information provision, enables communication according to the user's emotions, and achieves higher customer satisfaction.

[0305] The processing flow will be described below.

[0306] Step 1:

[0307] The user inputs a question in natural language using the terminal. The input is processed by the terminal as reception means and sent to the server.

[0308] Step 2:

[0309] The server inputs the question received from the terminal into the emotion engine. The emotion engine analyzes the content of the question and detects the user's emotion. For example, it identifies emotional states such as joy, anger, and anxiety.

[0310] Step 3:

[0311] The server receives the result of the emotion engine and analyzes the content of the question and the detected emotion using analysis means. It understands the intention of the question and extracts relevant keywords.

[0312] Step 4:

[0313] Based on the analysis result, the server searches the database to extract relevant information. The database includes statutes, manuals, and past case data.

[0314] Step 5:

[0315] The server uses a generation mechanism to construct a response based on the retrieved information. During this process, the response is adjusted according to the emotions recognized by the emotion engine. For example, careful and empathetic language is selected to reflect the user's feelings.

[0316] Step 6:

[0317] The server uses an annotation mechanism to add referenced supporting information, such as the article number of a law or a detailed explanation, to the generated response.

[0318] Step 7:

[0319] The server sends the completed answer to the terminal via a presentation device, and the terminal displays it to the user. The displayed answer is presented in a format that takes the user's feelings into consideration.

[0320] Step 8:

[0321] The user can ask additional questions about the provided answers as needed. These additional questions are also accepted by the terminal, and the same processing flow is repeated.

[0322] (Example 2)

[0323] 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".

[0324] Traditional information delivery systems lack personalized responses that cater to user emotions, leading to decreased user satisfaction. Furthermore, there is a need to improve the reliability of the responses provided.

[0325] 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.

[0326] In this invention, the server includes an input means, an emotion recognition means, an information retrieval means, a generation means, an information addition means, and a display means. This enables the provision of personalized responses that correspond to the user's emotions and the presentation of highly reliable information.

[0327] An "input device" is a device that has the function of receiving questions from the user in natural language and transmitting them to the analysis device.

[0328] An "emotion recognition device" is a device that analyzes the context of an input question and has the function of identifying the user's emotional state.

[0329] An "information retrieval device" is a device that has the function of retrieving relevant information based on the user's question and perceived emotions.

[0330] A "generation means" is a device that has the function of constructing the optimal answer using a generation AI model based on the retrieved information.

[0331] An "information-adding device" is a device that has the function of adding supporting information to the generated response to increase its reliability.

[0332] A "display means" is a device that has the function of presenting the generated response to the user in a format appropriate to the user's emotions.

[0333] This invention is a system that utilizes natural language processing and emotion recognition technologies to respond to user inquiries. When a user inputs a question in natural language using a terminal, the system analyzes the question and identifies the user's emotions.

[0334] The server uses a natural language processing library as its emotion recognition engine. Specifically, it can utilize tools such as the Natural Language Processing Toolkit (NLTK) and TextBlob to analyze the context of the input text and determine the user's emotional state (e.g., anger, frustration, confusion).

[0335] The server considers the content and emotional state of the user's question and uses an information search engine to retrieve relevant information from the database. For database management, relational database management systems (RDBMS) such as MySQL or PostgreSQL are used.

[0336] Subsequently, the server utilizes a generative AI model to generate the optimal response. By using generative AI such as the OpenAI API, it adjusts the tone according to specific emotions, constructing a response that is sensitive to the user's feelings. In this process, supporting information from laws and manuals is added to ensure the reliability of the response, and it is presented to the user in an easy-to-understand manner.

[0337] For example, if a user enters a question expressing frustration, such as "Why is this procedure so complicated?", the system recognizes this emotion, the server retrieves relevant information from the database, and the AI ​​model generates a response such as, "Each step of the procedure is based on Law XX and is designed to protect the user's safety and rights. We apologize for any inconvenience, but we will do our best to respond promptly." This allows for a response that is appropriate to the user's emotions.

[0338] An example of a prompt message to input into a generative AI model might be: "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure."

[0339] This system enables more personalized communication that responds to user emotions, which is expected to improve customer satisfaction.

[0340] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0341] Step 1:

[0342] The user inputs questions using natural language through the terminal. This input process generates unstructured text data. The terminal then sends this text data to a server for analysis.

[0343] Step 2:

[0344] The server analyzes the received text data using natural language processing libraries (e.g., NLTK or TextBlob) as a means of sentiment recognition. This analysis extracts the emotional characteristics of the text. Specifically, it determines the user's emotional state (e.g., anger, frustration, confusion) from the text and outputs the result as sentiment data.

[0345] Step 3:

[0346] The server uses information retrieval methods based on the user's question content and sentiment data, and searches for relevant information using a data management system (e.g., MySQL or PostgreSQL). By executing SQL queries, the server extracts appropriate information from the database that matches the user's question and outputs it as search result data.

[0347] Step 4:

[0348] The server uses a generative AI model (e.g., OpenAI API) to generate responses appropriate to the user's emotions based on search result data. During this process, prompt text (e.g., "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure.") is input, and the generated text is tone-adjusted. The generated answer is then output as response data.

[0349] Step 5:

[0350] The server uses information enhancement tools to incorporate supporting information such as laws and manuals to add reliability to the response data. This supplementary process results in more reliable responses, which are then output as presented data.

[0351] Step 6:

[0352] The server sends the final presentation data to the terminal. The terminal displays the response to the user in a format that is appropriate to their emotions. Based on this information, the user can ask further questions if necessary.

[0353] (Application Example 2)

[0354] 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."

[0355] Conventional user inquiry systems typically provide impersonal responses without considering the user's emotions, and are particularly incapable of adequately addressing emotionally charged inquiries, thus posing a challenge to improving customer satisfaction. When users contact an e-commerce site with anxieties or dissatisfactions, it is necessary to understand their emotions and respond appropriately, but this has not been adequately achieved with current technologies.

[0356] 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.

[0357] In this invention, the server includes emotion analysis means for analyzing user questions and their context and recognizing emotions; analysis means for searching for relevant information based on the analyzed questions and emotions; and providing means for attaching referenced supporting information to the generated answers. This enables flexible and appropriate responses in accordance with the user's emotions, thereby improving customer satisfaction.

[0358] A "reception mechanism" is an interface for receiving questions from users in natural language.

[0359] An "emotion analysis device" is a processing device that analyzes an input question and its context to recognize the user's emotions.

[0360] "Analysis tools" refer to devices and software used to retrieve relevant information based on the sentiment analysis results and the content of the questions.

[0361] A "generation means" is a device that has the function of constructing the optimal response based on retrieved information and recognized emotions.

[0362] "Methods for adding information" refer to techniques for adding supporting evidence to generated responses to enhance their reliability.

[0363] A "presentation method" is an interface for presenting answers in a format that responds to the user's emotions.

[0364] This system aims to automatically process user inquiries based on their sentiment. The entire system consists of a server, user terminals, sentiment analyzers, a database, and an interface.

[0365] When a user enters a query in natural language using a terminal, that data is sent to the server. The server analyzes the input data using sentiment analysis tools to identify the user's emotions. This process utilizes a sentiment analysis engine. The sentiment engine analyzes the context and expression of the user's question to determine whether the user is angry, confused, or otherwise feeling something.

