system

Abstract

We provide the system. [Solution] An information processing device that performs natural language processing, Verification means for an information recording device to confirm the validity of the input information, A means for generating a processing plan and creating work instructions based on the request, An analytical means for evaluating the validity of the post-execution report, A means of receiving requests using an interactive information terminal and analyzing related information, A means for checking inventory information and generating work orders, 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, 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional reception operations, the transfer and confirmation of information rely on a large number of personnel, so the complexity of the operations and the occurrence of human errors have become problems. In response to such problems, it is necessary to improve the efficiency of manual work and reduce mistakes in reception operations. Also, when multilingual support is required, a mechanism for appropriately processing information is required.

Means for Solving the Problems

[0005] This invention constructs a system including a natural language processing unit and incorporates a database verification means to confirm the validity of input information, thereby preventing errors in information. Furthermore, by using means to generate an execution plan for processing based on requests and create work instructions, the amount of manual work performed by humans is reduced, and work progress is made efficient. In addition, it is equipped with analysis means to evaluate the validity of the report after execution, guaranteeing accurate processing results. As a result, it becomes possible to perform information processing in multiple languages ​​and provides a system that can be used not only in data centers but also in various information processing servers.

[0006] "Natural language processing" is a technology that enables computers to understand, analyze, and generate natural language that humans use in everyday life.

[0007] A "processing unit" is a general term for a system consisting of hardware and software that performs information processing and executes specified tasks.

[0008] A "database verification means" is a processing means that compares the input data with an existing database to verify its consistency and accuracy.

[0009] A "request" is an action or indication of content in which a user communicates a specific operation or service they desire from the system.

[0010] A "process execution plan" refers to a detailed plan outlining the steps and resource allocation necessary to perform a requested task.

[0011] "Work instructions" are documents or digital information that specify the concrete procedures and conditions necessary to perform a particular task.

[0012] "Analytical means" refers to techniques and methods for analyzing data and information in detail to clarify their content and structure.

[0013] "Multilingual support" means that data can be input, processed, and output in multiple languages, and that the system has the functionality to accurately exchange information even in different language environments.

[0014] An "information processing server" refers to a computer system that has the ability to receive, process, store, and transmit various types of information, and is particularly responsible for providing services via a network. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

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

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

[0032] As shown in Figure 2, in the data processing device 12, 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.

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

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

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

[0036] This invention provides a system for automating reception operations and reducing human error in those operations. This system uses a program that functions as an agent to automatically verify the validity of user requests, process necessary information, and provide accurate instructions for related tasks.

[0037] System Overview

[0038] The system is server-centric and accepts requests from users in natural language. These requests are parsed using natural language processing to accurately extract their intent. Based on this analysis, the server checks the database to verify the appropriateness of the request.

[0039] Terminals are devices used by users and workers, handling requests from users and receiving instructions for workers. Communication with the server is optimized on the terminals to improve response speed.

[0040] Specific examples of how the system works

[0041] 1. The user sends a message to the system via their device, for example, "I'd like to request that you prepare presentation materials for next month's event." The server receives this message and begins analyzing it.

[0042] 2. Once the server recognizes through natural language processing that the request is for "preparation of presentation materials," it checks the existing request database and compares it to similar requests from the past. This verifies whether the specific content of the request and the required resources are appropriate.

[0043] 3. If the request is valid, the server will create a processing plan and automatically generate instructions to send to the worker. The instructions will include a work overview, required steps, responsible parties, and deadlines.

[0044] 4. When a worker completes a task, they submit a completion report from their terminal. The server then analyzes the report and evaluates its validity as to whether the task was completed. After the evaluation, a completion notification is automatically sent to the user.

[0045] This system significantly reduces human error and improves operational efficiency. Furthermore, its multilingual request system offers flexibility to handle various environments, providing a versatile service.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] Users input and send requests using natural language via their device. Users do not need to be aware of language, as the system supports multiple languages, allowing input in any language.

[0049] Step 2:

[0050] The server receives a request from the user. The received request is analyzed by a natural language processing engine, and its content and intent are extracted. This allows the system to understand the user's specific requirements.

[0051] Step 3:

[0052] The server uses the analysis results to check the database for validity. Here, it compares the request with similar past requests and contract terms to verify that there is no inappropriate content or inconsistency.

[0053] Step 4:

[0054] After the server verifies the validity of the request, it automatically generates an execution plan for processing. This plan includes the steps, responsible parties, and necessary resources for performing the requested task.

[0055] Step 5:

[0056] Based on the execution plan generated by the server, a work order is created. This order is sent to the relevant workers, providing them with the necessary details and procedures for the work.

[0057] Step 6:

[0058] When a task is completed, the worker sends a completion report to the server from their terminal. This report includes details about whether the task was completed as scheduled.

[0059] Step 7:

[0060] The server receives the work completion report and evaluates its contents using specialized analytical tools. After the evaluation is complete, if the report is deemed appropriate, a completion notification is automatically sent to the user.

[0061] This series of processes enables efficient work execution and reduces human error.

[0062] (Example 1)

[0063] 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."

[0064] In today's business environment, there is a growing need for automated systems that can reduce human errors in reception and work instruction processes, and that can flexibly handle multilingual requests. Traditional methods are plagued by communication errors involving multiple workers and language barriers in international business, so efficient solutions are required to overcome these challenges.

[0065] 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.

[0066] In this invention, the server includes an information processing device means for natural language processing, a data set matching means for verifying the validity of input requests, and a means for generating work plans and creating work content based on requests. This enables automation of reception operations, reduction of human error, and multilingual support.

[0067] A "natural language processing device" is a computer system that analyzes natural language text input by a user and understands its meaning and intent.

[0068] A "data set matching means" is a function that compares and contrasts the input requests and data with existing databases to confirm their validity and suitability.

[0069] A "means for generating work plans and creating work content" refers to a system that plans specific work flows and procedures based on user requirements and creates work instructions based on these.

[0070] "Information analysis means" refers to techniques for analyzing the results of work reported after execution and evaluating whether the work was carried out as planned.

[0071] "Means for sending requests via a terminal" refers to an interface or function that allows a user to send a request to a system using a device they are using.

[0072] The "means for receiving work reports and sending completion notifications" refers to a function that receives reports from workers, verifies their contents, and then notifies the user that the work has been completed.

[0073] This invention is an automated reception system that utilizes natural language processing, and is mainly composed of server, terminal, and user interaction. The server, as an information processing device that performs natural language processing, uses a generative AI model to analyze natural language requests received from users. Specifically, it uses models such as BERT and GPT to accurately understand the intent of the request and perform the corresponding processing.

[0074] The server utilizes database management systems such as MySQL® and PostgreSQL as a means of data set matching. This enables a process to compare the content of requests with past cases and benchmark data to verify their validity. Furthermore, the generation of work plans and the creation of work content based on requests are performed automatically based on program logic, and accurate instruction sheets are generated for workers.

[0075] The terminal functions as a device used by users and workers, providing a means for users to send requests to the server. This allows users to easily send requests by entering prompts in text format, such as "I would like to request that presentation materials be prepared for next month's event."

[0076] After receiving a work report, the server evaluates the validity of the report's contents and sends a completion notification to the user. This series of actions reduces human error and improves work efficiency. Furthermore, because it supports multiple languages, it can be easily operated in an international environment.

[0077] As a concrete example, the following are examples of prompt statements.

[0078] "I'd like you to create a project plan for next month's event."

[0079] "Could you please prepare the materials in English for the international conference?"

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user sends a request to the system using a terminal. The user inputs the request in natural language and sends a prompt message, for example, "I would like to request that presentation materials be prepared for next month's event." Based on this input, the terminal sends the data to the server.

[0083] Step 2:

[0084] The server receives a request from the user and performs natural language processing. The server uses a generative AI model to analyze the text and extract its intent. In this process, techniques such as BERT and GPT are used to decompose the input data and clarify its meaning and purpose. The output is the analyzed instruction.

[0085] Step 3:

[0086] The server performs data set matching based on the analyzed instructions. The server uses a database to compare the request with past data and criteria. This comparison process verifies the validity of the request. The input is the analysis result, and the output is the validity verification result.

[0087] Step 4:

[0088] If the server determines the request is valid, it generates a work plan and creates a work order. Based on the request, the server plans which resources are needed and when each task should be performed. The work order includes specific details of the work, such as the person responsible and the deadline. The input is the validity check result, and the output is the work order.

[0089] Step 5:

[0090] Workers receive work instructions from the server using a terminal and perform tasks according to the instructions. In this process, workers perform specific actions to carry out the planned tasks. No feedback is provided regarding the progress of the work at this stage.

[0091] Step 6:

[0092] After completing a task, the worker sends a completion report to the server via their terminal. The report includes details of the work performed and the results. The input is the work completion report data, and the output to the server is the report data.

[0093] Step 7:

[0094] The server receives the completion report and evaluates its validity. The server verifies that the report aligns with the original work plan and generates feedback as needed. The output of this step is a completion notification to the user.

[0095] Step 8:

[0096] Based on the server's evaluation of the report's validity, it sends a completion notification to the user. This allows the user to confirm that the requested task has been completed. The output is the completion notification to the user.

[0097] (Application Example 1)

[0098] 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."

[0099] Traditional in-store reception and inventory management often rely heavily on manual processes, leading to inefficiencies and a high risk of human error. Furthermore, insufficient multilingual support makes it difficult to meet diverse customer needs. A system that addresses these challenges is needed.

[0100] 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.

[0101] In this invention, the server includes an information processing device for natural language processing, a verification means for an information recording device for verifying the validity of input information, and a means for generating a processing plan and creating work instructions based on a request. This automates reception work, reduces human error, and enables efficient multilingual support.

[0102] "Natural language processing" is the technology that enables computers to understand and process human language.

[0103] An "information processing device" is an electronic device used to receive, analyze, calculate, and store data.

[0104] An "information recording device" is a device that stores data and, as needed, verifies or retrieves that data.

[0105] A "comparison means" is a method or apparatus for comparing input information with existing data to confirm whether there is a match or a mismatch.

[0106] A "work instruction sheet" is a document or piece of information that outlines the necessary procedures, assigned personnel, deadlines, and other details required to carry out a specific task.

[0107] An "interactive information terminal" is a communication device that can receive input from a user and return a response in return.

[0108] "Inventory information" refers to data about how many of a particular product or item are in stock.

[0109] A "work instruction" is a set of instructions that outlines the information and procedures necessary to perform a specific task.

[0110] The system implementing this invention mainly consists of a server and a terminal. The server uses spaCy, a Python library for natural language processing, to parse natural language requests received from users. It also uses Firebase for database management and performs verification to confirm the validity of the input information. The server uses Node.js to generate a request processing plan and automatically generate work instructions.

[0111] The terminal is an interactive information terminal for use by users and workers. Developed using React Native, it can operate on both iOS and Android® platforms. The terminal sends user-input requests to the server in real time and receives responses from the server.

[0112] In terms of hardware, typical smartphones and tablets are used as user terminals. On the server side, high-performance server machines or cloud-based server infrastructure are utilized.

[0113] As a concrete example, a user might input "I want to buy clothes suitable for winter" into their device. The server, upon receiving this request, uses natural language processing to analyze the request and generate a list of appropriate products. Based on this list, the user can select products on their device and proceed with reserving or purchasing them.

