system

Abstract

We provide the system. [Solution] A method for analyzing user inquiries using a natural language processing model, A means for generating the optimal answer based on the analyzed query, A means of predicting the occurrence of problems by analyzing past data and providing information to users in advance, A means of escalating inquiries that exceed the scope of what can be handled automatically to the relevant departments, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Since the inquiry operations occurring within the company are diverse and scattered, it takes time for employees to determine which department or person in charge to inquire, resulting in a problem of reduced work efficiency. In addition, there is a problem that a lot of time and resources are spent on responses due to repeated occurrence of the same inquiries. In such a situation, it is necessary to provide quick and appropriate information and to improve the efficiency of inquiry response across the company.

Means for Solving the Problems

[0005] This invention introduces a natural language processing model to automatically analyze natural language inquiries from users and instantly generate the optimal response. Furthermore, it implements a function to predict the occurrence of problems using past inquiry data and notify users in advance, thereby preventing problems before they occur. Additionally, it provides a means to escalate inquiries that cannot be handled automatically to the appropriate department, thereby improving the overall efficiency of inquiry processing.

[0006] A "natural language processing model" refers to algorithms and technologies that enable computers to understand, analyze, and generate human natural language.

[0007] "User" refers to an employee or individual who makes an inquiry using the system.

[0008] "Inquiry" refers to the act of a user entering questions or problems they have into the system.

[0009] "Analysis" refers to the process of analyzing input data and information to understand its meaning and intent.

[0010] "Reply generation" refers to the process of creating appropriate information or solutions based on the content of an inquiry.

[0011] "Past data" refers to the history of inquiries and related information that the system has handled in the past.

[0012] "Prediction" refers to making judgments based on past data, anticipating potential problems or situations that may occur in the future.

[0013] "Escalation" refers to the process of transferring inquiries that cannot be resolved by the system to a specialized department or person for handling.

[0014] "Notifying information" refers to the act of sending important data or solutions to inform users.

Brief Description of the Drawings

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

Modes for Carrying Out the Invention

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

[0017] First, the terms 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 multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[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 aims to automate an internal inquiry system, enabling employees to efficiently obtain information. The system incorporates a natural language processing model for analyzing human natural language, with the goal of providing quick and appropriate responses when users make inquiries.

[0037] The server receives natural language queries sent from users through their devices. The received queries are sent to a natural language processing model, where the intent of the query is analyzed. Based on this analysis, the server searches the company's internal database and generates the optimal answer. The generated answer is then sent back to the user through their device.

[0038] Furthermore, the server analyzes past data to predict recurring problems. This predictive function allows the server to prepare solutions in advance for anticipated problems and send information to the device via push notification. This makes it possible to prevent problems from occurring in the first place.

[0039] Furthermore, if an inquiry cannot be resolved automatically, the server generates a notification for escalation to the appropriate department or specialist. This feature enables a quick and accurate response, improving efficiency compared to traditional manual responses.

[0040] For example, if a user types "Please tell me the reporting format for the new project" into their terminal, the server analyzes the content, generates a link containing the most appropriate answer, and sends it back to the user. Furthermore, based on historical data, the server predicts inquiries about payroll procedures, which tend to increase at the end of the year, and proactively provides relevant guidelines to employees' terminals via push notifications. In this way, it contributes to improving the efficiency and productivity of company-wide inquiry handling.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user uses a device to input their inquiry in natural language. The entered data is then sent from the device to the server.

[0044] Step 2:

[0045] The server passes the received query data to a natural language processing model for analysis. The analysis extracts the intent of the query and necessary information.

[0046] Step 3:

[0047] Based on the analysis results, the server searches the company's internal database to find appropriate information and answers. Relevant regulations and manuals are used in this process.

[0048] Step 4:

[0049] The server generates the best answer using the search results and sends that answer to the device. The user receives the answer on the device and checks the information to solve the problem.

[0050] Step 5:

[0051] The server analyzes past query data to predict recurring problems. It then prepares solutions in advance for these predicted problems.

[0052] Step 6:

[0053] The server will periodically or at predicted times send push notifications to the user's device, providing proactive solutions and relevant information.

[0054] Step 7:

[0055] If a user's inquiry cannot be resolved automatically, the server will escalate it to the appropriate department or specialist. This enables a quicker response.

[0056] Step 8:

[0057] The server collects user feedback and uses that information to improve the natural language processing model and the overall system. This process ensures continuous improvement in system accuracy.

[0058] (Example 1)

[0059] 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."

[0060] In modern businesses, efficient information sharing and inquiry handling are crucial. However, traditional systems often suffer from slow response times and wasted resources due to repeated inquiries. Furthermore, inquiries that cannot be automated are not properly escalated, leading to delays in resolution. Solving these problems and achieving efficient information management within the company is essential.

[0061] 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.

[0062] In this invention, the server includes means for analyzing information requests from users using natural language processing technology, means for generating appropriate responses based on the analyzed information requests, and means for predicting the occurrence of problems by analyzing historical information and providing information to the user in advance. This enables rapid and accurate information provision and proactive measures through problem prediction.

[0063] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate natural language used by humans.

[0064] A "user" refers to a person or organization that uses the system to query information.

[0065] An "information request" refers to an inquiry from a user regarding the information they want to know or the data they need.

[0066] "Analysis" is the process of breaking down given data or information into smaller parts and understanding their meaning and structure.

[0067] An "appropriate response" means providing the most relevant, accurate, and satisfactory answer to an information request.

[0068] "Historical information" refers to a collection of inquiries, responses, and related data that the system has recorded in the past.

[0069] "Prediction" is the act of anticipating future events or trends based on past data and patterns.

[0070] "Escalation" is the process of transferring a problem to a person or organization with higher authority or expertise when the problem cannot be resolved automatically.

[0071] This invention is a system that utilizes natural language processing to efficiently handle internal company inquiries. The server receives inquiries entered by users through terminals. The server incorporates natural language processing technology, such as using BERT or GPT as a generative AI model. This allows the server to analyze the intent of the user's inquiry and identify important keywords and context.

[0072] Based on the analyzed query, the server searches an internal database containing accumulated historical information. This database stores FAQs, reference materials, and past problem-solving examples for handling inquiries. From the retrieved information, the server generates the optimal response and sends it back to the user's terminal.

[0073] For example, if a user types "Please tell me the project report format" into their device, the server analyzes this and generates links and explanations of relevant formats to provide to the user. The server also analyzes past inquiry data and uses machine learning algorithms to predict issues such as the increase in payroll calculation problems at the end of the year, and proactively pushes guidelines to the user's device.

[0074] Furthermore, if the server receives a complex inquiry that cannot be resolved automatically, it will generate a notification to escalate the issue to the relevant expert or department. This feature facilitates the rapid resolution of problems.

[0075] An example of a prompt message could be a question like, "Please tell me about recent changes to employee benefits." This system can process such inquiries quickly and accurately, providing users with the necessary information in a timely manner.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The user enters their inquiry into the terminal using natural language. The entered information is received as digital data and sent to the server. This data is used as initial information to identify the user's request.

[0079] Step 2:

[0080] The server inputs the received query data into a generating AI model (e.g., BERT or GPT) and performs natural language processing. Through this process, the server analyzes the intent of the query and identifies important keywords and context. As output, structured data containing the intent of the query is generated.

[0081] Step 3:

[0082] The server searches the company's internal database based on the analysis results. Here, database queries are generated and executed to extract relevant information. The input is the analyzed intent data, and the output is a set of relevant documents and information retrieved from the database.

[0083] Step 4:

[0084] The server generates an appropriate response to the user using information retrieved from the database. Here, the response text is automatically generated based on the retrieved data. For example, it might include specific sentences and links such as, "The project report format is here."

[0085] Step 5:

[0086] The generated response is sent to the user via the terminal. The user can then view the response on the terminal and obtain information to resolve the problem. The output here is the response message from the server itself.

[0087] Step 6:

[0088] The server has the capability to analyze historical data and predict new queries. It uses machine learning algorithms to identify regularly occurring query patterns. In this procedure, the input is historical query data, and the output is potential future query scenarios.

[0089] Step 7:

[0090] If a potential inquiry is anticipated in the future, the server will notify the user's terminal of proactive measures. The notification will include guidance and procedures to reduce the workload for employees. The output here is a push notification message.

[0091] Step 8:

[0092] When the server receives an inquiry that cannot be resolved automatically, it generates an escalation notification to the relevant department or expert. This is a crucial process for quickly resolving problems. The input is data for an inquiry that is difficult to resolve, and the output is an escalation notification.

[0093] (Application Example 1)

[0094] 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."

[0095] Within factories, the time spent responding to inquiries and troubleshooting regarding the operation of machinery and equipment can lead to decreased productivity and errors. To solve this problem, a system is needed that can quickly and efficiently acquire information about machinery and equipment and implement appropriate countermeasures. Furthermore, it is crucial to anticipate and prevent recurring problems in advance.

[0096] 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.

[0097] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for generating optimal answers based on the analyzed inquiries, means for predicting the occurrence of problems by analyzing past data and providing information to users in advance, means for escalating inquiries that exceed the scope of what can be automatically handled to the relevant departments, and database search means for providing solutions to operation and troubles of machinery and equipment within the factory. This enables faster response times for inquiries and more efficient troubleshooting within the factory.

[0098] A "natural language processing model" refers to algorithms and frameworks that enable computers to understand and analyze human natural language.

[0099] "Inquiry analysis" is the process of identifying the intent and content of questions and requests submitted by users and classifying them into appropriate categories and procedures.

[0100] A "database search method" is a system function that quickly retrieves and presents necessary data from stored information.

[0101] "Escalation" is the process of notifying the appropriate person or department of a problem when it exceeds the scope of what can be handled automatically, and requesting further action.

[0102] "Push notifications" are a technology that automatically sends information to a user's device to immediately inform the user.

[0103] "Machine learning" is a technology that learns patterns and rules from data and automatically makes predictions and decisions.

[0104] "Machinery and equipment within a factory" refers to equipment including various tools and automation systems used in the production process.

[0105] The system for carrying out this invention mainly consists of a server and a user's device (terminal).

[0106] The server first uses a natural language processing model to analyze the inquiry sent by the user. Specifically, it uses a generative AI model to analyze the intent of the inquiry and extract the necessary information. This model is implemented using deep learning frameworks such as TENSORFLOW® and PyTorch. Once the analysis is complete, the server searches the database for relevant information and generates the optimal answer.

[0107] Next, machine learning is used to analyze problem occurrence trends based on past data, and relevant information and solutions are provided to users in advance. Libraries such as scikit-learn are used for this prediction. For example, if there is a tendency for inquiries to increase at a specific time each year, guidelines will be sent to the device via push notification before that time.

[0108] Furthermore, for issues that the server cannot resolve automatically, it generates escalation notifications to the relevant departments or specialists. These notifications are sent using communication tools such as Slack or email.

[0109] The user's device is implemented as a web or mobile application, providing an interface for making inquiries. Users can enter prompts such as, "Please tell me how to troubleshoot this device." This allows for smoother factory operations and improved productivity.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The user enters their inquiry from the terminal. Specifically, this involves sending a prompt message to the interface, such as "Please tell me how to troubleshoot this device." The input data is natural language text.

[0113] Step 2:

[0114] The server sends the query received from the terminal to a natural language processing model. The generative AI model analyzes the intent of the query. The input is natural language text from the user, and the output is a data structure that shows the analyzed intent.

[0115] Step 3:

[0116] Based on the analyzed intent, the server searches the database for highly relevant information and generates the optimal response. Specifically, it executes SQL queries to extract the necessary data. The input is the data structure of the analysis result, and the output is the response data.

[0117] Step 4:

[0118] The server generates an answer and sends it back to the user's terminal. The terminal displays this information to the user. The output consists of solutions and steps for the user's inquiry.

[0119] Step 5:

[0120] The server runs a machine learning algorithm to predict problem patterns based on past query history and current analysis data. The input is past query data and current results, and the output is insights indicating periods and themes that require attention.

