system

Abstract

We provide the system. [Solution] Information processing means for receiving inquiry information from users, A response generation means that analyzes the aforementioned inquiry information and generates a response based on its content, A communication means for sending the generated response to the user, A distribution means for identifying inquiries related to a specific service and distributing those inquiries to the appropriate personnel, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional customer support system, all general inquiries are handled by staff, resulting in a problem of heavy workload. In addition, due to insufficient support, user satisfaction may decrease. In particular, in a specific area, there is a problem that it is difficult to provide prompt and detailed support because no staff is physically located there.

Means for Solving the Problems

[0005] This invention provides a system that receives inquiry information from users, generates a response based on its content using a generation AI, and sends it to the user. This system includes a function to automatically route inquiries related to specific services to the appropriate personnel, thereby reducing workload and enabling rapid responses. Furthermore, by employing a feedback learning method that collects feedback information and improves the accuracy of response generation, user satisfaction can be further enhanced.

[0006] "Information processing means" refers to a device or module for receiving inquiry information transmitted by a user and performing appropriate processing.

[0007] A "response generation means" is a device or module that analyzes received inquiry information and generates an appropriate response based on its content.

[0008] "Communication means" refers to a device or module for transmitting the generated response to the user.

[0009] A "sorting device" is a device or module that identifies inquiries related to a specific service and, if necessary, automatically sends those inquiries to the appropriate personnel.

[0010] A "support tool" is a device or module used by a business representative to respond to specific inquiries assigned to them and to provide additional information or support.

[0011] A "feedback learning device" is a device or module that collects feedback information from users and uses that information as learning data to improve the performance of a response generation device. [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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0015] In the following embodiments, a processor with a reference numeral (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, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral 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, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable 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] The system of this invention enables users to make inquiries through an online contact point. This system responds to user requests by analyzing received inquiries, generating appropriate responses, and sending them back. It also has a function to automatically route inquiries that are deemed necessary by the business staff.

[0034] This system consists of multiple components. It primarily includes information processing means, response generation means, communication means, sorting means, support means, and feedback learning means. The detailed configuration is as follows:

[0035] The server receives inquiries from users and processes their content using information processing tools.

[0036] The server analyzes the key keywords in the query and generates an appropriate response using a response generation system. This response is generated using natural language processing and is in a format that is easy for the user to understand.

[0037] Once a response is generated, the server sends that response to the user via the communication means.

[0038] If the inquiry concerns a specific service or is complex, the server uses a routing mechanism to automatically assign the inquiry to the appropriate person.

[0039] The terminal processes the assigned inquiries and, if necessary, allows business personnel to provide additional support directly using support tools.

[0040] The server collects feedback information from users and uses it to improve the response generation system through feedback learning. This process improves the overall response accuracy of the system.

[0041] Specific example

[0042] For example, if a user submits an inquiry through the online system stating, "I want to change my data plan," the server receives this inquiry. The information processing system recognizes the key phrase "data plan," and the response generation system generates a response such as, "You can change your data plan online or in-store. Would you like to be connected to a representative near you for detailed instructions?" This response is then sent to the user via the communication system. If necessary, this inquiry is automatically routed to a terminal, allowing a business representative to provide specific assistance.

[0043] Thus, the present invention offers the advantages of enabling users to receive prompt and accurate support, as well as reducing the burden on those responsible for operations.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user enters their question through an online interface and submits it.

[0047] Step 2:

[0048] The server receives query data from users, formats that data, and performs basic consistency checks.

[0049] Step 3:

[0050] The server passes the received query to a natural language processing engine, which analyzes important keywords and sentence structure.

[0051] Step 4:

[0052] Based on the analysis results, the server generates an appropriate response using a response generation mechanism. The response is combined with information templates as needed and formatted into a user-friendly format.

[0053] Step 5:

[0054] The server sends the generated response to the user via a communication method.

[0055] Step 6:

[0056] The server classifies the inquiry content and determines whether it is a general inquiry or an inquiry related to a specific service.

[0057] Step 7:

[0058] If the server determines that an inquiry is related to a specific service, it uses a routing mechanism to automatically assign the inquiry to a terminal.