[0114] An example of a prompt to input into a generative AI model is, "Analyze the natural language request received from the user, check the inventory information for the relevant products, and generate the necessary instructions." This prompt allows the server to accurately understand the content of the request and derive an appropriate response.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] A user enters a specific request using a smartphone application. This request is written in natural language and includes the user's demands and questions. The entered request is output as data sent from the application to the server.

[0118] Step 2:

[0119] The server analyzes the user's request using spaCy, a natural language processing library. Here, the received request is analyzed, and a data structure is output that clearly explains what the request is asking for. This step focuses on analyzing the sentence structure, primarily nouns and verbs, to extract the essence of the request.

[0120] Step 3:

[0121] The server uses the analyzed data to match it with inventory information and other data in the database. This matching uses Firebase's real-time database. The input is matched with inventory information using the analysis results, and a list of relevant products and information is generated as output. This verification confirms whether the user's request is truly possible.

[0122] Step 4:

[0123] The server automatically generates work instructions as a response to the user based on the matching results. It structures the information and creates a dataset to present related information in an easy-to-understand format for the user. This dataset becomes the output sent to the user.

[0124] Step 5:

[0125] The user receives the response from the server through their device. Here, the information returned to the smartphone is displayed as a list or detail screen. Based on this information, the user can select products or request more detailed information. A new request may also be created as output.

[0126] Step 6:

[0127] Upon completion of the process, the user confirms through the application that the information entered on the screen has been processed and the results are automatically displayed. These results include a confirmation screen for reserved items and options for additional orders. The output at this stage provides information for the user to determine their next action.

[0128] 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.

[0129] This invention is a system for recognizing user emotions during user request processing and optimizing responses and work instructions based on those emotions. This system utilizes natural language processing and an emotion engine to automate multilingual and emotion-responsive business processes.

[0130] System Overview

[0131] The server plays a central role, receiving user requests and performing natural language processing. During the natural language processing, an emotion engine is activated to analyze the user's emotions and extract emotional data from the user's writing. This ensures that processing takes into account not only the request content but also the user's emotional state.

[0132] The terminal is used as an interface for users to enter requests. After the emotion engine analyzes the user's emotions, the user is given feedback on the most appropriate response or instructions.

[0133] Specific examples of how the system works

[0134] 1. When a user sends an inquiry to the system using their device, they enter a message that conveys emotion, such as "I need the information immediately, and it's very urgent." This message is sent to the server.

[0135] 2. The server analyzes the content of the request from the received message through natural language processing. Simultaneously, the emotion engine activates to detect emotions such as "urgent" from the message.

[0136] 3. Based on the analyzed sentiment information, the server sets the request's priority higher than usual and generates an execution plan for processing that allows for a quick response. Based on that plan, urgent instructions are generated and sent to the relevant workers.

[0137] 4. If the work is completed as scheduled, a completion report is sent by the worker. The server analyzes the report and promptly sends a completion notification to the user.

[0138] This system can dynamically adjust tasks in response to user emotions, leading to even greater customer satisfaction. Furthermore, its multilingual capabilities enable consistent service delivery to users from all cultural backgrounds.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] Users use their devices to input and send requests in natural language. These messages may contain emotional nuances, such as "I need this addressed urgently."

[0142] Step 2:

[0143] The server receives a request from the user and uses a natural language processing engine to parse the message. While understanding the request, the sentiment engine extracts the user's emotions and detects that they are in a hurry.

[0144] Step 3:

[0145] The server checks the database to verify the validity of the request. It integrates the request content with user sentiment information to dynamically set the request priority. If it determines that an urgent response is needed, it performs a process to increase the processing priority.

[0146] Step 4:

[0147] The server generates an execution plan for the most efficient processing based on the request. This plan is faster than the normal processing flow and sends a work order to the relevant workers. This order includes a note indicating the urgency of the task and the necessary details.

[0148] Step 5:

[0149] After completing the work, the worker sends a completion report to the server using their terminal. This report includes information indicating whether the work was completed as requested.

[0150] Step 6:

[0151] The server receives the completion report and analyzes its contents. It evaluates whether the completion report is valid and promptly sends a completion notification to the user. This notification informs the user that their request has been successfully completed and provides feedback on the results in a sentiment-sensitive manner.

[0152] This approach enables system operation that incorporates user emotions, leading to the provision of more appropriate services.

[0153] (Example 2)

[0154] 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".

[0155] Modern information processing systems require the generation of optimal responses and work instructions that take into account the emotions contained in user requests. However, conventional systems have suffered from the problem of failing to meet user expectations due to insufficient sentiment analysis, resulting in decreased customer satisfaction. Furthermore, the complexity of multilingual support has made it difficult to provide consistent service to a global user base.

[0156] 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.

[0157] In this invention, the server includes an information processing device for natural language processing, an information storage device for verifying the validity of input information, and a device capable of analyzing emotions from the input information and resetting priorities. This enables multilingual support while considering the user's emotions, and allows for the provision of fast and appropriate services through dynamic adjustment of priorities.

[0158] A "natural language processing unit" is a computing device that analyzes natural language text input by a user and understands its meaning and intent.

[0159] An "information storage device" is a device used to store various types of data in a specific manner and to verify the validity of that data as needed.

[0160] An "information processing device" is a computer that processes input information through calculations and operations and generates output according to a specific purpose.

[0161] A "device for analyzing emotions" is an analytical device that extracts emotions from a user's text messages and adjusts the priority and processing method of information based on those emotions.

[0162] "Multilingual support" refers to the ability to process information written in different languages ​​and produce consistent results through translation and cross-language adjustments.

[0163] "Reprioritizing" is the operation of dynamically changing the importance and urgency of a particular process or task according to the situation.

[0164] This invention is a system that accurately grasps the diverse emotions of users and automatically generates responses and work instructions accordingly. This system consists of a server that performs natural language processing, a terminal operated by the user, and an information processing device that performs complex emotion analysis.

[0165] The server is primarily responsible for natural language processing, utilizing libraries such as Python's Natural Language Toolkit (NLTK) and TENSORFLOW®. These tools allow for morphological analysis of user-input text messages, providing a deep understanding of context and grammar. Furthermore, the server uses the Hugging Face Transformers library as its emotion engine to extract user emotions.

[0166] The device serves to provide an interface for users to input messages in natural language. This interface is multilingual and designed to accurately process questions and requests entered by users in different languages.

[0167] Messages from users may contain emotional or urgent content, such as "The project deadline is fast approaching, and I need a quick response." When the server receives such a message, it analyzes the emotional nuances and dynamically adjusts the request's priority. As a result, it becomes possible to quickly plan the necessary actions and responses.

[0168] As a concrete example, here is an example of a prompt message for a generative AI model: "How should the AI ​​respond and act when the user displays 'This is very urgent, and I would like it done by the end of today if possible.'" This prompt allows the AI ​​to accurately determine the user's urgency and take appropriate action.

[0169] Thus, the present invention is a system that integrates emotion analysis and automated processes to realize the provision of services that meet user needs.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The user enters a message in natural language using a terminal. For example, they might enter a request such as, "I need to finish the project this week, but I'm worried." This input is text data containing the user's request and feelings. This is sent to the server and used as data for the next processing step.

[0173] Step 2:

[0174] The server analyzes messages received from users using a natural language processing engine. Leveraging Python's NLTK and TensorFlow, it performs morphological analysis on messages to understand grammatical structure and vocabulary meaning. This analysis processes the request content and the sentiment contained within the sentence, and the analyzed data is output.

[0175] Step 3:

[0176] The server uses the analyzed data to activate the emotion engine. It utilizes Hugging Face's Transformers to extract emotions such as "worry" and "urgency" from the text. This extraction process generates emotion labels, which are then output as emotion data.

[0177] Step 4:

[0178] The server repriors requests based on sentiment data. If high urgency is detected, the request's priority is increased, and an immediate response plan is generated. Data processing automatically adjusts schedules and resources, and a new execution plan is output.

[0179] Step 5:

[0180] The server creates a corresponding work order based on the generated execution plan and sends it to the assigned worker. Specifically, an instruction sheet is created that details resource allocation and necessary procedures. This process outputs the work order and distributes it appropriately to the relevant personnel.

[0181] (Application Example 2)

[0182] 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".

[0183] In modern information processing and service delivery, it is necessary not only to receive and respond to user requests, but also to dynamically adjust responses according to the user's emotions and circumstances. However, conventional systems struggle to optimize responses and work instructions while considering user emotions, resulting in a limited user experience.

[0184] 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.

[0185] In this invention, the server includes an information processing device for natural language processing, an information-based matching means for verifying the validity of input information, a means for generating an execution plan for processing based on a request and creating work instructions, a means for recognizing the user's emotions and optimizing work instructions based on those emotions, and an analysis means for evaluating the validity of the post-execution report. This makes it possible to provide an excellent experience that responds immediately to the user's emotions.

[0186] A "natural language processing device" is a device that analyzes textual information input by a user, understands its meaning and structure, and processes instructions and questions accordingly.

[0187] An "information-based verification method" is a function that compares input information with a specific database or information source in order to verify its accuracy and validity.

[0188] "Means for generating execution plans and creating work instructions" refers to a function that formulates specific task execution procedures in response to user requests and creates instructions based on those procedures.

[0189] "Means of recognizing user emotions and optimizing work instructions based on those emotions" refers to a function that detects the emotions a user expresses and adjusts task priorities and procedures while taking those emotions into consideration.

[0190] "Analysis means" refers to functions for evaluating the results of an executed task and analyzing its validity and effectiveness.

[0191] The system for realizing this invention consists of a server for information processing and a terminal for the user to input information. The server combines natural language processing and emotion recognition technology to generate the optimal response according to the user's request.

[0192] The server runs Python-based programs and uses NLTK as its natural language processing library. It also utilizes sentiment analysis tools such as Google Cloud Natural Language API for sentiment recognition. This configuration enables semantic analysis and sentiment identification of text received from users.

[0193] The user input received by the server is first analyzed using natural language processing. The data obtained from this analysis includes the language and grammatical structure of the text, as well as the user's intent. Subsequently, emotion recognition evaluates the user's emotional state, identifying emotions such as whether they are in a hurry or calm.

[0194] After receiving a series of pieces of information, the server prioritizes work instructions and guides users through specific steps based on their emotional state. For example, if a user requests "immediate help," the server recognizes the urgency through emotional recognition and prepares a rapid response.

[0195] For example, if this system were incorporated into a home robot, when a user requests cooking assistance, the system would analyze the recipe and provide instructions to efficiently prepare the food. If the user is in a hurry, the system would optimize the process by selecting a simpler dish.

[0196] Using a generative AI model, the following can be considered as examples of prompt statements.

[0197] "Think of ways to help users perform tasks they find difficult more smoothly."

[0198] This will enable the system to provide more human-centered services that are tailored to the user's intentions.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The user inputs information through a device. This input can be in text or voice format and includes the user's requests and emotions. This data is then sent to the server.

[0202] Step 2:

[0203] The server receives the input data and begins analysis using the NLTK natural language processing library. The data analyzed consists of extracted semantic information, including grammatical structure and keywords. This clarifies the content of the request.

[0204] Step 3:

[0205] The server applies an emotion recognition algorithm and uses the Google Cloud Natural Language API to extract emotion data from the input data. Examples of emotion data identified include "hurried" and "calm."

[0206] Step 4:

[0207] The server prioritizes tasks based on the results of natural language processing and sentiment data. Priority data is generated, and if a user's request is urgent, it is given a higher priority.

