system

Abstract

We provide the system. [Solution] A language processing means for analyzing requests in natural language based on accumulated information and generating related data, A means for escalating requests to the relevant department or individual based on the requests analyzed by the language processing means, An analytical tool that analyzes past request data to predict future problems and notifies users of necessary information in advance, A means for analyzing inquiries related to electronic transactions entered by users in natural language from communication devices and for presenting relevant information in real time, A computing device that includes a function to predict recurring inquiries and automatically notify them in advance, 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 and includes 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 in-house inquiry operations are distributed among multiple windows, employees often get confused about which window to inquire. Also, the inquiry response takes time and it is laborious to search for information, resulting in a decline in work efficiency. Due to the repetition of similar inquiries, the operation side also spends a lot of man-hours. These problems have led to a decline in work efficiency and dissatisfaction among employees.

Means for Solving the Problems

[0005] This invention provides a system that uses natural language processing technology based on internal company data to analyze employee inquiries and automatically generate optimal answers. By analyzing past inquiry data, predicting future problems, and providing proactive push notifications of necessary information, the system prevents problems from arising. Furthermore, it enables efficient inquiry handling by escalating inquiries to the appropriate departments and personnel based on their content. This allows employees to quickly obtain necessary information, leading to improved work efficiency and increased employee satisfaction.

[0006] "Natural language processing methods" refer to technical techniques that enable computers to understand and analyze the meaning of human input in natural language.

[0007] "Escalation mechanisms" refer to the function of implementing a process to transfer unresolved issues or inquiries to the appropriate department or person in charge.

[0008] "Predictive analytics" refers to analytical methods that use past data to predict future events and problems, and to provide countermeasures and information in advance.

[0009] A "server" refers to a computer system that provides data and services to clients over a network.

[0010] "Employee" refers to a person who belongs to a company or organization and performs duties.

[0011] An "inquiry" refers to a question or request made to obtain specific information or support. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]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.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

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

[0015] 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.

[0016] 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.

[0017] 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, etc.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

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

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0027] 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.

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

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention relates to a system for streamlining internal inquiry handling within a company. This system is server-centric and provides a series of processes for handling inquiries made by employees via terminals.

[0034] The server collects pre-stored internal company information and implements a model using natural language processing technology. This model has the ability to analyze natural language inquiries entered by employees and generate appropriate responses based on their content. The server quickly processes inquiries received through terminals, accesses necessary internal company information, and generates the optimal response.

[0035] The terminal provides an interface where employees can input inquiries in natural language. For example, they might type questions about payslips or leave application procedures into a chat window. The server receives these inquiries, analyzes the context, gathers relevant information from the company's internal database, generates an answer, and returns it to the user.

[0036] Furthermore, the server uses predictive analytics to analyze past inquiry data and identify recurring problems. Based on this information, it can predict future problems and provide employees with solutions and necessary information in advance via push notifications. For example, by notifying employees in advance about "how to apply for leave," a question that frequently arises at the end of the fiscal year, the burden of inquiries can be reduced.

[0037] Furthermore, the server includes escalation mechanisms, and inquiries that the system cannot resolve automatically are escalated to the appropriate department or personnel. For example, if a technical problem is reported, it is forwarded directly to the IT support team. This process enables quick and efficient problem resolution.

[0038] This system allows employees to quickly obtain the information they need, improving the efficiency of inquiry handling and increasing employee satisfaction.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user enters their inquiry in natural language via their device. Specifically, they type a question such as "How do I check my payslip?" into the chat window on their device.

[0042] Step 2:

[0043] The server receives the inquiry sent from the terminal. The received text is analyzed using natural language processing technology to extract the intent of the inquiry and keywords. For example, "payslip" and "how to check" are extracted as the main keywords.

[0044] Step 3:

[0045] The server searches its internal database based on the keywords it extracts and collects relevant information. For example, the server accesses the human resources information system and retrieves information such as "payslip verification procedure."

[0046] Step 4:

[0047] Based on the information acquired by the server, the system generates the most appropriate response to the inquiry. For example, it might construct a response such as, "You can check your payslip on the intranet's 'My Page'."

[0048] Step 5:

[0049] The server sends the generated response to the user's device. The user can then view the response returned by the server in the chat window on their device.

[0050] Step 6:

[0051] The server analyzes past inquiry data to predict recurring issues. Based on these predictions, the server provides users with necessary information in advance via push notifications. For example, it might send a notification stating, "Working hours are scheduled to change next month."

[0052] Step 7:

[0053] If the server detects an inquiry it cannot resolve, it will escalate it to the appropriate department or personnel. Specifically, inquiries such as "A system error has occurred" are automatically forwarded to the IT support team.

[0054] This series of steps allows users to receive answers smoothly and enables efficient management of inquiries.

[0055] (Example 1)

[0056] 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."

[0057] In today's business environment, it is crucial to provide timely and accurate information to employees in response to the diverse inquiries they face in their daily work. However, many companies spend a significant amount of time and resources on handling inquiries, and the lack of efficient systems hinders business operations. This invention aims to improve employee satisfaction by streamlining employee inquiry handling and accelerating information provision.

[0058] 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.

[0059] In this invention, the server includes a natural language processing means that analyzes natural language queries based on accumulated information and generates relevant information based on that analysis; an escalation means that routes queries to the relevant department or person in charge based on the queries analyzed by the natural language processing means; and a predictive analysis means that analyzes past query data to predict future problems and notifies the user of necessary information in advance. This enables efficient responses to diverse inquiries from employees, facilitating smooth business operations and continuous business improvement.

[0060] "Accumulated information" refers to historical records and knowledge stored within a company or related databases, and is a collection of data used for future reference and analysis.

[0061] "Natural language processing" is a technology used by computers to understand, generate, and interact with human language. It is a means of accurately analyzing the content of inquiries and generating appropriate responses.

[0062] "Escalation" is the process of routing inquiries that require action and cannot be automatically resolved by the system to the appropriate person or department, and is a means of supporting efficient problem solving.

[0063] "Predictive analytics" is a technology that analyzes data accumulated in the past, uses the patterns derived from that data to predict future events and problems, and takes proactive measures.

[0064] "Answer generation" refers to the process of creating specific and easy-to-understand answers for users based on the analyzed inquiry content.

[0065] "Information gathering" is the process of obtaining necessary information from databases and other sources and using that information to help answer inquiries.

[0066] This invention is a system for efficiently handling customer inquiries for businesses. The system mainly consists of a server and terminals.

[0067] The server processes queries using the following technologies:

[0068] The system utilizes Python and the Tensorflow® library as natural language processing technologies. The generative AI model is used to analyze employee inquiries and accurately understand their intent. Specifically, it focuses on analyzing question intent and extracting keywords.

[0069] The server uses database management systems such as MySQL® or MongoDB to collect information based on the analysis results. This allows it to quickly retrieve the necessary relevant information and generate answers to queries.

[0070] For predictive analytics, we use the Pandas and Scikit-learn libraries to analyze past query data and predict future problem occurrences.

[0071] Data collected from the frontend is sent to the server via a web service using Flask, enabling bidirectional data communication.

[0072] The terminal provides a user interface for employees to make inquiries.

[0073] The frontend is built using React.js, allowing employees to input inquiries in natural language. In particular, input from terminals is done via a chat window.

[0074] For example, if a question such as "How do I check my payslip?" is entered into the chat window, it is sent to the server and processing begins.

[0075] Users can quickly obtain information through this system.

[0076] Employees can obtain the necessary information at any time through automated responses from the server.

[0077] If a problem cannot be resolved through automated responses, the inquiry will be forwarded to the appropriate person through an escalation mechanism, ensuring a swift resolution.

[0078] For example, if an employee types "Please tell me the procedure for applying for leave next year" at the end of the fiscal year, the server will retrieve relevant information from the database and respond with the appropriate procedure in the chat window. Furthermore, prompts such as "Create a notice regarding leave applications for employees as the fiscal year ends next week" can be input into the AI ​​model to provide advance notice.

[0079] In this way, the system of the present invention improves operational efficiency and accelerates information provision, thereby providing value to corporate operations.

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

[0081] Step 1:

[0082] Users enter their inquiries using their devices. Specifically, when a user types "How do I get my payslip?" into the chat window, this inquiry is sent to the server as an HTTP request. The input data is in natural language text format.

[0083] Step 2:

[0084] The server analyzes natural language text, which is the query received from the terminal. Using a generative AI model powered by TensorFlow, the server understands the content of the query and identifies its intent. The model tokenizes the text and uses a neural network to classify the intent. The output is the identified intent and associated keywords.

[0085] Step 3:

[0086] The server sends a query to the internal database based on the analysis results. It uses a database management system (MySQL or MongoDB) to retrieve information related to the query. Specifically, it queries the database for procedural information regarding "payslips" and retrieves the relevant records. The output is a collection of related information.

[0087] Step 4:

[0088] The server generates a natural language response based on the acquired information. It uses the Pandas library to format the data and create the response text. Furthermore, it uses a generative AI model to produce fluent, contextually relevant output. The output is a complete response sentence to be presented to the user.

[0089] Step 5:

[0090] The server sends the generated response to the terminal. The response is sent as JSON data in an HTTP response. The terminal receives this data and parses it to display it in the user's chat window. The displayed output is a clear answer to the user's inquiry.

[0091] Step 6:

[0092] The server escalates inquiries if the content follows past patterns or if data is insufficient. Predictive analytics are used to detect recurring inquiry problems and route them to the appropriate personnel. The output is an escalation message to the responsible person or department.

[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] In modern electronic transactions, diverse user inquiries and troubleshooting occur frequently, requiring service providers to respond quickly and accurately. However, traditional systems suffered from time-consuming response times and increased costs due to the prevalence of manual handling. Furthermore, insufficient preventative measures against recurring inquiries made it difficult to maintain user satisfaction.

[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 language processing means for analyzing requests in natural language based on accumulated information and generating relevant data; analysis means for analyzing past request data to predict future problems and notifying necessary information in advance; and means for analyzing inquiries related to electronic transactions entered by users in natural language from communication devices and presenting relevant information in real time. This enables a rapid and accurate response to user inquiries, resulting in cost-effective service provision. Furthermore, by predicting recurring inquiries and automatically notifying users in advance, improved user satisfaction can be expected.

[0098] "Accumulated information" refers to databases and records stored in the past, and is the information that a system uses to generate appropriate responses to inquiries and requests.

[0099] "Requests in natural language" refer to inquiries and requests made using the language that humans normally use, and computer systems are required to understand and analyze this language.

[0100] "Language processing means" refers to technologies and methods for analyzing natural language and converting it into a format that a computer can understand.

[0101] "Analytical methods" refer to methods and techniques for predicting future patterns and problems based on past data.

[0102] "Communication equipment" refers to terminals that possess the technology to send and receive information through a connection, and includes smartphones and computers.

[0103] "Presenting in real time" means providing relevant information immediately and without delay in response to user requests and inquiries.

[0104] "Automatic notification" refers to the system automatically sending pre-configured information to the user based on predictions and analysis.

[0105] To implement this invention, a system comprising the following components is used. The server analyzes natural language queries input by the user through language processing means. Depending on the content of the query, it retrieves appropriate information from the database and provides the user with an answer in real time. Natural language processing libraries such as TensorFlow and spaCy are used for this purpose.

[0106] Furthermore, the server uses analytical tools to analyze past query data. This allows it to predict future problems and automatically notify users in advance. A specific example of such notification is that the system can proactively inform users of solutions for certain queries that increase during the end of the year.

[0107] The device provides an interface for users to enter inquiries. This is a smartphone application developed using React Native, allowing users to easily submit inquiries in natural language. The entered information is transferred to the server and processed quickly.

[0108] The entire system is intended to communicate via APIs and function efficiently to improve the user experience. Below is an example of input to the generative AI model.

[0109] Example of a prompt:

[0110] User inquiry: "I want to change my payment method."

[0111] Information provided by the system: "Please log in to your account, select 'Settings' and then 'Payment Methods', and register a new payment method."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The terminal receives queries entered by the user in natural language. When the user enters a question into the application interface, the terminal prepares to send the content to the server. At this point, the input is the user's natural language input, and the output is the data sent directly to the server.

[0115] Step 2:

[0116] The server analyzes the user's query using natural language processing tools. The input is natural language text, and semantic analysis and keyword extraction are performed using natural language processing techniques (e.g., TensorFlow or spaCy). The output is structured data that reflects the intent of the query.

[0117] Step 3:

[0118] Based on the analysis results, the server retrieves relevant information from the company's internal database. The input is the structured data obtained in the previous step, and an SQL query is generated based on it and sent to the database. As output, the server prepares information related to the user's inquiry.