[0366] Next, the server uses analytical tools to search for relevant information in the database based on the analysis results. After collecting the information, a generation tool generates a response based on this information and in a manner that is appropriate to the user's emotions. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite in order to provide reassurance.

[0367] Supporting information is provided with the response. This supporting information, such as laws and operating procedures, is obtained from a database and attached to the response using a designated method. This increases the reliability of the response.

[0368] Ultimately, the server uses a presentation mechanism to display the answer to the user in an emotionally appropriate format. This display allows the user to be satisfied with the information provided and to enter further questions if necessary. In this case, the further questions are also processed.

[0369] As a concrete example, consider a scenario where a user becomes frustrated because their order hasn't arrived on an online shopping site and contacts customer support. The emotion engine identifies the emotion as "frustration," and the server analyzes the situation using analytical tools to obtain appropriate information regarding delivery. Then, a generation tool constructs an emotionally sensitive response such as, "We apologize for the delay. We will investigate immediately and take appropriate action."

[0370] An example of a prompt message would be: "I want to design an AI assistant that can determine the user's emotions in response to their inquiries and consider an appropriate response. If the user inputs 'I'm frustrated because the delivery is late,' I want it to analyze their emotions and generate a response that shows empathy while promising prompt support."

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The user enters a query in natural language using a terminal. This input data is then prepared for processing by the sentiment analysis engine. In this process, the input is the user's natural language text, and the output is text data ready for analysis.

[0374] Step 2:

[0375] The server uses an emotion analysis engine to analyze the user's input data and recognize their emotions. The input is the text data prepared in step 1, and the output is the user's emotion information. As part of the data processing, contextual analysis and expression analysis are performed on the input text, and an emotion determination algorithm is applied.

[0376] Step 3:

[0377] The server uses analytical tools to retrieve relevant information based on sentiment information. The input is the sentiment information obtained in step 2 and the original query text, and the output is data related to the query content. This data is retrieved from a database. Sentiment-intensive search queries are used for data calculation.

[0378] Step 4:

[0379] The generation mechanism generates the optimal response based on the data and sentiment information retrieved by the server. The input is the search results and sentiment information from step 3, and the output is the optimized response text. Specifically, the generation AI model constructs a unique response.

[0380] Step 5:

[0381] The annotation method attaches supporting information to the generated response. The input is the response generated in step 4, and the output is the response text with the supporting information attached. Specifically, a process is executed to attach reference information from relevant laws and procedures.

[0382] Step 6:

[0383] The server uses a presentation mechanism to display the answer to the user. The input is the answer text formatted in step 5, and the output is the final answer displayed on the user's terminal. Specifically, the message is displayed in a tone that corresponds to the user's emotions.

[0384] Step 7:

[0385] The user can enter additional questions, which are then processed again through a similar process. The input is a newly entered natural language question, and the process restarts from step 1. The server performs a new analysis, taking into account the previous sentiment analysis.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] [Third Embodiment]

[0390] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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".

[0402] This invention begins with a user inputting a question in natural language through a terminal. The terminal functions as a receiving device, and once a question is entered, it is sent to a server. The server analyzes the received question using natural language processing technology as an analysis device. The information obtained from the analysis is used to quickly retrieve relevant data based on the content of the question.

[0403] The server searches the database for laws, past cases, and manual data, and constructs the optimal answer based on the information obtained using generation methods. The server then adds specific supporting information from the laws and manuals used to the generated answer using an annotation method, and presents it to the user based on that content. This presentation is again done via the terminal, providing the user with accurate and timely information.

[0404] As a concrete example, let's consider a scenario where a user asks, "Please tell me about the procedures required under the new Building Standards Act." The terminal receives this question, and the server analyzes it according to the means of the present invention. It searches the database for relevant legal data and generates the optimal answer using an AI model. The answer includes the details of the procedure, along with which law it is based on and the specific article number. In this way, the user can quickly obtain the necessary procedural information.

[0405] In addition, if a user requires further clarification of the information presented, they can ask additional questions. These additional questions are also entered in natural language, and the answers are generated through the same process. As described above, the embodiment of the present invention makes it possible to always provide accurate and prompt answers to questions at the counter, thereby achieving operational efficiency.

[0406] The following describes the processing flow.

[0407] Step 1:

[0408] The user accesses the device and enters a question in natural language. The entered data is sent from the device to the server.

[0409] Step 2:

[0410] The server receives the question sent from the terminal. Natural language processing techniques are used to analyze the question. Through analysis, keywords and context of the question are extracted, and the intent of the question is identified.

[0411] Step 3:

[0412] The server searches the database based on the analysis results. The database contains relevant laws, manuals, and past cases, allowing it to quickly identify data that matches the keywords of the query.

[0413] Step 4:

[0414] The server uses a generative AI model to construct the optimal answer based on the information obtained through the search. The answer includes not only direct information related to the question, but also supplementary information to present relevant evidence.

[0415] Step 5:

[0416] The server adds specific supporting information, such as the section and paragraph numbers of the laws and manuals it referenced, to the answers it generates. This supporting information allows users to verify the reliability of the answers.

[0417] Step 6:

[0418] The server sends the completed answer to the terminal, which then displays it to the user. The user can then review the answer on the screen and obtain information related to the question.

[0419] Step 7:

[0420] The user can ask additional questions about the provided answers as needed. These additional questions are sent again from the device, and a new answer is generated through the same processing steps.

[0421] (Example 1)

[0422] 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."

[0423] There is a need for a system that can provide users with quick and accurate answers to their questions regarding laws and guidelines. However, conventional systems have problems with reliability because they take time to analyze user questions, search for relevant information, and generate optimal answers, and often do not include specific supporting information in the answers.

[0424] 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.

[0425] In this invention, the server includes means for analyzing the user's question using natural language processing technology, means for retrieving relevant information from a data store based on the analysis results, and means for using a generative model to construct the optimal answer based on the search results. This enables the user to obtain a quick, accurate answer with specific supporting information.

[0426] A "user" refers to someone who uses the system to input questions and receive answers.

[0427] "Language" refers to natural language, and is the format of information input via a terminal.

[0428] A "terminal" refers to a device that allows a user to input a question and receive an answer from a server.

[0429] A "server" is a computing unit that receives information sent from a terminal and performs analysis, retrieval, and generation.

[0430] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0431] "Analysis" refers to the process of understanding the linguistic information received from the user and clarifying its intent.

[0432] "Related information" refers to data related to the user's question, identified based on the analysis results.

[0433] A "data store" is an information aggregation location where relevant information such as laws and guidelines are registered in advance.

[0434] "Searching" refers to the process of finding specific, relevant information from a data store.

[0435] A "generative model" refers to an algorithm that generates the most appropriate sentence or response based on the input information.

[0436] "Supporting information" refers to specific references added to a generated response to support its accuracy and reliability.

[0437] The user first inputs a question in natural language using a terminal. The terminal formats this user input appropriately and sends it to the server using a communication protocol. The server analyzes the received input data using one of several natural language processing technologies. The analysis uses a generative AI model (for example, a model for natural language processing) to understand the intent of the input question.