[0208] Step 5:

[0209] The server generates work instructions according to the set priority. For example, it creates and outputs specific instructions such as "Start cooking immediately" as an instruction for operating a household robot.

[0210] Step 6:

[0211] Work instructions are sent to the relevant work equipment or terminals and executed. In the case of robots, they start cooking or other tasks according to the instructions.

[0212] Step 7:

[0213] Once the task is complete, the work unit reports the results to the server. The server analyzes the results and sends a completion notification to the user. Upon receiving the completion notification, the user confirms that the actions were performed correctly.

[0214] In this way, the entire system works in coordination, enabling flexible responses that respond to the user's emotions.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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".

[0231] This invention provides a system for automating reception operations and reducing human error in those operations. This system uses a program that functions as an agent to automatically verify the validity of user requests, process necessary information, and provide accurate instructions for related tasks.

[0232] System Overview

[0233] The system is server-centric and accepts requests from users in natural language. These requests are parsed using natural language processing to accurately extract their intent. Based on this analysis, the server checks the database to verify the appropriateness of the request.

[0234] Terminals are devices used by users and workers, handling requests from users and receiving instructions for workers. Communication with the server is optimized on the terminals to improve response speed.

[0235] Specific examples of how the system works

[0236] 1. The user sends a message to the system via their device, for example, "I'd like to request that you prepare presentation materials for next month's event." The server receives this message and begins analyzing it.

[0237] 2. Once the server recognizes through natural language processing that the request is for "preparation of presentation materials," it checks the existing request database and compares it to similar requests from the past. This verifies whether the specific content of the request and the required resources are appropriate.

[0238] 3. If the request is valid, the server will create a processing plan and automatically generate instructions to send to the worker. The instructions will include a work overview, required steps, responsible parties, and deadlines.

[0239] 4. When a worker completes a task, they submit a completion report from their terminal. The server then analyzes the report and evaluates its validity as to whether the task was completed. After the evaluation, a completion notification is automatically sent to the user.

[0240] This system significantly reduces human error and improves operational efficiency. Furthermore, its multilingual request system offers flexibility to handle various environments, providing a versatile service.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] Users input and send requests using natural language via their device. Users do not need to be aware of language, as the system supports multiple languages, allowing input in any language.

[0244] Step 2:

[0245] The server receives a request from the user. The received request is analyzed by a natural language processing engine, and its content and intent are extracted. This allows the system to understand the user's specific requirements.

[0246] Step 3:

[0247] The server uses the analysis results to check the database for validity. Here, it compares the request with similar past requests and contract terms to verify that there is no inappropriate content or inconsistency.

[0248] Step 4:

[0249] After the server verifies the validity of the request, it automatically generates an execution plan for processing. This plan includes the steps, responsible parties, and necessary resources for performing the requested task.

[0250] Step 5:

[0251] Based on the execution plan generated by the server, a work order is created. This order is sent to the relevant workers, providing them with the necessary details and procedures for the work.

[0252] Step 6:

[0253] When a task is completed, the worker sends a completion report to the server from their terminal. This report includes details about whether the task was completed as scheduled.

[0254] Step 7:

[0255] The server receives the work completion report and evaluates its contents using specialized analytical tools. After the evaluation is complete, if the report is deemed appropriate, a completion notification is automatically sent to the user.

[0256] This series of processes enables efficient work execution and reduces human error.

[0257] (Example 1)

[0258] 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."

[0259] In today's business environment, there is a growing need for automated systems that can reduce human errors in reception and work instruction processes, and that can flexibly handle multilingual requests. Traditional methods are plagued by communication errors involving multiple workers and language barriers in international business, so efficient solutions are required to overcome these challenges.

[0260] 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.

[0261] In this invention, the server includes an information processing device means for natural language processing, a data set matching means for verifying the validity of input requests, and a means for generating work plans and creating work content based on requests. This enables automation of reception operations, reduction of human error, and multilingual support.

[0262] A "natural language processing device" is a computer system that analyzes natural language text input by a user and understands its meaning and intent.

[0263] A "data set matching means" is a function that compares and contrasts the input requests and data with existing databases to confirm their validity and suitability.

[0264] A "means for generating work plans and creating work content" refers to a system that plans specific work flows and procedures based on user requirements and creates work instructions based on these.

[0265] "Information analysis means" refers to techniques for analyzing the results of work reported after execution and evaluating whether the work was carried out as planned.

[0266] "Means for sending requests via a terminal" refers to an interface or function that allows a user to send a request to a system using a device they are using.

[0267] The "means for receiving work reports and sending completion notifications" refers to a function that receives reports from workers, verifies their contents, and then notifies the user that the work has been completed.

[0268] This invention is an automated reception system that utilizes natural language processing, and is mainly composed of server, terminal, and user interaction. The server, as an information processing device that performs natural language processing, uses a generative AI model to analyze natural language requests received from users. Specifically, it uses models such as BERT and GPT to accurately understand the intent of the request and perform the corresponding processing.

[0269] The server utilizes database management systems such as MySQL and PostgreSQL as a means of data set matching. This enables a process to compare the content of requests with past cases and benchmark data to verify their validity. Furthermore, the generation of work plans and the creation of work details based on requests are performed automatically based on program logic, and accurate instructions are generated for workers.

[0270] The terminal functions as a device used by users and workers, providing a means for users to send requests to the server. This allows users to easily send requests by entering prompts in text format, such as "I would like to request that presentation materials be prepared for next month's event."

[0271] After receiving a work report, the server evaluates the validity of the report's contents and sends a completion notification to the user. This series of actions reduces human error and improves work efficiency. Furthermore, because it supports multiple languages, it can be easily operated in an international environment.

[0272] As a concrete example, the following are examples of prompt statements.

[0273] "I'd like you to create a project plan for next month's event."

[0274] "Could you please prepare the materials in English for the international conference?"

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The user sends a request to the system using a terminal. The user inputs the request in natural language and sends a prompt message, for example, "I would like to request that presentation materials be prepared for next month's event." Based on this input, the terminal sends the data to the server.

[0278] Step 2:

[0279] The server receives a request from the user and performs natural language processing. The server uses a generative AI model to analyze the text and extract its intent. In this process, technologies such as BERT and GPT are used to decompose the input data and clarify its meaning and purpose. As output, the analyzed instruction content is generated.

[0280] Step 3:

[0281] The server performs data set matching based on the analyzed instruction content. The server uses a database to compare the past data and criteria with the request. Through this comparison process, the validity of the request is confirmed. The input is the analysis result, and the output is the result of the validity confirmation.

[0282] Step 4:

[0283] If the server determines that the request is valid, it generates a work plan and creates a work instruction. Based on the request, the server plans which resources are needed and which tasks should be performed at what timing. The work instruction includes specific work content such as the person in charge and the deadline. The input is the result of the validity confirmation, and the output is the work instruction.

[0284] Step 5:

[0285] The worker uses the terminal to receive the work instruction from the server and performs the task according to the instruction. In this process, the worker performs specific actions to implement the planned task. At this stage, no feedback on the progress of the work is given.

[0286] Step 6:

[0287] After completing a task, the worker sends a completion report to the server via their terminal. The report includes details of the work performed and the results. The input is the work completion report data, and the output to the server is the report data.

[0288] Step 7:

[0289] The server receives the completion report and evaluates its validity. The server verifies that the report aligns with the original work plan and generates feedback as needed. The output of this step is a completion notification to the user.

[0290] Step 8:

[0291] Based on the server's evaluation of the report's validity, it sends a completion notification to the user. This allows the user to confirm that the requested task has been completed. The output is the completion notification to the user.

[0292] (Application Example 1)

[0293] 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."

[0294] Traditional in-store reception and inventory management often rely heavily on manual processes, leading to inefficiencies and a high risk of human error. Furthermore, insufficient multilingual support makes it difficult to meet diverse customer needs. A system that addresses these challenges is needed.

[0295] 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.

[0296] In this invention, the server includes an information processing device for natural language processing, a verification means for an information recording device for verifying the validity of input information, and a means for generating a processing plan and creating work instructions based on a request. This automates reception work, reduces human error, and enables efficient multilingual support.

[0297] "Natural language processing" is the technology that enables computers to understand and process human language.

[0298] An "information processing device" is an electronic device used to receive, analyze, calculate, and store data.

[0299] An "information recording device" is a device that stores data and, as needed, verifies or retrieves that data.

[0300] A "comparison means" is a method or apparatus for comparing input information with existing data to confirm whether there is a match or a mismatch.

[0301] A "work instruction sheet" is a document or piece of information that outlines the necessary procedures, assigned personnel, deadlines, and other details required to carry out a specific task.

[0302] An "interactive information terminal" is a communication device that can receive input from a user and return a response in return.

[0303] "Inventory information" refers to data about how many of a particular product or item are in stock.

[0304] A "work instruction" is a set of instructions that outlines the information and procedures necessary to perform a specific task.

[0305] The system for implementing this invention is mainly composed of a server and a terminal. The server uses spaCy, a Python library for natural language processing, to analyze natural language requests received from users. Additionally, Firebase is used for database management to perform collation to confirm the validity of the input information. The server uses Node.js and has the function of generating a request processing plan and automatically generating work instructions.

[0306] The terminal is an interactive information terminal for users and operators to use. This terminal is developed using React Native and is operable on both iOS and Android platforms. The terminal sends the requests input by the user to the server in real time and receives responses from the server.

[0307] As hardware, general smartphones and tablets are used as user terminals. On the server side, high-performance server machines or cloud-based server infrastructures are utilized.

[0308] As a specific example, a user inputs "I want to buy clothes suitable for winter" into the terminal. The server that receives this request makes full use of natural language processing, analyzes the request, and generates an appropriate product list. Based on the result, the user can select products on the terminal and proceed with the reservation or purchase procedure.

[0309] An example of the prompt text input to the generation AI model is "Analyze the natural language request received from the user, check the inventory information of related products, and generate necessary instructions." With this prompt text, the server can accurately understand the content of the request and derive an appropriate answer.

[0310] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0311] Step 1:

[0312] A user enters a specific request using a smartphone application. This request is written in natural language and includes the user's demands and questions. The entered request is output as data sent from the application to the server.

[0313] Step 2:

[0314] The server analyzes the user's request using spaCy, a natural language processing library. Here, the received request is analyzed, and a data structure is output that clearly explains what the request is asking for. This step focuses on analyzing the sentence structure, primarily nouns and verbs, to extract the essence of the request.

[0315] Step 3:

[0316] The server uses the analyzed data to match it with inventory information and other data in the database. This matching uses Firebase's real-time database. The input is matched with inventory information using the analysis results, and a list of relevant products and information is generated as output. This verification confirms whether the user's request is truly possible.

[0317] Step 4:

[0318] The server automatically generates work instructions as a response to the user based on the matching results. It structures the information and creates a dataset to present related information in an easy-to-understand format for the user. This dataset becomes the output sent to the user.

[0319] Step 5:

[0320] The user receives the response from the server through their device. Here, the information returned to the smartphone is displayed as a list or detail screen. Based on this information, the user can select products or request more detailed information. A new request may also be created as output.

[0321] Step 6:

[0322] Upon completion of the process, the user confirms through the application that the information entered on the screen has been processed and the results are automatically displayed. These results include a confirmation screen for reserved items and options for additional orders. The output at this stage provides information for the user to determine their next action.

[0323] 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.