[0119] Step 4:

[0120] The server generates a response to the user based on the acquired information. The input is raw data retrieved from a database, and a generative AI model is used to form a response in natural language. The output is formatted text for the user to respond to.

[0121] Step 5:

[0122] The server sends the generated response back to the terminal. At this point, the input is the generated text, and the output is displayed on the terminal in a format that the user can read. The terminal then displays this information on the user's screen.

[0123] Step 6:

[0124] The server records the query content and its results in a database. The input is the entire query process information, stored in the database, and used for future predictive analytics. This allows for the detection of recurring query patterns and the accumulation of foundational data for proactive notification as prompt messages.

[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 relates to a system that streamlines internal inquiry handling while utilizing user sentiment analysis to provide more effective responses. This system is server-centric and processes user inquiries using natural language processing capabilities that incorporate a sentiment engine.

[0127] The server collects pre-stored internal company information and uses a model that implements natural language processing technology. This model has the ability to analyze natural language queries entered by users via terminals and simultaneously grasp the content of those queries and the user's emotions. The server quickly processes the text received from the terminal and recognizes the user's emotions using an emotion engine. For example, if a user expresses dissatisfaction regarding their salary, the server can detect feelings of frustration and dissatisfaction.

[0128] The emotion engine extracts emotional information from the user's text and uses that information to adjust the feedback and escalation methods provided by the server. The server then presents a response to the terminal that is appropriate to the user's emotions. Specifically, if the emotion engine detects "dissatisfaction," the server will take steps to improve user satisfaction, such as including a follow-up suggestion like, "Please contact HR if you need further explanation."

[0129] Furthermore, the server uses predictive analytics to analyze past inquiry data and user sentiment information to predict potential problems in the future. Based on these predictions, it can proactively provide users with appropriate information and solutions via push notifications. For example, it can proactively alert all employees based on the timing when a particular sentiment pattern is detected frequently.

[0130] Furthermore, for issues that are difficult to resolve, the server automatically uses escalation mechanisms to forward inquiries to the appropriate department or person based on the emotional analysis results. For example, if the emotional engine detects the emotion of "anger," it can quickly forward the inquiry to the customer support team.

[0131] This system allows employees to receive prompt and appropriate information that is sensitive to their feelings, streamlines inquiry handling, and is expected to further improve employee satisfaction.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user enters their inquiry in natural language using their device. The user enters their question or request as specific text in the chat window.

[0135] Step 2:

[0136] The server analyzes the query received from the terminal. The server uses natural language processing techniques to extract the query's intent and key keywords.

[0137] Step 3:

[0138] The server uses an emotion engine to analyze the text extracted from the inquiry and determine the user's emotional state. For example, the emotion engine can recognize emotions such as "dissatisfaction" or "frustration" from the input text.

[0139] Step 4:

[0140] The server searches its internal database for information related to the query and generates the optimal response. The response is constructed to include adjustments based on the user's emotional state.

[0141] Step 5:

[0142] The server generates a response, sends it to the terminal, and provides it to the user. By showing the user explanations that include emotional considerations and follow-up suggestions, a highly satisfactory response is achieved.

[0143] Step 6:

[0144] The server analyzes past query history and sentiment data to predict future issues and trends. If a specific sentiment pattern is increasing, it prepares to send a pre-notification.

[0145] Step 7:

[0146] The server automatically escalates inquiries it cannot resolve to the appropriate department or person. It considers the results of the sentiment engine to ensure quick and appropriate escalation.

[0147] This process makes customer inquiries more effective and personal, improving the employee experience.

[0148] (Example 2)

[0149] 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".

[0150] Conventional inquiry processing systems were inadequate in responding to user inquiries and failed to provide effective feedback that took emotions into consideration. Furthermore, the lack of means to predict future problems and take appropriate preventative measures made it difficult to provide a highly satisfactory service.

[0151] 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.

[0152] In this invention, the server includes language processing means for analyzing inquiries based on stored information sources and generating relevant information, sentiment analysis means for simultaneously analyzing the inquiry content and sentiment analyzed by the language processing means to generate optimal feedback, and escalation means for forwarding inquiries to the relevant department or person in charge based on the analyzed inquiry. This enables the provision of sentiment-sensitive responses and problem-solving based on predictions.

[0153] A "language processing means" is a means of analyzing queries in natural language form from accumulated information and generating related information.

[0154] "Emotional analysis means" refers to a method for simultaneously analyzing the user's emotions from the analyzed inquiry content and providing optimal feedback.

[0155] An "escalation mechanism" is a means of forwarding an inquiry to the appropriate department or person based on the analyzed inquiry.

[0156] A "predictive provision method" is a means of using past data to predict future problems and providing necessary information in advance.

[0157] This invention provides a system to streamline internal inquiry handling and analyze user emotions to provide more effective responses. The system is server-centric and built using natural language processing technology to enable emotion analysis.

[0158] The server collects accumulated information from a database and uses a natural language processing (NLP) engine to analyze queries based on this information. This NLP engine has text analysis skills and extracts the content of the query and important keywords. The analyzed information is then sent to an emotion engine, which is used to identify the user's sentiment.

[0159] The server generates feedback tailored to the user's emotions based on emotional information extracted by the emotion engine, and provides it to the user via the terminal. This process is rapid, taking into account both the user's inquiry and their emotions to enable appropriate feedback. For example, if a user expresses dissatisfaction about a delayed salary payment, the server will generate feedback such as, "We apologize for the inconvenience. Please contact Human Resources for further details."

[0160] Furthermore, the server can use predictive means to analyze past inquiry data and sentiment data to predict future problems and notify users of countermeasures in advance. This prediction allows for early warnings to all employees if a large number of sentiment patterns are detected at a particular time.

[0161] The system also incorporates escalation mechanisms, ensuring that complex issues or inquiries expressing strong emotions such as anger are promptly forwarded to the appropriate department or person in charge. This design allows users to receive timely and accurate information while being sensitive to their emotions, resulting in more efficient inquiry handling and improved employee satisfaction.

[0162] An example of a prompt might be: "Generate a prompt that analyzes the user's inquiry, analyzes their sentiment, and generates appropriate feedback. For example, if the user is expressing dissatisfaction with their salary, indicate what kind of feedback would be appropriate."

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server receives the user's query text from the terminal. The input is the natural language query entered by the user using the terminal, and the output is the received text data. This text data is then prepared for the next parsing step.

[0166] Step 2:

[0167] The server activates a natural language processing (NLP) engine to analyze the query text. The input is the text data received in step 1, and the output is data containing keywords and main themes extracted from the query. Specifically, the NLP engine analyzes the linguistic structure of the text and identifies important words such as "salary" and "payment delay."

[0168] Step 3:

[0169] The server uses an emotion engine to perform sentiment analysis on the query text. The input is analysis data from an NLP engine, and the output is a label or indicator representing the user's emotion (e.g., "dissatisfied," "frustrated"). Specifically, it scrutinizes the textual expression and implements an algorithm to identify the user's emotional state.

[0170] Step 4:

[0171] The server generates feedback based on extracted keywords and sentiment data. The input is the output data from steps 2 and 3, and the output is the response message provided to the user. The generated feedback includes language that is sensitive to the user's feelings, and a message such as "We apologize for the inconvenience. Please contact Human Resources if you would like more information" is created.

[0172] Step 5:

[0173] The server automatically forwards inquiries requiring escalation to the appropriate department or person in charge. The input is data indicating emotions such as "anger" or other strong emotions, and the output is the escalated inquiry information. Specifically, the system immediately sends the information to the appropriate department's contact based on the emotion assessment.

[0174] Step 6:

[0175] The server analyzes past query data to make future predictions. The input is historical query data, and the output is a list of predicted problems and their solutions. This allows for proactive notifications to be sent to employees when specific emotional patterns are frequently detected.

[0176] (Application Example 2)

[0177] 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".

[0178] In modern organizations, there is a demand for prompt and appropriate handling of customer inquiries and complaints. However, traditional systems often have limitations, such as their mechanical nature and insufficient empathy for the customer's feelings. Furthermore, balancing problem prediction using historical data with human-centered responses is difficult, hindering improvements in customer satisfaction. There is a need to overcome these challenges and achieve a higher level of customer service.

[0179] 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.

[0180] In this invention, the server includes a natural language analysis means that analyzes natural language queries based on accumulated internal organizational information, a predictive analysis means that analyzes past query records to predict future problems, and an emotional analysis means that analyzes the user's emotional information and reflects it in the response. This enables more appropriate and prompt responses that are attentive to the customer's emotions.

[0181] "Natural language processing" refers to a technology that analyzes natural language queries based on accumulated internal organizational information and understands their content.

[0182] An "escalation mechanism" is a function that, based on an analyzed inquiry, quickly transfers information to the appropriate department or person in charge to facilitate a response.

[0183] "Predictive analysis means" refers to technology that predicts potential problems that may occur in the future based on past inquiry records and provides necessary advance notice.

[0184] An "emotional analysis tool" is a means of analyzing a user's inquiry to understand their emotional state and reflecting that information in the response.

[0185] A "response optimization system" is a system that improves customer service by detecting a specific emotional state and generating a response appropriate to that state.

[0186] "Speech processing means" refers to technology that processes speech input in real time and converts speech into text.

[0187] An "emotion estimation method" is a system that analyzes a user's biometric information and calculates the optimal response to improve customer satisfaction.

[0188] The system for realizing this invention consists of a server and user terminals. The server implements natural language processing technology that performs natural language analysis based on accumulated internal organizational information. Specifically, it deploys a natural language analysis means that analyzes inquiry content using the Transformer technology of the natural language processing library Hugging Face. The analyzed content is promptly addressed through an escalation means that routes it to the relevant department or person in charge.

[0189] Furthermore, the server is equipped with predictive analytics means to predict future problems based on past query records. This makes it possible to predict potential future problems in advance and notify relevant parties beforehand. In addition, an emotional analysis means is implemented to capture user emotional information and reflect that information in the response. For example, if dissatisfaction is detected from a user's query, that information is used to provide appropriate follow-up through the response optimization means.

[0190] The device implements a speech processing mechanism that processes voice input in real time and converts it to text using Google® Cloud Speech-to-Text API and other technologies. To more accurately understand the user's emotions, an emotion estimation mechanism works in conjunction with the server to estimate the user's emotions from text and biometric information. This information is analyzed by a generative AI model and used as prompt text.

[0191] As a concrete example, by generating a prompt message such as, "The customer appears to be having trouble because their product hasn't arrived. Please respond kindly and propose a concrete solution," the optimal response can be constructed. This allows for a response that better matches the user's needs, contributing to an overall improvement in customer satisfaction.

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The user provides voice input through the device. The device uses the Google Cloud Speech-to-Text API to convert the speech to text. In this step, the voice data is input and the text data is output. This text data serves as the basis for subsequent processing.

[0195] Step 2:

[0196] The server receives text data sent from the terminal. Next, to perform natural language processing, it uses the Hugging Face Transformer model to analyze the query and extract the necessary information. The input for this step is text data from the terminal, and the output is the analyzed query. Here, the linguistic patterns of the text data are analyzed and key information is extracted.

[0197] Step 3:

[0198] The server uses emotion analysis tools to estimate the user's emotional state from the analyzed text. This process involves applying a data model for understanding emotions and analyzing emotional patterns. The input to this step is the analyzed query, and the output is the estimated emotional state. Specifically, this step estimates emotions by measuring emotional patterns using emotion indicators within the text.

[0199] Step 4:

[0200] The server generates an appropriate response through response optimization means based on the estimated emotional state. It utilizes a generative AI model to output the most appropriate response based on the prompt. In this step, the estimated emotional state is the input, and the output is the optimized response. The generative AI model is used to select the best response from multiple candidates, preparing a response that meets the user's needs.

[0201] Step 5:

[0202] The server uses escalation mechanisms to notify the appropriate department or person in charge, depending on the situation. This facilitates coordination to ensure that any necessary additional actions are taken. The inputs to this step are estimated emotional states and responses, and the outputs are the information required for escalation. When a situation requiring escalation is identified, a rapid response procedure is triggered.

[0203] Step 6:

[0204] Finally, the server-generated response is sent to the terminal and presented to the user. This allows the user to obtain answers to their questions and problems. In this step, the input is the optimized response, and the output is the information presented to the user. To enhance user satisfaction, clear and helpful information is provided at the appropriate time.

[0205] 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.

[0206] Data generation model 58 is a type of 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.