[0438] Next, the server searches a data store containing pre-registered laws and guidelines based on the analysis results. This search process executes database queries to quickly extract relevant items.

[0439] After the search is complete, the server uses a generative AI model to generate the most suitable answer based on the searched information. Before providing the generated answer to the user, supporting information is added and the format is edited to include legal codes and relevant guideline sections.

[0440] The server then sends the completed response to the terminal, which displays the result to the user. The display format is designed to be easily understood by the user.

[0441] As a concrete example, if a user enters "Please tell me about the procedures required under the new Building Standards Act" into their terminal, the system will begin analysis. It will then extract relevant legal data from its data store and use a generating AI model to create detailed procedural guidance based on that information. The final response will include the details of the procedure, along with the specific legal provision and article number. In this way, users can quickly obtain the necessary procedural information.

[0442] This embodiment of the invention enables users to immediately access the information they need, thereby achieving efficient and effective response provision.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1: The user enters the question in natural language through the terminal. The entered data is stored on the terminal as text. This text will serve as the basic input for subsequent processes. The terminal appropriately encodes this input and prepares it to be sent to the server.

[0445] Step 2: The terminal uses a communication protocol to send the entered text data to the server, delivering the encoded data over the network to the server. The output here is the question data that has been accurately transmitted to the server.

[0446] Step 3: The server uses natural language processing techniques to analyze the received input data. A generative AI model is activated to understand the intent of the question, breaking down the text data into tokens and extracting relevant keywords and phrases. The output of this step is the analyzed tokenized data and its intent.

[0447] Step 4: Based on the analysis results, the server searches the data store for relevant information. The server generates database queries to quickly extract information related to laws and guidelines. The output obtained here is a dataset related to the user's question.

[0448] Step 5: The server uses the information obtained from the search and constructs the optimal answer using a generative AI model. It integrates multiple data points to generate a logical and consistent answer. The output of this process is the answer text that should be provided to the user.

[0449] Step 6: The server adds supporting information to the generated response. It adds legal code numbers and relevant guideline sections to the response to increase its reliability. This step outputs a final response with supporting information added.

[0450] Step 7: The server sends the completed answer to the terminal. The terminal displays the received data in a format suitable for the user interface, presenting it visually to the user. The user reviews the answer on the screen and considers additional questions as needed. The output of this step is the answer information that the user can view directly.

[0451] (Application Example 1)

[0452] 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."

[0453] In recent years, with the advancement of information technology, companies and organizations are required to acquire information quickly and accurately. However, information such as laws and guidelines is vast, and security-related information in particular is updated frequently, making it difficult to reliably grasp its contents. Therefore, a system is needed that allows employees to easily obtain the latest information and take appropriate action quickly.

[0454] 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.

[0455] In this invention, the server includes an information processing means for inputting information requests from users in natural language, an analysis means for analyzing the input information requests and searching for relevant information, and a response formation means for generating an optimal response based on the retrieved information. This enables employees to request information in natural language and quickly obtain accurate information based on the latest laws and guidelines.

[0456] An "information request" is a natural language query submitted by a user to obtain specific information.

[0457] "Information processing means" refers to technology for receiving and appropriately processing information requests from users.

[0458] "Analysis means" refers to a technology that analyzes input information requests using natural language processing techniques and retrieves relevant information.

[0459] "Response formation means" refers to a technology for generating an optimal response based on analyzed information.

[0460] "Element addition means" refers to a technique for adding supplementary information, such as supporting information, to a generated response.

[0461] "Communication methods" refer to technologies for appropriately conveying the generated response to the user.

[0462] An "information processing device" is a device that includes the means described above and provides predetermined information in response to a user's information request.

[0463] A "data storage device" is a device used to register and store information such as laws and guidelines in advance.

[0464] The system for implementing this invention consists of a terminal that receives information requests from users in natural language and a server that analyzes the information and generates a response. The terminal functions as a mobile device such as a smartphone and is designed to receive user information requests via an interface. Once the user enters an information request, the terminal sends it to the server.

[0465] The server uses natural language processing (NLP) tools such as BERT and spaCy to analyze information requests and quickly retrieve relevant information from the database. This analysis allows the server to understand the context and accurately extract information such as laws and guidelines.

[0466] Next, the server generates the optimal response based on the analysis results. Utilizing a generative AI model, a comprehensive answer is created from the collected data. This response includes relevant supporting information, such as references to specific legal norms or provisions. The generated response helps the user take appropriate action.

[0467] The response generated by the server is presented to the user via the terminal. This allows the user to obtain information quickly and accurately. For example, if an employee enters a prompt such as "Please tell me about the latest security protocol changes," the server can provide information on the latest regulations and protocols.

[0468] This system enables rapid information sharing within companies and organizations, making compliance and adherence to guidelines, particularly in the security field, much smoother.

[0469] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0470] Step 1:

[0471] The user enters information requests in natural language using a terminal. This input data is in text format and is sent to the terminal as a prompt. The terminal converts this input into the appropriate format and prepares it for transmission to the server.

[0472] Step 2:

[0473] When a terminal receives an information request from a user, it sends it to the server. The server first receives this input data and preprocesses it into a format suitable for database querying. This preprocessing includes text tokenization and tagging as needed.

[0474] Step 3:

[0475] The server uses natural language processing tools (e.g., spaCy, BERT) to analyze the received information request. It extracts relevant keywords and phrases from the analyzed data and generates a database search query based on these. The query is then generated as output.

[0476] Step 4:

[0477] The server executes the generated query against the database to retrieve relevant information. This database contains laws and guidelines that have been pre-registered, and the relevant information is output as a search result.

[0478] Step 5:

[0479] The server uses a generative AI model to generate responses based on search results. The generative model collects necessary information from the input query and creates a comprehensive answer. The output includes the answer along with relevant supporting information.

[0480] Step 6:

[0481] The generated response is sent from the server to the terminal, which then displays it to the user. The user then uses this information to take specific actions or make decisions. For example, the terminal displays a response to the prompt, "Please tell me about the latest security protocol changes."

[0482] 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.

[0483] This invention is a system that combines user emotion recognition with user inquiry handling. When a user inputs a question in natural language using a terminal, the input data is first analyzed by an emotion engine to determine the user's emotion. The emotion engine analyzes the context and expression of the question to identify whether the user is, for example, angry, irritated, or confused.

[0484] The server receives the results from the emotion engine and uses analysis tools to search for relevant data, taking into account both the content of the question and the user's emotions. The server then uses the obtained information to construct the optimal answer through a generation tool. In this generation process, the answer is adjusted according to the emotion. For example, if the user is expressing dissatisfaction, the answer will be written using more polite and reassuring language.

[0485] The answers are accompanied by supporting information, increasing their reliability. This information is added through various means, such as specifically citing laws, manuals, and relevant chapters.

[0486] The user receives the presented answers through their device. The server uses a presentation method to display the answers in a format that matches the user's emotions. Based on the presented information, the user can input additional information if they have further questions. Similarly, emotions are recognized and a corresponding process is performed for these additional questions.

[0487] As a concrete example, suppose a user asks an irritated question such as, "Why is this procedure so complicated?" The emotion engine recognizes this irritation, and the server analyzes it using analytical tools and retrieves appropriate information from the database. In the generated response, the server conveys a message that takes the user's feelings into consideration, such as, "Each step of the procedure is based on Law XX and is in order to protect the user's safety and rights. We apologize for the inconvenience, but we will do our best to respond as quickly as possible."