[0324] This invention is a system for recognizing user emotions during user request processing and optimizing responses and work instructions based on those emotions. This system utilizes natural language processing and an emotion engine to automate multilingual and emotion-responsive business processes.

[0325] System Overview

[0326] The server plays a central role, receiving user requests and performing natural language processing. During the natural language processing, an emotion engine is activated to analyze the user's emotions and extract emotional data from the user's writing. This ensures that processing takes into account not only the request content but also the user's emotional state.

[0327] The terminal is used as an interface for users to enter requests. After the emotion engine analyzes the user's emotions, the user is given feedback on the most appropriate response or instructions.

[0328] Specific examples of how the system works

[0329] 1. When a user sends an inquiry to the system using their device, they enter a message that conveys emotion, such as "I need the information immediately, and it's very urgent." This message is sent to the server.

[0330] 2. The server analyzes the content of the request from the received message through natural language processing. Simultaneously, the emotion engine activates to detect emotions such as "urgent" from the message.

[0331] 3. Based on the analyzed sentiment information, the server sets the request's priority higher than usual and generates an execution plan for processing that allows for a quick response. Based on that plan, urgent instructions are generated and sent to the relevant workers.

[0332] 4. If the work is completed as scheduled, a completion report is sent by the worker. The server analyzes the report and promptly sends a completion notification to the user.

[0333] This system can dynamically adjust tasks in response to user emotions, leading to even greater customer satisfaction. Furthermore, its multilingual capabilities enable consistent service delivery to users from all cultural backgrounds.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] Users use their devices to input and send requests in natural language. These messages may contain emotional nuances, such as "I need this addressed urgently."

[0337] Step 2:

[0338] The server receives a request from the user and uses a natural language processing engine to parse the message. While understanding the request, the sentiment engine extracts the user's emotions and detects that they are in a hurry.

[0339] Step 3:

[0340] The server checks the database to verify the validity of the request. It integrates the request content with user sentiment information to dynamically set the request priority. If it determines that an urgent response is needed, it performs a process to increase the processing priority.

[0341] Step 4:

[0342] The server generates an execution plan for the most efficient processing based on the request. This plan is faster than the normal processing flow and sends a work order to the relevant workers. This order includes a note indicating the urgency of the task and the necessary details.

[0343] Step 5:

[0344] After completing the work, the worker sends a completion report to the server using their terminal. This report includes information indicating whether the work was completed as requested.

[0345] Step 6:

[0346] The server receives the completion report and analyzes its contents. It evaluates whether the completion report is valid and promptly sends a completion notification to the user. This notification informs the user that their request has been successfully completed and provides feedback on the results in a sentiment-sensitive manner.

[0347] This approach enables system operation that incorporates user emotions, leading to the provision of more appropriate services.

[0348] (Example 2)

[0349] 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".

[0350] Modern information processing systems require the generation of optimal responses and work instructions that take into account the emotions contained in user requests. However, conventional systems have suffered from the problem of failing to meet user expectations due to insufficient sentiment analysis, resulting in decreased customer satisfaction. Furthermore, the complexity of multilingual support has made it difficult to provide consistent service to a global user base.

[0351] 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.

[0352] In this invention, the server includes an information processing device for natural language processing, an information storage device for verifying the validity of input information, and a device capable of analyzing emotions from the input information and resetting priorities. This enables multilingual support while considering the user's emotions, and allows for the provision of fast and appropriate services through dynamic adjustment of priorities.

[0353] A "natural language processing unit" is a computing device that analyzes natural language text input by a user and understands its meaning and intent.

[0354] An "information storage device" is a device used to store various types of data in a specific manner and to verify the validity of that data as needed.

[0355] An "information processing device" is a computer that processes input information through calculations and operations and generates output according to a specific purpose.

[0356] A "device for analyzing emotions" is an analytical device that extracts emotions from a user's text messages and adjusts the priority and processing method of information based on those emotions.

[0357] "Multilingual support" refers to the ability to process information written in different languages ​​and produce consistent results through translation and cross-language adjustments.

[0358] "Reprioritizing" is the operation of dynamically changing the importance and urgency of a particular process or task according to the situation.

[0359] This invention is a system that accurately grasps the diverse emotions of users and automatically generates responses and work instructions accordingly. This system consists of a server that performs natural language processing, a terminal operated by the user, and an information processing device that performs complex emotion analysis.

[0360] The server is primarily responsible for natural language processing, utilizing libraries such as Python's Natural Language Toolkit (NLTK) and TensorFlow. These tools allow it to perform morphological analysis on user-input text messages, gaining a deep understanding of their context and grammar. Furthermore, the server uses the Hugging Face Transformers library as its emotion engine to extract user emotions.

[0361] The device serves to provide an interface for users to input messages in natural language. This interface is multilingual and designed to accurately process questions and requests entered by users in different languages.

[0362] Messages from users may contain emotional or urgent content, such as "The project deadline is fast approaching, and I need a quick response." When the server receives such a message, it analyzes the emotional nuances and dynamically adjusts the request's priority. As a result, it becomes possible to quickly plan the necessary actions and responses.

[0363] As a concrete example, here is an example of a prompt message for a generative AI model: "How should the AI ​​respond and act when the user displays 'This is very urgent, and I would like it done by the end of today if possible.'" This prompt allows the AI ​​to accurately determine the user's urgency and take appropriate action.

[0364] Thus, the present invention is a system that integrates emotion analysis and automated processes to realize the provision of services that meet user needs.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The user enters a message in natural language using a terminal. For example, they might enter a request such as, "I need to finish the project this week, but I'm worried." This input is text data containing the user's request and feelings. This is sent to the server and used as data for the next processing step.

[0368] Step 2:

[0369] The server analyzes messages received from users using a natural language processing engine. Leveraging Python's NLTK and TensorFlow, it performs morphological analysis on messages to understand grammatical structure and vocabulary meaning. This analysis processes the request content and the sentiment contained within the sentence, and the analyzed data is output.

[0370] Step 3:

[0371] The server uses the analyzed data to activate the emotion engine. It utilizes Hugging Face's Transformers to extract emotions such as "worry" and "urgency" from the text. This extraction process generates emotion labels, which are then output as emotion data.

[0372] Step 4:

[0373] The server repriors requests based on sentiment data. If high urgency is detected, the request's priority is increased, and an immediate response plan is generated. Data processing automatically adjusts schedules and resources, and a new execution plan is output.

[0374] Step 5:

[0375] The server creates a corresponding work order based on the generated execution plan and sends it to the assigned worker. Specifically, an instruction sheet is created that details resource allocation and necessary procedures. This process outputs the work order and distributes it appropriately to the relevant personnel.

[0376] (Application Example 2)

[0377] 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."

[0378] In modern information processing and service delivery, it is necessary not only to receive and respond to user requests, but also to dynamically adjust responses according to the user's emotions and circumstances. However, conventional systems struggle to optimize responses and work instructions while considering user emotions, resulting in a limited user experience.

[0379] 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.

[0380] In this invention, the server includes an information processing device for natural language processing, an information-based matching means for verifying the validity of input information, a means for generating an execution plan for processing based on a request and creating work instructions, a means for recognizing the user's emotions and optimizing work instructions based on those emotions, and an analysis means for evaluating the validity of the post-execution report. This makes it possible to provide an excellent experience that responds immediately to the user's emotions.

[0381] A "natural language processing device" is a device that analyzes textual information input by a user, understands its meaning and structure, and processes instructions and questions accordingly.

[0382] An "information-based verification method" is a function that compares input information with a specific database or information source in order to verify its accuracy and validity.

[0383] "Means for generating execution plans and creating work instructions" refers to a function that formulates specific task execution procedures in response to user requests and creates instructions based on those procedures.

[0384] "Means of recognizing user emotions and optimizing work instructions based on those emotions" refers to a function that detects the emotions a user expresses and adjusts task priorities and procedures while taking those emotions into consideration.

[0385] "Analysis means" refers to functions for evaluating the results of an executed task and analyzing its validity and effectiveness.

[0386] The system for realizing this invention consists of a server for information processing and a terminal for the user to input information. The server combines natural language processing and emotion recognition technology to generate the optimal response according to the user's request.

[0387] The server runs Python-based programs and uses NLTK as its natural language processing library. It also utilizes sentiment analysis tools such as the Google Cloud Natural Language API for sentiment recognition. This configuration enables semantic analysis and sentiment identification of text received from users.

[0388] The user input received by the server is first analyzed using natural language processing. The data obtained from this analysis includes the language and grammatical structure of the text, as well as the user's intent. Subsequently, emotion recognition evaluates the user's emotional state, identifying emotions such as whether they are in a hurry or calm.

[0389] After receiving a series of pieces of information, the server prioritizes work instructions and guides users through specific steps based on their emotional state. For example, if a user requests "immediate help," the server recognizes the urgency through emotional recognition and prepares a rapid response.

[0390] For example, if this system were incorporated into a home robot, when a user requests cooking assistance, the system would analyze the recipe and provide instructions to efficiently prepare the food. If the user is in a hurry, the system would optimize the process by selecting a simpler dish.

[0391] Using a generative AI model, the following can be considered as examples of prompt statements.

[0392] "Think of ways to help users perform tasks they find difficult more smoothly."

[0393] This will enable the system to provide more human-centered services that are tailored to the user's intentions.

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The user inputs information through a device. This input can be in text or voice format and includes the user's requests and emotions. This data is then sent to the server.

[0397] Step 2:

[0398] The server receives the input data and begins analysis using the NLTK natural language processing library. The data analyzed consists of extracted semantic information, including grammatical structure and keywords. This clarifies the content of the request.

[0399] Step 3:

[0400] The server applies an emotion recognition algorithm and uses the Google Cloud Natural Language API to extract emotion data from the input data. Examples of emotion data identified include "hurried" and "calm."

[0401] Step 4:

[0402] The server prioritizes tasks based on the results of natural language processing and sentiment data. Priority data is generated, and if a user's request is urgent, it is given a higher priority.

[0403] Step 5:

[0404] The server generates work instructions according to the set priority. For example, it creates and outputs specific instructions such as "Start cooking immediately" as an instruction for operating a household robot.

[0405] Step 6:

[0406] Work instructions are sent to the relevant work equipment or terminals and executed. In the case of robots, they start cooking or other tasks according to the instructions.

[0407] Step 7:

[0408] Once the task is complete, the work unit reports the results to the server. The server analyzes the results and sends a completion notification to the user. Upon receiving the completion notification, the user confirms that the actions were performed correctly.

[0409] In this way, the entire system works in coordination, enabling flexible responses that respond to the user's emotions.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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".

[0426] This invention provides a system for automating reception operations and reducing human error in those operations. This system uses a program that functions as an agent to automatically verify the validity of user requests, process necessary information, and provide accurate instructions for related tasks.

[0427] System Overview

[0428] The system is server-centric and accepts requests from users in natural language. These requests are parsed using natural language processing to accurately extract their intent. Based on this analysis, the server checks the database to verify the appropriateness of the request.

[0429] Terminals are devices used by users and workers, handling requests from users and receiving instructions for workers. Communication with the server is optimized on the terminals to improve response speed.

[0430] Specific examples of how the system works

[0431] 1. The user sends a message to the system via their device, for example, "I'd like to request that you prepare presentation materials for next month's event." The server receives this message and begins analyzing it.