[0207] 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.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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".

[0221] This invention relates to a system for streamlining internal inquiry handling within a company. This system is server-centric and provides a series of processes for handling inquiries made by employees via terminals.

[0222] The server collects pre-stored internal company information and implements a model using natural language processing technology. This model has the ability to analyze natural language inquiries entered by employees and generate appropriate responses based on their content. The server quickly processes inquiries received through terminals, accesses necessary internal company information, and generates the optimal response.

[0223] The terminal provides an interface where employees can input inquiries in natural language. For example, they might type questions about payslips or leave application procedures into a chat window. The server receives these inquiries, analyzes the context, gathers relevant information from the company's internal database, generates an answer, and returns it to the user.

[0224] Furthermore, the server uses predictive analytics to analyze past inquiry data and identify recurring problems. Based on this information, it can predict future problems and provide employees with solutions and necessary information in advance via push notifications. For example, by notifying employees in advance about "how to apply for leave," a question that frequently arises at the end of the fiscal year, the burden of inquiries can be reduced.

[0225] Furthermore, the server includes escalation mechanisms, and inquiries that the system cannot resolve automatically are escalated to the appropriate department or personnel. For example, if a technical problem is reported, it is forwarded directly to the IT support team. This process enables quick and efficient problem resolution.

[0226] This system allows employees to quickly obtain the information they need, improving the efficiency of inquiry handling and increasing employee satisfaction.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The user enters their inquiry in natural language via their device. Specifically, they type a question such as "How do I check my payslip?" into the chat window on their device.

[0230] Step 2:

[0231] The server receives the inquiry sent from the terminal. The received text is analyzed using natural language processing technology to extract the intent of the inquiry and keywords. For example, "payslip" and "how to check" are extracted as the main keywords.

[0232] Step 3:

[0233] The server searches its internal database based on the keywords it extracts and collects relevant information. For example, the server accesses the human resources information system and retrieves information such as "payslip verification procedure."

[0234] Step 4:

[0235] Based on the information acquired by the server, the system generates the most appropriate response to the inquiry. For example, it might construct a response such as, "You can check your payslip on the intranet's 'My Page'."

[0236] Step 5:

[0237] The server sends the generated response to the user's device. The user can then view the response returned by the server in the chat window on their device.

[0238] Step 6:

[0239] The server analyzes past inquiry data to predict recurring issues. Based on these predictions, the server provides users with necessary information in advance via push notifications. For example, it might send a notification stating, "Working hours are scheduled to change next month."

[0240] Step 7:

[0241] If the server detects an inquiry it cannot resolve, it will escalate it to the appropriate department or personnel. Specifically, inquiries such as "A system error has occurred" are automatically forwarded to the IT support team.

[0242] This series of steps allows users to receive answers smoothly and enables efficient management of inquiries.

[0243] (Example 1)

[0244] 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."

[0245] In today's business environment, it is crucial to provide timely and accurate information to employees in response to the diverse inquiries they face in their daily work. However, many companies spend a significant amount of time and resources on handling inquiries, and the lack of efficient systems hinders business operations. This invention aims to improve employee satisfaction by streamlining employee inquiry handling and accelerating information provision.

[0246] 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.

[0247] In this invention, the server includes a natural language processing means that analyzes natural language queries based on accumulated information and generates relevant information based on that analysis; an escalation means that routes queries to the relevant department or person in charge based on the queries analyzed by the natural language processing means; and a predictive analysis means that analyzes past query data to predict future problems and notifies the user of necessary information in advance. This enables efficient responses to diverse inquiries from employees, facilitating smooth business operations and continuous business improvement.

[0248] "Accumulated information" refers to historical records and knowledge stored within a company or related databases, and is a collection of data used for future reference and analysis.

[0249] "Natural language processing" is a technology used by computers to understand, generate, and interact with human language. It is a means of accurately analyzing the content of inquiries and generating appropriate responses.

[0250] "Escalation" is the process of routing inquiries that require action and cannot be automatically resolved by the system to the appropriate person or department, and is a means of supporting efficient problem solving.

[0251] "Predictive analytics" is a technology that analyzes data accumulated in the past, uses the patterns derived from that data to predict future events and problems, and takes proactive measures.

[0252] "Answer generation" refers to the process of creating specific and easy-to-understand answers for users based on the analyzed inquiry content.

[0253] "Information gathering" is the process of obtaining necessary information from databases and other sources and using that information to help answer inquiries.

[0254] This invention is a system for efficiently handling customer inquiries for businesses. The system mainly consists of a server and terminals.

[0255] The server processes queries using the following technologies:

[0256] The system utilizes Python and TensorFlow libraries for natural language processing. The generative AI model is used to analyze employee inquiries and accurately understand their intent. Specifically, it focuses on analyzing question intent and extracting keywords.

[0257] The server uses database management systems such as MySQL or MongoDB to collect information based on the analysis results. This allows it to quickly retrieve the necessary relevant information and generate answers to queries.

[0258] For predictive analytics, we use the Pandas and Scikit-learn libraries to analyze past query data and predict future problem occurrences.

[0259] Data collected from the frontend is sent to the server via a web service using Flask, enabling bidirectional data communication.

[0260] The terminal provides a user interface for employees to make inquiries.

[0261] The frontend is built using React.js, allowing employees to input inquiries in natural language. In particular, input from terminals is done via a chat window.

[0262] For example, if a question such as "How do I check my payslip?" is entered into the chat window, it is sent to the server and processing begins.

[0263] Users can quickly obtain information through this system.

[0264] Employees can obtain the necessary information at any time through automated responses from the server.

[0265] If a problem cannot be resolved through automated responses, the inquiry will be forwarded to the appropriate person through an escalation mechanism, ensuring a swift resolution.

[0266] For example, if an employee types "Please tell me the procedure for applying for leave next year" at the end of the fiscal year, the server will retrieve relevant information from the database and respond with the appropriate procedure in the chat window. Furthermore, prompts such as "Create a notice regarding leave applications for employees as the fiscal year ends next week" can be input into the AI ​​model to provide advance notice.

[0267] In this way, the system of the present invention improves operational efficiency and accelerates information provision, thereby providing value to corporate operations.

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] Users enter their inquiries using their devices. Specifically, when a user types "How do I get my payslip?" into the chat window, this inquiry is sent to the server as an HTTP request. The input data is in natural language text format.

[0271] Step 2:

[0272] The server analyzes natural language text, which is the query received from the terminal. Using a generative AI model powered by TensorFlow, the server understands the content of the query and identifies its intent. The model tokenizes the text and uses a neural network to classify the intent. The output is the identified intent and associated keywords.

[0273] Step 3:

[0274] The server sends a query to the internal database based on the analysis results. It uses a database management system (MySQL or MongoDB) to retrieve information related to the query. Specifically, it queries the database for procedural information regarding "payslips" and retrieves the relevant records. The output is a collection of related information.

[0275] Step 4:

[0276] The server generates a natural language response based on the acquired information. It uses the Pandas library to format the data and create the response text. Furthermore, it uses a generative AI model to produce fluent, contextually relevant output. The output is a complete response sentence to be presented to the user.

[0277] Step 5:

[0278] The server sends the generated response to the terminal. The response is sent as JSON data in an HTTP response. The terminal receives this data and parses it to display it in the user's chat window. The displayed output is a clear answer to the user's inquiry.

[0279] Step 6:

[0280] The server escalates inquiries if the content follows past patterns or if data is insufficient. Predictive analytics are used to detect recurring inquiry problems and route them to the appropriate personnel. The output is an escalation message to the responsible person or department.

[0281] (Application Example 1)

[0282] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0283] In modern electronic transactions, diverse user inquiries and troubleshooting occur frequently, requiring service providers to respond quickly and accurately. However, traditional systems suffered from time-consuming response times and increased costs due to the prevalence of manual handling. Furthermore, insufficient preventative measures against recurring inquiries made it difficult to maintain user satisfaction.

[0284] 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.

[0285] In this invention, the server includes language processing means for analyzing a request in natural language based on the accumulated information and generating related data, analysis means for analyzing past request data to predict future problems and notify necessary information in advance, and means for analyzing inquiries related to electronic transactions input in natural language by the user from a communication device and presenting related information in real time. As a result, it becomes possible to quickly and accurately respond to the user's inquiries, and a cost-effective service can be provided. In addition, by predicting repeated inquiries and automatically notifying in advance, an improvement in user satisfaction can be expected.

[0286] The "accumulated information" refers to databases and records stored in the past, which are the information used by the system to generate appropriate answers to queries and requests.

[0287] The "request in natural language" refers to the input of inquiries and requests using the language commonly used by humans, and in a computer system, this language is required to be understood and analyzed.

[0288] The "language processing means" refers to the technologies and methods for analyzing natural language and converting it into a form understandable by a computer.

[0289] The "analysis means" refers to the methods and technologies for predicting future patterns and problems based on past data.

[0290] The "communication device" refers to a terminal having the technology for transmitting and receiving information through a connection, including smartphones, computers, and the like.

[0291] "Presenting in real time" means providing related information immediately without delay in response to the user's requests and inquiries.

[0292] "Automatic notification" refers to the system automatically sending pre-configured information to the user based on predictions and analysis.

[0293] To implement this invention, a system comprising the following components is used. The server analyzes natural language queries input by the user through language processing means. Depending on the content of the query, it retrieves appropriate information from the database and provides the user with an answer in real time. Natural language processing libraries such as TensorFlow and spaCy are used for this purpose.

[0294] Furthermore, the server uses analytical tools to analyze past query data. This allows it to predict future problems and automatically notify users in advance. A specific example of such notification is that the system can proactively inform users of solutions for certain queries that increase during the end of the year.

[0295] The device provides an interface for users to enter inquiries. This is a smartphone application developed using React Native, allowing users to easily submit inquiries in natural language. The entered information is transferred to the server and processed quickly.

[0296] The entire system is intended to communicate via APIs and function efficiently to improve the user experience. Below is an example of input to the generative AI model.

[0297] Example of a prompt:

[0298] User inquiry: "I want to change my payment method."

[0299] Information provided by the system: "Please log in to your account, select 'Settings' and then 'Payment Methods', and register a new payment method."

[0300] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0301] Step 1:

[0302] The terminal receives the inquiry input by the user in natural language. When the user inputs a question to the application interface, the terminal prepares to send the content to the server. At this point, the input is the user's natural language input, and as the output, the data to be sent to the server is generated as it is.

[0303] Step 2:

[0304] The server analyzes the received user inquiry using language processing means. The input is the text in natural language, and semantic analysis and keyword extraction are performed using natural language processing technologies (for example, TensorFlow or spaCy). As the output, structured data reflecting the intention of the inquiry is generated.

[0305] Step 3:

[0306] Based on the analysis result, the server retrieves relevant information from the in-house database. The input is the structured data obtained in the previous step, and based on it, an SQL query is generated and sent to the database. As the output, information related to the user's inquiry is prepared on the server side.

[0307] Step 4:

[0308] Based on the retrieved information, the server generates an answer to the user. The input is the raw data retrieved from the database, and a natural language form answer is formed using a generation AI model. As the output, formatted text for replying to the user is generated.

[0309] Step 5:

[0310] The server sends the generated response back to the terminal. At this point, the input is the generated text, and the output is displayed on the terminal in a format that the user can read. The terminal then displays this information on the user's screen.

[0311] Step 6:

[0312] The server records the query content and its results in a database. The input is the entire query process information, stored in the database, and used for future predictive analytics. This allows for the detection of recurring query patterns and the accumulation of foundational data for proactive notification as prompt messages.

[0313] 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.

[0314] This invention relates to a system that streamlines internal inquiry handling while utilizing user sentiment analysis to provide more effective responses. This system is server-centric and processes user inquiries using natural language processing capabilities that incorporate a sentiment engine.

[0315] The server collects pre-stored internal company information and uses a model that implements natural language processing technology. This model has the ability to analyze natural language queries entered by users via terminals and simultaneously grasp the content of those queries and the user's emotions. The server quickly processes the text received from the terminal and recognizes the user's emotions using an emotion engine. For example, if a user expresses dissatisfaction regarding their salary, the server can detect feelings of frustration and dissatisfaction.

[0316] The emotion engine extracts emotional information from the user's text and uses that information to adjust the feedback and escalation methods provided by the server. The server then presents a response to the terminal that is appropriate to the user's emotions. Specifically, if the emotion engine detects "dissatisfaction," the server will take steps to improve user satisfaction, such as including a follow-up suggestion like, "Please contact HR if you need further explanation."