[0059] Step 8:

[0060] The terminal notifies the business representative of the inquiry, and the business representative provides support to the user directly as needed.

[0061] Step 9:

[0062] The server collects user feedback and uses feedback learning mechanisms to improve the response generation algorithm. This process contributes to improving the overall system performance.

[0063] (Example 1)

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

[0065] The challenge lies in providing prompt and accurate responses to a wide range of online user inquiries while simultaneously reducing the burden on employees and continuously improving the overall accuracy of responses.

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

[0067] In this invention, the server includes information processing means for receiving inquiry information from a user, natural language processing means for analyzing the inquiry information and generating a response based on its content, and data transmission means for sending the generated response to the user. This makes it possible to respond to inquiries quickly.

[0068] "Information processing means" refers to a device or program that has the function of organizing and analyzing inquiry information received from a user.

[0069] "Natural language processing means" refers to a device or program that uses natural language processing technology to generate an appropriate response based on query information.

[0070] "Data transmission means" refers to a device or program that has a communication function for transmitting the generated response to the user.

[0071] "Inquiry management means" refers to a device or program that has the function of identifying inquiries related to a specific task and assigning said inquiries to the appropriate person performing the task.

[0072] A "data adaptation means" is a device or program that has the function of using feedback information collected from users as learning data to improve response generation capabilities.

[0073] "Support execution means" refers to a device or program that has the function of providing additional information or support in response to specific inquiries assigned to employees.

[0074] This invention provides a system that receives user inquiries through an online contact point and processes them quickly and appropriately. The system primarily operates with a server, utilizing information processing means, natural language processing means, data transmission means, inquiry management means, and data adaptation means.

[0075] The server uses information processing tools when receiving inquiries from users. The data of the received inquiries is stored on the server, and natural language processing libraries (e.g., NLTK and spaCy) are utilized. This allows for the analysis of the input text, including tokenization of important terms and syntactic analysis. Furthermore, a generative AI model (e.g., GPT-3®) is used as a natural language processing tool to generate an appropriate response based on the prompt. A specific example of a prompt is, "Please explain how to easily change the data plan using the online system."

[0076] The generated response is sent to the user by the server's data transmission mechanism. The data transmission mechanism uses the HTTP protocol and returns the response via the client-side user interface.

[0077] Furthermore, if the inquiry relates to a specific task, the server uses an inquiry management system to assign the inquiry to the appropriate person in charge of that task. The person in charge can then use their terminal to provide additional information and support to the user through specific software (e.g., a CRM system).

[0078] The server uses user feedback as a data adaptation tool and leverages it to improve response generation. This continuously improves the overall accuracy and efficiency of the system.

[0079] This configuration allows the system to respond promptly to diverse user needs, reduce the burden on employees, and maintain a high level of response quality.

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

[0081] Step 1:

[0082] Users enter and submit inquiries through an online form. The input is in the form of natural language questions. The data entered by the user is sent to the server as an HTTP request.

[0083] Step 2:

[0084] The server analyzes the query received from the user using information processing tools. At this stage, the received query data is converted into tokens, and part-of-speech tagging and syntactic analysis are performed using a natural language processing library. As a result of the analysis, important words and phrases are extracted, which become the input for the next response generation process.

[0085] Step 3:

[0086] The server uses natural language processing techniques based on the analyzed data to generate responses via a generative AI model. Specifically, it inputs data, including prompts, into a model such as GPT-3, and generates responses accordingly. The output responses are temporarily stored on the server as a reply to the user.

[0087] Step 4:

[0088] The server sends the generated response to the user using a data transmission method. Here, the response data is sent back to the user's device via an HTTP response. The user can instantly view this response on their device.

[0089] Step 5:

[0090] When an inquiry related to a specific task arises, the server uses an inquiry management system to assign the inquiry to the appropriate person in charge. The management system analyzes the content of the inquiry, identifies the person or team to whom it can be assigned, and notifies the person in charge of that information on their terminal.

[0091] Step 6:

[0092] The terminal provides additional information and support to business users through business software such as CRM systems in response to inquiries received by business personnel. This allows business personnel to respond directly to users as needed.