[0121] Step 6:

[0122] Based on specific times and conditions, push notifications containing preventative measures and guidelines are sent to the user's device. Specifically, this involves generating the notification content and sending it to the device. This helps reduce unnecessary inquiries.

[0123] Step 7:

[0124] If an inquiry cannot be automatically handled by the server, the server initiates an escalation process and notifies the appropriate department or expert with details. This process is carried out in real time via the notification system. The input is the unresolved inquiry, and the output is the action taken by the notified person.

[0125] 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.

[0126] This invention aims to further enhance internal inquiry systems and improve the user experience by combining natural language processing models and emotion engines. The system is capable of interpreting inquiries and recognizing emotions, enabling more nuanced and appropriate responses.

[0127] The server receives inquiries sent by users via their terminals in natural language and analyzes them using a natural language processing model. This analysis clarifies the user's intent and extracts foundational data to identify corresponding information and solutions.

[0128] Simultaneously, the server sends the inquiry text to the sentiment engine to recognize the user's emotional state. The sentiment engine infers the emotion from the user's word choice and style of expression, and adjusts the response based on the result. If the recognized emotion is urgent or negative, the server takes this into consideration and promptly escalates it to the relevant department.

[0129] The generated response is returned to the user's device, and the user attempts to solve the problem based on that response. Furthermore, the server uses predictive analytics to predict the likelihood of similar problems occurring based on past data, and provides proactive solutions and information via push notifications.

[0130] For example, if a user enters "I'm worried about the progress of the recent project," the server analyzes this inquiry, and if the emotion engine determines that it contains emotions such as anxiety or stress, it suggests that immediate action is needed. The server quickly escalates the issue to the appropriate person in charge and simultaneously provides the user with links to general progress reports and information on support contacts.

[0131] This system allows inquiries to be handled not merely as administrative tasks, but with a more human touch that takes into account the emotions of the employees. As a result, the speed and quality of responses across the entire company will improve, leading to better internal communication and increased operational efficiency.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user uses a device to input and submit an inquiry in natural language. The user's input includes information about the question and its context.

[0135] Step 2:

[0136] The terminal sends the entered query data to the server. This data includes the user's language input.

[0137] Step 3:

[0138] The server analyzes the received query using a natural language processing model. Here, the server understands the intent of the query and extracts the necessary information.

[0139] Step 4:

[0140] The server processes the query data using an emotion engine to determine the user's emotional state. The emotion engine analyzes emotions based on keywords and expressions in the text.

[0141] Step 5:

[0142] The server adjusts its responses based on the results of the emotion engine. In particular, it considers high-priority responses when the user indicates emotions such as anxiety or anger.

[0143] Step 6:

[0144] The server generates the optimal response based on the analysis results and sentiment assessment. This response may include specific details, relevant links, and additional support information.

[0145] Step 7:

[0146] The server sends the generated response back to the terminal. The user checks the response received through the terminal and uses it to help solve the problem.

[0147] Step 8:

[0148] The server analyzes past query history and prepares to push notifications to terminals with information and alerts regarding predicted problems. This allows for proactive measures to be taken.

[0149] Step 9:

[0150] If the server determines that an inquiry cannot be resolved automatically, it will immediately escalate it to the relevant department. In this case, if there is a high level of urgency in the sentiment assessment, it will be given particular priority.

[0151] Step 10:

[0152] By receiving feedback from users, the server accumulates data that helps improve its natural language processing model and sentiment engine. This information is used to improve the system's accuracy.

[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] Handling customer inquiries within a company can be challenging because it's difficult to accurately grasp the needs and feelings of users, leading to inconsistent service quality. Furthermore, when users repeatedly encounter similar problems, there's often a lack of anticipation and proactive measures. This can result in decreased customer satisfaction and inefficient use of internal resources.

[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 means for analyzing user inquiries using natural language processing technology to clarify the user's intent, means for recognizing emotions from the user's linguistic information and adjusting the response content accordingly, and means for generating an optimal response based on the analyzed inquiry and emotion information. This enables highly accurate responses to inquiries, improves user satisfaction by providing responses that take the user's emotions into consideration, and allows for efficient responses and proactive information provision by predicting the occurrence of problems based on past data.

[0158] "Natural language processing technology" refers to a set of technologies that enable computers to understand, generate, and manipulate human language.

[0159] "Means of clarifying user intent" refers to the process of identifying the information and actions that users are seeking based on their inquiries.

[0160] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their linguistic expressions.

[0161] "Means of adjusting response content" refers to the process of changing the information provided and the way responses are handled based on the detected emotions.

[0162] "Methods for analyzing past data" refer to techniques for analyzing accumulated inquiry information to predict future trends and problem occurrences.

[0163] "Escalation" refers to the process by which a server forwards inquiries that cannot be handled automatically to the appropriate person or department.

[0164] "Push notifications" are a technology that allows a service provider to proactively send information to a device.

[0165] The embodiments for carrying out this invention are as follows.

[0166] Hardware and software configuration

[0167] This system consists of two main components: a server and terminals. The server is a central control unit equipped with a powerful processor and a large amount of memory, performing large-scale data processing and storage. Terminals are devices that users directly interact with, and can take the form of PCs, smartphones, tablets, etc.

[0168] Software Module

[0169] The server will be equipped with software modules for implementing natural language processing technology. Specifically, it is possible to use OpenAI's GPT series or other domain-specific AI models as natural language processing models. For emotion recognition, a commonly used natural language analysis tool will be used as an emotion engine. Here, open-source emotion analysis libraries can be used.

[0170] Data processing and data calculation

[0171] The server receives information sent by the user from the terminal and analyzes it using a natural language processing model. The purpose of the analysis is to clarify the user's intentions and find relevant information and appropriate countermeasures. At the same time, an emotion engine estimates the user's emotions and communicates accordingly.

[0172] Specific example

[0173] If a user enters "I'm worried about the recent project's progress," the server analyzes the inquiry and determines that it detects emotions including anxiety and stress. Based on this, the server determines that immediate action is needed and escalates the issue to the appropriate person, while also providing the user with links to general progress reports and support contact information.

[0174] Example of a prompt

[0175] "Assess the user's emotions based on their language and suggest escalation actions as needed."

[0176] As described above, by precisely analyzing user inquiries and providing empathetic and considerate responses, companies can improve the speed and quality of their responses, leading to increased operational efficiency and improved internal communication.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The user enters their inquiry in text format from their terminal. This input may include specific questions or concerns, such as "I'm worried about the progress of the recent project." When the user presses the submit button, the entered text is sent to the server.

[0180] Step 2:

[0181] The server inputs the text data received from the terminal into a natural language processing model. Here, a generative AI model is used to analyze the text and clarify the user's intent. This process analyzes keywords and context in the text to identify the subject of the inquiry. For example, from the phrase "I'm worried about the progress," it is determined that information about the current project progress is needed.

[0182] Step 3:

[0183] The server inputs the analyzed text into an emotion recognition engine to estimate the user's emotions. The emotion engine detects emotions from the wording and expressions in the text, identifying emotions such as "anxiety" and "stress." The intensity and urgency of the emotion are also evaluated. For example, the word "worry" might be judged to represent a strong emotion.

[0184] Step 4:

[0185] The server determines the appropriate course of action based on the results of natural language processing and sentiment recognition, and escalates the issue as needed. Specifically, if the identified sentiment is negative and urgent, it sends an alert directly to the relevant department. It also generates links to general Q&A and progress reports.

[0186] Step 5:

[0187] The server uses a generative AI model to create specific responses. These responses are customized to reflect the analysis results and escalation status. For example, they might include phrases like, "We apologize for any inconvenience this may have caused. Please refer to this link for the current project progress."

[0188] Step 6:

[0189] The generated response is sent from the server to the user's device. The user can review the received response and attempt to resolve the problem based on the provided links and information.

[0190] (Application Example 2)

[0191] 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".

[0192] In modern electronic transactions, promptly and appropriately handling customer inquiries and complaints is essential for improving customer satisfaction. However, conventional systems are unable to analyze the emotional state of users and flexibly adjust responses based on that analysis, resulting in unnecessary escalations and inadequate responses. To solve this problem, a new approach is needed that utilizes natural language processing and sentiment analysis technologies to improve the user experience.

[0193] 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.

[0194] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for recognizing the user's emotional state using an emotion analysis engine and adjusting the response accordingly, and means for predicting the occurrence of problems by analyzing past data and providing information to the user in advance. This enables accurate and flexible responses to inquiries.

[0195] A "natural language processing model" is a technology that includes algorithms for interpreting user inquiries and accurately understanding their intent.

[0196] An "emotion analysis engine" is software that infers emotions from a user's language and expression style, and adjusts responses accordingly.

[0197] "Escalation" is the process of transferring inquiries that are beyond the scope of what can be handled to a more specialized department or person in charge.

[0198] "Push notifications" are a communication method that sends information to a user's device in real time to attract their attention.

[0199] "Predictive analytics" is a data processing technique that uses past inquiry patterns to predict future problems and provide preventative measures.

[0200] "Response adjustment" is the process of achieving more appropriate communication by adjusting the content of responses to match the emotional state of the user.

[0201] The system for implementing this invention first has a server receive a query from the user's terminal and analyze the query using a natural language processing (NLP) model. The NLP model used is the Hugging Face Transformers library, which performs a process to clarify the user's intent. Through this NLP process, the content of the query is identified and the information necessary for subsequent processing is extracted.

[0202] Next, the server uses an emotion analysis engine to identify the user's emotions from the query. This emotion analysis uses a pre-trained model such as 'j-hartmann / emotion-english-distilroberta-base' to estimate emotions from the user's word choice and expression style. Based on this analysis, the response is adjusted to enable a more human-like response that matches the user's emotional state.

[0203] Furthermore, the server performs predictive analysis based on historical data to generate proactive measures to prevent similar problems from recurring. This involves using machine learning algorithms to predict problem patterns from large datasets.

[0204] If necessary, the server will immediately escalate the inquiry to the relevant department based on the content of the inquiry and the results of sentiment analysis. Then, it will send information and solutions based on sentiment to the user's device as a push notification.

[0205] For example, if a user inquires that they are worried because their recent payments have been delayed, the server will analyze this inquiry using NLP and an emotion analysis engine and recognize the emotion of "anxiety." Based on this result, the issue will be quickly escalated to the relevant department, and the user can be promptly informed of the progress and solutions to alleviate their anxiety.

[0206] An example of a prompt would be: "Analyze the sentiment of the following sentence and identify the primary sentiment: I am worried because my recent payment has been delayed." This entire process can improve the user experience.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The user's device inputs a query and sends it to the server. The server receives the query and inputs it as natural language text data. This data serves as the basis for subsequent processing.

[0210] Step 2:

[0211] The server uses a natural language processing (NLP) model to analyze the query text. Based on the input text data, the NLP model processes the data to identify the user's intent, extracting the purpose of the query and important information to obtain output. Specifically, the Hugging Face Transformers library is used to clarify the content of the query.

[0212] Step 3:

[0213] The server uses an emotion analysis engine to identify emotions from the analyzed query text. Using the extracted text information as input, the emotion engine performs data calculations to identify the emotional state (e.g., "anxiety," "satisfaction"). Based on this output, subsequent response adjustments are made.

[0214] Step 4:

[0215] The server generates the optimal response to a query based on the analyzed intent and emotional state. It uses the output of natural language processing models and sentiment analysis as input data. Response generation is based on pre-determined response templates and document generation techniques. It generates specific answers and prepares them to be sent to the user.

[0216] Step 5:

[0217] Based on the analysis results, the server escalates inquiries to the relevant departments if necessary. Inquiries exceeding the urgency or scope of the system are used as input, and the escalation process is automatically initiated. This output facilitates rapid problem resolution.

[0218] Step 6:

[0219] The server performs predictive analytics, analyzing historical data to forecast the occurrence of problems. The input consists of historical query data and its pattern analysis. Machine learning algorithms are applied to generate output that preemptively addresses potential failures and problems.