[0317] Furthermore, the server uses predictive analytics to analyze past inquiry data and user sentiment information to predict potential problems in the future. Based on these predictions, it can proactively provide users with appropriate information and solutions via push notifications. For example, it can proactively alert all employees based on the timing when a particular sentiment pattern is detected frequently.

[0318] Furthermore, for issues that are difficult to resolve, the server automatically uses escalation mechanisms to forward inquiries to the appropriate department or person based on the emotional analysis results. For example, if the emotional engine detects the emotion of "anger," it can quickly forward the inquiry to the customer support team.

[0319] This system allows employees to receive prompt and appropriate information that is sensitive to their feelings, streamlines inquiry handling, and is expected to further improve employee satisfaction.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] The user enters their inquiry in natural language using their device. The user enters their question or request as specific text in the chat window.

[0323] Step 2:

[0324] The server analyzes the query received from the terminal. The server uses natural language processing techniques to extract the query's intent and key keywords.

[0325] Step 3:

[0326] The server uses an emotion engine to analyze the text extracted from the inquiry and determine the user's emotional state. For example, the emotion engine can recognize emotions such as "dissatisfaction" or "frustration" from the input text.

[0327] Step 4:

[0328] The server searches its internal database for information related to the query and generates the optimal response. The response is constructed to include adjustments based on the user's emotional state.

[0329] Step 5:

[0330] The server generates a response, sends it to the terminal, and provides it to the user. By showing the user explanations that include emotional considerations and follow-up suggestions, a highly satisfactory response is achieved.

[0331] Step 6:

[0332] The server analyzes past query history and sentiment data to predict future issues and trends. If a specific sentiment pattern is increasing, it prepares to send a pre-notification.

[0333] Step 7:

[0334] The server automatically escalates inquiries it cannot resolve to the appropriate department or person. It considers the results of the sentiment engine to ensure quick and appropriate escalation.

[0335] This process makes customer inquiries more effective and personal, improving the employee experience.

[0336] (Example 2)

[0337] 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".

[0338] Conventional inquiry processing systems were inadequate in responding to user inquiries and failed to provide effective feedback that took emotions into consideration. Furthermore, the lack of means to predict future problems and take appropriate preventative measures made it difficult to provide a highly satisfactory service.

[0339] 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.

[0340] In this invention, the server includes language processing means for analyzing inquiries based on stored information sources and generating relevant information, sentiment analysis means for simultaneously analyzing the inquiry content and sentiment analyzed by the language processing means to generate optimal feedback, and escalation means for forwarding inquiries to the relevant department or person in charge based on the analyzed inquiry. This enables the provision of sentiment-sensitive responses and problem-solving based on predictions.

[0341] A "language processing means" is a means of analyzing queries in natural language form from accumulated information and generating related information.

[0342] "Emotional analysis means" refers to a method for simultaneously analyzing the user's emotions from the analyzed inquiry content and providing optimal feedback.

[0343] An "escalation mechanism" is a means of forwarding an inquiry to the appropriate department or person based on the analyzed inquiry.

[0344] A "predictive provision method" is a means of using past data to predict future problems and providing necessary information in advance.

[0345] This invention provides a system to streamline internal inquiry handling and analyze user emotions to provide more effective responses. The system is server-centric and built using natural language processing technology to enable emotion analysis.

[0346] The server collects accumulated information from a database and uses a natural language processing (NLP) engine to analyze queries based on this information. This NLP engine has text analysis skills and extracts the content of the query and important keywords. The analyzed information is then sent to an emotion engine, which is used to identify the user's sentiment.

[0347] The server generates feedback tailored to the user's emotions based on emotional information extracted by the emotion engine, and provides it to the user via the terminal. This process is rapid, taking into account both the user's inquiry and their emotions to enable appropriate feedback. For example, if a user expresses dissatisfaction about a delayed salary payment, the server will generate feedback such as, "We apologize for the inconvenience. Please contact Human Resources for further details."

[0348] Furthermore, the server can use predictive means to analyze past inquiry data and sentiment data to predict future problems and notify users of countermeasures in advance. This prediction allows for early warnings to all employees if a large number of sentiment patterns are detected at a particular time.

[0349] The system also incorporates escalation mechanisms, ensuring that complex issues or inquiries expressing strong emotions such as anger are promptly forwarded to the appropriate department or person in charge. This design allows users to receive timely and accurate information while being sensitive to their emotions, resulting in more efficient inquiry handling and improved employee satisfaction.

[0350] An example of a prompt might be: "Generate a prompt that analyzes the user's inquiry, analyzes their sentiment, and generates appropriate feedback. For example, if the user is expressing dissatisfaction with their salary, indicate what kind of feedback would be appropriate."

[0351] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0352] Step 1:

[0353] The server receives the user's query text from the terminal. The input is the natural language query entered by the user using the terminal, and the output is the received text data. This text data is then prepared for the next parsing step.

[0354] Step 2:

[0355] The server activates a natural language processing (NLP) engine to analyze the query text. The input is the text data received in step 1, and the output is data containing keywords and main themes extracted from the query. Specifically, the NLP engine analyzes the linguistic structure of the text and identifies important words such as "salary" and "payment delay."

[0356] Step 3:

[0357] The server uses an emotion engine to perform sentiment analysis on the query text. The input is analysis data from an NLP engine, and the output is a label or indicator representing the user's emotion (e.g., "dissatisfied," "frustrated"). Specifically, it scrutinizes the textual expression and implements an algorithm to identify the user's emotional state.

[0358] Step 4:

[0359] The server generates feedback based on extracted keywords and sentiment data. The input is the output data from steps 2 and 3, and the output is the response message provided to the user. The generated feedback includes language that is sensitive to the user's feelings, and a message such as "We apologize for the inconvenience. Please contact Human Resources if you would like more information" is created.

[0360] Step 5:

[0361] The server automatically forwards inquiries requiring escalation to the appropriate department or person in charge. The input is data indicating emotions such as "anger" or other strong emotions, and the output is the escalated inquiry information. Specifically, the system immediately sends the information to the appropriate department's contact based on the emotion assessment.

[0362] Step 6:

[0363] The server analyzes past query data to make future predictions. The input is historical query data, and the output is a list of predicted problems and their solutions. This allows for proactive notifications to be sent to employees when specific emotional patterns are frequently detected.

[0364] (Application Example 2)

[0365] 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."

[0366] In modern organizations, there is a demand for prompt and appropriate handling of customer inquiries and complaints. However, traditional systems often have limitations, such as their mechanical nature and insufficient empathy for the customer's feelings. Furthermore, balancing problem prediction using historical data with human-centered responses is difficult, hindering improvements in customer satisfaction. There is a need to overcome these challenges and achieve a higher level of customer service.

[0367] 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.

[0368] In this invention, the server includes a natural language analysis means that analyzes natural language queries based on accumulated internal organizational information, a predictive analysis means that analyzes past query records to predict future problems, and an emotional analysis means that analyzes the user's emotional information and reflects it in the response. This enables more appropriate and prompt responses that are attentive to the customer's emotions.

[0369] "Natural language processing" refers to a technology that analyzes natural language queries based on accumulated internal organizational information and understands their content.

[0370] An "escalation mechanism" is a function that, based on an analyzed inquiry, quickly transfers information to the appropriate department or person in charge to facilitate a response.

[0371] "Predictive analysis means" refers to technology that predicts potential problems that may occur in the future based on past inquiry records and provides necessary advance notice.

[0372] An "emotional analysis tool" is a means of analyzing a user's inquiry to understand their emotional state and reflecting that information in the response.

[0373] A "response optimization system" is a system that improves customer service by detecting a specific emotional state and generating a response appropriate to that state.

[0374] "Speech processing means" refers to technology that processes speech input in real time and converts speech into text.

[0375] An "emotion estimation method" is a system that analyzes a user's biometric information and calculates the optimal response to improve customer satisfaction.

[0376] The system for realizing this invention consists of a server and user terminals. The server implements natural language processing technology that performs natural language analysis based on accumulated internal organizational information. Specifically, it deploys a natural language analysis means that analyzes inquiry content using the Transformer technology of the natural language processing library Hugging Face. The analyzed content is promptly addressed through an escalation means that routes it to the relevant department or person in charge.

[0377] Furthermore, the server is equipped with predictive analytics means to predict future problems based on past query records. This makes it possible to predict potential future problems in advance and notify relevant parties beforehand. In addition, an emotional analysis means is implemented to capture user emotional information and reflect that information in the response. For example, if dissatisfaction is detected from a user's query, that information is used to provide appropriate follow-up through the response optimization means.

[0378] The device implements speech processing capabilities that process voice input in real time and convert it to text using the Google Cloud Speech-to-Text API, among others. To more accurately understand the user's emotions, an emotion estimation mechanism works in conjunction with the server to estimate the user's emotions from text and biometric information. This information is analyzed by a generative AI model and used as prompt text.

[0379] As a concrete example, by generating a prompt message such as, "The customer appears to be having trouble because their product hasn't arrived. Please respond kindly and propose a concrete solution," the optimal response can be constructed. This allows for a response that better matches the user's needs, contributing to an overall improvement in customer satisfaction.

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The user provides voice input through the device. The device uses the Google Cloud Speech-to-Text API to convert the speech to text. In this step, the voice data is input and the text data is output. This text data serves as the basis for subsequent processing.

[0383] Step 2:

[0384] The server receives text data sent from the terminal. Next, to perform natural language processing, it uses the Hugging Face Transformer model to analyze the query and extract the necessary information. The input for this step is text data from the terminal, and the output is the analyzed query. Here, the linguistic patterns of the text data are analyzed and key information is extracted.

[0385] Step 3:

[0386] The server uses emotion analysis tools to estimate the user's emotional state from the analyzed text. This process involves applying a data model for understanding emotions and analyzing emotional patterns. The input to this step is the analyzed query, and the output is the estimated emotional state. Specifically, this step estimates emotions by measuring emotional patterns using emotion indicators within the text.

[0387] Step 4:

[0388] The server generates an appropriate response through response optimization means based on the estimated emotional state. It utilizes a generative AI model to output the most appropriate response based on the prompt. In this step, the estimated emotional state is the input, and the output is the optimized response. The generative AI model is used to select the best response from multiple candidates, preparing a response that meets the user's needs.

[0389] Step 5:

[0390] The server uses escalation mechanisms to notify the appropriate department or person in charge, depending on the situation. This facilitates coordination to ensure that any necessary additional actions are taken. The inputs to this step are estimated emotional states and responses, and the outputs are the information required for escalation. When a situation requiring escalation is identified, a rapid response procedure is triggered.

[0391] Step 6:

[0392] Finally, the server-generated response is sent to the terminal and presented to the user. This allows the user to obtain answers to their questions and problems. In this step, the input is the optimized response, and the output is the information presented to the user. To enhance user satisfaction, clear and helpful information is provided at the appropriate time.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] This invention relates to a system for streamlining internal inquiry handling within a company. This system is server-centric and provides a series of processes for handling inquiries made by employees via terminals.

[0410] The server collects pre-stored internal company information and implements a model using natural language processing technology. This model has the ability to analyze natural language inquiries entered by employees and generate appropriate responses based on their content. The server quickly processes inquiries received through terminals, accesses necessary internal company information, and generates the optimal response.

[0411] The terminal provides an interface where employees can input inquiries in natural language. For example, they might type questions about payslips or leave application procedures into a chat window. The server receives these inquiries, analyzes the context, gathers relevant information from the company's internal database, generates an answer, and returns it to the user.

[0412] Furthermore, the server uses predictive analytics to analyze past inquiry data and identify recurring problems. Based on this information, it can predict future problems and provide employees with solutions and necessary information in advance via push notifications. For example, by notifying employees in advance about "how to apply for leave," a question that frequently arises at the end of the fiscal year, the burden of inquiries can be reduced.

[0413] Furthermore, the server includes escalation mechanisms, and inquiries that the system cannot resolve automatically are escalated to the appropriate department or personnel. For example, if a technical problem is reported, it is forwarded directly to the IT support team. This process enables quick and efficient problem resolution.

[0414] This system allows employees to quickly obtain the information they need, improving the efficiency of inquiry handling and increasing employee satisfaction.

[0415] The following describes the processing flow.

[0416] Step 1:

[0417] The user enters their inquiry in natural language via their device. Specifically, they type a question such as "How do I check my payslip?" into the chat window on their device.

[0418] Step 2:

[0419] The server receives the inquiry sent from the terminal. The received text is analyzed using natural language processing technology to extract the intent of the inquiry and keywords. For example, "payslip" and "how to check" are extracted as the main keywords.