[0093] Step 7:

[0094] During the feedback phase, the server receives post-use feedback information from users and uses it to improve the response generation system through data adaptation mechanisms. The feedback obtained in this process is utilized as training data for the generation AI model, improving the overall response accuracy of the system.

[0095] (Application Example 1)

[0096] 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."

[0097] Responding to customer inquiries in online stores requires prompt and accurate responses. However, the large number of inquiries regarding purchasing procedures, return procedures, and delivery status increases the burden on staff, leading to delays and incorrect answers. This can result in decreased customer satisfaction and negatively impact the store's credibility.

[0098] 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.

[0099] In this invention, the server includes information processing means for receiving inquiry information from users, natural language generation means for analyzing the inquiry information and generating a response based on its content, and communication means for transmitting the generated response to the user. This enables the automatic processing of inquiries regarding purchasing procedures, return procedures, and delivery status confirmation procedures, reducing the burden on business staff and providing users with prompt and accurate support.

[0100] "Information processing means" refers to a device or program that has the function of collecting and analyzing inquiry information received from users.

[0101] A "natural language generation means" is a program or device that generates a response in a format easily understood by the user, based on analyzed query information.

[0102] "Communication means" refers to a device or program that uses a network interface or protocol to transmit a generated response to a user.

[0103] A "distribution tool" is a program or device that has the function of automatically identifying inquiries related to a specific task and assigning them to the person in charge of that task.

[0104] A "feedback learning method" is a program or device that collects evaluation information from users and uses it to improve the performance of a natural language generation method.

[0105] To implement this invention, several important functions must be implemented on the server. First, the server utilizes information processing means via an API to receive user inquiry information. For example, the Flask framework in Python can be used for this processing. The received inquiry information is parsed using the Google® Cloud Natural Language API to extract important words and intents.

[0106] Next, as a means of natural language generation, a generative AI model such as OpenAI's GPT-3 is used to generate appropriate responses based on the extracted key words. These generated responses are then adjusted to be in a format that is easy for the user to understand.

[0107] The generated response is sent to the user's device via a communication method. This involves forwarding the response via a RESTful API so that it can be received on the user's smartphone or other device. If the user asks, "I want to know the delivery status," the system will immediately respond with something like, "Your current estimated delivery date is tomorrow."

[0108] Furthermore, feedback learning mechanisms allow the server to collect evaluation information from users. This evaluation is used to adjust the generative model to improve the overall system performance. In this process, a database can be built on the cloud to store the evaluation information as data records.

[0109] As a concrete example, in response to the inquiry, "Is it possible to exchange this product?", the model generates a response with the prompt, "If unused, it can be exchanged at your nearest store." An example of a prompt statement is expressed as follows: "Generate a simple Japanese response to the following inquiry: 'Is it possible to exchange this product?'" Automatic generation of such responses enables quick and accurate responses to customers.

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

[0111] Step 1:

[0112] Users enter their inquiries via their smartphones. This input is sent to the server via a RESTful API. The input data consists of text data of the user's question.

[0113] Step 2:

[0114] The server analyzes the received query information using the Google Cloud Natural Language API. During the analysis process, it extracts important keywords and intent from the query. This process outputs the keywords and context necessary for generating a response from the input text data.

[0115] Step 3:

[0116] The server sends a prompt message to the generative AI model, GPT-3, based on the extracted key keywords. This prompt message contains specific instructions related to the user's inquiry. The generative AI model then generates appropriate response data based on this prompt message.

[0117] Step 4:

[0118] The server analyzes the response data received from GPT-3 and processes it into a user-friendly response format. This processing transforms the text generated by the AI ​​model into an optimized natural language response.

[0119] Step 5:

[0120] The server sends a formatted response to the user's terminal via a communication method. The user's terminal receives this response and displays it as the answer to the query. This allows the user to immediately verify the information provided in the response.

[0121] Step 6:

[0122] Once the interaction is complete, the server collects user feedback and saves it as data for retraining using a feedback learning mechanism. This saved data is then used in a feedback loop to improve the response accuracy of the generated AI model.

[0123] 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.