[0220] Step 7:

[0221] The server sends the generated solution information as a push notification to the user's device along with the final response. The output information is used to alleviate the user's anxiety and guide them through the necessary procedures. Specifically, it provides progress and solutions regarding the inquiry.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] This invention aims to automate an internal inquiry system, enabling employees to efficiently obtain information. The system incorporates a natural language processing model for analyzing human natural language, with the goal of providing quick and appropriate responses when users make inquiries.

[0239] The server receives natural language queries sent from users through their devices. The received queries are sent to a natural language processing model, where the intent of the query is analyzed. Based on this analysis, the server searches the company's internal database and generates the optimal answer. The generated answer is then sent back to the user through their device.

[0240] Furthermore, the server analyzes past data to predict recurring problems. This predictive function allows the server to prepare solutions in advance for anticipated problems and send information to the device via push notification. This makes it possible to prevent problems from occurring in the first place.

[0241] Furthermore, if an inquiry cannot be resolved automatically, the server generates a notification for escalation to the appropriate department or specialist. This feature enables a quick and accurate response, improving efficiency compared to traditional manual responses.

[0242] For example, if a user types "Please tell me the reporting format for the new project" into their terminal, the server analyzes the content, generates a link containing the most appropriate answer, and sends it back to the user. Furthermore, based on historical data, the server predicts inquiries about payroll procedures, which tend to increase at the end of the year, and proactively provides relevant guidelines to employees' terminals via push notifications. In this way, it contributes to improving the efficiency and productivity of company-wide inquiry handling.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The user uses a device to input their inquiry in natural language. The entered data is then sent from the device to the server.

[0246] Step 2:

[0247] The server passes the received query data to a natural language processing model for analysis. The analysis extracts the intent of the query and necessary information.

[0248] Step 3:

[0249] Based on the analysis results, the server searches the company's internal database to find appropriate information and answers. Relevant regulations and manuals are used in this process.

[0250] Step 4:

[0251] The server generates the best answer using the search results and sends that answer to the device. The user receives the answer on the device and checks the information to solve the problem.

[0252] Step 5:

[0253] The server analyzes past query data to predict recurring problems. It then prepares solutions in advance for these predicted problems.

[0254] Step 6:

[0255] The server will periodically or at predicted times send push notifications to the user's device, providing proactive solutions and relevant information.

[0256] Step 7:

[0257] If a user's inquiry cannot be resolved automatically, the server will escalate it to the appropriate department or specialist. This enables a quicker response.

[0258] Step 8:

[0259] The server collects user feedback and uses that information to improve the natural language processing model and the overall system. This process ensures continuous improvement in system accuracy.

[0260] (Example 1)

[0261] 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."

[0262] In modern businesses, efficient information sharing and inquiry handling are crucial. However, traditional systems often suffer from slow response times and wasted resources due to repeated inquiries. Furthermore, inquiries that cannot be automated are not properly escalated, leading to delays in resolution. Solving these problems and achieving efficient information management within the company is essential.

[0263] 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.

[0264] In this invention, the server includes means for analyzing information requests from users using natural language processing technology, means for generating appropriate responses based on the analyzed information requests, and means for predicting the occurrence of problems by analyzing historical information and providing information to the user in advance. This enables rapid and accurate information provision and proactive measures through problem prediction.

[0265] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate natural language used by humans.

[0266] A "user" refers to a person or organization that uses the system to query information.

[0267] An "information request" refers to an inquiry from a user regarding the information they want to know or the data they need.

[0268] "Analysis" is the process of breaking down given data or information into smaller parts and understanding their meaning and structure.

[0269] An "appropriate response" means providing the most relevant, accurate, and satisfactory answer to an information request.

[0270] "Historical information" refers to a collection of inquiries, responses, and related data that the system has recorded in the past.

[0271] "Prediction" is the act of anticipating future events or trends based on past data and patterns.

[0272] "Escalation" is the process of transferring a problem to a person or organization with higher authority or expertise when the problem cannot be resolved automatically.

[0273] This invention is a system that utilizes natural language processing to efficiently handle internal company inquiries. The server receives inquiries entered by users through terminals. The server incorporates natural language processing technology, such as using BERT or GPT as a generative AI model. This allows the server to analyze the intent of the user's inquiry and identify important keywords and context.

[0274] Based on the analyzed query, the server searches an internal database containing accumulated historical information. This database stores FAQs, reference materials, and past problem-solving examples for handling inquiries. From the retrieved information, the server generates the optimal response and sends it back to the user's terminal.

[0275] For example, if a user types "Please tell me the project report format" into their device, the server analyzes this and generates links and explanations of relevant formats to provide to the user. The server also analyzes past inquiry data and uses machine learning algorithms to predict issues such as the increase in payroll calculation problems at the end of the year, and proactively pushes guidelines to the user's device.

[0276] Furthermore, if the server receives a complex inquiry that cannot be resolved automatically, it will generate a notification to escalate the issue to the relevant expert or department. This feature facilitates the rapid resolution of problems.

[0277] As an example of a prompt sentence, an inquiry such as "Please tell me about the recent changes in welfare" can be provided. This system enables such inquiries to be processed quickly and accurately and provides the necessary information to the user in a timely manner.

[0278] The flow of specific processing in Example 1 will be described using FIG. 11.

[0279] Step 1:

[0280] The user inputs an inquiry in natural language on the terminal. The input content is received as digital data in a form transmitted to the server. This data is used as initial information for identifying the user's information request.

[0281] Step 2:

[0282] The server inputs the received inquiry data into a generative AI model (e.g., BERT or GPT) for natural language processing. Through this process, the server analyzes the intent of the inquiry and identifies important keywords and context. As output, structured data including the intent of the inquiry is generated.

[0283] Step 3:

[0284] The server searches the in-house database based on the analysis result. Here, a database query is generated and executed to extract relevant information. The input is the analyzed intent data, and the output is a set of relevant documents or information retrieved from the database.

[0285] Step 4:

[0286] The server generates an appropriate response to the user using the information obtained from the database. Here, a response sentence is automatically generated based on the retrieved data. For example, it includes a specific sentence such as "The project report format is as follows" or a link.

[0287] Step 5:

[0288] The generated response is sent to the user via the terminal. The user can check the response on the terminal and obtain information for problem-solving. The output here is the response message itself from the server.

[0289] Step 6:

[0290] The server has a function to analyze past data and predict new inquiries. Using machine learning algorithms, it identifies inquiry patterns that occur regularly. In this procedure, the input is past inquiry data, and the output is possible future inquiry scenarios.

[0291] Step 7:

[0292] If there are inquiries predicted for the future, the server notifies the user's terminal of pre-emptive countermeasures. The notification includes guidance and procedures to reduce the workload of employees. The output here is a message in the form of a push notification.

[0293] Step 8:

[0294] When the server receives an inquiry that cannot be automatically resolved, it generates an escalation notification to the relevant department or expert. This is an important process to quickly resolve problems. The input is inquiry data that is difficult to solve, and the output is an escalation notification.

[0295] (Application Example 1)

[0296] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0297] Within factories, the time spent responding to inquiries and troubleshooting regarding the operation of machinery and equipment can lead to decreased productivity and errors. To solve this problem, a system is needed that can quickly and efficiently acquire information about machinery and equipment and implement appropriate countermeasures. Furthermore, it is crucial to anticipate and prevent recurring problems in advance.

[0298] 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.

[0299] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for generating optimal answers based on the analyzed inquiries, means for predicting the occurrence of problems by analyzing past data and providing information to users in advance, means for escalating inquiries that exceed the scope of what can be automatically handled to the relevant departments, and database search means for providing solutions to operation and troubles of machinery and equipment within the factory. This enables faster response times for inquiries and more efficient troubleshooting within the factory.

[0300] A "natural language processing model" refers to algorithms and frameworks that enable computers to understand and analyze human natural language.

[0301] "Inquiry analysis" is the process of identifying the intent and content of questions and requests submitted by users and classifying them into appropriate categories and procedures.

[0302] A "database search method" is a system function that quickly retrieves and presents necessary data from stored information.

[0303] "Escalation" is the process of notifying the appropriate person or department of a problem when it exceeds the scope of what can be handled automatically, and requesting further action.

[0304] "Push notification" is a technology that automatically sends information to a user's device to immediately notify the user.

[0305] "Machine learning" is a technology that learns patterns and rules from data and automatically makes predictions and judgments.

[0306] "Machines and devices in the factory" refer to equipment including various tools and automation systems used in the production process.

[0307] The system for implementing this invention mainly consists of a server and a user's device (terminal).

[0308] First, the server uses a natural language processing model to analyze inquiries sent from the user. Specifically, it uses a generative AI model to analyze the intention of the inquiries and extract the necessary information. This model is implemented using deep learning frameworks such as TensorFlow and PyTorch. When the analysis is complete, the server searches for highly relevant information from the database and generates an optimal answer.

[0309] Next, it uses machine learning based on past data to analyze the tendency of problem occurrence and provides the user with relevant information and solutions in advance. Libraries such as scikit-learn are used for this prediction. For example, if there is a tendency for inquiries to increase at a specific time every year, guidelines are sent to the terminal via push notification before that time.

[0310] Also, for problems that the server cannot automatically solve, it generates an escalation notification to relevant departments and experts. This notification is implemented using communication tools such as Slack and email.

[0311] The user's device is implemented as a web or mobile application, providing an interface for making inquiries. Users can enter prompts such as, "Please tell me how to troubleshoot this device." This allows for smoother factory operations and improved productivity.

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] The user enters their inquiry from the terminal. Specifically, this involves sending a prompt message to the interface, such as "Please tell me how to troubleshoot this device." The input data is natural language text.

[0315] Step 2:

[0316] The server sends the query received from the terminal to a natural language processing model. The generative AI model analyzes the intent of the query. The input is natural language text from the user, and the output is a data structure that shows the analyzed intent.

[0317] Step 3:

[0318] Based on the analyzed intent, the server searches the database for highly relevant information and generates the optimal response. Specifically, it executes SQL queries to extract the necessary data. The input is the data structure of the analysis result, and the output is the response data.

[0319] Step 4:

[0320] The server generates an answer and sends it back to the user's terminal. The terminal displays this information to the user. The output consists of solutions and steps for the user's inquiry.

[0321] Step 5:

[0322] The server runs a machine learning algorithm to predict problem patterns based on past query history and current analysis data. The input is past query data and current results, and the output is insights indicating periods and themes that require attention.

[0323] Step 6:

[0324] Based on specific times and conditions, push notifications containing preventative measures and guidelines are sent to the user's device. Specifically, this involves generating the notification content and sending it to the device. This helps reduce unnecessary inquiries.

[0325] Step 7:

[0326] If an inquiry cannot be automatically handled by the server, the server initiates an escalation process and notifies the appropriate department or expert with details. This process is carried out in real time via the notification system. The input is the unresolved inquiry, and the output is the action taken by the notified person.

[0327] 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.

[0328] This invention aims to further enhance internal inquiry systems and improve the user experience by combining natural language processing models and emotion engines. The system is capable of interpreting inquiries and recognizing emotions, enabling more nuanced and appropriate responses.

[0329] The server receives inquiries sent by users via their terminals in natural language and analyzes them using a natural language processing model. This analysis clarifies the user's intent and extracts foundational data to identify corresponding information and solutions.

[0330] Simultaneously, the server sends the inquiry text to the sentiment engine to recognize the user's emotional state. The sentiment engine infers the emotion from the user's word choice and style of expression, and adjusts the response based on the result. If the recognized emotion is urgent or negative, the server takes this into consideration and promptly escalates it to the relevant department.

[0331] The generated response is returned to the user's device, and the user attempts to solve the problem based on that response. Furthermore, the server uses predictive analytics to predict the likelihood of similar problems occurring based on past data, and provides proactive solutions and information via push notifications.