[0488] This form goes beyond mere information provision, enabling communication that responds to the user's emotions and achieving higher customer satisfaction.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The user enters the question in natural language using a terminal. The terminal processes the input as a means of reception and sends it to the server.

[0492] Step 2:

[0493] The server inputs the question received from the terminal into the emotion engine. The emotion engine analyzes the content of the question and detects the user's emotions. For example, it identifies emotional states such as joy, anger, and anxiety.

[0494] Step 3:

[0495] The server receives the results from the sentiment engine and uses analytical tools to analyze the question content and detected sentiment. It understands the intent of the question and extracts relevant keywords.

[0496] Step 4:

[0497] Based on the analysis results, the server searches the database and extracts relevant information. The database includes laws, manuals, and past case data.

[0498] Step 5:

[0499] The server uses a generation mechanism to construct a response based on the retrieved information. During this process, the response is adjusted according to the emotions recognized by the emotion engine. For example, careful and empathetic language is selected to reflect the user's feelings.

[0500] Step 6:

[0501] The server uses an annotation mechanism to add referenced supporting information, such as the article number of a law or a detailed explanation, to the generated response.

[0502] Step 7:

[0503] The server sends the completed answer to the terminal via a presentation device, and the terminal displays it to the user. The displayed answer is presented in a format that takes the user's feelings into consideration.

[0504] Step 8:

[0505] The user can ask additional questions about the provided answers as needed. These additional questions are also accepted by the terminal, and the same processing flow is repeated.

[0506] (Example 2)

[0507] 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."

[0508] Traditional information delivery systems lack personalized responses that cater to user emotions, leading to decreased user satisfaction. Furthermore, there is a need to improve the reliability of the responses provided.

[0509] 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.

[0510] In this invention, the server includes an input means, an emotion recognition means, an information retrieval means, a generation means, an information addition means, and a display means. This enables the provision of personalized responses that correspond to the user's emotions and the presentation of highly reliable information.

[0511] An "input device" is a device that has the function of receiving questions from the user in natural language and transmitting them to the analysis device.

[0512] An "emotion recognition device" is a device that analyzes the context of an input question and has the function of identifying the user's emotional state.

[0513] An "information retrieval device" is a device that has the function of retrieving relevant information based on the user's question and perceived emotions.

[0514] A "generation means" is a device that has the function of constructing the optimal answer using a generation AI model based on the retrieved information.

[0515] An "information-adding device" is a device that has the function of adding supporting information to the generated response to increase its reliability.

[0516] A "display means" is a device that has the function of presenting the generated response to the user in a format appropriate to the user's emotions.

[0517] This invention is a system that utilizes natural language processing and emotion recognition technologies to respond to user inquiries. When a user inputs a question in natural language using a terminal, the system analyzes the question and identifies the user's emotions.

[0518] The server uses a natural language processing library as its emotion recognition engine. Specifically, it can utilize tools such as the Natural Language Processing Toolkit (NLTK) and TextBlob to analyze the context of the input text and determine the user's emotional state (e.g., anger, frustration, confusion).

[0519] The server considers the content and emotional state of the user's question and uses an information search engine to retrieve relevant information from the database. For database management, relational database management systems (RDBMS) such as MySQL or PostgreSQL are used.

[0520] Subsequently, the server utilizes a generative AI model to generate the optimal response. By using generative AI such as the OpenAI API, it adjusts the tone according to specific emotions, constructing a response that is sensitive to the user's feelings. In this process, supporting information from laws and manuals is added to ensure the reliability of the response, and it is presented to the user in an easy-to-understand manner.

[0521] For example, if a user enters a question expressing frustration, such as "Why is this procedure so complicated?", the system recognizes this emotion, the server retrieves relevant information from the database, and the AI ​​model generates a response such as, "Each step of the procedure is based on Law XX and is designed to protect the user's safety and rights. We apologize for any inconvenience, but we will do our best to respond promptly." This allows for a response that is appropriate to the user's emotions.

[0522] An example of a prompt message to input into a generative AI model might be: "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure."

[0523] This system enables more personalized communication that responds to user emotions, which is expected to improve customer satisfaction.

[0524] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0525] Step 1:

[0526] The user inputs questions using natural language through the terminal. This input process generates unstructured text data. The terminal then sends this text data to a server for analysis.

[0527] Step 2:

[0528] The server analyzes the received text data using natural language processing libraries (e.g., NLTK or TextBlob) as a means of sentiment recognition. This analysis extracts the emotional characteristics of the text. Specifically, it determines the user's emotional state (e.g., anger, frustration, confusion) from the text and outputs the result as sentiment data.

[0529] Step 3:

[0530] The server uses information retrieval methods based on the user's question content and sentiment data, and searches for relevant information using a data management system (e.g., MySQL or PostgreSQL). By executing SQL queries, the server extracts appropriate information from the database that matches the user's question and outputs it as search result data.

[0531] Step 4:

[0532] The server uses a generative AI model (e.g., OpenAI API) to generate responses appropriate to the user's emotions based on search result data. During this process, prompt text (e.g., "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure.") is input, and the generated text is tone-adjusted. The generated answer is then output as response data.

[0533] Step 5:

[0534] The server uses information enhancement tools to incorporate supporting information such as laws and manuals to add reliability to the response data. This supplementary process results in more reliable responses, which are then output as presented data.

[0535] Step 6:

[0536] The server sends the final presentation data to the terminal. The terminal displays the response to the user in a format that is appropriate to their emotions. Based on this information, the user can ask further questions if necessary.

[0537] (Application Example 2)

[0538] 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."

[0539] Conventional user inquiry systems typically provide impersonal responses without considering the user's emotions, and are particularly incapable of adequately addressing emotionally charged inquiries, thus posing a challenge to improving customer satisfaction. When users contact an e-commerce site with anxieties or dissatisfactions, it is necessary to understand their emotions and respond appropriately, but this has not been adequately achieved with current technologies.

[0540] 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.

[0541] In this invention, the server includes emotion analysis means for analyzing user questions and their context and recognizing emotions; analysis means for searching for relevant information based on the analyzed questions and emotions; and providing means for attaching referenced supporting information to the generated answers. This enables flexible and appropriate responses in accordance with the user's emotions, thereby improving customer satisfaction.

[0542] A "reception mechanism" is an interface for receiving questions from users in natural language.

[0543] An "emotion analysis device" is a processing device that analyzes an input question and its context to recognize the user's emotions.

[0544] "Analysis tools" refer to devices and software used to retrieve relevant information based on the sentiment analysis results and the content of the questions.

[0545] A "generation means" is a device that has the function of constructing the optimal response based on retrieved information and recognized emotions.

[0546] "Methods for adding information" refer to techniques for adding supporting evidence to generated responses to enhance their reliability.

[0547] A "presentation method" is an interface for presenting answers in a format that responds to the user's emotions.

[0548] This system aims to automatically process user inquiries based on their sentiment. The entire system consists of a server, user terminals, sentiment analyzers, a database, and an interface.