[0420] Step 3:

[0421] The server searches its internal database based on the keywords it extracts and collects relevant information. For example, the server accesses the human resources information system and retrieves information such as "payslip verification procedure."

[0422] Step 4:

[0423] Based on the information acquired by the server, the system generates the most appropriate response to the inquiry. For example, it might construct a response such as, "You can check your payslip on the intranet's 'My Page'."

[0424] Step 5:

[0425] The server sends the generated response to the user's device. The user can then view the response returned by the server in the chat window on their device.

[0426] Step 6:

[0427] The server analyzes past inquiry data to predict recurring issues. Based on these predictions, the server provides users with necessary information in advance via push notifications. For example, it might send a notification stating, "Working hours are scheduled to change next month."

[0428] Step 7:

[0429] If the server detects an inquiry it cannot resolve, it will escalate it to the appropriate department or personnel. Specifically, inquiries such as "A system error has occurred" are automatically forwarded to the IT support team.

[0430] This series of steps allows users to receive answers smoothly and enables efficient management of inquiries.

[0431] (Example 1)

[0432] 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."

[0433] In today's business environment, it is crucial to provide timely and accurate information to employees in response to the diverse inquiries they face in their daily work. However, many companies spend a significant amount of time and resources on handling inquiries, and the lack of efficient systems hinders business operations. This invention aims to improve employee satisfaction by streamlining employee inquiry handling and accelerating information provision.

[0434] 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.

[0435] In this invention, the server includes a natural language processing means that analyzes natural language queries based on accumulated information and generates relevant information based on that analysis; an escalation means that routes queries to the relevant department or person in charge based on the queries analyzed by the natural language processing means; and a predictive analysis means that analyzes past query data to predict future problems and notifies the user of necessary information in advance. This enables efficient responses to diverse inquiries from employees, facilitating smooth business operations and continuous business improvement.

[0436] "Accumulated information" refers to historical records and knowledge stored within a company or related databases, and is a collection of data used for future reference and analysis.

[0437] "Natural language processing" is a technology used by computers to understand, generate, and interact with human language. It is a means of accurately analyzing the content of inquiries and generating appropriate responses.

[0438] "Escalation" is the process of routing inquiries that require action and cannot be automatically resolved by the system to the appropriate person or department, and is a means of supporting efficient problem solving.

[0439] "Predictive analytics" is a technology that analyzes data accumulated in the past, uses the patterns derived from that data to predict future events and problems, and takes proactive measures.

[0440] "Answer generation" refers to the process of creating specific and easy-to-understand answers for users based on the analyzed inquiry content.

[0441] "Information gathering" is the process of obtaining necessary information from databases and other sources and using that information to help answer inquiries.

[0442] This invention is a system for efficiently handling customer inquiries for businesses. The system mainly consists of a server and terminals.

[0443] The server processes queries using the following technologies:

[0444] The system utilizes Python and TensorFlow libraries for natural language processing. The generative AI model is used to analyze employee inquiries and accurately understand their intent. Specifically, it focuses on analyzing question intent and extracting keywords.

[0445] The server uses database management systems such as MySQL or MongoDB to collect information based on the analysis results. This allows it to quickly retrieve the necessary relevant information and generate answers to queries.

[0446] For predictive analytics, we use the Pandas and Scikit-learn libraries to analyze past query data and predict future problem occurrences.

[0447] Data collected from the frontend is sent to the server via a web service using Flask, enabling bidirectional data communication.

[0448] The terminal provides a user interface for employees to make inquiries.

[0449] The frontend is built using React.js, allowing employees to input inquiries in natural language. In particular, input from terminals is done via a chat window.

[0450] For example, if a question such as "How do I check my payslip?" is entered into the chat window, it is sent to the server and processing begins.

[0451] Users can quickly obtain information through this system.

[0452] Employees can obtain the necessary information at any time through automated responses from the server.

[0453] If a problem cannot be resolved through automated responses, the inquiry will be forwarded to the appropriate person through an escalation mechanism, ensuring a swift resolution.

[0454] For example, if an employee types "Please tell me the procedure for applying for leave next year" at the end of the fiscal year, the server will retrieve relevant information from the database and respond with the appropriate procedure in the chat window. Furthermore, prompts such as "Create a notice regarding leave applications for employees as the fiscal year ends next week" can be input into the AI ​​model to provide advance notice.

[0455] In this way, the system of the present invention improves operational efficiency and accelerates information provision, thereby providing value to corporate operations.

[0456] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0457] Step 1:

[0458] Users enter their inquiries using their devices. Specifically, when a user types "How do I get my payslip?" into the chat window, this inquiry is sent to the server as an HTTP request. The input data is in natural language text format.

[0459] Step 2:

[0460] The server analyzes natural language text, which is the query received from the terminal. Using a generative AI model powered by TensorFlow, the server understands the content of the query and identifies its intent. The model tokenizes the text and uses a neural network to classify the intent. The output is the identified intent and associated keywords.

[0461] Step 3:

[0462] The server sends a query to the internal database based on the analysis results. It uses a database management system (MySQL or MongoDB) to retrieve information related to the query. Specifically, it queries the database for procedural information regarding "payslips" and retrieves the relevant records. The output is a collection of related information.

[0463] Step 4:

[0464] The server generates a natural language response based on the acquired information. It uses the Pandas library to format the data and create the response text. Furthermore, it uses a generative AI model to produce fluent, contextually relevant output. The output is a complete response sentence to be presented to the user.

[0465] Step 5:

[0466] The server sends the generated response to the terminal. The response is sent as JSON data in an HTTP response. The terminal receives this data and parses it to display it in the user's chat window. The displayed output is a clear answer to the user's inquiry.

[0467] Step 6:

[0468] The server escalates inquiries if the content follows past patterns or if data is insufficient. Predictive analytics are used to detect recurring inquiry problems and route them to the appropriate personnel. The output is an escalation message to the responsible person or department.

[0469] (Application Example 1)

[0470] 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."

[0471] In modern electronic transactions, diverse user inquiries and troubleshooting occur frequently, requiring service providers to respond quickly and accurately. However, traditional systems suffered from time-consuming response times and increased costs due to the prevalence of manual handling. Furthermore, insufficient preventative measures against recurring inquiries made it difficult to maintain user satisfaction.

[0472] 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.

[0473] In this invention, the server includes language processing means for analyzing requests in natural language based on accumulated information and generating relevant data; analysis means for analyzing past request data to predict future problems and notifying necessary information in advance; and means for analyzing inquiries related to electronic transactions entered by users in natural language from communication devices and presenting relevant information in real time. This enables a rapid and accurate response to user inquiries, resulting in cost-effective service provision. Furthermore, by predicting recurring inquiries and automatically notifying users in advance, improved user satisfaction can be expected.

[0474] "Accumulated information" refers to databases and records stored in the past, and is the information that a system uses to generate appropriate responses to inquiries and requests.

[0475] "Requests in natural language" refer to inquiries and requests made using the language that humans normally use, and computer systems are required to understand and analyze this language.

[0476] "Language processing means" refers to technologies and methods for analyzing natural language and converting it into a format that a computer can understand.

[0477] "Analytical methods" refer to methods and techniques for predicting future patterns and problems based on past data.

[0478] "Communication equipment" refers to terminals that possess the technology to send and receive information through a connection, and includes smartphones and computers.

[0479] "Presenting in real time" means providing relevant information immediately and without delay in response to user requests and inquiries.

[0480] "Automatic notification" refers to the system automatically sending pre-configured information to the user based on predictions and analysis.

[0481] To implement this invention, a system comprising the following components is used. The server analyzes natural language queries input by the user through language processing means. Depending on the content of the query, it retrieves appropriate information from the database and provides the user with an answer in real time. Natural language processing libraries such as TensorFlow and spaCy are used for this purpose.

[0482] Furthermore, the server uses analytical tools to analyze past query data. This allows it to predict future problems and automatically notify users in advance. A specific example of such notification is that the system can proactively inform users of solutions for certain queries that increase during the end of the year.

[0483] The device provides an interface for users to enter inquiries. This is a smartphone application developed using React Native, allowing users to easily submit inquiries in natural language. The entered information is transferred to the server and processed quickly.

[0484] The entire system is intended to communicate via APIs and function efficiently to improve the user experience. Below is an example of input to the generative AI model.

[0485] Example of a prompt:

[0486] User inquiry: "I want to change my payment method."

[0487] Information provided by the system: "Please log in to your account, select 'Settings' and then 'Payment Methods', and register a new payment method."

[0488] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0489] Step 1:

[0490] The terminal receives queries entered by the user in natural language. When the user enters a question into the application interface, the terminal prepares to send the content to the server. At this point, the input is the user's natural language input, and the output is the data sent directly to the server.

[0491] Step 2:

[0492] The server analyzes the user's query using natural language processing tools. The input is natural language text, and semantic analysis and keyword extraction are performed using natural language processing techniques (e.g., TensorFlow or spaCy). The output is structured data that reflects the intent of the query.

[0493] Step 3:

[0494] Based on the analysis results, the server retrieves relevant information from the company's internal database. The input is the structured data obtained in the previous step, and an SQL query is generated based on it and sent to the database. As output, the server prepares information related to the user's inquiry.

[0495] Step 4:

[0496] The server generates a response to the user based on the acquired information. The input is raw data retrieved from a database, and a generative AI model is used to form a response in natural language. The output is formatted text for the user to respond to.

[0497] Step 5:

[0498] The server sends the generated response back to the terminal. At this point, the input is the generated text, and the output is displayed on the terminal in a format that the user can read. The terminal then displays this information on the user's screen.

[0499] Step 6:

[0500] The server records the query content and its results in a database. The input is the entire query process information, stored in the database, and used for future predictive analytics. This allows for the detection of recurring query patterns and the accumulation of foundational data for proactive notification as prompt messages.

[0501] 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.

[0502] This invention relates to a system that streamlines internal inquiry handling while utilizing user sentiment analysis to provide more effective responses. This system is server-centric and processes user inquiries using natural language processing capabilities that incorporate a sentiment engine.

[0503] The server collects pre-stored internal company information and uses a model that implements natural language processing technology. This model has the ability to analyze natural language queries entered by users via terminals and simultaneously grasp the content of those queries and the user's emotions. The server quickly processes the text received from the terminal and recognizes the user's emotions using an emotion engine. For example, if a user expresses dissatisfaction regarding their salary, the server can detect feelings of frustration and dissatisfaction.

[0504] The emotion engine extracts emotional information from the user's text and uses that information to adjust the feedback and escalation methods provided by the server. The server then presents a response to the terminal that is appropriate to the user's emotions. Specifically, if the emotion engine detects "dissatisfaction," the server will take steps to improve user satisfaction, such as including a follow-up suggestion like, "Please contact HR if you need further explanation."

[0505] Furthermore, the server uses predictive analytics to analyze past inquiry data and user sentiment information to predict potential problems in the future. Based on these predictions, it can proactively provide users with appropriate information and solutions via push notifications. For example, it can proactively alert all employees based on the timing when a particular sentiment pattern is detected frequently.

[0506] Furthermore, for issues that are difficult to resolve, the server automatically uses escalation mechanisms to forward inquiries to the appropriate department or person based on the emotional analysis results. For example, if the emotional engine detects the emotion of "anger," it can quickly forward the inquiry to the customer support team.

[0507] This system allows employees to receive prompt and appropriate information that is sensitive to their feelings, streamlines inquiry handling, and is expected to further improve employee satisfaction.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The user enters their inquiry in natural language using their device. The user enters their question or request as specific text in the chat window.

[0511] Step 2:

[0512] The server analyzes the query received from the terminal. The server uses natural language processing techniques to extract the query's intent and key keywords.

[0513] Step 3:

[0514] The server uses an emotion engine to analyze the text extracted from the inquiry and determine the user's emotional state. For example, the emotion engine can recognize emotions such as "dissatisfaction" or "frustration" from the input text.

[0515] Step 4:

[0516] The server searches its internal database for information related to the query and generates the optimal response. The response is constructed to include adjustments based on the user's emotional state.

[0517] Step 5:

[0518] The server generates a response, sends it to the terminal, and provides it to the user. By showing the user explanations that include emotional considerations and follow-up suggestions, a highly satisfactory response is achieved.

[0519] Step 6:

[0520] The server analyzes past query history and sentiment data to predict future issues and trends. If a specific sentiment pattern is increasing, it prepares to send a pre-notification.

[0521] Step 7:

[0522] The server automatically escalates inquiries it cannot resolve to the appropriate department or person. It considers the results of the sentiment engine to ensure quick and appropriate escalation.