[0124] The system of this invention is equipped with an advanced response generation function that combines an emotion engine to provide appropriate responses to user inquiries. This allows the system to provide more human-like responses while considering the user's emotions. The system mainly consists of the following elements.

[0125] The server receives inquiry information from users and performs initial analysis through information processing tools. During this process, user sentiment data sent along with the inquiry is also collected.

[0126] The emotion engine analyzes this emotional data to recognize what emotions the user is experiencing. For example, emotions such as "anger," "joy," and "anxiety" may be identified.

[0127] The server adjusts its response generation mechanisms based on the recognized emotions, generating a response that aligns with the user's feelings. This response not only conveys facts but also includes nuances that reflect an understanding of the user's emotions.

[0128] The server sends the generated response to the user via communication means. Emotionally responsive responses demonstrate understanding and consideration for the user, and have the effect of improving satisfaction.

[0129] When an inquiry regarding a specific service is received, the server uses a routing mechanism to assign it to the appropriate person in charge. If the user's emotional state is, for example, "anxiety," the server can assign the inquiry to a person capable of providing appropriate support.

[0130] On the terminal, the assigned staff member can receive details of the assigned inquiry and provide further support tailored to the user's feelings.

[0131] The server uses feedback learning to collect feedback from users and improve the performance of the response generation means and the emotion engine. This feedback increases the accuracy of emotion recognition and the sophistication of responses.

[0132] Specific example

[0133] For example, if a user inquires, "I'm worried because I missed the payment deadline," the server might not simply respond with a businesslike "Here's how to pay," but rather, through its emotional engine, provide a more empathetic response such as, "Don't worry. You can proceed with these steps and use the service with peace of mind." This can give users a greater sense of security and increase their trust in the system.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] Users enter and submit inquiries through an online customer service interface. In this process, the user's input may include elements that express emotion (e.g., language choice or emojis).

[0137] Step 2:

[0138] The server receives query data from the user, formats the data, and performs basic integrity checks.

[0139] Step 3:

[0140] The server passes the received query to a natural language processing engine for linguistic analysis. This analysis identifies important words and sentence structures.

[0141] Step 4:

[0142] The server uses an emotion engine to recognize the user's emotions from the wording and emojis included in the query data. In this step, specific emotions such as "anger," "joy," and "anxiety" are extracted.

[0143] Step 5:

[0144] Based on the analyzed content and recognized emotions, the server generates an appropriate response using a response generation mechanism. The response will be tailored to the user's emotions.

[0145] Step 6:

[0146] The server sends the generated response to the user via a communication method. The sent response will have nuances that take emotions into consideration and will be tailored to the user's needs.

[0147] Step 7:

[0148] If the inquiry is related to a specific service, the server uses a routing mechanism to automatically route the inquiry to the appropriate person in charge, taking into consideration the perceived emotions.

[0149] Step 8:

[0150] The terminal notifies the business person of the inquiry that has been routed to them, and the business person provides feedback and additional support while keeping the user's feelings in mind.

[0151] Step 9:

[0152] The server collects user feedback and uses that feedback to improve the performance of its response generation methods and emotion engine. This improves the overall response accuracy and emotion recognition capabilities of the system.

[0153] (Example 2)

[0154] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0155] This invention aims to solve the problem of needing to understand and respond to users' emotions, rather than simply providing administrative responses, when communicating with users. Conventional systems have struggled to respond in a way that considers user emotions, leading to decreased satisfaction. Furthermore, there is a need to improve the quality of responses from business personnel to routed inquiries.

[0156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0157] In this invention, the server includes information processing means for receiving inquiry information and emotion data from a user, response generation means using a generative AI model that analyzes the inquiry information and emotion data and generates a response based on the user's emotions, and communication means for transmitting the generated response to the user. This makes it possible to improve the quality of communication and increase user satisfaction by providing responses that include nuances that take into account the user's emotions. Furthermore, it enables appropriate responses based on the user's emotion data for business personnel, thereby improving the quality of service.

[0158] An "information processing device" is a device equipped with the function of receiving inquiry information and sentiment data transmitted by users and performing initial analysis of this data.