[0549] When a user enters a query in natural language using a terminal, that data is sent to the server. The server analyzes the input data using sentiment analysis tools to identify the user's emotions. This process utilizes a sentiment analysis engine. The sentiment engine analyzes the context and expression of the user's question to determine whether the user is angry, confused, or otherwise feeling something.

[0550] Next, the server uses analytical tools to search for relevant information in the database based on the analysis results. After collecting the information, a generation tool generates a response based on this information and in a manner that is appropriate to the user's emotions. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite in order to provide reassurance.

[0551] Supporting information is provided with the response. This supporting information, such as laws and operating procedures, is obtained from a database and attached to the response using a designated method. This increases the reliability of the response.

[0552] Ultimately, the server uses a presentation mechanism to display the answer to the user in an emotionally appropriate format. This display allows the user to be satisfied with the information provided and to enter further questions if necessary. In this case, the further questions are also processed.

[0553] As a concrete example, consider a scenario where a user becomes frustrated because their order hasn't arrived on an online shopping site and contacts customer support. The emotion engine identifies the emotion as "frustration," and the server analyzes the situation using analytical tools to obtain appropriate information regarding delivery. Then, a generation tool constructs an emotionally sensitive response such as, "We apologize for the delay. We will investigate immediately and take appropriate action."

[0554] An example of a prompt message would be: "I want to design an AI assistant that can determine the user's emotions in response to their inquiries and consider an appropriate response. If the user inputs 'I'm frustrated because the delivery is late,' I want it to analyze their emotions and generate a response that shows empathy while promising prompt support."

[0555] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0556] Step 1:

[0557] The user enters a query in natural language using a terminal. This input data is then prepared for processing by the sentiment analysis engine. In this process, the input is the user's natural language text, and the output is text data ready for analysis.

[0558] Step 2:

[0559] The server uses an emotion analysis engine to analyze the user's input data and recognize their emotions. The input is the text data prepared in step 1, and the output is the user's emotion information. As part of the data processing, contextual analysis and expression analysis are performed on the input text, and an emotion determination algorithm is applied.

[0560] Step 3:

[0561] The server uses analytical tools to retrieve relevant information based on sentiment information. The input is the sentiment information obtained in step 2 and the original query text, and the output is data related to the query content. This data is retrieved from a database. Sentiment-intensive search queries are used for data calculation.

[0562] Step 4:

[0563] The generation mechanism generates the optimal response based on the data and sentiment information retrieved by the server. The input is the search results and sentiment information from step 3, and the output is the optimized response text. Specifically, the generation AI model constructs a unique response.

[0564] Step 5:

[0565] The annotation method attaches supporting information to the generated response. The input is the response generated in step 4, and the output is the response text with the supporting information attached. Specifically, a process is executed to attach reference information from relevant laws and procedures.

[0566] Step 6:

[0567] The server uses a presentation mechanism to display the answer to the user. The input is the answer text formatted in step 5, and the output is the final answer displayed on the user's terminal. Specifically, the message is displayed in a tone that corresponds to the user's emotions.

[0568] Step 7:

[0569] The user can enter additional questions, which are then processed again through a similar process. The input is a newly entered natural language question, and the process restarts from step 1. The server performs a new analysis, taking into account the previous sentiment analysis.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] [Fourth Embodiment]

[0574] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0575] 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.

[0576] 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).

[0577] 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.

[0578] 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.

[0579] 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).

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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".

[0587] This invention begins with a user inputting a question in natural language through a terminal. The terminal functions as a receiving device, and once a question is entered, it is sent to a server. The server analyzes the received question using natural language processing technology as an analysis device. The information obtained from the analysis is used to quickly retrieve relevant data based on the content of the question.

[0588] The server searches the database for laws, past cases, and manual data, and constructs the optimal answer based on the information obtained using generation methods. The server then adds specific supporting information from the laws and manuals used to the generated answer using an annotation method, and presents it to the user based on that content. This presentation is again done via the terminal, providing the user with accurate and timely information.

[0589] As a concrete example, let's consider a scenario where a user asks, "Please tell me about the procedures required under the new Building Standards Act." The terminal receives this question, and the server analyzes it according to the means of the present invention. It searches the database for relevant legal data and generates the optimal answer using an AI model. The answer includes the details of the procedure, along with which law it is based on and the specific article number. In this way, the user can quickly obtain the necessary procedural information.

[0590] In addition, if a user requires further clarification of the information presented, they can ask additional questions. These additional questions are also entered in natural language, and the answers are generated through the same process. As described above, the embodiment of the present invention makes it possible to always provide accurate and prompt answers to questions at the counter, thereby achieving operational efficiency.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The user accesses the device and enters a question in natural language. The entered data is sent from the device to the server.

[0594] Step 2:

[0595] The server receives the question sent from the terminal. Natural language processing techniques are used to analyze the question. Through analysis, keywords and context of the question are extracted, and the intent of the question is identified.

[0596] Step 3:

[0597] The server searches the database based on the analysis results. The database contains relevant laws, manuals, and past cases, allowing it to quickly identify data that matches the keywords of the query.

[0598] Step 4:

[0599] The server uses a generative AI model to construct the optimal answer based on the information obtained through the search. The answer includes not only direct information related to the question, but also supplementary information to present relevant evidence.

[0600] Step 5:

[0601] The server adds specific supporting information, such as the section and paragraph numbers of the laws and manuals it referenced, to the answers it generates. This supporting information allows users to verify the reliability of the answers.

[0602] Step 6:

[0603] The server sends the completed answer to the terminal, which then displays it to the user. The user can then review the answer on the screen and obtain information related to the question.

[0604] Step 7:

[0605] The user can ask additional questions about the provided answers as needed. These additional questions are sent again from the device, and a new answer is generated through the same processing steps.

[0606] (Example 1)

[0607] 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".

[0608] There is a need for a system that can provide users with quick and accurate answers to their questions regarding laws and guidelines. However, conventional systems have problems with reliability because they take time to analyze user questions, search for relevant information, and generate optimal answers, and often do not include specific supporting information in the answers.

[0609] 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.

[0610] In this invention, the server includes means for analyzing the user's question using natural language processing technology, means for retrieving relevant information from a data store based on the analysis results, and means for using a generative model to construct the optimal answer based on the search results. This enables the user to obtain a quick, accurate answer with specific supporting information.

[0611] A "user" refers to someone who uses the system to input questions and receive answers.

[0612] "Language" refers to natural language, and is the format of information input via a terminal.

[0613] A "terminal" refers to a device that allows a user to input a question and receive an answer from a server.

[0614] A "server" is a computing unit that receives information sent from a terminal and performs analysis, retrieval, and generation.

[0615] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0616] "Analysis" refers to the process of understanding the linguistic information received from the user and clarifying its intent.

[0617] "Related information" refers to data related to the user's question, identified based on the analysis results.

[0618] A "data store" is an information aggregation location where relevant information such as laws and guidelines are registered in advance.

[0619] "Searching" refers to the process of finding specific, relevant information from a data store.

[0620] A "generative model" refers to an algorithm that generates the most appropriate sentence or response based on the input information.

[0621] "Supporting information" refers to specific references added to a generated response to support its accuracy and reliability.