[0432] 2. Once the server recognizes through natural language processing that the request is for "preparation of presentation materials," it checks the existing request database and compares it to similar requests from the past. This verifies whether the specific content of the request and the required resources are appropriate.

[0433] 3. If the request is valid, the server will create a processing plan and automatically generate instructions to send to the worker. The instructions will include a work overview, required steps, responsible parties, and deadlines.

[0434] 4. When a worker completes a task, they submit a completion report from their terminal. The server then analyzes the report and evaluates its validity as to whether the task was completed. After the evaluation, a completion notification is automatically sent to the user.

[0435] This system significantly reduces human error and improves operational efficiency. Furthermore, its multilingual request system offers flexibility to handle various environments, providing a versatile service.

[0436] The following describes the processing flow.

[0437] Step 1:

[0438] Users input and send requests using natural language via their device. Users do not need to be aware of language, as the system supports multiple languages, allowing input in any language.

[0439] Step 2:

[0440] The server receives a request from the user. The received request is analyzed by a natural language processing engine, and its content and intent are extracted. This allows the system to understand the user's specific requirements.

[0441] Step 3:

[0442] The server uses the analysis results to check the database for validity. Here, it compares the request with similar past requests and contract terms to verify that there is no inappropriate content or inconsistency.

[0443] Step 4:

[0444] After the server verifies the validity of the request, it automatically generates an execution plan for processing. This plan includes the steps, responsible parties, and necessary resources for performing the requested task.

[0445] Step 5:

[0446] Based on the execution plan generated by the server, a work order is created. This order is sent to the relevant workers, providing them with the necessary details and procedures for the work.

[0447] Step 6:

[0448] When a task is completed, the worker sends a completion report to the server from their terminal. This report includes details about whether the task was completed as scheduled.

[0449] Step 7:

[0450] The server receives the work completion report and evaluates its contents using specialized analytical tools. After the evaluation is complete, if the report is deemed appropriate, a completion notification is automatically sent to the user.

[0451] This series of processes enables efficient work execution and reduces human error.

[0452] (Example 1)

[0453] 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."

[0454] In today's business environment, there is a growing need for automated systems that can reduce human errors in reception and work instruction processes, and that can flexibly handle multilingual requests. Traditional methods are plagued by communication errors involving multiple workers and language barriers in international business, so efficient solutions are required to overcome these challenges.

[0455] 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.

[0456] In this invention, the server includes an information processing device means for natural language processing, a data set matching means for verifying the validity of input requests, and a means for generating work plans and creating work content based on requests. This enables automation of reception operations, reduction of human error, and multilingual support.

[0457] A "natural language processing device" is a computer system that analyzes natural language text input by a user and understands its meaning and intent.

[0458] A "data set matching means" is a function that compares and contrasts the input requests and data with existing databases to confirm their validity and suitability.

[0459] A "means for generating work plans and creating work content" refers to a system that plans specific work flows and procedures based on user requirements and creates work instructions based on these.

[0460] "Information analysis means" refers to techniques for analyzing the results of work reported after execution and evaluating whether the work was carried out as planned.

[0461] "Means for sending requests via a terminal" refers to an interface or function that allows a user to send a request to a system using a device they are using.

[0462] The "means for receiving work reports and sending completion notifications" refers to a function that receives reports from workers, verifies their contents, and then notifies the user that the work has been completed.

[0463] This invention is an automated reception system that utilizes natural language processing, and is mainly composed of server, terminal, and user interaction. The server, as an information processing device that performs natural language processing, uses a generative AI model to analyze natural language requests received from users. Specifically, it uses models such as BERT and GPT to accurately understand the intent of the request and perform the corresponding processing.

[0464] The server utilizes database management systems such as MySQL and PostgreSQL as a means of data set matching. This enables a process to compare the content of requests with past cases and benchmark data to verify their validity. Furthermore, the generation of work plans and the creation of work details based on requests are performed automatically based on program logic, and accurate instructions are generated for workers.

[0465] The terminal functions as a device used by users and workers, providing a means for users to send requests to the server. This allows users to easily send requests by entering prompts in text format, such as "I would like to request that presentation materials be prepared for next month's event."

[0466] After receiving a work report, the server evaluates the validity of the report's contents and sends a completion notification to the user. This series of actions reduces human error and improves work efficiency. Furthermore, because it supports multiple languages, it can be easily operated in an international environment.

[0467] As a concrete example, the following are examples of prompt statements.

[0468] "I'd like you to create a project plan for next month's event."

[0469] "Could you please prepare the materials in English for the international conference?"

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Step 1:

[0472] The user sends a request to the system using a terminal. The user inputs the request in natural language and sends a prompt message, for example, "I would like to request that presentation materials be prepared for next month's event." Based on this input, the terminal sends the data to the server.

[0473] Step 2:

[0474] The server receives a request from the user and performs natural language processing. The server uses a generative AI model to analyze the text and extract its intent. In this process, techniques such as BERT and GPT are used to decompose the input data and clarify its meaning and purpose. The output is the analyzed instruction.

[0475] Step 3:

[0476] The server performs data set matching based on the analyzed instructions. The server uses a database to compare the request with past data and criteria. This comparison process verifies the validity of the request. The input is the analysis result, and the output is the validity verification result.

[0477] Step 4:

[0478] If the server determines the request is valid, it generates a work plan and creates a work order. Based on the request, the server plans which resources are needed and when each task should be performed. The work order includes specific details of the work, such as the person responsible and the deadline. The input is the validity check result, and the output is the work order.

[0479] Step 5:

[0480] Workers receive work instructions from the server using a terminal and perform tasks according to the instructions. In this process, workers perform specific actions to carry out the planned tasks. No feedback is provided regarding the progress of the work at this stage.

[0481] Step 6:

[0482] After completing a task, the worker sends a completion report to the server via their terminal. The report includes details of the work performed and the results. The input is the work completion report data, and the output to the server is the report data.

[0483] Step 7:

[0484] The server receives the completion report and evaluates its validity. The server verifies that the report aligns with the original work plan and generates feedback as needed. The output of this step is a completion notification to the user.

[0485] Step 8:

[0486] Based on the server's evaluation of the report's validity, it sends a completion notification to the user. This allows the user to confirm that the requested task has been completed. The output is the completion notification to the user.

[0487] (Application Example 1)

[0488] 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."

[0489] Traditional in-store reception and inventory management often rely heavily on manual processes, leading to inefficiencies and a high risk of human error. Furthermore, insufficient multilingual support makes it difficult to meet diverse customer needs. A system that addresses these challenges is needed.

[0490] 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.

[0491] In this invention, the server includes an information processing device for natural language processing, a verification means for an information recording device for verifying the validity of input information, and a means for generating a processing plan and creating work instructions based on a request. This automates reception work, reduces human error, and enables efficient multilingual support.

[0492] "Natural language processing" is the technology that enables computers to understand and process human language.

[0493] An "information processing device" is an electronic device used to receive, analyze, calculate, and store data.

[0494] An "information recording device" is a device that stores data and, as needed, verifies or retrieves that data.

[0495] A "comparison means" is a method or apparatus for comparing input information with existing data to confirm whether there is a match or a mismatch.

[0496] A "work instruction sheet" is a document or piece of information that outlines the necessary procedures, assigned personnel, deadlines, and other details required to carry out a specific task.

[0497] An "interactive information terminal" is a communication device that can receive input from a user and return a response in return.

[0498] "Inventory information" refers to data about how many of a particular product or item are in stock.

[0499] A "work instruction" is a set of instructions that outlines the information and procedures necessary to perform a specific task.

[0500] The system implementing this invention mainly consists of a server and a terminal. The server uses spaCy, a Python library for natural language processing, to parse natural language requests received from users. It also uses Firebase for database management and performs verification to confirm the validity of the input information. The server uses Node.js to generate a request processing plan and automatically generate work instructions.

[0501] The terminal is an interactive information terminal for use by users and workers. It is developed using React Native and can run on both iOS and Android platforms. The terminal sends user-input requests to the server in real time and receives responses from the server.

[0502] In terms of hardware, typical smartphones and tablets are used as user terminals. On the server side, high-performance server machines or cloud-based server infrastructure are utilized.

[0503] As a concrete example, a user might input "I want to buy clothes suitable for winter" into their device. The server, upon receiving this request, uses natural language processing to analyze the request and generate a list of appropriate products. Based on this list, the user can select products on their device and proceed with reserving or purchasing them.

[0504] An example of a prompt to input into a generative AI model is, "Analyze the natural language request received from the user, check the inventory information for the relevant products, and generate the necessary instructions." This prompt allows the server to accurately understand the content of the request and derive an appropriate response.

[0505] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0506] Step 1:

[0507] A user enters a specific request using a smartphone application. This request is written in natural language and includes the user's demands and questions. The entered request is output as data sent from the application to the server.

[0508] Step 2:

[0509] The server analyzes the user's request using spaCy, a natural language processing library. Here, the received request is analyzed, and a data structure is output that clearly explains what the request is asking for. This step focuses on analyzing the sentence structure, primarily nouns and verbs, to extract the essence of the request.

[0510] Step 3:

[0511] The server uses the analyzed data to match it with inventory information and other data in the database. This matching uses Firebase's real-time database. The input is matched with inventory information using the analysis results, and a list of relevant products and information is generated as output. This verification confirms whether the user's request is truly possible.

[0512] Step 4:

[0513] The server automatically generates work instructions as a response to the user based on the matching results. It structures the information and creates a dataset to present related information in an easy-to-understand format for the user. This dataset becomes the output sent to the user.

[0514] Step 5:

[0515] The user receives the response from the server through their device. Here, the information returned to the smartphone is displayed as a list or detail screen. Based on this information, the user can select products or request more detailed information. A new request may also be created as output.

[0516] Step 6:

[0517] Upon completion of the process, the user confirms through the application that the information entered on the screen has been processed and the results are automatically displayed. These results include a confirmation screen for reserved items and options for additional orders. The output at this stage provides information for the user to determine their next action.

[0518] 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.

[0519] This invention is a system for recognizing user emotions during user request processing and optimizing responses and work instructions based on those emotions. This system utilizes natural language processing and an emotion engine to automate multilingual and emotion-responsive business processes.

[0520] System Overview

[0521] The server plays a central role, receiving user requests and performing natural language processing. During the natural language processing, an emotion engine is activated to analyze the user's emotions and extract emotional data from the user's writing. This ensures that processing takes into account not only the request content but also the user's emotional state.

[0522] The terminal is used as an interface for users to enter requests. After the emotion engine analyzes the user's emotions, the user is given feedback on the most appropriate response or instructions.

[0523] Specific examples of how the system works

[0524] 1. When a user sends an inquiry to the system using their device, they enter a message that conveys emotion, such as "I need the information immediately, and it's very urgent." This message is sent to the server.

[0525] 2. The server analyzes the content of the request from the received message through natural language processing. Simultaneously, the emotion engine activates to detect emotions such as "urgent" from the message.

[0526] 3. Based on the analyzed sentiment information, the server sets the request's priority higher than usual and generates an execution plan for processing that allows for a quick response. Based on that plan, urgent instructions are generated and sent to the relevant workers.

[0527] 4. If the work is completed as scheduled, a completion report is sent by the worker. The server analyzes the report and promptly sends a completion notification to the user.

[0528] This system can dynamically adjust tasks in response to user emotions, leading to even greater customer satisfaction. Furthermore, its multilingual capabilities enable consistent service delivery to users from all cultural backgrounds.