[0159] A "generative AI model" is an artificial intelligence program used to generate appropriate and emotionally resonant responses based on user inquiry information and sentiment data.

[0160] A "response generation means" is a means that has the function of generating a response to be provided to the user from analyzed data using a generation AI model.

[0161] "Communication means" refers to a device or method for quickly and effectively transmitting a generated response to a user.

[0162] A "distribution means" is a device or method that has the function of identifying inquiries related to a specific task and distributing those inquiries to the appropriate person in charge of that task.

[0163] "Display means" refers to a visual display device or method for a business person to confirm the details of an assigned inquiry.

[0164] A "feedback learning means" is a device or method for analyzing feedback information received from a user and improving the performance of a generated AI model and a response generation means based on the results.

[0165] This invention provides a system that enables more humane responses to user inquiries. It focuses on effectively processing user inquiry information and emotional data, and generating appropriate responses based on that information.

[0166] In this system, the server functions as an information processing unit, receiving inquiry information and emotion data sent by the user. The received data is then sent to a response generation unit that uses a generative AI model to generate a response tailored to the user's specific emotions and situation. The generative AI model incorporates an emotion analysis algorithm, which allows for the accurate identification of emotions such as "worry" and "joy."

[0167] The generated response is sent from the server to the user via a communication method. The user can receive a warm, considerate response that takes their emotions into account, rather than simply providing purely businesslike information.

[0168] For inquiries related to specific tasks, the server uses a routing mechanism to assign them to the appropriate person in charge. The person in charge then reviews the inquiry details on their terminal and provides support based on analyzed sentiment data. This leads to improved information provision and increased customer satisfaction.

[0169] Furthermore, the server utilizes feedback learning mechanisms to analyze feedback information obtained from users, continuously improving the performance of its generative AI models and response generation methods. This feedback loop ensures that the system is constantly optimized, enabling it to continuously provide responses tailored to user needs.

[0170] For example, if a user inquires, "I'm worried about late fees," the server can perform sentiment analysis and generate a reassuring response that reflects that anxiety. An example of a prompt would be to input a command to the AI ​​model, such as "Generate a response that is empathetic to the user's emotions," which helps the system create a desirable response.

[0171] As described above, the present invention provides specific methods and means for understanding the emotions of users and providing responses that are appropriate to them.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] Users submit inquiries to the system. This input includes text data of the question or request, and, if possible, metadata indicating the user's sentiment. This data is fundamental information for accurately performing subsequent processing within the system.

[0175] Step 2:

[0176] The server receives this query information and sentiment data using information processing tools. The received data is stored in a database. The specific actions performed here are to standardize the data format and prepare the sentiment data for analysis. This input data becomes the material for sentiment analysis and response generation.

[0177] Step 3:

[0178] The server sends query information and sentiment data to the sentiment engine for analysis. The sentiment engine uses natural language processing techniques to identify emotions and outputs labels such as "joy" or "anxiety." The process involves detecting keywords in the text and determining emotions based on the context. This result becomes the data needed to generate the response in the next step.

[0179] Step 4:

[0180] The server uses a generative AI model to generate responses based on analyzed sentiment data. Specifically, it constructs sentences by combining appropriate phrases and expressions based on templates corresponding to sentiment labels. This output is the response text sent back to the user.

[0181] Step 5:

[0182] The server sends the generated response to the user via a communication method. This output is designed to include a more human-like response. Specifically, it delivers text data to the user's device using a data communication protocol.

[0183] Step 6:

[0184] The server receives and analyzes user feedback for feedback learning. A key function here is to store the received feedback as training data and use it to improve the accuracy of the generated AI model. The output results are data that will contribute to improving future response quality.

[0185] (Application Example 2)

[0186] 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".

[0187] Conventional response systems failed to adequately consider user emotions, resulting in uniform and impersonal responses. Furthermore, even assigned staff struggled to provide emotionally responsive responses, highlighting the need for improved user experience. Additionally, there was a lack of mechanisms to continuously improve the overall system performance by fully utilizing feedback.

[0188] 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.