[0332] For example, if a user enters "I'm worried about the progress of the recent project," the server analyzes this inquiry, and if the emotion engine determines that it contains emotions such as anxiety or stress, it suggests that immediate action is needed. The server quickly escalates the issue to the appropriate person in charge and simultaneously provides the user with links to general progress reports and information on support contacts.

[0333] This system allows inquiries to be handled not merely as administrative tasks, but with a more human touch that takes into account the emotions of the employees. As a result, the speed and quality of responses across the entire company will improve, leading to better internal communication and increased operational efficiency.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The user uses a device to input and submit an inquiry in natural language. The user's input includes information about the question and its context.

[0337] Step 2:

[0338] The terminal sends the entered query data to the server. This data includes the user's language input.

[0339] Step 3:

[0340] The server analyzes the received query using a natural language processing model. Here, the server understands the intent of the query and extracts the necessary information.

[0341] Step 4:

[0342] The server processes the query data using an emotion engine to determine the user's emotional state. The emotion engine analyzes emotions based on keywords and expressions in the text.

[0343] Step 5:

[0344] The server adjusts its responses based on the results of the emotion engine. In particular, it considers high-priority responses when the user indicates emotions such as anxiety or anger.

[0345] Step 6:

[0346] The server generates the optimal response based on the analysis results and sentiment assessment. This response may include specific details, relevant links, and additional support information.

[0347] Step 7:

[0348] The server sends the generated response back to the terminal. The user checks the response received through the terminal and uses it to help solve the problem.

[0349] Step 8:

[0350] The server analyzes past query history and prepares to push notifications to terminals with information and alerts regarding predicted problems. This allows for proactive measures to be taken.

[0351] Step 9:

[0352] If the server determines that an inquiry cannot be resolved automatically, it will immediately escalate it to the relevant department. In this case, if there is a high level of urgency in the sentiment assessment, it will be given particular priority.

[0353] Step 10:

[0354] By receiving feedback from users, the server accumulates data that helps improve its natural language processing model and sentiment engine. This information is used to improve the system's accuracy.

[0355] (Example 2)

[0356] 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".

[0357] Handling customer inquiries within a company can be challenging because it's difficult to accurately grasp the needs and feelings of users, leading to inconsistent service quality. Furthermore, when users repeatedly encounter similar problems, there's often a lack of anticipation and proactive measures. This can result in decreased customer satisfaction and inefficient use of internal resources.

[0358] 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.

[0359] In this invention, the server includes means for analyzing user inquiries using natural language processing technology to clarify the user's intent, means for recognizing emotions from the user's linguistic information and adjusting the response content accordingly, and means for generating an optimal response based on the analyzed inquiry and emotion information. This enables highly accurate responses to inquiries, improves user satisfaction by providing responses that take the user's emotions into consideration, and allows for efficient responses and proactive information provision by predicting the occurrence of problems based on past data.

[0360] "Natural language processing technology" refers to a set of technologies that enable computers to understand, generate, and manipulate human language.

[0361] "Means of clarifying user intent" refers to the process of identifying the information and actions that users are seeking based on their inquiries.

[0362] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their linguistic expressions.

[0363] "Means of adjusting response content" refers to the process of changing the information provided and the way responses are handled based on the detected emotions.

[0364] "Methods for analyzing past data" refer to techniques for analyzing accumulated inquiry information to predict future trends and problem occurrences.

[0365] "Escalation" refers to the process by which a server forwards inquiries that cannot be handled automatically to the appropriate person or department.

[0366] "Push notifications" are a technology that allows a service provider to proactively send information to a device.

[0367] The embodiments for carrying out this invention are as follows.

[0368] Hardware and software configuration

[0369] This system consists of two main components: a server and terminals. The server is a central control unit equipped with a powerful processor and a large amount of memory, performing large-scale data processing and storage. Terminals are devices that users directly interact with, and can take the form of PCs, smartphones, tablets, etc.

[0370] Software Module

[0371] The server will be equipped with software modules for implementing natural language processing technology. Specifically, OpenAI's GPT series or other domain-specific AI models could be used as natural language processing models. For emotion recognition, a commonly used natural language analysis tool would be employed as an emotion engine. Here, open-source emotion analysis libraries can be used.

[0372] Data processing and data calculation

[0373] The server receives information sent by the user from the terminal and analyzes it using a natural language processing model. The purpose of the analysis is to clarify the user's intentions and find relevant information and appropriate countermeasures. At the same time, an emotion engine estimates the user's emotions and communicates accordingly.

[0374] Specific example

[0375] If a user enters "I'm worried about the recent project's progress," the server analyzes the inquiry and determines that it detects emotions including anxiety and stress. Based on this, the server determines that immediate action is needed and escalates the issue to the appropriate person, while also providing the user with links to general progress reports and support contact information.

[0376] Example of a prompt

[0377] "Assess the user's emotions based on their language and suggest escalation actions as needed."

[0378] As described above, by precisely analyzing user inquiries and providing empathetic and considerate responses, companies can improve the speed and quality of their responses, leading to increased operational efficiency and improved internal communication.

[0379] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0380] Step 1:

[0381] The user enters their inquiry in text format from their terminal. This input may include specific questions or concerns, such as "I'm worried about the progress of the recent project." When the user presses the submit button, the entered text is sent to the server.

[0382] Step 2:

[0383] The server inputs the text data received from the terminal into a natural language processing model. Here, a generative AI model is used to analyze the text and clarify the user's intent. This process analyzes keywords and context in the text to identify the subject of the inquiry. For example, from the phrase "I'm worried about the progress," it is determined that information about the current project progress is needed.

[0384] Step 3:

[0385] The server inputs the analyzed text into an emotion recognition engine to estimate the user's emotions. The emotion engine detects emotions from the wording and expressions in the text, identifying emotions such as "anxiety" and "stress." The intensity and urgency of the emotion are also evaluated. For example, the word "worry" might be judged to represent a strong emotion.

[0386] Step 4:

[0387] The server determines the appropriate course of action based on the results of natural language processing and sentiment recognition, and escalates the issue as needed. Specifically, if the identified sentiment is negative and urgent, it sends an alert directly to the relevant department. It also generates links to general Q&A and progress reports.

[0388] Step 5:

[0389] The server uses a generative AI model to create specific responses. These responses are customized to reflect the analysis results and escalation status. For example, they might include phrases like, "We apologize for any inconvenience this may have caused. Please refer to this link for the current project progress."

[0390] Step 6:

[0391] The generated response is sent from the server to the user's device. The user can review the received response and attempt to resolve the problem based on the provided links and information.

[0392] (Application Example 2)

[0393] 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."

[0394] In modern electronic transactions, promptly and appropriately handling customer inquiries and complaints is essential for improving customer satisfaction. However, conventional systems are unable to analyze the emotional state of users and flexibly adjust responses based on that analysis, resulting in unnecessary escalations and inadequate responses. To solve this problem, a new approach is needed that utilizes natural language processing and sentiment analysis technologies to improve the user experience.

[0395] 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.

[0396] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for recognizing the user's emotional state using an emotion analysis engine and adjusting the response accordingly, and means for predicting the occurrence of problems by analyzing past data and providing information to the user in advance. This enables accurate and flexible responses to inquiries.

[0397] A "natural language processing model" is a technology that includes algorithms for interpreting user inquiries and accurately understanding their intent.

[0398] An "emotion analysis engine" is software that infers emotions from a user's language and expression style, and adjusts responses accordingly.

[0399] "Escalation" is the process of transferring inquiries that are beyond the scope of what can be handled to a more specialized department or person in charge.

[0400] "Push notifications" are a communication method that sends information to a user's device in real time to attract their attention.

[0401] "Predictive analytics" is a data processing technique that uses past inquiry patterns to predict future problems and provide preventative measures.

[0402] "Response adjustment" is the process of achieving more appropriate communication by adjusting the content of responses to match the emotional state of the user.

[0403] The system for implementing this invention first has a server receive a query from the user's terminal and analyze the query using a natural language processing (NLP) model. The NLP model used is the Hugging Face Transformers library, which performs a process to clarify the user's intent. Through this NLP process, the content of the query is identified and the information necessary for subsequent processing is extracted.

[0404] Next, the server uses an emotion analysis engine to identify the user's emotions from the query. This emotion analysis uses a pre-trained model such as 'j-hartmann / emotion-english-distilroberta-base' to estimate emotions from the user's word choice and expression style. Based on this analysis, the response is adjusted to enable a more human-like response that matches the user's emotional state.

[0405] Furthermore, the server performs predictive analysis based on historical data to generate proactive measures to prevent similar problems from recurring. This involves using machine learning algorithms to predict problem patterns from large datasets.

[0406] If necessary, the server will immediately escalate the inquiry to the relevant department based on the content of the inquiry and the results of sentiment analysis. Then, it will send information and solutions based on sentiment to the user's device as a push notification.

[0407] For example, if a user inquires that they are worried because their recent payments have been delayed, the server will analyze this inquiry using NLP and an emotion analysis engine and recognize the emotion of "anxiety." Based on this result, the issue will be quickly escalated to the relevant department, and the user can be promptly informed of the progress and solutions to alleviate their anxiety.

[0408] An example of a prompt would be: "Analyze the sentiment of the following sentence and identify the primary sentiment: I am worried because my recent payment has been delayed." This entire process can improve the user experience.

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The user's device inputs a query and sends it to the server. The server receives the query and inputs it as natural language text data. This data serves as the basis for subsequent processing.

[0412] Step 2:

[0413] The server uses a natural language processing (NLP) model to analyze the query text. Based on the input text data, the NLP model processes the data to identify the user's intent, extracting the purpose of the query and important information to obtain output. Specifically, the Hugging Face Transformers library is used to clarify the content of the query.

[0414] Step 3:

[0415] The server uses an emotion analysis engine to identify emotions from the analyzed query text. Using the extracted text information as input, the emotion engine performs data calculations to identify the emotional state (e.g., "anxiety," "satisfaction"). Based on this output, subsequent response adjustments are made.

[0416] Step 4:

[0417] The server generates the optimal response to a query based on the analyzed intent and emotional state. It uses the output of natural language processing models and sentiment analysis as input data. Response generation is based on pre-determined response templates and document generation techniques. It generates specific answers and prepares them to be sent to the user.

[0418] Step 5:

[0419] Based on the analysis results, the server escalates inquiries to the relevant departments if necessary. Inquiries exceeding the urgency or scope of the system are used as input, and the escalation process is automatically initiated. This output facilitates rapid problem resolution.

[0420] Step 6:

[0421] The server performs predictive analytics, analyzing historical data to forecast the occurrence of problems. The input consists of historical query data and its pattern analysis. Machine learning algorithms are applied to generate output that preemptively addresses potential failures and problems.

[0422] Step 7:

[0423] The server sends the generated solution information as a push notification to the user's device along with the final response. The output information is used to alleviate the user's anxiety and guide them through the necessary procedures. Specifically, it provides progress and solutions regarding the inquiry.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] This invention aims to automate an internal inquiry system, enabling employees to efficiently obtain information. The system incorporates a natural language processing model for analyzing human natural language, with the goal of providing quick and appropriate responses when users make inquiries.

[0441] The server receives natural language queries sent from users through their devices. The received queries are sent to a natural language processing model, where the intent of the query is analyzed. Based on this analysis, the server searches the company's internal database and generates the optimal answer. The generated answer is then sent back to the user through their device.

[0442] Furthermore, the server analyzes past data to predict recurring problems. This predictive function allows the server to prepare solutions in advance for anticipated problems and send information to the device via push notification. This makes it possible to prevent problems from occurring in the first place.

[0443] Furthermore, if an inquiry cannot be resolved automatically, the server generates a notification for escalation to the appropriate department or specialist. This feature enables a quick and accurate response, improving efficiency compared to traditional manual responses.