[0523] This process makes customer inquiries more effective and personal, improving the employee experience.

[0524] (Example 2)

[0525] 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."

[0526] Conventional inquiry processing systems were inadequate in responding to user inquiries and failed to provide effective feedback that took emotions into consideration. Furthermore, the lack of means to predict future problems and take appropriate preventative measures made it difficult to provide a highly satisfactory service.

[0527] 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.

[0528] In this invention, the server includes language processing means for analyzing inquiries based on stored information sources and generating relevant information, sentiment analysis means for simultaneously analyzing the inquiry content and sentiment analyzed by the language processing means to generate optimal feedback, and escalation means for forwarding inquiries to the relevant department or person in charge based on the analyzed inquiry. This enables the provision of sentiment-sensitive responses and problem-solving based on predictions.

[0529] A "language processing means" is a means of analyzing queries in natural language form from accumulated information and generating related information.

[0530] "Emotional analysis means" refers to a method for simultaneously analyzing the user's emotions from the analyzed inquiry content and providing optimal feedback.

[0531] An "escalation mechanism" is a means of forwarding an inquiry to the appropriate department or person based on the analyzed inquiry.

[0532] A "predictive provision method" is a means of using past data to predict future problems and providing necessary information in advance.

[0533] This invention provides a system to streamline internal inquiry handling and analyze user emotions to provide more effective responses. The system is server-centric and built using natural language processing technology to enable emotion analysis.

[0534] The server collects accumulated information from a database and uses a natural language processing (NLP) engine to analyze queries based on this information. This NLP engine has text analysis skills and extracts the content of the query and important keywords. The analyzed information is then sent to an emotion engine, which is used to identify the user's sentiment.

[0535] The server generates feedback tailored to the user's emotions based on emotional information extracted by the emotion engine, and provides it to the user via the terminal. This process is rapid, taking into account both the user's inquiry and their emotions to enable appropriate feedback. For example, if a user expresses dissatisfaction about a delayed salary payment, the server will generate feedback such as, "We apologize for the inconvenience. Please contact Human Resources for further details."

[0536] Furthermore, the server can use predictive means to analyze past inquiry data and sentiment data to predict future problems and notify users of countermeasures in advance. This prediction allows for early warnings to all employees if a large number of sentiment patterns are detected at a particular time.

[0537] The system also incorporates escalation mechanisms, ensuring that complex issues or inquiries expressing strong emotions such as anger are promptly forwarded to the appropriate department or person in charge. This design allows users to receive timely and accurate information while being sensitive to their emotions, resulting in more efficient inquiry handling and improved employee satisfaction.

[0538] An example of a prompt might be: "Generate a prompt that analyzes the user's inquiry, analyzes their sentiment, and generates appropriate feedback. For example, if the user is expressing dissatisfaction with their salary, indicate what kind of feedback would be appropriate."

[0539] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0540] Step 1:

[0541] The server receives the user's query text from the terminal. The input is the natural language query entered by the user using the terminal, and the output is the received text data. This text data is then prepared for the next parsing step.

[0542] Step 2:

[0543] The server activates a natural language processing (NLP) engine to analyze the query text. The input is the text data received in step 1, and the output is data containing keywords and main themes extracted from the query. Specifically, the NLP engine analyzes the linguistic structure of the text and identifies important words such as "salary" and "payment delay."

[0544] Step 3:

[0545] The server uses an emotion engine to perform sentiment analysis on the query text. The input is analysis data from an NLP engine, and the output is a label or indicator representing the user's emotion (e.g., "dissatisfied," "frustrated"). Specifically, it scrutinizes the textual expression and implements an algorithm to identify the user's emotional state.

[0546] Step 4:

[0547] The server generates feedback based on extracted keywords and sentiment data. The input is the output data from steps 2 and 3, and the output is the response message provided to the user. The generated feedback includes language that is sensitive to the user's feelings, and a message such as "We apologize for the inconvenience. Please contact Human Resources if you would like more information" is created.

[0548] Step 5:

[0549] The server automatically forwards inquiries requiring escalation to the appropriate department or person in charge. The input is data indicating emotions such as "anger" or other strong emotions, and the output is the escalated inquiry information. Specifically, the system immediately sends the information to the appropriate department's contact based on the emotion assessment.

[0550] Step 6:

[0551] The server analyzes past query data to make future predictions. The input is historical query data, and the output is a list of predicted problems and their solutions. This allows for proactive notifications to be sent to employees when specific emotional patterns are frequently detected.

[0552] (Application Example 2)

[0553] 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."

[0554] In modern organizations, there is a demand for prompt and appropriate handling of customer inquiries and complaints. However, traditional systems often have limitations, such as their mechanical nature and insufficient empathy for the customer's feelings. Furthermore, balancing problem prediction using historical data with human-centered responses is difficult, hindering improvements in customer satisfaction. There is a need to overcome these challenges and achieve a higher level of customer service.

[0555] 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.

[0556] In this invention, the server includes a natural language analysis means that analyzes natural language queries based on accumulated internal organizational information, a predictive analysis means that analyzes past query records to predict future problems, and an emotional analysis means that analyzes the user's emotional information and reflects it in the response. This enables more appropriate and prompt responses that are attentive to the customer's emotions.

[0557] "Natural language processing" refers to a technology that analyzes natural language queries based on accumulated internal organizational information and understands their content.

[0558] An "escalation mechanism" is a function that, based on an analyzed inquiry, quickly transfers information to the appropriate department or person in charge to facilitate a response.

[0559] "Predictive analysis means" refers to technology that predicts potential problems that may occur in the future based on past inquiry records and provides necessary advance notice.

[0560] An "emotional analysis tool" is a means of analyzing a user's inquiry to understand their emotional state and reflecting that information in the response.

[0561] A "response optimization system" is a system that improves customer service by detecting a specific emotional state and generating a response appropriate to that state.

[0562] "Speech processing means" refers to technology that processes speech input in real time and converts speech into text.

[0563] An "emotion estimation method" is a system that analyzes a user's biometric information and calculates the optimal response to improve customer satisfaction.

[0564] The system for realizing this invention consists of a server and user terminals. The server implements natural language processing technology that performs natural language analysis based on accumulated internal organizational information. Specifically, it deploys a natural language analysis means that analyzes inquiry content using the Transformer technology of the natural language processing library Hugging Face. The analyzed content is promptly addressed through an escalation means that routes it to the relevant department or person in charge.

[0565] Furthermore, the server is equipped with predictive analytics means to predict future problems based on past query records. This makes it possible to predict potential future problems in advance and notify relevant parties beforehand. In addition, an emotional analysis means is implemented to capture user emotional information and reflect that information in the response. For example, if dissatisfaction is detected from a user's query, that information is used to provide appropriate follow-up through the response optimization means.

[0566] The device implements speech processing capabilities that process voice input in real time and convert it to text using the Google Cloud Speech-to-Text API, among others. To more accurately understand the user's emotions, an emotion estimation mechanism works in conjunction with the server to estimate the user's emotions from text and biometric information. This information is analyzed by a generative AI model and used as prompt text.

[0567] As a concrete example, by generating a prompt message such as, "The customer appears to be having trouble because their product hasn't arrived. Please respond kindly and propose a concrete solution," the optimal response can be constructed. This allows for a response that better matches the user's needs, contributing to an overall improvement in customer satisfaction.

[0568] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0569] Step 1:

[0570] The user provides voice input through the device. The device uses the Google Cloud Speech-to-Text API to convert the speech to text. In this step, the voice data is input and the text data is output. This text data serves as the basis for subsequent processing.

[0571] Step 2:

[0572] The server receives text data sent from the terminal. Next, to perform natural language processing, it uses the Hugging Face Transformer model to analyze the query and extract the necessary information. The input for this step is text data from the terminal, and the output is the analyzed query. Here, the linguistic patterns of the text data are analyzed and key information is extracted.

[0573] Step 3:

[0574] The server uses emotion analysis tools to estimate the user's emotional state from the analyzed text. This process involves applying a data model for understanding emotions and analyzing emotional patterns. The input to this step is the analyzed query, and the output is the estimated emotional state. Specifically, this step estimates emotions by measuring emotional patterns using emotion indicators within the text.

[0575] Step 4:

[0576] The server generates an appropriate response through response optimization means based on the estimated emotional state. It utilizes a generative AI model to output the most appropriate response based on the prompt. In this step, the estimated emotional state is the input, and the output is the optimized response. The generative AI model is used to select the best response from multiple candidates, preparing a response that meets the user's needs.

[0577] Step 5:

[0578] The server uses escalation mechanisms to notify the appropriate department or person in charge, depending on the situation. This facilitates coordination to ensure that any necessary additional actions are taken. The inputs to this step are estimated emotional states and responses, and the outputs are the information required for escalation. When a situation requiring escalation is identified, a rapid response procedure is triggered.

[0579] Step 6:

[0580] Finally, the server-generated response is sent to the terminal and presented to the user. This allows the user to obtain answers to their questions and problems. In this step, the input is the optimized response, and the output is the information presented to the user. To enhance user satisfaction, clear and helpful information is provided at the appropriate time.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] This invention relates to a system for streamlining internal inquiry handling within a company. This system is server-centric and provides a series of processes for handling inquiries made by employees via terminals.

[0599] The server collects pre-stored internal company information and implements a model using natural language processing technology. This model has the ability to analyze natural language inquiries entered by employees and generate appropriate responses based on their content. The server quickly processes inquiries received through terminals, accesses necessary internal company information, and generates the optimal response.

[0600] The terminal provides an interface where employees can input inquiries in natural language. For example, they might type questions about payslips or leave application procedures into a chat window. The server receives these inquiries, analyzes the context, gathers relevant information from the company's internal database, generates an answer, and returns it to the user.

[0601] Furthermore, the server uses predictive analytics to analyze past inquiry data and identify recurring problems. Based on this information, it can predict future problems and provide employees with solutions and necessary information in advance via push notifications. For example, by notifying employees in advance about "how to apply for leave," a question that frequently arises at the end of the fiscal year, the burden of inquiries can be reduced.

[0602] Furthermore, the server includes escalation mechanisms, and inquiries that the system cannot resolve automatically are escalated to the appropriate department or personnel. For example, if a technical problem is reported, it is forwarded directly to the IT support team. This process enables quick and efficient problem resolution.

[0603] This system allows employees to quickly obtain the information they need, improving the efficiency of inquiry handling and increasing employee satisfaction.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] The user enters their inquiry in natural language via their device. Specifically, they type a question such as "How do I check my payslip?" into the chat window on their device.

[0607] Step 2:

[0608] The server receives the inquiry sent from the terminal. The received text is analyzed using natural language processing technology to extract the intent of the inquiry and keywords. For example, "payslip" and "how to check" are extracted as the main keywords.

[0609] Step 3:

[0610] The server searches its internal database based on the keywords it extracts and collects relevant information. For example, the server accesses the human resources information system and retrieves information such as "payslip verification procedure."

[0611] Step 4:

[0612] Based on the information acquired by the server, the system generates the most appropriate response to the inquiry. For example, it might construct a response such as, "You can check your payslip on the intranet's 'My Page'."

[0613] Step 5:

[0614] The server sends the generated response to the user's device. The user can then view the response returned by the server in the chat window on their device.

[0615] Step 6:

[0616] The server analyzes past inquiry data to predict recurring issues. Based on these predictions, the server provides users with necessary information in advance via push notifications. For example, it might send a notification stating, "Working hours are scheduled to change next month."

[0617] Step 7:

[0618] If the server detects an inquiry it cannot resolve, it will escalate it to the appropriate department or personnel. Specifically, inquiries such as "A system error has occurred" are automatically forwarded to the IT support team.

[0619] This series of steps allows users to receive answers smoothly and enables efficient management of inquiries.

[0620] (Example 1)

[0621] 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".

[0622] In today's business environment, it is crucial to provide timely and accurate information to employees in response to the diverse inquiries they face in their daily work. However, many companies spend a significant amount of time and resources on handling inquiries, and the lack of efficient systems hinders business operations. This invention aims to improve employee satisfaction by streamlining employee inquiry handling and accelerating information provision.

[0623] 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.

[0624] In this invention, the server includes a natural language processing means that analyzes natural language queries based on accumulated information and generates relevant information based on that analysis; an escalation means that routes queries to the relevant department or person in charge based on the queries analyzed by the natural language processing means; and a predictive analysis means that analyzes past query data to predict future problems and notifies the user of necessary information in advance. This enables efficient responses to diverse inquiries from employees, facilitating smooth business operations and continuous business improvement.