[0189] In this invention, the server includes information processing means for receiving user inquiry information, response generation means for analyzing the inquiry information and generating a response based on its content, and emotion recognition means for analyzing the user's emotion data and generating a response based on that emotion. This enables more human-like responses. Furthermore, by including communication means for transmitting the generated response to the user, and distribution means for identifying inquiries related to a specific service and distributing the inquiry to a business person, business people can provide appropriate support in accordance with the user's emotions. In addition, by providing feedback learning means for collecting user feedback information and emotion data and using them as learning data to improve the performance of the response generation means and emotion recognition means, the overall performance of the system can be continuously improved.

[0190] "Information processing means" refers to a function for receiving inquiry information from users and analyzing it.

[0191] A "response generation means" is a function that generates an appropriate response based on the content of the received inquiry information.

[0192] An "emotion recognition tool" is a function that analyzes the user's emotional data and generates an emotionally conscious response based on the results.

[0193] "Communication means" refers to a function for sending the generated response to the user.

[0194] A "distribution mechanism" is a function that identifies inquiries related to a specific service and distributes them to the appropriate person in charge of that task.

[0195] "Support measures" refer to functions that provide additional information or support for specific inquiries that have been routed to a particular inquiry.

[0196] A "feedback learning method" is a function that collects feedback information and emotional data from users and uses them as learning data to improve the performance of response generation and emotion recognition methods.

[0197] This invention is primarily implemented as a system that provides emotionally conscious responses to user inquiries.

[0198] The server first receives user inquiry information and analyzes it through information processing tools. The received inquiry information also includes the user's emotional data. Specifically, the server uses a speech recognition and text analysis engine (e.g., Google Cloud Speech-to-Text) to convert speech to text, and then uses an emotional analysis engine (e.g., IBM Watson® Tone Analyzer) to identify emotions from the text. During this process, emotions such as "anxiety," "joy," and "anger" are recognized.

[0199] Based on the emotional information analyzed by the emotion recognition means, the server adjusts the response generation means to generate a response that matches the user's emotions. A generation AI model (e.g., the OpenAI GPT model) is used for response generation, and specific and emotionally resonant responses are generated through prompts. The generated response is sent to the user via the communication means.

[0200] For example, if a user makes an inquiry expressing concern such as, "I'm worried about security before making a large payment," the server will recognize the user's anxiety and respond with, "Don't worry, your transaction is protected by a high level of security. Also, if you have any questions, support is available immediately."

[0201] Examples of prompts for a generative AI model include the following:

[0202] "User inquiry: 'I'm worried about security, so I'd like to confirm before making a large payment.' AI response: Generate a response here that includes consideration to alleviate the user's concerns."

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server receives voice inquiries from users. The input here is the user's voice data, and the server uses a speech recognition engine to convert this voice data into text data. Specifically, this involves digitizing the voice collected by the microphone and sending it to Google Cloud Speech-to-Text.

[0206] Step 2:

[0207] The server passes the converted text data to the sentiment analysis engine. To recognize emotions from the input text, it calls the IBM Watson Tone Analyzer to identify the emotion labels in the text (e.g., "anxiety," "joy," "anger," etc.). This specifically involves sending the text data to the analysis engine and applying the sentiment classification algorithm.

[0208] Step 3:

[0209] The server invokes a response generation engine based on the recognized emotion data. Here, the OpenAI GPT generative AI model is used to form a prompt. This prompt contains instructions for generating a response that takes a specific emotion into account. Specifically, this involves constructing a prompt based on emotion labels and inputting it into the AI ​​model.

[0210] Step 4:

[0211] The server sends the generated response to the user. The text output obtained from the response generation engine is transmitted to the user's terminal via communication means. This specific operation involves transferring data over the network and displaying or playing it on the user's device.

[0212] Step 5:

[0213] User feedback is sent to the server. This feedback may include evaluations of the response quality and additional sentiment information. This input is processed by a feedback learning mechanism to improve the performance of the response generation mechanism and the sentiment recognition mechanism. Specifically, this involves collecting evaluation data and using it for analysis to improve the system.

[0214] 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.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] 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.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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".