[0444] For example, if a user types "Please tell me the reporting format for the new project" into their terminal, the server analyzes the content, generates a link containing the most appropriate answer, and sends it back to the user. Furthermore, based on historical data, the server predicts inquiries about payroll procedures, which tend to increase at the end of the year, and proactively provides relevant guidelines to employees' terminals via push notifications. In this way, it contributes to improving the efficiency and productivity of company-wide inquiry handling.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The user uses a device to input their inquiry in natural language. The entered data is then sent from the device to the server.

[0448] Step 2:

[0449] The server passes the received query data to a natural language processing model for analysis. The analysis extracts the intent of the query and necessary information.

[0450] Step 3:

[0451] Based on the analysis results, the server searches the company's internal database to find appropriate information and answers. Relevant regulations and manuals are used in this process.

[0452] Step 4:

[0453] The server generates the best answer using the search results and sends that answer to the device. The user receives the answer on the device and checks the information to solve the problem.

[0454] Step 5:

[0455] The server analyzes past query data to predict recurring problems. It then prepares solutions in advance for these predicted problems.

[0456] Step 6:

[0457] The server will periodically or at predicted times send push notifications to the user's device, providing proactive solutions and relevant information.

[0458] Step 7:

[0459] If a user's inquiry cannot be resolved automatically, the server will escalate it to the appropriate department or specialist. This enables a quicker response.

[0460] Step 8:

[0461] The server collects user feedback and uses that information to improve the natural language processing model and the overall system. This process ensures continuous improvement in system accuracy.

[0462] (Example 1)

[0463] 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."

[0464] In modern businesses, efficient information sharing and inquiry handling are crucial. However, traditional systems often suffer from slow response times and wasted resources due to repeated inquiries. Furthermore, inquiries that cannot be automated are not properly escalated, leading to delays in resolution. Solving these problems and achieving efficient information management within the company is essential.

[0465] 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.

[0466] In this invention, the server includes means for analyzing information requests from users using natural language processing technology, means for generating appropriate responses based on the analyzed information requests, and means for predicting the occurrence of problems by analyzing historical information and providing information to the user in advance. This enables rapid and accurate information provision and proactive measures through problem prediction.

[0467] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate natural language used by humans.

[0468] A "user" refers to a person or organization that uses the system to query information.

[0469] An "information request" refers to an inquiry from a user regarding the information they want to know or the data they need.

[0470] "Analysis" is the process of breaking down given data or information into smaller parts and understanding their meaning and structure.

[0471] An "appropriate response" means providing the most relevant, accurate, and satisfactory answer to an information request.

[0472] "Historical information" refers to a collection of inquiries, responses, and related data that the system has recorded in the past.

[0473] "Prediction" is the act of anticipating future events or trends based on past data and patterns.

[0474] "Escalation" is the process of transferring a problem to a person or organization with higher authority or expertise when the problem cannot be resolved automatically.

[0475] This invention is a system that utilizes natural language processing to efficiently handle internal company inquiries. The server receives inquiries entered by users through terminals. The server incorporates natural language processing technology, such as using BERT or GPT as a generative AI model. This allows the server to analyze the intent of the user's inquiry and identify important keywords and context.

[0476] Based on the analyzed query, the server searches an internal database containing accumulated historical information. This database stores FAQs, reference materials, and past problem-solving examples for handling inquiries. From the retrieved information, the server generates the optimal response and sends it back to the user's terminal.

[0477] For example, if a user types "Please tell me the project report format" into their device, the server analyzes this and generates links and explanations of relevant formats to provide to the user. The server also analyzes past inquiry data and uses machine learning algorithms to predict issues such as the increase in payroll calculation problems at the end of the year, and proactively pushes guidelines to the user's device.

[0478] Furthermore, if the server receives a complex inquiry that cannot be resolved automatically, it will generate a notification to escalate the issue to the relevant expert or department. This feature facilitates the rapid resolution of problems.

[0479] An example of a prompt message could be a question like, "Please tell me about recent changes to employee benefits." This system can process such inquiries quickly and accurately, providing users with the necessary information in a timely manner.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The user enters their inquiry into the terminal using natural language. The entered information is received as digital data and sent to the server. This data is used as initial information to identify the user's request.

[0483] Step 2:

[0484] The server inputs the received query data into a generating AI model (e.g., BERT or GPT) and performs natural language processing. Through this process, the server analyzes the intent of the query and identifies important keywords and context. As output, structured data containing the intent of the query is generated.

[0485] Step 3:

[0486] The server searches the company's internal database based on the analysis results. Here, database queries are generated and executed to extract relevant information. The input is the analyzed intent data, and the output is a set of relevant documents and information retrieved from the database.

[0487] Step 4:

[0488] The server generates an appropriate response to the user using information retrieved from the database. Here, the response text is automatically generated based on the retrieved data. For example, it might include specific sentences and links such as, "The project report format is here."

[0489] Step 5:

[0490] The generated response is sent to the user via the terminal. The user can then view the response on the terminal and obtain information to resolve the problem. The output here is the response message from the server itself.

[0491] Step 6:

[0492] The server has the capability to analyze historical data and predict new queries. It uses machine learning algorithms to identify regularly occurring query patterns. In this procedure, the input is historical query data, and the output is potential future query scenarios.

[0493] Step 7:

[0494] If a potential inquiry is anticipated in the future, the server will notify the user's terminal of proactive measures. The notification will include guidance and procedures to reduce the workload for employees. The output here is a push notification message.

[0495] Step 8:

[0496] When the server receives an inquiry that cannot be resolved automatically, it generates an escalation notification to the relevant department or expert. This is a crucial process for quickly resolving problems. The input is data for an inquiry that is difficult to resolve, and the output is an escalation notification.

[0497] (Application Example 1)

[0498] 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."

[0499] Within factories, the time spent responding to inquiries and troubleshooting regarding the operation of machinery and equipment can lead to decreased productivity and errors. To solve this problem, a system is needed that can quickly and efficiently acquire information about machinery and equipment and implement appropriate countermeasures. Furthermore, it is crucial to anticipate and prevent recurring problems in advance.

[0500] 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.

[0501] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for generating optimal answers based on the analyzed inquiries, means for predicting the occurrence of problems by analyzing past data and providing information to users in advance, means for escalating inquiries that exceed the scope of what can be automatically handled to the relevant departments, and database search means for providing solutions to operation and troubles of machinery and equipment within the factory. This enables faster response times for inquiries and more efficient troubleshooting within the factory.

[0502] A "natural language processing model" refers to algorithms and frameworks that enable computers to understand and analyze human natural language.

[0503] "Inquiry analysis" is the process of identifying the intent and content of questions and requests submitted by users and classifying them into appropriate categories and procedures.

[0504] A "database search method" is a system function that quickly retrieves and presents necessary data from stored information.

[0505] "Escalation" is the process of notifying the appropriate person or department of a problem when it exceeds the scope of what can be handled automatically, and requesting further action.

[0506] "Push notifications" are a technology that automatically sends information to a user's device to immediately inform the user.

[0507] "Machine learning" is a technology that learns patterns and rules from data and automatically makes predictions and decisions.

[0508] "Machinery and equipment within a factory" refers to equipment including various tools and automation systems used in the production process.

[0509] The system for carrying out this invention mainly consists of a server and a user's device (terminal).

[0510] The server first uses a natural language processing model to analyze the user's inquiry. Specifically, it uses a generative AI model to analyze the intent of the inquiry and extract the necessary information. This model is implemented using deep learning frameworks such as TensorFlow and PyTorch. Once the analysis is complete, the server searches the database for relevant information and generates the optimal answer.

[0511] Next, machine learning is used to analyze problem occurrence trends based on past data, and relevant information and solutions are provided to users in advance. Libraries such as scikit-learn are used for this prediction. For example, if there is a tendency for inquiries to increase at a specific time each year, guidelines will be sent to the device via push notification before that time.

[0512] Furthermore, for issues that the server cannot resolve automatically, it generates escalation notifications to the relevant departments or specialists. These notifications are sent using communication tools such as Slack or email.

[0513] The user's device is implemented as a web or mobile application, providing an interface for making inquiries. Users can enter prompts such as, "Please tell me how to troubleshoot this device." This allows for smoother factory operations and improved productivity.

[0514] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0515] Step 1:

[0516] The user enters their inquiry from the terminal. Specifically, this involves sending a prompt message to the interface, such as "Please tell me how to troubleshoot this device." The input data is natural language text.

[0517] Step 2:

[0518] The server sends the query received from the terminal to a natural language processing model. The generative AI model analyzes the intent of the query. The input is natural language text from the user, and the output is a data structure that shows the analyzed intent.

[0519] Step 3:

[0520] Based on the analyzed intent, the server searches the database for highly relevant information and generates the optimal response. Specifically, it executes SQL queries to extract the necessary data. The input is the data structure of the analysis result, and the output is the response data.

[0521] Step 4:

[0522] The server generates an answer and sends it back to the user's terminal. The terminal displays this information to the user. The output consists of solutions and steps for the user's inquiry.

[0523] Step 5:

[0524] The server runs a machine learning algorithm to predict problem patterns based on past query history and current analysis data. The input is past query data and current results, and the output is insights indicating periods and themes that require attention.

[0525] Step 6:

[0526] Based on specific times and conditions, push notifications containing preventative measures and guidelines are sent to the user's device. Specifically, this involves generating the notification content and sending it to the device. This helps reduce unnecessary inquiries.

[0527] Step 7:

[0528] If an inquiry cannot be automatically handled by the server, the server initiates an escalation process and notifies the appropriate department or expert with details. This process is carried out in real time via the notification system. The input is the unresolved inquiry, and the output is the action taken by the notified person.

[0529] 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.

[0530] This invention aims to further enhance internal inquiry systems and improve the user experience by combining natural language processing models and emotion engines. The system is capable of interpreting inquiries and recognizing emotions, enabling more nuanced and appropriate responses.

[0531] The server receives inquiries sent by users via their terminals in natural language and analyzes them using a natural language processing model. This analysis clarifies the user's intent and extracts foundational data to identify corresponding information and solutions.

[0532] Simultaneously, the server sends the inquiry text to the sentiment engine to recognize the user's emotional state. The sentiment engine infers the emotion from the user's word choice and style of expression, and adjusts the response based on the result. If the recognized emotion is urgent or negative, the server takes this into consideration and promptly escalates it to the relevant department.

[0533] The generated response is returned to the user's device, and the user attempts to solve the problem based on that response. Furthermore, the server uses predictive analytics to predict the likelihood of similar problems occurring based on past data, and provides proactive solutions and information via push notifications.

[0534] For example, if a user enters "I'm worried about the progress of the recent project," the server analyzes this inquiry, and if the emotion engine determines that it contains emotions such as anxiety or stress, it suggests that immediate action is needed. The server quickly escalates the issue to the appropriate person in charge and simultaneously provides the user with links to general progress reports and information on support contacts.

[0535] This system allows inquiries to be handled not merely as administrative tasks, but with a more human touch that takes into account the emotions of the employees. As a result, the speed and quality of responses across the entire company will improve, leading to better internal communication and increased operational efficiency.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The user uses a device to input and submit an inquiry in natural language. The user's input includes information about the question and its context.

[0539] Step 2:

[0540] The terminal sends the entered query data to the server. This data includes the user's language input.

[0541] Step 3:

[0542] The server analyzes the received query using a natural language processing model. Here, the server understands the intent of the query and extracts the necessary information.

[0543] Step 4:

[0544] The server processes the query data using an emotion engine to determine the user's emotional state. The emotion engine analyzes emotions based on keywords and expressions in the text.

[0545] Step 5:

[0546] The server adjusts its responses based on the results of the emotion engine. In particular, it considers high-priority responses when the user indicates emotions such as anxiety or anger.

[0547] Step 6:

[0548] The server generates the optimal response based on the analysis results and sentiment assessment. This response may include specific details, relevant links, and additional support information.

[0549] Step 7:

[0550] The server sends the generated response back to the terminal. The user checks the response received through the terminal and uses it to help solve the problem.