[0622] The user first inputs a question in natural language using a terminal. The terminal formats this user input appropriately and sends it to the server using a communication protocol. The server analyzes the received input data using one of several natural language processing technologies. The analysis uses a generative AI model (for example, a model for natural language processing) to understand the intent of the input question.

[0623] Next, the server searches a data store containing pre-registered laws and guidelines based on the analysis results. This search process executes database queries to quickly extract relevant items.

[0624] After the search is complete, the server uses a generative AI model to generate the most suitable answer based on the searched information. Before providing the generated answer to the user, supporting information is added and the format is edited to include legal codes and relevant guideline sections.

[0625] The server then sends the completed response to the terminal, which displays the result to the user. The display format is designed to be easily understood by the user.

[0626] As a concrete example, if a user enters "Please tell me about the procedures required under the new Building Standards Act" into their terminal, the system will begin analysis. It will then extract relevant legal data from its data store and use a generating AI model to create detailed procedural guidance based on that information. The final response will include the details of the procedure, along with the specific legal provision and article number. In this way, users can quickly obtain the necessary procedural information.

[0627] This embodiment of the invention enables users to immediately access the information they need, thereby achieving efficient and effective response provision.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1: The user enters the question in natural language through the terminal. The entered data is stored on the terminal as text. This text will serve as the basic input for subsequent processes. The terminal appropriately encodes this input and prepares it to be sent to the server.

[0630] Step 2: The terminal uses a communication protocol to send the entered text data to the server, delivering the encoded data over the network to the server. The output here is the question data that has been accurately transmitted to the server.

[0631] Step 3: The server uses natural language processing techniques to analyze the received input data. A generative AI model is activated to understand the intent of the question, breaking down the text data into tokens and extracting relevant keywords and phrases. The output of this step is the analyzed tokenized data and its intent.

[0632] Step 4: Based on the analysis results, the server searches the data store for relevant information. The server generates database queries to quickly extract information related to laws and guidelines. The output obtained here is a dataset related to the user's question.

[0633] Step 5: The server uses the information obtained from the search and constructs the optimal answer using a generative AI model. It integrates multiple data points to generate a logical and consistent answer. The output of this process is the answer text that should be provided to the user.

[0634] Step 6: The server adds supporting information to the generated response. It adds legal code numbers and relevant guideline sections to the response to increase its reliability. This step outputs a final response with supporting information added.

[0635] Step 7: The server sends the completed answer to the terminal. The terminal displays the received data in a format suitable for the user interface, presenting it visually to the user. The user reviews the answer on the screen and considers additional questions as needed. The output of this step is the answer information that the user can view directly.

[0636] (Application Example 1)

[0637] 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".

[0638] In recent years, with the advancement of information technology, companies and organizations are required to acquire information quickly and accurately. However, information such as laws and guidelines is vast, and security-related information in particular is updated frequently, making it difficult to reliably grasp its contents. Therefore, a system is needed that allows employees to easily obtain the latest information and take appropriate action quickly.

[0639] 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.

[0640] In this invention, the server includes an information processing means for inputting information requests from users in natural language, an analysis means for analyzing the input information requests and searching for relevant information, and a response formation means for generating an optimal response based on the retrieved information. This enables employees to request information in natural language and quickly obtain accurate information based on the latest laws and guidelines.

[0641] An "information request" is a natural language query submitted by a user to obtain specific information.

[0642] "Information processing means" refers to technology for receiving and appropriately processing information requests from users.

[0643] "Analysis means" refers to a technology that analyzes input information requests using natural language processing techniques and retrieves relevant information.

[0644] "Response formation means" refers to a technology for generating an optimal response based on analyzed information.

[0645] "Element addition means" refers to a technique for adding supplementary information, such as supporting information, to a generated response.

[0646] "Communication methods" refer to technologies for appropriately conveying the generated response to the user.

[0647] An "information processing device" is a device that includes the means described above and provides predetermined information in response to a user's information request.

[0648] A "data storage device" is a device used to register and store information such as laws and guidelines in advance.

[0649] The system for implementing this invention consists of a terminal that receives information requests from users in natural language and a server that analyzes the information and generates a response. The terminal functions as a mobile device such as a smartphone and is designed to receive user information requests via an interface. Once the user enters an information request, the terminal sends it to the server.

[0650] The server uses natural language processing (NLP) tools such as BERT and spaCy to analyze information requests and quickly retrieve relevant information from the database. This analysis allows the server to understand the context and accurately extract information such as laws and guidelines.

[0651] Next, the server generates the optimal response based on the analysis results. Utilizing a generative AI model, a comprehensive answer is created from the collected data. This response includes relevant supporting information, such as references to specific legal norms or provisions. The generated response helps the user take appropriate action.

[0652] The response generated by the server is presented to the user via the terminal. This allows the user to obtain information quickly and accurately. For example, if an employee enters a prompt such as "Please tell me about the latest security protocol changes," the server can provide information on the latest regulations and protocols.

[0653] This system enables rapid information sharing within companies and organizations, making compliance and adherence to guidelines, particularly in the security field, much smoother.

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] The user enters information requests in natural language using a terminal. This input data is in text format and is sent to the terminal as a prompt. The terminal converts this input into the appropriate format and prepares it for transmission to the server.

[0657] Step 2:

[0658] When a terminal receives an information request from a user, it sends it to the server. The server first receives this input data and preprocesses it into a format suitable for database querying. This preprocessing includes text tokenization and tagging as needed.

[0659] Step 3:

[0660] The server uses natural language processing tools (e.g., spaCy, BERT) to analyze the received information request. It extracts relevant keywords and phrases from the analyzed data and generates a database search query based on these. The query is then generated as output.

[0661] Step 4:

[0662] The server executes the generated query against the database to retrieve relevant information. This database contains laws and guidelines that have been pre-registered, and the relevant information is output as a search result.

[0663] Step 5:

[0664] The server uses a generative AI model to generate responses based on search results. The generative model collects necessary information from the input query and creates a comprehensive answer. The output includes the answer along with relevant supporting information.

[0665] Step 6:

[0666] The generated response is sent from the server to the terminal, which then displays it to the user. The user then uses this information to take specific actions or make decisions. For example, the terminal displays a response to the prompt, "Please tell me about the latest security protocol changes."

[0667] 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.

[0668] This invention is a system that combines user emotion recognition with user inquiry handling. When a user inputs a question in natural language using a terminal, the input data is first analyzed by an emotion engine to determine the user's emotion. The emotion engine analyzes the context and expression of the question to identify whether the user is, for example, angry, irritated, or confused.

[0669] The server receives the results from the emotion engine and uses analysis tools to search for relevant data, taking into account both the content of the question and the user's emotions. The server then uses the obtained information to construct the optimal answer through a generation tool. In this generation process, the answer is adjusted according to the emotion. For example, if the user is expressing dissatisfaction, the answer will be written using more polite and reassuring language.

[0670] The answers are accompanied by supporting information, increasing their reliability. This information is added through various means, such as specifically citing laws, manuals, and relevant chapters.

[0671] The user receives the presented answers through their device. The server uses a presentation method to display the answers in a format that matches the user's emotions. Based on the presented information, the user can input additional information if they have further questions. Similarly, emotions are recognized and a corresponding process is performed for these additional questions.