[0529] The following describes the processing flow.

[0530] Step 1:

[0531] Users use their devices to input and send requests in natural language. These messages may contain emotional nuances, such as "I need this addressed urgently."

[0532] Step 2:

[0533] The server receives a request from the user and uses a natural language processing engine to parse the message. While understanding the request, the sentiment engine extracts the user's emotions and detects that they are in a hurry.

[0534] Step 3:

[0535] The server checks the database to verify the validity of the request. It integrates the request content with user sentiment information to dynamically set the request priority. If it determines that an urgent response is needed, it performs a process to increase the processing priority.

[0536] Step 4:

[0537] The server generates an execution plan for the most efficient processing based on the request. This plan is faster than the normal processing flow and sends a work order to the relevant workers. This order includes a note indicating the urgency of the task and the necessary details.

[0538] Step 5:

[0539] After completing the work, the worker sends a completion report to the server using their terminal. This report includes information indicating whether the work was completed as requested.

[0540] Step 6:

[0541] The server receives the completion report and analyzes its contents. It evaluates whether the completion report is valid and promptly sends a completion notification to the user. This notification informs the user that their request has been successfully completed and provides feedback on the results in a sentiment-sensitive manner.

[0542] This approach enables system operation that incorporates user emotions, leading to the provision of more appropriate services.

[0543] (Example 2)

[0544] 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."

[0545] Modern information processing systems require the generation of optimal responses and work instructions that take into account the emotions contained in user requests. However, conventional systems have suffered from the problem of failing to meet user expectations due to insufficient sentiment analysis, resulting in decreased customer satisfaction. Furthermore, the complexity of multilingual support has made it difficult to provide consistent service to a global user base.

[0546] 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.

[0547] In this invention, the server includes an information processing device for natural language processing, an information storage device for verifying the validity of input information, and a device capable of analyzing emotions from the input information and resetting priorities. This enables multilingual support while considering the user's emotions, and allows for the provision of fast and appropriate services through dynamic adjustment of priorities.

[0548] A "natural language processing unit" is a computing device that analyzes natural language text input by a user and understands its meaning and intent.

[0549] An "information storage device" is a device used to store various types of data in a specific manner and to verify the validity of that data as needed.

[0550] An "information processing device" is a computer that processes input information through calculations and operations and generates output according to a specific purpose.

[0551] A "device for analyzing emotions" is an analytical device that extracts emotions from a user's text messages and adjusts the priority and processing method of information based on those emotions.

[0552] "Multilingual support" refers to the ability to process information written in different languages ​​and produce consistent results through translation and cross-language adjustments.

[0553] "Reprioritizing" is the operation of dynamically changing the importance and urgency of a particular process or task according to the situation.

[0554] This invention is a system that accurately grasps the diverse emotions of users and automatically generates responses and work instructions accordingly. This system consists of a server that performs natural language processing, a terminal operated by the user, and an information processing device that performs complex emotion analysis.

[0555] The server is primarily responsible for natural language processing, utilizing libraries such as Python's Natural Language Toolkit (NLTK) and TensorFlow. These tools allow it to perform morphological analysis on user-input text messages, gaining a deep understanding of their context and grammar. Furthermore, the server uses the Hugging Face Transformers library as its emotion engine to extract user emotions.

[0556] The device serves to provide an interface for users to input messages in natural language. This interface is multilingual and designed to accurately process questions and requests entered by users in different languages.

[0557] Messages from users may contain emotional or urgent content, such as "The project deadline is fast approaching, and I need a quick response." When the server receives such a message, it analyzes the emotional nuances and dynamically adjusts the request's priority. As a result, it becomes possible to quickly plan the necessary actions and responses.

[0558] As a concrete example, here is an example of a prompt message for a generative AI model: "How should the AI ​​respond and act when the user displays 'This is very urgent, and I would like it done by the end of today if possible.'" This prompt allows the AI ​​to accurately determine the user's urgency and take appropriate action.

[0559] Thus, the present invention is a system that integrates emotion analysis and automated processes to realize the provision of services that meet user needs.

[0560] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0561] Step 1:

[0562] The user enters a message in natural language using a terminal. For example, they might enter a request such as, "I need to finish the project this week, but I'm worried." This input is text data containing the user's request and feelings. This is sent to the server and used as data for the next processing step.

[0563] Step 2:

[0564] The server analyzes messages received from users using a natural language processing engine. Leveraging Python's NLTK and TensorFlow, it performs morphological analysis on messages to understand grammatical structure and vocabulary meaning. This analysis processes the request content and the sentiment contained within the sentence, and the analyzed data is output.

[0565] Step 3:

[0566] The server uses the analyzed data to activate the emotion engine. It utilizes Hugging Face's Transformers to extract emotions such as "worry" and "urgency" from the text. This extraction process generates emotion labels, which are then output as emotion data.

[0567] Step 4:

[0568] The server repriors requests based on sentiment data. If high urgency is detected, the request's priority is increased, and an immediate response plan is generated. Data processing automatically adjusts schedules and resources, and a new execution plan is output.

[0569] Step 5:

[0570] The server creates a corresponding work order based on the generated execution plan and sends it to the assigned worker. Specifically, an instruction sheet is created that details resource allocation and necessary procedures. This process outputs the work order and distributes it appropriately to the relevant personnel.

[0571] (Application Example 2)

[0572] 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."

[0573] In modern information processing and service delivery, it is necessary not only to receive and respond to user requests, but also to dynamically adjust responses according to the user's emotions and circumstances. However, conventional systems struggle to optimize responses and work instructions while considering user emotions, resulting in a limited user experience.

[0574] 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.

[0575] In this invention, the server includes an information processing device for natural language processing, an information-based matching means for verifying the validity of input information, a means for generating an execution plan for processing based on a request and creating work instructions, a means for recognizing the user's emotions and optimizing work instructions based on those emotions, and an analysis means for evaluating the validity of the post-execution report. This makes it possible to provide an excellent experience that responds immediately to the user's emotions.

[0576] A "natural language processing device" is a device that analyzes textual information input by a user, understands its meaning and structure, and processes instructions and questions accordingly.

[0577] An "information-based verification method" is a function that compares input information with a specific database or information source in order to verify its accuracy and validity.

[0578] "Means for generating execution plans and creating work instructions" refers to a function that formulates specific task execution procedures in response to user requests and creates instructions based on those procedures.

[0579] "Means of recognizing user emotions and optimizing work instructions based on those emotions" refers to a function that detects the emotions a user expresses and adjusts task priorities and procedures while taking those emotions into consideration.

[0580] "Analysis means" refers to functions for evaluating the results of an executed task and analyzing its validity and effectiveness.

[0581] The system for realizing this invention consists of a server for information processing and a terminal for the user to input information. The server combines natural language processing and emotion recognition technology to generate the optimal response according to the user's request.

[0582] The server runs Python-based programs and uses NLTK as its natural language processing library. It also utilizes sentiment analysis tools such as the Google Cloud Natural Language API for sentiment recognition. This configuration enables semantic analysis and sentiment identification of text received from users.

[0583] The user input received by the server is first analyzed using natural language processing. The data obtained from this analysis includes the language and grammatical structure of the text, as well as the user's intent. Subsequently, emotion recognition evaluates the user's emotional state, identifying emotions such as whether they are in a hurry or calm.

[0584] After receiving a series of pieces of information, the server prioritizes work instructions and guides users through specific steps based on their emotional state. For example, if a user requests "immediate help," the server recognizes the urgency through emotional recognition and prepares a rapid response.

[0585] For example, if this system were incorporated into a home robot, when a user requests cooking assistance, the system would analyze the recipe and provide instructions to efficiently prepare the food. If the user is in a hurry, the system would optimize the process by selecting a simpler dish.

[0586] Using a generative AI model, the following can be considered as examples of prompt statements.

[0587] "Think of ways to help users perform tasks they find difficult more smoothly."

[0588] This will enable the system to provide more human-centered services that are tailored to the user's intentions.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The user inputs information through a device. This input can be in text or voice format and includes the user's requests and emotions. This data is then sent to the server.

[0592] Step 2:

[0593] The server receives the input data and begins analysis using the NLTK natural language processing library. The data analyzed consists of extracted semantic information, including grammatical structure and keywords. This clarifies the content of the request.

[0594] Step 3:

[0595] The server applies an emotion recognition algorithm and uses the Google Cloud Natural Language API to extract emotion data from the input data. Examples of emotion data identified include "hurried" and "calm."

[0596] Step 4:

[0597] The server prioritizes tasks based on the results of natural language processing and sentiment data. Priority data is generated, and if a user's request is urgent, it is given a higher priority.

[0598] Step 5:

[0599] The server generates work instructions according to the set priority. For example, it creates and outputs specific instructions such as "Start cooking immediately" as an instruction for operating a household robot.

[0600] Step 6:

[0601] Work instructions are sent to the relevant work equipment or terminals and executed. In the case of robots, they start cooking or other tasks according to the instructions.

[0602] Step 7:

[0603] Once the task is complete, the work unit reports the results to the server. The server analyzes the results and sends a completion notification to the user. Upon receiving the completion notification, the user confirms that the actions were performed correctly.

[0604] In this way, the entire system works in coordination, enabling flexible responses that respond to the user's emotions.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] [Fourth Embodiment]

[0609] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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".

[0622] This invention provides a system for automating reception operations and reducing human error in those operations. This system uses a program that functions as an agent to automatically verify the validity of user requests, process necessary information, and provide accurate instructions for related tasks.

[0623] System Overview

[0624] The system is server-centric and accepts requests from users in natural language. These requests are parsed using natural language processing to accurately extract their intent. Based on this analysis, the server checks the database to verify the appropriateness of the request.

[0625] Terminals are devices used by users and workers, handling requests from users and receiving instructions for workers. Communication with the server is optimized on the terminals to improve response speed.

[0626] Specific examples of how the system works

[0627] 1. The user sends a message to the system via their device, for example, "I'd like to request that you prepare presentation materials for next month's event." The server receives this message and begins analyzing it.

[0628] 2. Once the server recognizes through natural language processing that the request is for "preparation of presentation materials," it checks the existing request database and compares it to similar requests from the past. This verifies whether the specific content of the request and the required resources are appropriate.

[0629] 3. If the request is valid, the server will create a processing plan and automatically generate instructions to send to the worker. The instructions will include a work overview, required steps, responsible parties, and deadlines.

[0630] 4. When a worker completes a task, they submit a completion report from their terminal. The server then analyzes the report and evaluates its validity as to whether the task was completed. After the evaluation, a completion notification is automatically sent to the user.

[0631] This system significantly reduces human error and improves operational efficiency. Furthermore, its multilingual request system offers flexibility to handle various environments, providing a versatile service.

[0632] The following describes the processing flow.

[0633] Step 1:

[0634] Users input and send requests using natural language via their device. Users do not need to be aware of language, as the system supports multiple languages, allowing input in any language.

[0635] Step 2:

[0636] The server receives a request from the user. The received request is analyzed by a natural language processing engine, and its content and intent are extracted. This allows the system to understand the user's specific requirements.

[0637] Step 3:

[0638] The server uses the analysis results to check the database for validity. Here, it compares the request with similar past requests and contract terms to verify that there is no inappropriate content or inconsistency.

[0639] Step 4:

[0640] After the server verifies the validity of the request, it automatically generates an execution plan for processing. This plan includes the steps, responsible parties, and necessary resources for performing the requested task.