[0230] The system of this invention enables users to make inquiries through an online contact point. This system responds to user requests by analyzing received inquiries, generating appropriate responses, and sending them back. It also has a function to automatically route inquiries that are deemed necessary by the business staff.

[0231] This system consists of multiple components. It primarily includes information processing means, response generation means, communication means, sorting means, support means, and feedback learning means. The detailed configuration is as follows:

[0232] The server receives inquiries from users and processes their content using information processing tools.

[0233] The server analyzes the key keywords in the query and generates an appropriate response using a response generation system. This response is generated using natural language processing and is in a format that is easy for the user to understand.

[0234] Once a response is generated, the server sends that response to the user via the communication means.

[0235] If the inquiry concerns a specific service or is complex, the server uses a routing mechanism to automatically assign the inquiry to the appropriate person.

[0236] The terminal processes the assigned inquiries and, if necessary, allows business personnel to provide additional support directly using support tools.

[0237] The server collects feedback information from users and uses it to improve the response generation system through feedback learning. This process improves the overall response accuracy of the system.

[0238] Specific example

[0239] For example, if a user submits an inquiry through the online system stating, "I want to change my data plan," the server receives this inquiry. The information processing system recognizes the key phrase "data plan," and the response generation system generates a response such as, "You can change your data plan online or in-store. Would you like to be connected to a representative near you for detailed instructions?" This response is then sent to the user via the communication system. If necessary, this inquiry is automatically routed to a terminal, allowing a business representative to provide specific assistance.

[0240] Thus, the present invention offers the advantages of enabling users to receive prompt and accurate support, as well as reducing the burden on those responsible for operations.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The user enters their question through an online interface and submits it.

[0244] Step 2:

[0245] The server receives query data from users, formats that data, and performs basic consistency checks.

[0246] Step 3:

[0247] The server passes the received query to a natural language processing engine, which analyzes important keywords and sentence structure.

[0248] Step 4:

[0249] Based on the analysis results, the server generates an appropriate response using a response generation mechanism. The response is combined with information templates as needed and formatted into a user-friendly format.

[0250] Step 5:

[0251] The server sends the generated response to the user via a communication method.

[0252] Step 6:

[0253] The server classifies the inquiry content and determines whether it is a general inquiry or an inquiry related to a specific service.

[0254] Step 7:

[0255] If the server determines that an inquiry is related to a specific service, it uses a routing mechanism to automatically assign the inquiry to a terminal.

[0256] Step 8:

[0257] The terminal notifies the business representative of the inquiry, and the business representative provides support to the user directly as needed.

[0258] Step 9:

[0259] The server collects user feedback and uses feedback learning mechanisms to improve the response generation algorithm. This process contributes to improving the overall system performance.

[0260] (Example 1)

[0261] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0262] The challenge lies in providing prompt and accurate responses to a wide range of online user inquiries while simultaneously reducing the burden on employees and continuously improving the overall accuracy of responses.

[0263] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0264] In this invention, the server includes information processing means for receiving inquiry information from a user, natural language processing means for analyzing the inquiry information and generating a response based on its content, and data transmission means for sending the generated response to the user. This makes it possible to respond to inquiries quickly.

[0265] "Information processing means" refers to a device or program that has the function of organizing and analyzing inquiry information received from a user.

[0266] "Natural language processing means" refers to a device or program that uses natural language processing technology to generate an appropriate response based on query information.

[0267] "Data transmission means" refers to a device or program that has a communication function for transmitting the generated response to the user.

[0268] "Inquiry management means" refers to a device or program that has the function of identifying inquiries related to a specific task and assigning said inquiries to the appropriate person performing the task.

[0269] A "data adaptation means" is a device or program that has the function of using feedback information collected from users as learning data to improve response generation capabilities.

[0270] "Support execution means" refers to a device or program that has the function of providing additional information or support in response to specific inquiries assigned to employees.

[0271] This invention provides a system that receives user inquiries through an online contact point and processes them quickly and appropriately. The system primarily operates with a server, utilizing information processing means, natural language processing means, data transmission means, inquiry management means, and data adaptation means.