[0672] As a concrete example, suppose a user asks an irritated question such as, "Why is this procedure so complicated?" The emotion engine recognizes this irritation, and the server analyzes it using analytical tools and retrieves appropriate information from the database. In the generated response, the server conveys a message that takes the user's feelings into consideration, such as, "Each step of the procedure is based on Law XX and is in order to protect the user's safety and rights. We apologize for the inconvenience, but we will do our best to respond as quickly as possible."

[0673] This form goes beyond mere information provision, enabling communication that responds to the user's emotions and achieving higher customer satisfaction.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] The user enters the question in natural language using a terminal. The terminal processes the input as a means of reception and sends it to the server.

[0677] Step 2:

[0678] The server inputs the question received from the terminal into the emotion engine. The emotion engine analyzes the content of the question and detects the user's emotions. For example, it identifies emotional states such as joy, anger, and anxiety.

[0679] Step 3:

[0680] The server receives the results from the sentiment engine and uses analytical tools to analyze the question content and detected sentiment. It understands the intent of the question and extracts relevant keywords.

[0681] Step 4:

[0682] Based on the analysis results, the server searches the database and extracts relevant information. The database includes laws, manuals, and past case data.

[0683] Step 5:

[0684] The server uses a generation mechanism to construct a response based on the retrieved information. During this process, the response is adjusted according to the emotions recognized by the emotion engine. For example, careful and empathetic language is selected to reflect the user's feelings.

[0685] Step 6:

[0686] The server uses an annotation mechanism to add referenced supporting information, such as the article number of a law or a detailed explanation, to the generated response.

[0687] Step 7:

[0688] The server sends the completed answer to the terminal via a presentation device, and the terminal displays it to the user. The displayed answer is presented in a format that takes the user's feelings into consideration.

[0689] Step 8:

[0690] The user can ask additional questions about the provided answers as needed. These additional questions are also accepted by the terminal, and the same processing flow is repeated.

[0691] (Example 2)

[0692] 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".

[0693] Traditional information delivery systems lack personalized responses that cater to user emotions, leading to decreased user satisfaction. Furthermore, there is a need to improve the reliability of the responses provided.

[0694] 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.

[0695] In this invention, the server includes an input means, an emotion recognition means, an information retrieval means, a generation means, an information addition means, and a display means. This enables the provision of personalized responses that correspond to the user's emotions and the presentation of highly reliable information.

[0696] An "input device" is a device that has the function of receiving questions from the user in natural language and transmitting them to the analysis device.

[0697] An "emotion recognition device" is a device that analyzes the context of an input question and has the function of identifying the user's emotional state.

[0698] An "information retrieval device" is a device that has the function of retrieving relevant information based on the user's question and perceived emotions.

[0699] A "generation means" is a device that has the function of constructing the optimal answer using a generation AI model based on the retrieved information.

[0700] An "information-adding device" is a device that has the function of adding supporting information to the generated response to increase its reliability.

[0701] A "display means" is a device that has the function of presenting the generated response to the user in a format appropriate to the user's emotions.

[0702] This invention is a system that utilizes natural language processing and emotion recognition technologies to respond to user inquiries. When a user inputs a question in natural language using a terminal, the system analyzes the question and identifies the user's emotions.

[0703] The server uses a natural language processing library as its emotion recognition engine. Specifically, it can utilize tools such as the Natural Language Processing Toolkit (NLTK) and TextBlob to analyze the context of the input text and determine the user's emotional state (e.g., anger, frustration, confusion).

[0704] The server considers the content and emotional state of the user's question and uses an information search engine to retrieve relevant information from the database. For database management, relational database management systems (RDBMS) such as MySQL or PostgreSQL are used.

[0705] Subsequently, the server utilizes a generative AI model to generate the optimal response. By using generative AI such as the OpenAI API, it adjusts the tone according to specific emotions, constructing a response that is sensitive to the user's feelings. In this process, supporting information from laws and manuals is added to ensure the reliability of the response, and it is presented to the user in an easy-to-understand manner.

[0706] For example, if a user enters a question expressing frustration, such as "Why is this procedure so complicated?", the system recognizes this emotion, the server retrieves relevant information from the database, and the AI ​​model generates a response such as, "Each step of the procedure is based on Law XX and is designed to protect the user's safety and rights. We apologize for any inconvenience, but we will do our best to respond promptly." This allows for a response that is appropriate to the user's emotions.

[0707] An example of a prompt message to input into a generative AI model might be: "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure."

[0708] This system enables more personalized communication that responds to user emotions, which is expected to improve customer satisfaction.

[0709] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0710] Step 1:

[0711] The user inputs questions using natural language through the terminal. This input process generates unstructured text data. The terminal then sends this text data to a server for analysis.

[0712] Step 2:

[0713] The server analyzes the received text data using natural language processing libraries (e.g., NLTK or TextBlob) as a means of sentiment recognition. This analysis extracts the emotional characteristics of the text. Specifically, it determines the user's emotional state (e.g., anger, frustration, confusion) from the text and outputs the result as sentiment data.

[0714] Step 3:

[0715] The server uses information retrieval methods based on the user's question content and sentiment data, and searches for relevant information using a data management system (e.g., MySQL or PostgreSQL). By executing SQL queries, the server extracts appropriate information from the database that matches the user's question and outputs it as search result data.

[0716] Step 4:

[0717] The server uses a generative AI model (e.g., OpenAI API) to generate responses appropriate to the user's emotions based on search result data. During this process, prompt text (e.g., "For a user experiencing frustration, please provide a polite and supportive response to their question about the cumbersome nature of the procedure.") is input, and the generated text is tone-adjusted. The generated answer is then output as response data.

[0718] Step 5:

[0719] The server uses information enhancement tools to incorporate supporting information such as laws and manuals to add reliability to the response data. This supplementary process results in more reliable responses, which are then output as presented data.

[0720] Step 6:

[0721] The server sends the final presentation data to the terminal. The terminal displays the response to the user in a format that is appropriate to their emotions. Based on this information, the user can ask further questions if necessary.

[0722] (Application Example 2)

[0723] 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".

[0724] Conventional user inquiry systems typically provide impersonal responses without considering the user's emotions, and are particularly incapable of adequately addressing emotionally charged inquiries, thus posing a challenge to improving customer satisfaction. When users contact an e-commerce site with anxieties or dissatisfactions, it is necessary to understand their emotions and respond appropriately, but this has not been adequately achieved with current technologies.

[0725] 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.

[0726] In this invention, the server includes emotion analysis means for analyzing user questions and their context and recognizing emotions; analysis means for searching for relevant information based on the analyzed questions and emotions; and providing means for attaching referenced supporting information to the generated answers. This enables flexible and appropriate responses in accordance with the user's emotions, thereby improving customer satisfaction.

[0727] A "reception mechanism" is an interface for receiving questions from users in natural language.

[0728] An "emotion analysis device" is a processing device that analyzes an input question and its context to recognize the user's emotions.

[0729] "Analysis tools" refer to devices and software used to retrieve relevant information based on the sentiment analysis results and the content of the questions.

[0730] A "generation means" is a device that has the function of constructing the optimal response based on retrieved information and recognized emotions.

[0731] "Methods for adding information" refer to techniques for adding supporting evidence to generated responses to enhance their reliability.