[0551] Step 8:

[0552] The server analyzes past query history and prepares to push notifications to terminals with information and alerts regarding predicted problems. This allows for proactive measures to be taken.

[0553] Step 9:

[0554] If the server determines that an inquiry cannot be resolved automatically, it will immediately escalate it to the relevant department. In this case, if there is a high level of urgency in the sentiment assessment, it will be given particular priority.

[0555] Step 10:

[0556] By receiving feedback from users, the server accumulates data that helps improve its natural language processing model and sentiment engine. This information is used to improve the system's accuracy.

[0557] (Example 2)

[0558] 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."

[0559] Handling customer inquiries within a company can be challenging because it's difficult to accurately grasp the needs and feelings of users, leading to inconsistent service quality. Furthermore, when users repeatedly encounter similar problems, there's often a lack of anticipation and proactive measures. This can result in decreased customer satisfaction and inefficient use of internal resources.

[0560] 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.

[0561] In this invention, the server includes means for analyzing user inquiries using natural language processing technology to clarify the user's intent, means for recognizing emotions from the user's linguistic information and adjusting the response content accordingly, and means for generating an optimal response based on the analyzed inquiry and emotion information. This enables highly accurate responses to inquiries, improves user satisfaction by providing responses that take the user's emotions into consideration, and allows for efficient responses and proactive information provision by predicting the occurrence of problems based on past data.

[0562] "Natural language processing technology" refers to a set of technologies that enable computers to understand, generate, and manipulate human language.

[0563] "Means of clarifying user intent" refers to the process of identifying the information and actions that users are seeking based on their inquiries.

[0564] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their linguistic expressions.

[0565] "Means of adjusting response content" refers to the process of changing the information provided and the way responses are handled based on the detected emotions.

[0566] "Methods for analyzing past data" refer to techniques for analyzing accumulated inquiry information to predict future trends and problem occurrences.

[0567] "Escalation" refers to the process by which a server forwards inquiries that cannot be handled automatically to the appropriate person or department.

[0568] "Push notifications" are a technology that allows a service provider to proactively send information to a device.

[0569] The embodiments for carrying out this invention are as follows.

[0570] Hardware and software configuration

[0571] This system consists of two main components: a server and terminals. The server is a central control unit equipped with a powerful processor and a large amount of memory, performing large-scale data processing and storage. Terminals are devices that users directly interact with, and can take the form of PCs, smartphones, tablets, etc.

[0572] Software Module

[0573] The server will be equipped with software modules for implementing natural language processing technology. Specifically, OpenAI's GPT series or other domain-specific AI models could be used as natural language processing models. For emotion recognition, a commonly used natural language analysis tool would be employed as an emotion engine. Here, open-source emotion analysis libraries can be used.

[0574] Data processing and data calculation

[0575] The server receives information sent by the user from the terminal and analyzes it using a natural language processing model. The purpose of the analysis is to clarify the user's intentions and find relevant information and appropriate countermeasures. At the same time, an emotion engine estimates the user's emotions and communicates accordingly.

[0576] Specific example

[0577] If a user enters "I'm worried about the recent project's progress," the server analyzes the inquiry and determines that it detects emotions including anxiety and stress. Based on this, the server determines that immediate action is needed and escalates the issue to the appropriate person, while also providing the user with links to general progress reports and support contact information.

[0578] Example of a prompt

[0579] "Assess the user's emotions based on their language and suggest escalation actions as needed."

[0580] As described above, by precisely analyzing user inquiries and providing empathetic and considerate responses, companies can improve the speed and quality of their responses, leading to increased operational efficiency and improved internal communication.

[0581] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0582] Step 1:

[0583] The user enters their inquiry in text format from their terminal. This input may include specific questions or concerns, such as "I'm worried about the progress of the recent project." When the user presses the submit button, the entered text is sent to the server.

[0584] Step 2:

[0585] The server inputs the text data received from the terminal into a natural language processing model. Here, a generative AI model is used to analyze the text and clarify the user's intent. This process analyzes keywords and context in the text to identify the subject of the inquiry. For example, from the phrase "I'm worried about the progress," it is determined that information about the current project progress is needed.

[0586] Step 3:

[0587] The server inputs the analyzed text into an emotion recognition engine to estimate the user's emotions. The emotion engine detects emotions from the wording and expressions in the text, identifying emotions such as "anxiety" and "stress." The intensity and urgency of the emotion are also evaluated. For example, the word "worry" might be judged to represent a strong emotion.

[0588] Step 4:

[0589] The server determines the appropriate course of action based on the results of natural language processing and sentiment recognition, and escalates the issue as needed. Specifically, if the identified sentiment is negative and urgent, it sends an alert directly to the relevant department. It also generates links to general Q&A and progress reports.

[0590] Step 5:

[0591] The server uses a generative AI model to create specific responses. These responses are customized to reflect the analysis results and escalation status. For example, they might include phrases like, "We apologize for any inconvenience this may have caused. Please refer to this link for the current project progress."

[0592] Step 6:

[0593] The generated response is sent from the server to the user's device. The user can review the received response and attempt to resolve the problem based on the provided links and information.

[0594] (Application Example 2)

[0595] 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."

[0596] In modern electronic transactions, promptly and appropriately handling customer inquiries and complaints is essential for improving customer satisfaction. However, conventional systems are unable to analyze the emotional state of users and flexibly adjust responses based on that analysis, resulting in unnecessary escalations and inadequate responses. To solve this problem, a new approach is needed that utilizes natural language processing and sentiment analysis technologies to improve the user experience.

[0597] 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.

[0598] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for recognizing the user's emotional state using an emotion analysis engine and adjusting the response accordingly, and means for predicting the occurrence of problems by analyzing past data and providing information to the user in advance. This enables accurate and flexible responses to inquiries.

[0599] A "natural language processing model" is a technology that includes algorithms for interpreting user inquiries and accurately understanding their intent.

[0600] An "emotion analysis engine" is software that infers emotions from a user's language and expression style, and adjusts responses accordingly.

[0601] "Escalation" is the process of transferring inquiries that are beyond the scope of what can be handled to a more specialized department or person in charge.

[0602] "Push notifications" are a communication method that sends information to a user's device in real time to attract their attention.

[0603] "Predictive analytics" is a data processing technique that uses past inquiry patterns to predict future problems and provide preventative measures.

[0604] "Response adjustment" is the process of achieving more appropriate communication by adjusting the content of responses to match the emotional state of the user.

[0605] The system for implementing this invention first has a server receive a query from the user's terminal and analyze the query using a natural language processing (NLP) model. The NLP model used is the Hugging Face Transformers library, which performs a process to clarify the user's intent. Through this NLP process, the content of the query is identified and the information necessary for subsequent processing is extracted.

[0606] Next, the server uses an emotion analysis engine to identify the user's emotions from the query. This emotion analysis uses a pre-trained model such as 'j-hartmann / emotion-english-distilroberta-base' to estimate emotions from the user's word choice and expression style. Based on this analysis, the response is adjusted to enable a more human-like response that matches the user's emotional state.

[0607] Furthermore, the server performs predictive analysis based on historical data to generate proactive measures to prevent similar problems from recurring. This involves using machine learning algorithms to predict problem patterns from large datasets.

[0608] If necessary, the server will immediately escalate the inquiry to the relevant department based on the content of the inquiry and the results of sentiment analysis. Then, it will send information and solutions based on sentiment to the user's device as a push notification.

[0609] For example, if a user inquires that they are worried because their recent payments have been delayed, the server will analyze this inquiry using NLP and an emotion analysis engine and recognize the emotion of "anxiety." Based on this result, the issue will be quickly escalated to the relevant department, and the user can be promptly informed of the progress and solutions to alleviate their anxiety.

[0610] An example of a prompt would be: "Analyze the sentiment of the following sentence and identify the primary sentiment: I am worried because my recent payment has been delayed." This entire process can improve the user experience.

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] The user's device inputs a query and sends it to the server. The server receives the query and inputs it as natural language text data. This data serves as the basis for subsequent processing.

[0614] Step 2:

[0615] The server uses a natural language processing (NLP) model to analyze the query text. Based on the input text data, the NLP model processes the data to identify the user's intent, extracting the purpose of the query and important information to obtain output. Specifically, the Hugging Face Transformers library is used to clarify the content of the query.

[0616] Step 3:

[0617] The server uses an emotion analysis engine to identify emotions from the analyzed query text. Using the extracted text information as input, the emotion engine performs data calculations to identify the emotional state (e.g., "anxiety," "satisfaction"). Based on this output, subsequent response adjustments are made.

[0618] Step 4:

[0619] The server generates the optimal response to a query based on the analyzed intent and emotional state. It uses the output of natural language processing models and sentiment analysis as input data. Response generation is based on pre-determined response templates and document generation techniques. It generates specific answers and prepares them to be sent to the user.

[0620] Step 5:

[0621] Based on the analysis results, the server escalates inquiries to the relevant departments if necessary. Inquiries exceeding the urgency or scope of the system are used as input, and the escalation process is automatically initiated. This output facilitates rapid problem resolution.

[0622] Step 6:

[0623] The server performs predictive analytics, analyzing historical data to forecast the occurrence of problems. The input consists of historical query data and its pattern analysis. Machine learning algorithms are applied to generate output that preemptively addresses potential failures and problems.

[0624] Step 7:

[0625] The server sends the generated solution information as a push notification to the user's device along with the final response. The output information is used to alleviate the user's anxiety and guide them through the necessary procedures. Specifically, it provides progress and solutions regarding the inquiry.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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).

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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".

[0643] This invention aims to automate an internal inquiry system, enabling employees to efficiently obtain information. The system incorporates a natural language processing model for analyzing human natural language, with the goal of providing quick and appropriate responses when users make inquiries.

[0644] The server receives natural language queries sent from users through their devices. The received queries are sent to a natural language processing model, where the intent of the query is analyzed. Based on this analysis, the server searches the company's internal database and generates the optimal answer. The generated answer is then sent back to the user through their device.

[0645] Furthermore, the server analyzes past data to predict recurring problems. This predictive function allows the server to prepare solutions in advance for anticipated problems and send information to the device via push notification. This makes it possible to prevent problems from occurring in the first place.

[0646] Furthermore, if an inquiry cannot be resolved automatically, the server generates a notification for escalation to the appropriate department or specialist. This feature enables a quick and accurate response, improving efficiency compared to traditional manual responses.

[0647] For example, if a user types "Please tell me the reporting format for the new project" into their terminal, the server analyzes the content, generates a link containing the most appropriate answer, and sends it back to the user. Furthermore, based on historical data, the server predicts inquiries about payroll procedures, which tend to increase at the end of the year, and proactively provides relevant guidelines to employees' terminals via push notifications. In this way, it contributes to improving the efficiency and productivity of company-wide inquiry handling.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The user uses a device to input their inquiry in natural language. The entered data is then sent from the device to the server.

[0651] Step 2:

[0652] The server passes the received query data to a natural language processing model for analysis. The analysis extracts the intent of the query and necessary information.

[0653] Step 3:

[0654] Based on the analysis results, the server searches the company's internal database to find appropriate information and answers. Relevant regulations and manuals are used in this process.

[0655] Step 4:

[0656] The server generates the best answer using the search results and sends that answer to the device. The user receives the answer on the device and checks the information to solve the problem.

[0657] Step 5:

[0658] The server analyzes past query data to predict recurring problems. It then prepares solutions in advance for these predicted problems.

[0659] Step 6:

[0660] The server will periodically or at predicted times send push notifications to the user's device, providing proactive solutions and relevant information.

[0661] Step 7:

[0662] If a user's inquiry cannot be resolved automatically, the server will escalate it to the appropriate department or specialist. This enables a quicker response.

[0663] Step 8:

[0664] The server collects user feedback and uses that information to improve the natural language processing model and the overall system. This process ensures continuous improvement in system accuracy.

[0665] (Example 1)

[0666] 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".