[0625] "Accumulated information" refers to historical records and knowledge stored within a company or related databases, and is a collection of data used for future reference and analysis.

[0626] "Natural language processing" is a technology used by computers to understand, generate, and interact with human language. It is a means of accurately analyzing the content of inquiries and generating appropriate responses.

[0627] "Escalation" is the process of routing inquiries that require action and cannot be automatically resolved by the system to the appropriate person or department, and is a means of supporting efficient problem solving.

[0628] "Predictive analytics" is a technology that analyzes data accumulated in the past, uses the patterns derived from that data to predict future events and problems, and takes proactive measures.

[0629] "Answer generation" refers to the process of creating specific and easy-to-understand answers for users based on the analyzed inquiry content.

[0630] "Information gathering" is the process of obtaining necessary information from databases and other sources and using that information to help answer inquiries.

[0631] This invention is a system for efficiently handling customer inquiries for businesses. The system mainly consists of a server and terminals.

[0632] The server processes queries using the following technologies:

[0633] The system utilizes Python and TensorFlow libraries for natural language processing. The generative AI model is used to analyze employee inquiries and accurately understand their intent. Specifically, it focuses on analyzing question intent and extracting keywords.

[0634] The server uses database management systems such as MySQL or MongoDB to collect information based on the analysis results. This allows it to quickly retrieve the necessary relevant information and generate answers to queries.

[0635] For predictive analytics, we use the Pandas and Scikit-learn libraries to analyze past query data and predict future problem occurrences.

[0636] Data collected from the frontend is sent to the server via a web service using Flask, enabling bidirectional data communication.

[0637] The terminal provides a user interface for employees to make inquiries.

[0638] The frontend is built using React.js, allowing employees to input inquiries in natural language. In particular, input from terminals is done via a chat window.

[0639] For example, if a question such as "How do I check my payslip?" is entered into the chat window, it is sent to the server and processing begins.

[0640] Users can quickly obtain information through this system.

[0641] Employees can obtain the necessary information at any time through automated responses from the server.

[0642] If a problem cannot be resolved through automated responses, the inquiry will be forwarded to the appropriate person through an escalation mechanism, ensuring a swift resolution.

[0643] For example, if an employee types "Please tell me the procedure for applying for leave next year" at the end of the fiscal year, the server will retrieve relevant information from the database and respond with the appropriate procedure in the chat window. Furthermore, prompts such as "Create a notice regarding leave applications for employees as the fiscal year ends next week" can be input into the AI ​​model to provide advance notice.

[0644] In this way, the system of the present invention improves operational efficiency and accelerates information provision, thereby providing value to corporate operations.

[0645] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0646] Step 1:

[0647] Users enter their inquiries using their devices. Specifically, when a user types "How do I get my payslip?" into the chat window, this inquiry is sent to the server as an HTTP request. The input data is in natural language text format.

[0648] Step 2:

[0649] The server analyzes natural language text, which is the query received from the terminal. Using a generative AI model powered by TensorFlow, the server understands the content of the query and identifies its intent. The model tokenizes the text and uses a neural network to classify the intent. The output is the identified intent and associated keywords.

[0650] Step 3:

[0651] The server sends a query to the internal database based on the analysis results. It uses a database management system (MySQL or MongoDB) to retrieve information related to the query. Specifically, it queries the database for procedural information regarding "payslips" and retrieves the relevant records. The output is a collection of related information.

[0652] Step 4:

[0653] The server generates a natural language response based on the acquired information. It uses the Pandas library to format the data and create the response text. Furthermore, it uses a generative AI model to produce fluent, contextually relevant output. The output is a complete response sentence to be presented to the user.

[0654] Step 5:

[0655] The server sends the generated response to the terminal. The response is sent as JSON data in an HTTP response. The terminal receives this data and parses it to display it in the user's chat window. The displayed output is a clear answer to the user's inquiry.

[0656] Step 6:

[0657] The server escalates inquiries if the content follows past patterns or if data is insufficient. Predictive analytics are used to detect recurring inquiry problems and route them to the appropriate personnel. The output is an escalation message to the responsible person or department.

[0658] (Application Example 1)

[0659] 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".

[0660] In modern electronic transactions, diverse user inquiries and troubleshooting occur frequently, requiring service providers to respond quickly and accurately. However, traditional systems suffered from time-consuming response times and increased costs due to the prevalence of manual handling. Furthermore, insufficient preventative measures against recurring inquiries made it difficult to maintain user satisfaction.

[0661] 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.

[0662] In this invention, the server includes language processing means for analyzing requests in natural language based on accumulated information and generating relevant data; analysis means for analyzing past request data to predict future problems and notifying necessary information in advance; and means for analyzing inquiries related to electronic transactions entered by users in natural language from communication devices and presenting relevant information in real time. This enables a rapid and accurate response to user inquiries, resulting in cost-effective service provision. Furthermore, by predicting recurring inquiries and automatically notifying users in advance, improved user satisfaction can be expected.

[0663] "Accumulated information" refers to databases and records stored in the past, and is the information that a system uses to generate appropriate responses to inquiries and requests.

[0664] "Requests in natural language" refer to inquiries and requests made using the language that humans normally use, and computer systems are required to understand and analyze this language.

[0665] "Language processing means" refers to technologies and methods for analyzing natural language and converting it into a format that a computer can understand.

[0666] "Analytical methods" refer to methods and techniques for predicting future patterns and problems based on past data.

[0667] "Communication equipment" refers to terminals that possess the technology to send and receive information through a connection, and includes smartphones and computers.

[0668] "Presenting in real time" means providing relevant information immediately and without delay in response to user requests and inquiries.

[0669] "Automatic notification" refers to the system automatically sending pre-configured information to the user based on predictions and analysis.

[0670] To implement this invention, a system comprising the following components is used. The server analyzes natural language queries input by the user through language processing means. Depending on the content of the query, it retrieves appropriate information from the database and provides the user with an answer in real time. Natural language processing libraries such as TensorFlow and spaCy are used for this purpose.

[0671] Furthermore, the server uses analytical tools to analyze past query data. This allows it to predict future problems and automatically notify users in advance. A specific example of such notification is that the system can proactively inform users of solutions for certain queries that increase during the end of the year.

[0672] The device provides an interface for users to enter inquiries. This is a smartphone application developed using React Native, allowing users to easily submit inquiries in natural language. The entered information is transferred to the server and processed quickly.

[0673] The entire system is intended to communicate via APIs and function efficiently to improve the user experience. Below is an example of input to the generative AI model.

[0674] Example of a prompt:

[0675] User inquiry: "I want to change my payment method."

[0676] Information provided by the system: "Please log in to your account, select 'Settings' and then 'Payment Methods', and register a new payment method."

[0677] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0678] Step 1:

[0679] The terminal receives queries entered by the user in natural language. When the user enters a question into the application interface, the terminal prepares to send the content to the server. At this point, the input is the user's natural language input, and the output is the data sent directly to the server.

[0680] Step 2:

[0681] The server analyzes the user's query using natural language processing tools. The input is natural language text, and semantic analysis and keyword extraction are performed using natural language processing techniques (e.g., TensorFlow or spaCy). The output is structured data that reflects the intent of the query.

[0682] Step 3:

[0683] Based on the analysis results, the server retrieves relevant information from the company's internal database. The input is the structured data obtained in the previous step, and an SQL query is generated based on it and sent to the database. As output, the server prepares information related to the user's inquiry.

[0684] Step 4:

[0685] The server generates a response to the user based on the acquired information. The input is raw data retrieved from a database, and a generative AI model is used to form a response in natural language. The output is formatted text for the user to respond to.

[0686] Step 5:

[0687] The server sends the generated response back to the terminal. At this point, the input is the generated text, and the output is displayed on the terminal in a format that the user can read. The terminal then displays this information on the user's screen.

[0688] Step 6:

[0689] The server records the query content and its results in a database. The input is the entire query process information, stored in the database, and used for future predictive analytics. This allows for the detection of recurring query patterns and the accumulation of foundational data for proactive notification as prompt messages.

[0690] 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.

[0691] This invention relates to a system that streamlines internal inquiry handling while utilizing user sentiment analysis to provide more effective responses. This system is server-centric and processes user inquiries using natural language processing capabilities that incorporate a sentiment engine.

[0692] The server collects pre-stored internal company information and uses a model that implements natural language processing technology. This model has the ability to analyze natural language queries entered by users via terminals and simultaneously grasp the content of those queries and the user's emotions. The server quickly processes the text received from the terminal and recognizes the user's emotions using an emotion engine. For example, if a user expresses dissatisfaction regarding their salary, the server can detect feelings of frustration and dissatisfaction.

[0693] The emotion engine extracts emotional information from the user's text and uses that information to adjust the feedback and escalation methods provided by the server. The server then presents a response to the terminal that is appropriate to the user's emotions. Specifically, if the emotion engine detects "dissatisfaction," the server will take steps to improve user satisfaction, such as including a follow-up suggestion like, "Please contact HR if you need further explanation."

[0694] Furthermore, the server uses predictive analytics to analyze past inquiry data and user sentiment information to predict potential problems in the future. Based on these predictions, it can proactively provide users with appropriate information and solutions via push notifications. For example, it can proactively alert all employees based on the timing when a particular sentiment pattern is detected frequently.

[0695] Furthermore, for issues that are difficult to resolve, the server automatically uses escalation mechanisms to forward inquiries to the appropriate department or person based on the emotional analysis results. For example, if the emotional engine detects the emotion of "anger," it can quickly forward the inquiry to the customer support team.

[0696] This system allows employees to receive prompt and appropriate information that is sensitive to their feelings, streamlines inquiry handling, and is expected to further improve employee satisfaction.

[0697] The following describes the processing flow.

[0698] Step 1:

[0699] The user enters their inquiry in natural language using their device. The user enters their question or request as specific text in the chat window.

[0700] Step 2:

[0701] The server analyzes the query received from the terminal. The server uses natural language processing techniques to extract the query's intent and key keywords.

[0702] Step 3:

[0703] The server uses an emotion engine to analyze the text extracted from the inquiry and determine the user's emotional state. For example, the emotion engine can recognize emotions such as "dissatisfaction" or "frustration" from the input text.

[0704] Step 4:

[0705] The server searches its internal database for information related to the query and generates the optimal response. The response is constructed to include adjustments based on the user's emotional state.

[0706] Step 5:

[0707] The server generates a response, sends it to the terminal, and provides it to the user. By showing the user explanations that include emotional considerations and follow-up suggestions, a highly satisfactory response is achieved.

[0708] Step 6:

[0709] The server analyzes past query history and sentiment data to predict future issues and trends. If a specific sentiment pattern is increasing, it prepares to send a pre-notification.

[0710] Step 7:

[0711] The server automatically escalates inquiries it cannot resolve to the appropriate department or person. It considers the results of the sentiment engine to ensure quick and appropriate escalation.

[0712] This process makes customer inquiries more effective and personal, improving the employee experience.

[0713] (Example 2)

[0714] 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".

[0715] Conventional inquiry processing systems were inadequate in responding to user inquiries and failed to provide effective feedback that took emotions into consideration. Furthermore, the lack of means to predict future problems and take appropriate preventative measures made it difficult to provide a highly satisfactory service.

[0716] 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.

[0717] In this invention, the server includes language processing means for analyzing inquiries based on stored information sources and generating relevant information, sentiment analysis means for simultaneously analyzing the inquiry content and sentiment analyzed by the language processing means to generate optimal feedback, and escalation means for forwarding inquiries to the relevant department or person in charge based on the analyzed inquiry. This enables the provision of sentiment-sensitive responses and problem-solving based on predictions.

[0718] A "language processing means" is a means of analyzing queries in natural language form from accumulated information and generating related information.

[0719] "Emotional analysis means" refers to a method for simultaneously analyzing the user's emotions from the analyzed inquiry content and providing optimal feedback.

[0720] An "escalation mechanism" is a means of forwarding an inquiry to the appropriate department or person based on the analyzed inquiry.

[0721] A "predictive provision method" is a means of using past data to predict future problems and providing necessary information in advance.

[0722] This invention provides a system to streamline internal inquiry handling and analyze user emotions to provide more effective responses. The system is server-centric and built using natural language processing technology to enable emotion analysis.

[0723] The server collects accumulated information from a database and uses a natural language processing (NLP) engine to analyze queries based on this information. This NLP engine has text analysis skills and extracts the content of the query and important keywords. The analyzed information is then sent to an emotion engine, which is used to identify the user's sentiment.