[0732] A "presentation method" is an interface for presenting answers in a format that responds to the user's emotions.

[0733] This system aims to automatically process user inquiries based on their sentiment. The entire system consists of a server, user terminals, sentiment analyzers, a database, and an interface.

[0734] When a user enters a query in natural language using a terminal, that data is sent to the server. The server analyzes the input data using sentiment analysis tools to identify the user's emotions. This process utilizes a sentiment analysis engine. The sentiment engine analyzes the context and expression of the user's question to determine whether the user is angry, confused, or otherwise feeling something.

[0735] Next, the server uses analytical tools to search for relevant information in the database based on the analysis results. After collecting the information, a generation tool generates a response based on this information and in a manner that is appropriate to the user's emotions. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite in order to provide reassurance.

[0736] Supporting information is provided with the response. This supporting information, such as laws and operating procedures, is obtained from a database and attached to the response using a designated method. This increases the reliability of the response.

[0737] Ultimately, the server uses a presentation mechanism to display the answer to the user in an emotionally appropriate format. This display allows the user to be satisfied with the information provided and to enter further questions if necessary. In this case, the further questions are also processed.

[0738] As a concrete example, consider a scenario where a user becomes frustrated because their order hasn't arrived on an online shopping site and contacts customer support. The emotion engine identifies the emotion as "frustration," and the server analyzes the situation using analytical tools to obtain appropriate information regarding delivery. Then, a generation tool constructs an emotionally sensitive response such as, "We apologize for the delay. We will investigate immediately and take appropriate action."

[0739] An example of a prompt message would be: "I want to design an AI assistant that can determine the user's emotions in response to their inquiries and consider an appropriate response. If the user inputs 'I'm frustrated because the delivery is late,' I want it to analyze their emotions and generate a response that shows empathy while promising prompt support."

[0740] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0741] Step 1:

[0742] The user enters a query in natural language using a terminal. This input data is then prepared for processing by the sentiment analysis engine. In this process, the input is the user's natural language text, and the output is text data ready for analysis.

[0743] Step 2:

[0744] The server uses an emotion analysis engine to analyze the user's input data and recognize their emotions. The input is the text data prepared in step 1, and the output is the user's emotion information. As part of the data processing, contextual analysis and expression analysis are performed on the input text, and an emotion determination algorithm is applied.

[0745] Step 3:

[0746] The server uses analytical tools to retrieve relevant information based on sentiment information. The input is the sentiment information obtained in step 2 and the original query text, and the output is data related to the query content. This data is retrieved from a database. Sentiment-intensive search queries are used for data calculation.

[0747] Step 4:

[0748] The generation mechanism generates the optimal response based on the data and sentiment information retrieved by the server. The input is the search results and sentiment information from step 3, and the output is the optimized response text. Specifically, the generation AI model constructs a unique response.

[0749] Step 5:

[0750] The annotation method attaches supporting information to the generated response. The input is the response generated in step 4, and the output is the response text with the supporting information attached. Specifically, a process is executed to attach reference information from relevant laws and procedures.

[0751] Step 6:

[0752] The server uses a presentation mechanism to display the answer to the user. The input is the answer text formatted in step 5, and the output is the final answer displayed on the user's terminal. Specifically, the message is displayed in a tone that corresponds to the user's emotions.

[0753] Step 7:

[0754] The user can enter additional questions, which are then processed again through a similar process. The input is a newly entered natural language question, and the process restarts from step 1. The server performs a new analysis, taking into account the previous sentiment analysis.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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."

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] The following is further disclosed regarding the embodiments described above.

[0777] (Claim 1)

[0778] A means of receiving user questions in natural language,

[0779] An analytical tool that analyzes the input questions and searches for related data,

[0780] A generation means for generating the optimal answer based on the searched data,

[0781] A means for adding referenced supporting information to the generated response,

[0782] A means of presenting the answer to the user,

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, which pre-registers laws and manuals in a database.

[0786] (Claim 3)

[0787] The system according to claim 1, which accepts additional questions and performs analysis and generation again.

[0788] "Example 1"

[0789] (Claim 1)

[0790] A means of receiving language input from the user,

[0791] A means of sending data entered via a terminal to a server,

[0792] A means for a server to analyze data received using natural language processing technology,

[0793] A means of retrieving relevant information from a data store based on the analysis results,

[0794] One method is to use a generative model that constructs the best answer based on the search results,

[0795] A means of adding referenced information to the assembled answer,

[0796] A means of presenting the completed answer via a device,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, which uses laws and guidelines pre-registered in a data store.

[0800] (Claim 3)

[0801] The system according to claim 1, which performs parsing and generation again based on additional language input.

[0802] "Application Example 1"

[0803] (Claim 1)

[0804] An information processing means that takes user information requests as input in natural language,

[0805] An analysis means for analyzing the input information request and searching for related information,

[0806] A response formation means that generates an optimal response based on the retrieved information,

[0807] An element-adding means for adding supporting information corresponding to the generated response,

[0808] A means of communication that conveys the response to the user,

[0809] Information processing device including

[0810] (Claim 2)

[0811] The information processing device according to claim 1, which registers regulations and guidelines in advance in a data storage device.

[0812] (Claim 3)

[0813] The information processing apparatus according to claim 1, which accepts further information requests and performs analysis and response formation again.

[0814] "Example 2 of combining an emotion engine"

[0815] (Claim 1)

[0816] An input means that takes user questions in natural language and sends them to a processing unit for analysis,

[0817] An emotion recognition means that analyzes the context of the input question and recognizes the user's emotions,

[0818] An information retrieval method for searching for relevant information based on the results of emotion recognition and the content of the question,

[0819] A generation method that utilizes a generation AI model based on searched information to generate answers,

[0820] An information-adding means for providing supporting information to enhance the reliability of the generated response,

[0821] A display means that presents the generated response in a format suitable for the user's emotions,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, which has a storage device for storing laws and regulations and manuals, and adds supporting information by referring to them.

[0825] (Claim 3)

[0826] The system according to claim 1, which accepts additional questions, performs emotion recognition and information retrieval again, and generates an answer using a generative AI model.

[0827] "Application example 2 when combining with an emotional engine"

[0828] (Claim 1)

[0829] A means of receiving user questions in natural language,

[0830] An emotion analysis means that analyzes the input question and its context to recognize the user's emotions,

[0831] An analytical means for retrieving relevant information based on analyzed questions and emotions,

[0832] A generation means for generating the optimal response based on the retrieved information and recognized emotions,

[0833] A means of adding referenced supporting information to the generated response to enhance its reliability,

[0834] A presentation method that presents answers to users in an emotionally responsive format,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, which pre-registers laws and operating procedures in a database and generates responses that correspond to the user's emotions.

[0838] (Claim 3)

[0839] The system according to claim 1, which accepts additional questions and performs emotion analysis, interpretation, and generation again. [Explanation of symbols]

[0840] 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 of receiving user questions in natural language, An analytical tool that analyzes the input questions and searches for related data, A generation means for generating the optimal answer based on the searched data, A means for adding referenced supporting information to the generated response, A means of presenting the answer to the user, A system that includes this.

2. The system according to claim 1, which pre-registers laws and manuals in a database.

3. The system according to claim 1, which accepts additional questions and performs analysis and generation again.

Images