[0641] Step 5:

[0642] Based on the execution plan generated by the server, a work order is created. This order is sent to the relevant workers, providing them with the necessary details and procedures for the work.

[0643] Step 6:

[0644] When a task is completed, the worker sends a completion report to the server from their terminal. This report includes details about whether the task was completed as scheduled.

[0645] Step 7:

[0646] The server receives the work completion report and evaluates its contents using specialized analytical tools. After the evaluation is complete, if the report is deemed appropriate, a completion notification is automatically sent to the user.

[0647] This series of processes enables efficient work execution and reduces human error.

[0648] (Example 1)

[0649] 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".

[0650] In today's business environment, there is a growing need for automated systems that can reduce human errors in reception and work instruction processes, and that can flexibly handle multilingual requests. Traditional methods are plagued by communication errors involving multiple workers and language barriers in international business, so efficient solutions are required to overcome these challenges.

[0651] 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.

[0652] In this invention, the server includes an information processing device means for natural language processing, a data set matching means for verifying the validity of input requests, and a means for generating work plans and creating work content based on requests. This enables automation of reception operations, reduction of human error, and multilingual support.

[0653] A "natural language processing device" is a computer system that analyzes natural language text input by a user and understands its meaning and intent.

[0654] A "data set matching means" is a function that compares and contrasts the input requests and data with existing databases to confirm their validity and suitability.

[0655] A "means for generating work plans and creating work content" refers to a system that plans specific work flows and procedures based on user requirements and creates work instructions based on these.

[0656] "Information analysis means" refers to techniques for analyzing the results of work reported after execution and evaluating whether the work was carried out as planned.

[0657] "Means for sending requests via a terminal" refers to an interface or function that allows a user to send a request to a system using a device they are using.

[0658] The "means for receiving work reports and sending completion notifications" refers to a function that receives reports from workers, verifies their contents, and then notifies the user that the work has been completed.

[0659] This invention is an automated reception system that utilizes natural language processing, and is mainly composed of server, terminal, and user interaction. The server, as an information processing device that performs natural language processing, uses a generative AI model to analyze natural language requests received from users. Specifically, it uses models such as BERT and GPT to accurately understand the intent of the request and perform the corresponding processing.

[0660] The server utilizes database management systems such as MySQL and PostgreSQL as a means of data set matching. This enables a process to compare the content of requests with past cases and benchmark data to verify their validity. Furthermore, the generation of work plans and the creation of work details based on requests are performed automatically based on program logic, and accurate instructions are generated for workers.

[0661] The terminal functions as a device used by users and workers, providing a means for users to send requests to the server. This allows users to easily send requests by entering prompts in text format, such as "I would like to request that presentation materials be prepared for next month's event."

[0662] After receiving a work report, the server evaluates the validity of the report's contents and sends a completion notification to the user. This series of actions reduces human error and improves work efficiency. Furthermore, because it supports multiple languages, it can be easily operated in an international environment.

[0663] As a concrete example, the following are examples of prompt statements.

[0664] "I'd like you to create a project plan for next month's event."

[0665] "Could you please prepare the materials in English for the international conference?"

[0666] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0667] Step 1:

[0668] The user sends a request to the system using a terminal. The user inputs the request in natural language and sends a prompt message, for example, "I would like to request that presentation materials be prepared for next month's event." Based on this input, the terminal sends the data to the server.

[0669] Step 2:

[0670] The server receives a request from the user and performs natural language processing. The server uses a generative AI model to analyze the text and extract its intent. In this process, techniques such as BERT and GPT are used to decompose the input data and clarify its meaning and purpose. The output is the analyzed instruction.

[0671] Step 3:

[0672] The server performs data set matching based on the analyzed instructions. The server uses a database to compare the request with past data and criteria. This comparison process verifies the validity of the request. The input is the analysis result, and the output is the validity verification result.

[0673] Step 4:

[0674] If the server determines the request is valid, it generates a work plan and creates a work order. Based on the request, the server plans which resources are needed and when each task should be performed. The work order includes specific details of the work, such as the person responsible and the deadline. The input is the validity check result, and the output is the work order.

[0675] Step 5:

[0676] Workers receive work instructions from the server using a terminal and perform tasks according to the instructions. In this process, workers perform specific actions to carry out the planned tasks. No feedback is provided regarding the progress of the work at this stage.

[0677] Step 6:

[0678] After completing a task, the worker sends a completion report to the server via their terminal. The report includes details of the work performed and the results. The input is the work completion report data, and the output to the server is the report data.

[0679] Step 7:

[0680] The server receives the completion report and evaluates its validity. The server verifies that the report aligns with the original work plan and generates feedback as needed. The output of this step is a completion notification to the user.

[0681] Step 8:

[0682] Based on the server's evaluation of the report's validity, it sends a completion notification to the user. This allows the user to confirm that the requested task has been completed. The output is the completion notification to the user.

[0683] (Application Example 1)

[0684] 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".

[0685] Traditional in-store reception and inventory management often rely heavily on manual processes, leading to inefficiencies and a high risk of human error. Furthermore, insufficient multilingual support makes it difficult to meet diverse customer needs. A system that addresses these challenges is needed.

[0686] 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.

[0687] In this invention, the server includes an information processing device for natural language processing, a verification means for an information recording device for verifying the validity of input information, and a means for generating a processing plan and creating work instructions based on a request. This automates reception work, reduces human error, and enables efficient multilingual support.

[0688] "Natural language processing" is the technology that enables computers to understand and process human language.

[0689] An "information processing device" is an electronic device used to receive, analyze, calculate, and store data.

[0690] An "information recording device" is a device that stores data and, as needed, verifies or retrieves that data.

[0691] A "comparison means" is a method or apparatus for comparing input information with existing data to confirm whether there is a match or a mismatch.

[0692] A "work instruction sheet" is a document or piece of information that outlines the necessary procedures, assigned personnel, deadlines, and other details required to carry out a specific task.

[0693] An "interactive information terminal" is a communication device that can receive input from a user and return a response in return.

[0694] "Inventory information" refers to data about how many of a particular product or item are in stock.

[0695] A "work instruction" is a set of instructions that outlines the information and procedures necessary to perform a specific task.

[0696] The system implementing this invention mainly consists of a server and a terminal. The server uses spaCy, a Python library for natural language processing, to parse natural language requests received from users. It also uses Firebase for database management and performs verification to confirm the validity of the input information. The server uses Node.js to generate a request processing plan and automatically generate work instructions.

[0697] The terminal is an interactive information terminal for use by users and workers. It is developed using React Native and can run on both iOS and Android platforms. The terminal sends user-input requests to the server in real time and receives responses from the server.

[0698] In terms of hardware, typical smartphones and tablets are used as user terminals. On the server side, high-performance server machines or cloud-based server infrastructure are utilized.

[0699] As a concrete example, a user might input "I want to buy clothes suitable for winter" into their device. The server, upon receiving this request, uses natural language processing to analyze the request and generate a list of appropriate products. Based on this list, the user can select products on their device and proceed with reserving or purchasing them.

[0700] An example of a prompt to input into a generative AI model is, "Analyze the natural language request received from the user, check the inventory information for the relevant products, and generate the necessary instructions." This prompt allows the server to accurately understand the content of the request and derive an appropriate response.

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] A user enters a specific request using a smartphone application. This request is written in natural language and includes the user's demands and questions. The entered request is output as data sent from the application to the server.

[0704] Step 2:

[0705] The server analyzes the user's request using spaCy, a natural language processing library. Here, the received request is analyzed, and a data structure is output that clearly explains what the request is asking for. This step focuses on analyzing the sentence structure, primarily nouns and verbs, to extract the essence of the request.

[0706] Step 3:

[0707] The server uses the analyzed data to match it with inventory information and other data in the database. This matching uses Firebase's real-time database. The input is matched with inventory information using the analysis results, and a list of relevant products and information is generated as output. This verification confirms whether the user's request is truly possible.

[0708] Step 4:

[0709] The server automatically generates work instructions as a response to the user based on the matching results. It structures the information and creates a dataset to present related information in an easy-to-understand format for the user. This dataset becomes the output sent to the user.

[0710] Step 5:

[0711] The user receives the response from the server through their device. Here, the information returned to the smartphone is displayed as a list or detail screen. Based on this information, the user can select products or request more detailed information. A new request may also be created as output.

[0712] Step 6:

[0713] Upon completion of the process, the user confirms through the application that the information entered on the screen has been processed and the results are automatically displayed. These results include a confirmation screen for reserved items and options for additional orders. The output at this stage provides information for the user to determine their next action.

[0714] 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.

[0715] This invention is a system for recognizing user emotions during user request processing and optimizing responses and work instructions based on those emotions. This system utilizes natural language processing and an emotion engine to automate multilingual and emotion-responsive business processes.

[0716] System Overview

[0717] The server plays a central role, receiving user requests and performing natural language processing. During the natural language processing, an emotion engine is activated to analyze the user's emotions and extract emotional data from the user's writing. This ensures that processing takes into account not only the request content but also the user's emotional state.

[0718] The terminal is used as an interface for users to enter requests. After the emotion engine analyzes the user's emotions, the user is given feedback on the most appropriate response or instructions.

[0719] Specific examples of how the system works

[0720] 1. When a user sends an inquiry to the system using their device, they enter a message that conveys emotion, such as "I need the information immediately, and it's very urgent." This message is sent to the server.

[0721] 2. The server analyzes the content of the request from the received message through natural language processing. Simultaneously, the emotion engine activates to detect emotions such as "urgent" from the message.

[0722] 3. Based on the analyzed sentiment information, the server sets the request's priority higher than usual and generates an execution plan for processing that allows for a quick response. Based on that plan, urgent instructions are generated and sent to the relevant workers.

[0723] 4. If the work is completed as scheduled, a completion report is sent by the worker. The server analyzes the report and promptly sends a completion notification to the user.

[0724] This system can dynamically adjust tasks in response to user emotions, leading to even greater customer satisfaction. Furthermore, its multilingual capabilities enable consistent service delivery to users from all cultural backgrounds.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] Users use their devices to input and send requests in natural language. These messages may contain emotional nuances, such as "I need this addressed urgently."

[0728] Step 2:

[0729] The server receives a request from the user and uses a natural language processing engine to parse the message. While understanding the request, the sentiment engine extracts the user's emotions and detects that they are in a hurry.

[0730] Step 3:

[0731] The server checks the database to verify the validity of the request. It integrates the request content with user sentiment information to dynamically set the request priority. If it determines that an urgent response is needed, it performs a process to increase the processing priority.

[0732] Step 4:

[0733] The server generates an execution plan for the most efficient processing based on the request. This plan is faster than the normal processing flow and sends a work order to the relevant workers. This order includes a note indicating the urgency of the task and the necessary details.

[0734] Step 5:

[0735] After completing the work, the worker sends a completion report to the server using their terminal. This report includes information indicating whether the work was completed as requested.

[0736] Step 6:

[0737] The server receives the completion report and analyzes its contents. It evaluates whether the completion report is valid and promptly sends a completion notification to the user. This notification informs the user that their request has been successfully completed and provides feedback on the results in a sentiment-sensitive manner.

[0738] This approach enables system operation that incorporates user emotions, leading to the provision of more appropriate services.

[0739] (Example 2)

[0740] 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".