[0724] The server generates feedback tailored to the user's emotions based on emotional information extracted by the emotion engine, and provides it to the user via the terminal. This process is rapid, taking into account both the user's inquiry and their emotions to enable appropriate feedback. For example, if a user expresses dissatisfaction about a delayed salary payment, the server will generate feedback such as, "We apologize for the inconvenience. Please contact Human Resources for further details."

[0725] Furthermore, the server can use predictive means to analyze past inquiry data and sentiment data to predict future problems and notify users of countermeasures in advance. This prediction allows for early warnings to all employees if a large number of sentiment patterns are detected at a particular time.

[0726] The system also incorporates escalation mechanisms, ensuring that complex issues or inquiries expressing strong emotions such as anger are promptly forwarded to the appropriate department or person in charge. This design allows users to receive timely and accurate information while being sensitive to their emotions, resulting in more efficient inquiry handling and improved employee satisfaction.

[0727] An example of a prompt might be: "Generate a prompt that analyzes the user's inquiry, analyzes their sentiment, and generates appropriate feedback. For example, if the user is expressing dissatisfaction with their salary, indicate what kind of feedback would be appropriate."

[0728] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0729] Step 1:

[0730] The server receives the user's query text from the terminal. The input is the natural language query entered by the user using the terminal, and the output is the received text data. This text data is then prepared for the next parsing step.

[0731] Step 2:

[0732] The server activates a natural language processing (NLP) engine to analyze the query text. The input is the text data received in step 1, and the output is data containing keywords and main themes extracted from the query. Specifically, the NLP engine analyzes the linguistic structure of the text and identifies important words such as "salary" and "payment delay."

[0733] Step 3:

[0734] The server uses an emotion engine to perform sentiment analysis on the query text. The input is analysis data from an NLP engine, and the output is a label or indicator representing the user's emotion (e.g., "dissatisfied," "frustrated"). Specifically, it scrutinizes the textual expression and implements an algorithm to identify the user's emotional state.

[0735] Step 4:

[0736] The server generates feedback based on extracted keywords and sentiment data. The input is the output data from steps 2 and 3, and the output is the response message provided to the user. The generated feedback includes language that is sensitive to the user's feelings, and a message such as "We apologize for the inconvenience. Please contact Human Resources if you would like more information" is created.

[0737] Step 5:

[0738] The server automatically forwards inquiries requiring escalation to the appropriate department or person in charge. The input is data indicating emotions such as "anger" or other strong emotions, and the output is the escalated inquiry information. Specifically, the system immediately sends the information to the appropriate department's contact based on the emotion assessment.

[0739] Step 6:

[0740] The server analyzes past query data to make future predictions. The input is historical query data, and the output is a list of predicted problems and their solutions. This allows for proactive notifications to be sent to employees when specific emotional patterns are frequently detected.

[0741] (Application Example 2)

[0742] 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".

[0743] In modern organizations, there is a demand for prompt and appropriate handling of customer inquiries and complaints. However, traditional systems often have limitations, such as their mechanical nature and insufficient empathy for the customer's feelings. Furthermore, balancing problem prediction using historical data with human-centered responses is difficult, hindering improvements in customer satisfaction. There is a need to overcome these challenges and achieve a higher level of customer service.

[0744] 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.

[0745] In this invention, the server includes a natural language analysis means that analyzes natural language queries based on accumulated internal organizational information, a predictive analysis means that analyzes past query records to predict future problems, and an emotional analysis means that analyzes the user's emotional information and reflects it in the response. This enables more appropriate and prompt responses that are attentive to the customer's emotions.

[0746] "Natural language processing" refers to a technology that analyzes natural language queries based on accumulated internal organizational information and understands their content.

[0747] An "escalation mechanism" is a function that, based on an analyzed inquiry, quickly transfers information to the appropriate department or person in charge to facilitate a response.

[0748] "Predictive analysis means" refers to technology that predicts potential problems that may occur in the future based on past inquiry records and provides necessary advance notice.

[0749] An "emotional analysis tool" is a means of analyzing a user's inquiry to understand their emotional state and reflecting that information in the response.

[0750] A "response optimization system" is a system that improves customer service by detecting a specific emotional state and generating a response appropriate to that state.

[0751] "Speech processing means" refers to technology that processes speech input in real time and converts speech into text.

[0752] An "emotion estimation method" is a system that analyzes a user's biometric information and calculates the optimal response to improve customer satisfaction.

[0753] The system for realizing this invention consists of a server and user terminals. The server implements natural language processing technology that performs natural language analysis based on accumulated internal organizational information. Specifically, it deploys a natural language analysis means that analyzes inquiry content using the Transformer technology of the natural language processing library Hugging Face. The analyzed content is promptly addressed through an escalation means that routes it to the relevant department or person in charge.

[0754] Furthermore, the server is equipped with predictive analytics means to predict future problems based on past query records. This makes it possible to predict potential future problems in advance and notify relevant parties beforehand. In addition, an emotional analysis means is implemented to capture user emotional information and reflect that information in the response. For example, if dissatisfaction is detected from a user's query, that information is used to provide appropriate follow-up through the response optimization means.

[0755] The device implements speech processing capabilities that process voice input in real time and convert it to text using the Google Cloud Speech-to-Text API, among others. To more accurately understand the user's emotions, an emotion estimation mechanism works in conjunction with the server to estimate the user's emotions from text and biometric information. This information is analyzed by a generative AI model and used as prompt text.

[0756] As a concrete example, by generating a prompt message such as, "The customer appears to be having trouble because their product hasn't arrived. Please respond kindly and propose a concrete solution," the optimal response can be constructed. This allows for a response that better matches the user's needs, contributing to an overall improvement in customer satisfaction.

[0757] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0758] Step 1:

[0759] The user provides voice input through the device. The device uses the Google Cloud Speech-to-Text API to convert the speech to text. In this step, the voice data is input and the text data is output. This text data serves as the basis for subsequent processing.

[0760] Step 2:

[0761] The server receives text data sent from the terminal. Next, to perform natural language processing, it uses the Hugging Face Transformer model to analyze the query and extract the necessary information. The input for this step is text data from the terminal, and the output is the analyzed query. Here, the linguistic patterns of the text data are analyzed and key information is extracted.

[0762] Step 3:

[0763] The server uses emotion analysis tools to estimate the user's emotional state from the analyzed text. This process involves applying a data model for understanding emotions and analyzing emotional patterns. The input to this step is the analyzed query, and the output is the estimated emotional state. Specifically, this step estimates emotions by measuring emotional patterns using emotion indicators within the text.

[0764] Step 4:

[0765] The server generates an appropriate response through response optimization means based on the estimated emotional state. It utilizes a generative AI model to output the most appropriate response based on the prompt. In this step, the estimated emotional state is the input, and the output is the optimized response. The generative AI model is used to select the best response from multiple candidates, preparing a response that meets the user's needs.

[0766] Step 5:

[0767] The server uses escalation mechanisms to notify the appropriate department or person in charge, depending on the situation. This facilitates coordination to ensure that any necessary additional actions are taken. The inputs to this step are estimated emotional states and responses, and the outputs are the information required for escalation. When a situation requiring escalation is identified, a rapid response procedure is triggered.

[0768] Step 6:

[0769] Finally, the server-generated response is sent to the terminal and presented to the user. This allows the user to obtain answers to their questions and problems. In this step, the input is the optimized response, and the output is the information presented to the user. To enhance user satisfaction, clear and helpful information is provided at the appropriate time.

[0770] 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.

[0771] 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.

[0772] 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 robot 414.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] The following is further disclosed regarding the embodiments described above.

[0792] (Claim 1)

[0793] A natural language processing system for analyzing human-generated natural language queries based on accumulated internal company information and generating relevant information,

[0794] An escalation means that escalates inquiries to the relevant department or personnel based on the queries analyzed by the aforementioned natural language processing means,

[0795] A predictive analytics tool that analyzes past inquiry data to predict future problems and notifies users of necessary information in advance,

[0796] A system that generates the optimal response to an inquiry from an employee using the means provided by the server.

[0797] (Claim 2)

[0798] The system according to claim 1, characterized by generating rapid responses to inquiries using natural language processing technology and improving accuracy by collecting information from an internal database.

[0799] (Claim 3)

[0800] The system according to claim 1, characterized in that it provides a means to detect recurring problems and resolve them in advance through predictive analysis based on past inquiry history.

[0801] "Example 1"

[0802] (Claim 1)

[0803] A natural language processing means that analyzes natural language queries based on accumulated information and generates related information based on that analysis,

[0804] An escalation means that, based on the query analyzed by the aforementioned natural language processing means, distributes the inquiry to the relevant department or person in charge.

[0805] A predictive analytics tool that analyzes past inquiry data to predict future problems and notifies users of necessary information in advance,

[0806] A response generation means that generates the optimal response based on the information to be processed and presents it to the user through an output device,

[0807] An information gathering method that analyzes the content of the inquiry and retrieves relevant information from the database,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, characterized by using an implemented model to generate rapid responses to inquiries and improving accuracy by collecting data from information sources.

[0811] (Claim 3)

[0812] The system according to claim 1, characterized in that it provides a means to detect recurring problems and resolve them in advance by analyzing past inquiry history.

[0813] "Application Example 1"

[0814] (Claim 1)

[0815] A language processing means for analyzing requests in natural language based on accumulated information and generating related data,

[0816] A means for escalating requests to the relevant department or individual based on the requests analyzed by the language processing means,

[0817] An analytical tool that analyzes past request data to predict future problems and notifies users of necessary information in advance,

[0818] A means for analyzing inquiries related to electronic transactions entered by users in natural language from communication devices and for presenting relevant information in real time,

[0819] A computing device that includes a function to predict recurring inquiries and automatically notify them in advance,

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, characterized by generating rapid responses to inquiries using language processing technology and improving accuracy by collecting information from a data storage device.

[0823] (Claim 3)

[0824] The system according to claim 1, characterized in that it provides a means to detect recurring problems and resolve them in advance by analyzing past request history.

[0825] "Example 2 of combining an emotion engine"

[0826] (Claim 1)

[0827] A language processing means for analyzing queries based on accumulated information sources and generating relevant information,

[0828] A sentiment analysis means that simultaneously analyzes the query content and emotions analyzed by the language processing means to generate optimal feedback,

[0829] An escalation mechanism that forwards inquiries to the relevant department or person based on the analyzed query,

[0830] A predictive means that uses past data to predict future problems and provides necessary information in advance,

[0831] A system that generates the optimal response to an inquiry using the means provided by the server.

[0832] (Claim 2)

[0833] The system according to claim 1, characterized by generating a rapid and sentiment-responsive response to a query using language analysis technology and improving accuracy using information from a database.

[0834] (Claim 3)

[0835] The system according to claim 1, characterized in that it identifies recurring problems in advance and provides means to resolve them through predictive analysis based on past inquiry history and sentiment information.

[0836] "Application example 2 when combining with an emotional engine"

[0837] (Claim 1)

[0838] A natural language processing method for analyzing natural language queries based on accumulated internal organizational information and generating relevant information,

[0839] An escalation means that escalates inquiries to the relevant department or person in charge based on the inquiries analyzed by the aforementioned natural language processing means,

[0840] A predictive analysis tool that analyzes past inquiry records to predict future problems and notifies users of necessary information in advance,

[0841] An emotional analysis means that analyzes the user's emotional information and reflects it in the response content,

[0842] The emotion analysis means detects a specific emotional state and the response optimization means generates a response corresponding to that state,

[0843] A speech processing means that processes speech input in real time and converts it to text,

[0844] An emotion estimation method that calculates responses that improve customer satisfaction from biometric information,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, characterized by generating rapid responses to queries using natural language processing technology and improving accuracy by collecting information from an internal database.

[0848] (Claim 3)

[0849] The system according to claim 1, characterized in that it provides a means to detect recurring problems and resolve them in advance through predictive analysis based on past inquiry history. [Explanation of Symbols]

[0850] 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 language processing means for analyzing requests in natural language based on accumulated information and generating related data, A means for escalating requests to the relevant department or individual based on the requests analyzed by the language processing means, An analytical tool that analyzes past request data to predict future problems and notifies users of necessary information in advance, A means for analyzing inquiries related to electronic transactions entered by users in natural language from communication devices and for presenting relevant information in real time, A computing device that includes a function to predict recurring inquiries and automatically notify them in advance, A system that includes this.

2. The system according to claim 1, characterized by generating rapid responses to inquiries using language processing technology and improving accuracy by collecting information from a data storage device.

3. The system according to claim 1, characterized in that it provides a means to detect recurring problems and resolve them in advance by analyzing past request history.

Images