[0667] In modern businesses, efficient information sharing and inquiry handling are crucial. However, traditional systems often suffer from slow response times and wasted resources due to repeated inquiries. Furthermore, inquiries that cannot be automated are not properly escalated, leading to delays in resolution. Solving these problems and achieving efficient information management within the company is essential.

[0668] 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.

[0669] In this invention, the server includes means for analyzing information requests from users using natural language processing technology, means for generating appropriate responses based on the analyzed information requests, and means for predicting the occurrence of problems by analyzing historical information and providing information to the user in advance. This enables rapid and accurate information provision and proactive measures through problem prediction.

[0670] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate natural language used by humans.

[0671] A "user" refers to a person or organization that uses the system to query information.

[0672] An "information request" refers to an inquiry from a user regarding the information they want to know or the data they need.

[0673] "Analysis" is the process of breaking down given data or information into smaller parts and understanding their meaning and structure.

[0674] An "appropriate response" means providing the most relevant, accurate, and satisfactory answer to an information request.

[0675] "Historical information" refers to a collection of inquiries, responses, and related data that the system has recorded in the past.

[0676] "Prediction" is the act of anticipating future events or trends based on past data and patterns.

[0677] "Escalation" is the process of transferring a problem to a person or organization with higher authority or expertise when the problem cannot be resolved automatically.

[0678] This invention is a system that utilizes natural language processing to efficiently handle internal company inquiries. The server receives inquiries entered by users through terminals. The server incorporates natural language processing technology, such as using BERT or GPT as a generative AI model. This allows the server to analyze the intent of the user's inquiry and identify important keywords and context.

[0679] Based on the analyzed query, the server searches an internal database containing accumulated historical information. This database stores FAQs, reference materials, and past problem-solving examples for handling inquiries. From the retrieved information, the server generates the optimal response and sends it back to the user's terminal.

[0680] For example, if a user types "Please tell me the project report format" into their device, the server analyzes this and generates links and explanations of relevant formats to provide to the user. The server also analyzes past inquiry data and uses machine learning algorithms to predict issues such as the increase in payroll calculation problems at the end of the year, and proactively pushes guidelines to the user's device.

[0681] Furthermore, if the server receives a complex inquiry that cannot be resolved automatically, it will generate a notification to escalate the issue to the relevant expert or department. This feature facilitates the rapid resolution of problems.

[0682] An example of a prompt message could be a question like, "Please tell me about recent changes to employee benefits." This system can process such inquiries quickly and accurately, providing users with the necessary information in a timely manner.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The user enters their inquiry into the terminal using natural language. The entered information is received as digital data and sent to the server. This data is used as initial information to identify the user's request.

[0686] Step 2:

[0687] The server inputs the received query data into a generating AI model (e.g., BERT or GPT) and performs natural language processing. Through this process, the server analyzes the intent of the query and identifies important keywords and context. As output, structured data containing the intent of the query is generated.

[0688] Step 3:

[0689] The server searches the company's internal database based on the analysis results. Here, database queries are generated and executed to extract relevant information. The input is the analyzed intent data, and the output is a set of relevant documents and information retrieved from the database.

[0690] Step 4:

[0691] The server generates an appropriate response to the user using information retrieved from the database. Here, the response text is automatically generated based on the retrieved data. For example, it might include specific sentences and links such as, "The project report format is here."

[0692] Step 5:

[0693] The generated response is sent to the user via the terminal. The user can then view the response on the terminal and obtain information to resolve the problem. The output here is the response message from the server itself.

[0694] Step 6:

[0695] The server has the capability to analyze historical data and predict new queries. It uses machine learning algorithms to identify regularly occurring query patterns. In this procedure, the input is historical query data, and the output is potential future query scenarios.

[0696] Step 7:

[0697] If a potential inquiry is anticipated in the future, the server will notify the user's terminal of proactive measures. The notification will include guidance and procedures to reduce the workload for employees. The output here is a push notification message.

[0698] Step 8:

[0699] When the server receives an inquiry that cannot be resolved automatically, it generates an escalation notification to the relevant department or expert. This is a crucial process for quickly resolving problems. The input is data for an inquiry that is difficult to resolve, and the output is an escalation notification.

[0700] (Application Example 1)

[0701] 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".

[0702] Within factories, the time spent responding to inquiries and troubleshooting regarding the operation of machinery and equipment can lead to decreased productivity and errors. To solve this problem, a system is needed that can quickly and efficiently acquire information about machinery and equipment and implement appropriate countermeasures. Furthermore, it is crucial to anticipate and prevent recurring problems in advance.

[0703] 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.

[0704] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for generating optimal answers based on the analyzed inquiries, means for predicting the occurrence of problems by analyzing past data and providing information to users in advance, means for escalating inquiries that exceed the scope of what can be automatically handled to the relevant departments, and database search means for providing solutions to operation and troubles of machinery and equipment within the factory. This enables faster response times for inquiries and more efficient troubleshooting within the factory.

[0705] A "natural language processing model" refers to algorithms and frameworks that enable computers to understand and analyze human natural language.

[0706] "Inquiry analysis" is the process of identifying the intent and content of questions and requests submitted by users and classifying them into appropriate categories and procedures.

[0707] A "database search method" is a system function that quickly retrieves and presents necessary data from stored information.

[0708] "Escalation" is the process of notifying the appropriate person or department of a problem when it exceeds the scope of what can be handled automatically, and requesting further action.

[0709] "Push notifications" are a technology that automatically sends information to a user's device to immediately inform the user.

[0710] "Machine learning" is a technology that learns patterns and rules from data and automatically makes predictions and decisions.

[0711] "Machinery and equipment within a factory" refers to equipment including various tools and automation systems used in the production process.

[0712] The system for carrying out this invention mainly consists of a server and a user's device (terminal).

[0713] The server first uses a natural language processing model to analyze the user's inquiry. Specifically, it uses a generative AI model to analyze the intent of the inquiry and extract the necessary information. This model is implemented using deep learning frameworks such as TensorFlow and PyTorch. Once the analysis is complete, the server searches the database for relevant information and generates the optimal answer.

[0714] Next, machine learning is used to analyze problem occurrence trends based on past data, and relevant information and solutions are provided to users in advance. Libraries such as scikit-learn are used for this prediction. For example, if there is a tendency for inquiries to increase at a specific time each year, guidelines will be sent to the device via push notification before that time.

[0715] Furthermore, for issues that the server cannot resolve automatically, it generates escalation notifications to the relevant departments or specialists. These notifications are sent using communication tools such as Slack or email.

[0716] The user's device is implemented as a web or mobile application, providing an interface for making inquiries. Users can enter prompts such as, "Please tell me how to troubleshoot this device." This allows for smoother factory operations and improved productivity.

[0717] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0718] Step 1:

[0719] The user enters their inquiry from the terminal. Specifically, this involves sending a prompt message to the interface, such as "Please tell me how to troubleshoot this device." The input data is natural language text.

[0720] Step 2:

[0721] The server sends the query received from the terminal to a natural language processing model. The generative AI model analyzes the intent of the query. The input is natural language text from the user, and the output is a data structure that shows the analyzed intent.

[0722] Step 3:

[0723] Based on the analyzed intent, the server searches the database for highly relevant information and generates the optimal response. Specifically, it executes SQL queries to extract the necessary data. The input is the data structure of the analysis result, and the output is the response data.

[0724] Step 4:

[0725] The server generates an answer and sends it back to the user's terminal. The terminal displays this information to the user. The output consists of solutions and steps for the user's inquiry.

[0726] Step 5:

[0727] The server runs a machine learning algorithm to predict problem patterns based on past query history and current analysis data. The input is past query data and current results, and the output is insights indicating periods and themes that require attention.

[0728] Step 6:

[0729] Based on specific times and conditions, push notifications containing preventative measures and guidelines are sent to the user's device. Specifically, this involves generating the notification content and sending it to the device. This helps reduce unnecessary inquiries.

[0730] Step 7:

[0731] If an inquiry cannot be automatically handled by the server, the server initiates an escalation process and notifies the appropriate department or expert with details. This process is carried out in real time via the notification system. The input is the unresolved inquiry, and the output is the action taken by the notified person.

[0732] 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.

[0733] This invention aims to further enhance internal inquiry systems and improve the user experience by combining natural language processing models and emotion engines. The system is capable of interpreting inquiries and recognizing emotions, enabling more nuanced and appropriate responses.

[0734] The server receives inquiries sent by users via their terminals in natural language and analyzes them using a natural language processing model. This analysis clarifies the user's intent and extracts foundational data to identify corresponding information and solutions.

[0735] Simultaneously, the server sends the inquiry text to the sentiment engine to recognize the user's emotional state. The sentiment engine infers the emotion from the user's word choice and style of expression, and adjusts the response based on the result. If the recognized emotion is urgent or negative, the server takes this into consideration and promptly escalates it to the relevant department.

[0736] The generated response is returned to the user's device, and the user attempts to solve the problem based on that response. Furthermore, the server uses predictive analytics to predict the likelihood of similar problems occurring based on past data, and provides proactive solutions and information via push notifications.

[0737] For example, if a user enters "I'm worried about the progress of the recent project," the server analyzes this inquiry, and if the emotion engine determines that it contains emotions such as anxiety or stress, it suggests that immediate action is needed. The server quickly escalates the issue to the appropriate person in charge and simultaneously provides the user with links to general progress reports and information on support contacts.

[0738] This system allows inquiries to be handled not merely as administrative tasks, but with a more human touch that takes into account the emotions of the employees. As a result, the speed and quality of responses across the entire company will improve, leading to better internal communication and increased operational efficiency.

[0739] The following describes the processing flow.

[0740] Step 1:

[0741] The user uses a device to input and submit an inquiry in natural language. The user's input includes information about the question and its context.

[0742] Step 2:

[0743] The terminal sends the entered query data to the server. This data includes the user's language input.

[0744] Step 3:

[0745] The server analyzes the received query using a natural language processing model. Here, the server understands the intent of the query and extracts the necessary information.

[0746] Step 4:

[0747] The server processes the query data using an emotion engine to determine the user's emotional state. The emotion engine analyzes emotions based on keywords and expressions in the text.

[0748] Step 5:

[0749] The server adjusts its responses based on the results of the emotion engine. In particular, it considers high-priority responses when the user indicates emotions such as anxiety or anger.

[0750] Step 6:

[0751] The server generates the optimal response based on the analysis results and sentiment assessment. This response may include specific details, relevant links, and additional support information.

[0752] Step 7:

[0753] The server sends the generated response back to the terminal. The user checks the response received through the terminal and uses it to help solve the problem.

[0754] Step 8:

[0755] The server analyzes past query history and prepares to push notifications to terminals with information and alerts regarding predicted problems. This allows for proactive measures to be taken.

[0756] Step 9:

[0757] If the server determines that an inquiry cannot be resolved automatically, it will immediately escalate it to the relevant department. In this case, if there is a high level of urgency in the sentiment assessment, it will be given particular priority.

[0758] Step 10:

[0759] By receiving feedback from users, the server accumulates data that helps improve its natural language processing model and sentiment engine. This information is used to improve the system's accuracy.

[0760] (Example 2)

[0761] 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".

[0762] Handling customer inquiries within a company can be challenging because it's difficult to accurately grasp the needs and feelings of users, leading to inconsistent service quality. Furthermore, when users repeatedly encounter similar problems, there's often a lack of anticipation and proactive measures. This can result in decreased customer satisfaction and inefficient use of internal resources.

[0763] 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.

[0764] In this invention, the server includes means for analyzing user inquiries using natural language processing technology to clarify the user's intent, means for recognizing emotions from the user's linguistic information and adjusting the response content accordingly, and means for generating an optimal response based on the analyzed inquiry and emotion information. This enables highly accurate responses to inquiries, improves user satisfaction by providing responses that take the user's emotions into consideration, and allows for efficient responses and proactive information provision by predicting the occurrence of problems based on past data.

[0765] "Natural language processing technology" refers to a set of technologies that enable computers to understand, generate, and manipulate human language.