[0741] Modern information processing systems require the generation of optimal responses and work instructions that take into account the emotions contained in user requests. However, conventional systems have suffered from the problem of failing to meet user expectations due to insufficient sentiment analysis, resulting in decreased customer satisfaction. Furthermore, the complexity of multilingual support has made it difficult to provide consistent service to a global user base.

[0742] 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.

[0743] In this invention, the server includes an information processing device for natural language processing, an information storage device for verifying the validity of input information, and a device capable of analyzing emotions from the input information and resetting priorities. This enables multilingual support while considering the user's emotions, and allows for the provision of fast and appropriate services through dynamic adjustment of priorities.

[0744] A "natural language processing unit" is a computing device that analyzes natural language text input by a user and understands its meaning and intent.

[0745] An "information storage device" is a device used to store various types of data in a specific manner and to verify the validity of that data as needed.

[0746] An "information processing device" is a computer that processes input information through calculations and operations and generates output according to a specific purpose.

[0747] A "device for analyzing emotions" is an analytical device that extracts emotions from a user's text messages and adjusts the priority and processing method of information based on those emotions.

[0748] "Multilingual support" refers to the ability to process information written in different languages ​​and produce consistent results through translation and cross-language adjustments.

[0749] "Reprioritizing" is the operation of dynamically changing the importance and urgency of a particular process or task according to the situation.

[0750] This invention is a system that accurately grasps the diverse emotions of users and automatically generates responses and work instructions accordingly. This system consists of a server that performs natural language processing, a terminal operated by the user, and an information processing device that performs complex emotion analysis.

[0751] The server is primarily responsible for natural language processing, utilizing libraries such as Python's Natural Language Toolkit (NLTK) and TensorFlow. These tools allow it to perform morphological analysis on user-input text messages, gaining a deep understanding of their context and grammar. Furthermore, the server uses the Hugging Face Transformers library as its emotion engine to extract user emotions.

[0752] The device serves to provide an interface for users to input messages in natural language. This interface is multilingual and designed to accurately process questions and requests entered by users in different languages.

[0753] Messages from users may contain emotional or urgent content, such as "The project deadline is fast approaching, and I need a quick response." When the server receives such a message, it analyzes the emotional nuances and dynamically adjusts the request's priority. As a result, it becomes possible to quickly plan the necessary actions and responses.

[0754] As a concrete example, here is an example of a prompt message for a generative AI model: "How should the AI ​​respond and act when the user displays 'This is very urgent, and I would like it done by the end of today if possible.'" This prompt allows the AI ​​to accurately determine the user's urgency and take appropriate action.

[0755] Thus, the present invention is a system that integrates emotion analysis and automated processes to realize the provision of services that meet user needs.

[0756] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0757] Step 1:

[0758] The user enters a message in natural language using a terminal. For example, they might enter a request such as, "I need to finish the project this week, but I'm worried." This input is text data containing the user's request and feelings. This is sent to the server and used as data for the next processing step.

[0759] Step 2:

[0760] The server analyzes messages received from users using a natural language processing engine. Leveraging Python's NLTK and TensorFlow, it performs morphological analysis on messages to understand grammatical structure and vocabulary meaning. This analysis processes the request content and the sentiment contained within the sentence, and the analyzed data is output.

[0761] Step 3:

[0762] The server uses the analyzed data to activate the emotion engine. It utilizes Hugging Face's Transformers to extract emotions such as "worry" and "urgency" from the text. This extraction process generates emotion labels, which are then output as emotion data.

[0763] Step 4:

[0764] The server repriors requests based on sentiment data. If high urgency is detected, the request's priority is increased, and an immediate response plan is generated. Data processing automatically adjusts schedules and resources, and a new execution plan is output.

[0765] Step 5:

[0766] The server creates a corresponding work order based on the generated execution plan and sends it to the assigned worker. Specifically, an instruction sheet is created that details resource allocation and necessary procedures. This process outputs the work order and distributes it appropriately to the relevant personnel.

[0767] (Application Example 2)

[0768] 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".

[0769] In modern information processing and service delivery, it is necessary not only to receive and respond to user requests, but also to dynamically adjust responses according to the user's emotions and circumstances. However, conventional systems struggle to optimize responses and work instructions while considering user emotions, resulting in a limited user experience.

[0770] 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.

[0771] In this invention, the server includes an information processing device for natural language processing, an information-based matching means for verifying the validity of input information, a means for generating an execution plan for processing based on a request and creating work instructions, a means for recognizing the user's emotions and optimizing work instructions based on those emotions, and an analysis means for evaluating the validity of the post-execution report. This makes it possible to provide an excellent experience that responds immediately to the user's emotions.

[0772] A "natural language processing device" is a device that analyzes textual information input by a user, understands its meaning and structure, and processes instructions and questions accordingly.

[0773] An "information-based verification method" is a function that compares input information with a specific database or information source in order to verify its accuracy and validity.

[0774] "Means for generating execution plans and creating work instructions" refers to a function that formulates specific task execution procedures in response to user requests and creates instructions based on those procedures.

[0775] "Means of recognizing user emotions and optimizing work instructions based on those emotions" refers to a function that detects the emotions a user expresses and adjusts task priorities and procedures while taking those emotions into consideration.

[0776] "Analysis means" refers to functions for evaluating the results of an executed task and analyzing its validity and effectiveness.

[0777] The system for realizing this invention consists of a server for information processing and a terminal for the user to input information. The server combines natural language processing and emotion recognition technology to generate the optimal response according to the user's request.

[0778] The server runs Python-based programs and uses NLTK as its natural language processing library. It also utilizes sentiment analysis tools such as the Google Cloud Natural Language API for sentiment recognition. This configuration enables semantic analysis and sentiment identification of text received from users.

[0779] The user input received by the server is first analyzed using natural language processing. The data obtained from this analysis includes the language and grammatical structure of the text, as well as the user's intent. Subsequently, emotion recognition evaluates the user's emotional state, identifying emotions such as whether they are in a hurry or calm.

[0780] After receiving a series of pieces of information, the server prioritizes work instructions and guides users through specific steps based on their emotional state. For example, if a user requests "immediate help," the server recognizes the urgency through emotional recognition and prepares a rapid response.

[0781] For example, if this system were incorporated into a home robot, when a user requests cooking assistance, the system would analyze the recipe and provide instructions to efficiently prepare the food. If the user is in a hurry, the system would optimize the process by selecting a simpler dish.

[0782] Using a generative AI model, the following can be considered as examples of prompt statements.

[0783] "Think of ways to help users perform tasks they find difficult more smoothly."

[0784] This will enable the system to provide more human-centered services that are tailored to the user's intentions.

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The user inputs information through a device. This input can be in text or voice format and includes the user's requests and emotions. This data is then sent to the server.

[0788] Step 2:

[0789] The server receives the input data and begins analysis using the NLTK natural language processing library. The data analyzed consists of extracted semantic information, including grammatical structure and keywords. This clarifies the content of the request.

[0790] Step 3:

[0791] The server applies an emotion recognition algorithm and uses the Google Cloud Natural Language API to extract emotion data from the input data. Examples of emotion data identified include "hurried" and "calm."

[0792] Step 4:

[0793] The server prioritizes tasks based on the results of natural language processing and sentiment data. Priority data is generated, and if a user's request is urgent, it is given a higher priority.

[0794] Step 5:

[0795] The server generates work instructions according to the set priority. For example, it creates and outputs specific instructions such as "Start cooking immediately" as an instruction for operating a household robot.

[0796] Step 6:

[0797] Work instructions are sent to the relevant work equipment or terminals and executed. In the case of robots, they start cooking or other tasks according to the instructions.

[0798] Step 7:

[0799] Once the task is complete, the work unit reports the results to the server. The server analyzes the results and sends a completion notification to the user. Upon receiving the completion notification, the user confirms that the actions were performed correctly.

[0800] In this way, the entire system works in coordination, enabling flexible responses that respond to the user's emotions.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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."

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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 to be incorporated by reference.

[0822] The following is further disclosed regarding the embodiments described above.

[0823] (Claim 1)

[0824] A computing unit for natural language processing,

[0825] A database verification means for confirming the validity of the input information,

[0826] A means for generating an execution plan for processing and creating work instructions based on a request,

[0827] Analytical means for evaluating the validity of post-implementation reports,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, which enables multilingual support by analyzing information input in natural language.

[0831] (Claim 3)

[0832] The system according to claim 1, which is not limited to information processing in data centers but is also compatible with other information processing servers.

[0833] "Example 1"

[0834] (Claim 1)

[0835] An information processing device that performs natural language processing,

[0836] A data set matching means for verifying the validity of the input request,

[0837] A means of generating a work plan and creating work details based on requests,

[0838] Information analysis means for evaluating the validity of post-implementation reports,

[0839] A means of sending requests via a terminal,

[0840] A means of receiving work reports and sending completion notifications,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, which enables support for multiple languages ​​by analyzing requests entered in natural language.

[0844] (Claim 3)

[0845] The system according to claim 1, which is not limited to information processing in information processing facilities, but is also compatible with other information processing devices.

[0846] "Application Example 1"

[0847] (Claim 1)

[0848] An information processing device that performs natural language processing,

[0849] Verification means for an information recording device to confirm the validity of the input information,

[0850] A means for generating a processing plan and creating work instructions based on the request,

[0851] An analytical means for evaluating the validity of the post-execution report,

[0852] A means of receiving requests using an interactive information terminal and analyzing related information,

[0853] A means for checking inventory information and generating work orders,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, which enables multilingual support by analyzing information input in natural language.

[0857] (Claim 3)

[0858] The system according to claim 1, which utilizes an information processing device and is capable of handling information management in various industries.

[0859] "Example 2 of combining an emotion engine"

[0860] (Claim 1)

[0861] An information processing device that performs natural language processing,

[0862] An information storage device for verifying the validity of input information,

[0863] A device that generates a processing plan and creates work instructions based on a request,

[0864] A device that can analyze emotions from input information and reset priorities,

[0865] An analysis device for evaluating the validity of the post-execution report,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, which analyzes information input in natural language, is capable of supporting multiple languages, and adjusts priorities through emotion detection.

[0869] (Claim 3)

[0870] The system according to claim 1, which is not limited to information processing in data centers but can also be used with other information processing devices, and can dynamically adjust processing through sentiment analysis.

[0871] "Application example 2 when combining with an emotional engine"

[0872] (Claim 1)

[0873] An information processing device that performs natural language processing,

[0874] An information-based matching means for verifying the validity of the input information,

[0875] A means for generating an execution plan for processing based on a request and creating work instructions,

[0876] A means of recognizing user emotions and optimizing work instructions based on those emotions,

[0877] Analytical means for evaluating the validity of post-implementation reports,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, which analyzes information input in natural language and enables multilingual support and emotion-appropriate responses through emotion recognition.

[0881] (Claim 3)

[0882] The system according to claim 1, which is also compatible with all information processing devices, including those used for support in home environments. [Explanation of Symbols]

[0883] 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. An information processing device that performs natural language processing, Verification means for an information recording device to confirm the validity of the input information, A means for generating a processing plan and creating work instructions based on the request, An analytical means for evaluating the validity of the post-execution report, A means of receiving requests and analyzing related information using an interactive information terminal, A means for checking inventory information and generating work orders, A system that includes this.

2. The system according to claim 1, which enables multilingual support by analyzing information input in natural language.

3. The system according to claim 1, which utilizes an information processing device and is capable of handling information management in various industries.

Images