[0766] "Means of clarifying user intent" refers to the process of identifying the information and actions that users are seeking based on their inquiries.

[0767] "Means of recognizing emotions" refers to technologies that determine a user's emotional state from their linguistic expressions.

[0768] "Means of adjusting response content" refers to the process of changing the information provided and the way responses are handled based on the detected emotions.

[0769] "Methods for analyzing past data" refer to techniques for analyzing accumulated inquiry information to predict future trends and problem occurrences.

[0770] "Escalation" refers to the process by which a server forwards inquiries that cannot be handled automatically to the appropriate person or department.

[0771] "Push notifications" are a technology that allows a service provider to proactively send information to a device.

[0772] The embodiments for carrying out this invention are as follows.

[0773] Hardware and software configuration

[0774] This system consists of two main components: a server and terminals. The server is a central control unit equipped with a powerful processor and a large amount of memory, performing large-scale data processing and storage. Terminals are devices that users directly interact with, and can take the form of PCs, smartphones, tablets, etc.

[0775] Software Module

[0776] The server will be equipped with software modules for implementing natural language processing technology. Specifically, OpenAI's GPT series or other domain-specific AI models could be used as natural language processing models. For emotion recognition, a commonly used natural language analysis tool would be employed as an emotion engine. Here, open-source emotion analysis libraries can be used.

[0777] Data processing and data calculation

[0778] The server receives information sent by the user from the terminal and analyzes it using a natural language processing model. The purpose of the analysis is to clarify the user's intentions and find relevant information and appropriate countermeasures. At the same time, an emotion engine estimates the user's emotions and communicates accordingly.

[0779] Specific example

[0780] If a user enters "I'm worried about the recent project's progress," the server analyzes the inquiry and determines that it detects emotions including anxiety and stress. Based on this, the server determines that immediate action is needed and escalates the issue to the appropriate person, while also providing the user with links to general progress reports and support contact information.

[0781] Example of a prompt

[0782] "Assess the user's emotions based on their language and suggest escalation actions as needed."

[0783] As described above, by precisely analyzing user inquiries and providing empathetic and considerate responses, companies can improve the speed and quality of their responses, leading to increased operational efficiency and improved internal communication.

[0784] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0785] Step 1:

[0786] The user enters their inquiry in text format from their terminal. This input may include specific questions or concerns, such as "I'm worried about the progress of the recent project." When the user presses the submit button, the entered text is sent to the server.

[0787] Step 2:

[0788] The server inputs the text data received from the terminal into a natural language processing model. Here, a generative AI model is used to analyze the text and clarify the user's intent. This process analyzes keywords and context in the text to identify the subject of the inquiry. For example, from the phrase "I'm worried about the progress," it is determined that information about the current project progress is needed.

[0789] Step 3:

[0790] The server inputs the analyzed text into an emotion recognition engine to estimate the user's emotions. The emotion engine detects emotions from the wording and expressions in the text, identifying emotions such as "anxiety" and "stress." The intensity and urgency of the emotion are also evaluated. For example, the word "worry" might be judged to represent a strong emotion.

[0791] Step 4:

[0792] The server determines the appropriate course of action based on the results of natural language processing and sentiment recognition, and escalates the issue as needed. Specifically, if the identified sentiment is negative and urgent, it sends an alert directly to the relevant department. It also generates links to general Q&A and progress reports.

[0793] Step 5:

[0794] The server uses a generative AI model to create specific responses. These responses are customized to reflect the analysis results and escalation status. For example, they might include phrases like, "We apologize for any inconvenience this may have caused. Please refer to this link for the current project progress."

[0795] Step 6:

[0796] The generated response is sent from the server to the user's device. The user can review the received response and attempt to resolve the problem based on the provided links and information.

[0797] (Application Example 2)

[0798] 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".

[0799] In modern electronic transactions, promptly and appropriately handling customer inquiries and complaints is essential for improving customer satisfaction. However, conventional systems are unable to analyze the emotional state of users and flexibly adjust responses based on that analysis, resulting in unnecessary escalations and inadequate responses. To solve this problem, a new approach is needed that utilizes natural language processing and sentiment analysis technologies to improve the user experience.

[0800] 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.

[0801] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for recognizing the user's emotional state using an emotion analysis engine and adjusting the response accordingly, and means for predicting the occurrence of problems by analyzing past data and providing information to the user in advance. This enables accurate and flexible responses to inquiries.

[0802] A "natural language processing model" is a technology that includes algorithms for interpreting user inquiries and accurately understanding their intent.

[0803] An "emotion analysis engine" is software that infers emotions from a user's language and expression style, and adjusts responses accordingly.

[0804] "Escalation" is the process of transferring inquiries that are beyond the scope of what can be handled to a more specialized department or person in charge.

[0805] "Push notifications" are a communication method that sends information to a user's device in real time to attract their attention.

[0806] "Predictive analytics" is a data processing technique that uses past inquiry patterns to predict future problems and provide preventative measures.

[0807] "Response adjustment" is the process of achieving more appropriate communication by adjusting the content of responses to match the emotional state of the user.

[0808] The system for implementing this invention first has a server receive a query from the user's terminal and analyze the query using a natural language processing (NLP) model. The NLP model used is the Hugging Face Transformers library, which performs a process to clarify the user's intent. Through this NLP process, the content of the query is identified and the information necessary for subsequent processing is extracted.

[0809] Next, the server uses an emotion analysis engine to identify the user's emotions from the query. This emotion analysis uses a pre-trained model such as 'j-hartmann / emotion-english-distilroberta-base' to estimate emotions from the user's word choice and expression style. Based on this analysis, the response is adjusted to enable a more human-like response that matches the user's emotional state.

[0810] Furthermore, the server performs predictive analysis based on historical data to generate proactive measures to prevent similar problems from recurring. This involves using machine learning algorithms to predict problem patterns from large datasets.

[0811] If necessary, the server will immediately escalate the inquiry to the relevant department based on the content of the inquiry and the results of sentiment analysis. Then, it will send information and solutions based on sentiment to the user's device as a push notification.

[0812] For example, if a user inquires that they are worried because their recent payments have been delayed, the server will analyze this inquiry using NLP and an emotion analysis engine and recognize the emotion of "anxiety." Based on this result, the issue will be quickly escalated to the relevant department, and the user can be promptly informed of the progress and solutions to alleviate their anxiety.

[0813] An example of a prompt would be: "Analyze the sentiment of the following sentence and identify the primary sentiment: I am worried because my recent payment has been delayed." This entire process can improve the user experience.

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] The user's device inputs a query and sends it to the server. The server receives the query and inputs it as natural language text data. This data serves as the basis for subsequent processing.

[0817] Step 2:

[0818] The server uses a natural language processing (NLP) model to analyze the query text. Based on the input text data, the NLP model processes the data to identify the user's intent, extracting the purpose of the query and important information to obtain output. Specifically, the Hugging Face Transformers library is used to clarify the content of the query.

[0819] Step 3:

[0820] The server uses an emotion analysis engine to identify emotions from the analyzed query text. Using the extracted text information as input, the emotion engine performs data calculations to identify the emotional state (e.g., "anxiety," "satisfaction"). Based on this output, subsequent response adjustments are made.

[0821] Step 4:

[0822] The server generates the optimal response to a query based on the analyzed intent and emotional state. It uses the output of natural language processing models and sentiment analysis as input data. Response generation is based on pre-determined response templates and document generation techniques. It generates specific answers and prepares them to be sent to the user.

[0823] Step 5:

[0824] Based on the analysis results, the server escalates inquiries to the relevant departments if necessary. Inquiries exceeding the urgency or scope of the system are used as input, and the escalation process is automatically initiated. This output facilitates rapid problem resolution.

[0825] Step 6:

[0826] The server performs predictive analytics, analyzing historical data to forecast the occurrence of problems. The input consists of historical query data and its pattern analysis. Machine learning algorithms are applied to generate output that preemptively addresses potential failures and problems.

[0827] Step 7:

[0828] The server sends the generated solution information as a push notification to the user's device along with the final response. The output information is used to alleviate the user's anxiety and guide them through the necessary procedures. Specifically, it provides progress and solutions regarding the inquiry.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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."

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] The following is further disclosed regarding the embodiments described above.

[0851] (Claim 1)

[0852] A method for analyzing user inquiries using a natural language processing model,

[0853] A means for generating the optimal answer based on the analyzed query,

[0854] A means of predicting the occurrence of problems by analyzing past data and providing information to users in advance,

[0855] A means of escalating inquiries that exceed the scope of what can be handled automatically to the relevant departments,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, which analyzes past inquiry data using machine learning to predict recurring problems from users.

[0859] (Claim 3)

[0860] The system according to claim 1, which sends a push notification to the user's device to notify them of a solution to the problem in advance.

[0861] "Example 1"

[0862] (Claim 1)

[0863] A means of analyzing information requests from users using natural language processing technology,

[0864] Means for generating an appropriate response based on the analyzed information request,

[0865] A means of predicting the occurrence of problems by analyzing historical information and providing information to users in advance,

[0866] A means of forwarding information requests that exceed the scope of what can be handled automatically to the relevant departments,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, which analyzes historical information using machine learning to predict recurring problems from users.

[0870] (Claim 3)

[0871] The system according to claim 1, which communicates a notification to the user's device and notifies the user of a solution to the problem in advance.

[0872] "Application Example 1"

[0873] (Claim 1)

[0874] A method for analyzing user inquiries using a natural language processing model,

[0875] A means for generating the optimal answer based on the analyzed query,

[0876] A means of predicting the occurrence of problems by analyzing past data and providing information to users in advance,

[0877] A means of escalating inquiries that exceed the scope of what can be handled automatically to the relevant departments,

[0878] A database search method for providing solutions to problems and issues related to the operation of machinery and equipment within a factory,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, which analyzes past inquiry data using machine learning to predict recurring problems from users.

[0882] (Claim 3)

[0883] The system according to claim 1, which sends a push notification to the user's device to notify them of a solution to the problem in advance.

[0884] "Example 2 of combining an emotion engine"

[0885] (Claim 1)

[0886] A means of analyzing user inquiries using natural language processing technology to clarify the user's intent,

[0887] A means of recognizing emotions from the user's linguistic information and adjusting the response content based on that,

[0888] A means for generating the optimal response based on analyzed queries and sentiment information,

[0889] A means of analyzing past data to predict the occurrence of similar problems and providing solutions to users in advance,

[0890] A means of escalating inquiries that are deemed difficult to handle automatically to the relevant department,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, which analyzes past inquiry data using machine learning technology and predicts recurring problems from user inquiries.

[0894] (Claim 3)

[0895] The system according to claim 1, which sends push notifications to the user's device and provides proactive solutions to potential problems.

[0896] "Application example 2 when combining with an emotional engine"

[0897] (Claim 1)

[0898] A method for analyzing user inquiries using a natural language processing model,

[0899] A means for generating the optimal answer based on the analyzed query,

[0900] A means of predicting the occurrence of problems by analyzing past data and providing information to users in advance,

[0901] A means of escalating inquiries that exceed the scope of what can be handled automatically to the relevant departments,

[0902] A means for recognizing the user's emotional state using an emotion analysis engine and adjusting the response accordingly,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, which analyzes past inquiry data using machine learning to predict recurring problems from users.

[0906] (Claim 3)

[0907] The system according to claim 1, which sends a push notification to the user's device and notifies the user of response information based on sentiment analysis. [Explanation of symbols]

[0908] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method for analyzing user inquiries using a natural language processing model, A means for generating the optimal answer based on the analyzed query, A means of predicting the occurrence of problems by analyzing past data and providing information to users in advance, A means of escalating inquiries that exceed the scope of what can be handled automatically to the relevant departments, A system that includes this.

2. The system according to claim 1, which analyzes past inquiry data using machine learning to predict recurring problems from users.

3. The system according to claim 1, which sends a push notification to the user's device to notify them of a solution to the problem in advance.

Images