[0272] The server uses information processing tools when receiving inquiries from users. The data of the received inquiries is stored on the server, and natural language processing libraries (e.g., NLTK and spaCy) are utilized. This allows for the analysis of the input text, including tokenization of important terms and syntactic analysis. Furthermore, a generative AI model (e.g., GPT-3) is used as a natural language processing tool to generate an appropriate response based on the prompt. A specific example of a prompt would be, "Please explain how to easily change the data plan using the online system."

[0273] The generated response is sent to the user by the server's data transmission mechanism. The data transmission mechanism uses the HTTP protocol and returns the response via the client-side user interface.

[0274] Furthermore, if the inquiry relates to a specific task, the server uses an inquiry management system to assign the inquiry to the appropriate person in charge of that task. The person in charge can then use their terminal to provide additional information and support to the user through specific software (e.g., a CRM system).

[0275] The server uses user feedback as a data adaptation tool and leverages it to improve response generation. This continuously improves the overall accuracy and efficiency of the system.

[0276] This configuration allows the system to respond promptly to diverse user needs, reduce the burden on employees, and maintain a high level of response quality.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] Users enter and submit inquiries through an online form. The input is in the form of natural language questions. The data entered by the user is sent to the server as an HTTP request.

[0280] Step 2:

[0281] The server analyzes the query received from the user using information processing tools. At this stage, the received query data is converted into tokens, and part-of-speech tagging and syntactic analysis are performed using a natural language processing library. As a result of the analysis, important words and phrases are extracted, which become the input for the next response generation process.

[0282] Step 3:

[0283] Based on the analyzed data, the server uses natural language processing means to generate a response via a generative AI model. Specifically, data is input into a model such as GPT-3 in a form that includes a prompt sentence, and a response to it is generated. The output response is temporarily saved on the server as a reply to the user.

[0284] Step 4:

[0285] The server sends the generated response to the user using data transmission means. Here, the response data is sent back to the user's terminal via an HTTP response. The user can immediately check this response on their device.

[0286] Step 5:

[0287] When an inquiry related to a specific business occurs, the server uses inquiry management means to assign the corresponding inquiry to a business operator. The management means analyzes the content of the inquiry, identifies assignable business operators or teams, and notifies that information to the terminals of the business operators.

[0288] Step 6:

[0289] The terminal provides additional information or support for the inquiry received by the business operator via business software such as a CRM system. As a result, the business operator can directly respond to the user as needed.

[0290] Step 7:

[0291] At the feedback stage, the server receives post-use feedback information from the user and uses it to improve the response generation means through data adaptation means. The feedback obtained in this process is utilized as training data for the generative AI model, improving the response accuracy of the entire system.

[0292] (Application Example 1)

[0293] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0294] Responding to customer inquiries in online stores requires prompt and accurate responses. However, the large number of inquiries regarding purchasing procedures, return procedures, and delivery status increases the burden on staff, leading to delays and incorrect answers. This can result in decreased customer satisfaction and negatively impact the store's credibility.

[0295] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0296] In this invention, the server includes information processing means for receiving inquiry information from users, natural language generation means for analyzing the inquiry information and generating a response based on its content, and communication means for transmitting the generated response to the user. This enables the automatic processing of inquiries regarding purchasing procedures, return procedures, and delivery status confirmation procedures, reducing the burden on business staff and providing users with prompt and accurate support.

[0297] "Information processing means" refers to a device or program that has the function of collecting and analyzing inquiry information received from users.

[0298] A "natural language generation means" is a program or device that generates a response in a format easily understood by the user, based on analyzed query information.

[0299] "Communication means" refers to a device or program that uses a network interface or protocol to transmit a generated response to a user.

[0300] A "distribution tool" is a program or device that has the function of automatically identifying inquiries related to a specific task and assigning them to the person in charge of that task.

[0301] A "feedback learning method" is a program or device that collects evaluation information from users and uses it to improve the performance of a natural language generation method.

[0302] To implement this invention, several important functions must be implemented on the server. First, the server utilizes information processing means via an API to receive user inquiry information. For example, the Flask framework in Python can be used for this processing. The received inquiry information is parsed using the Google Cloud Natural Language API to extract important words and intents.

[0303] Next, as a means of natural language generation, a generative AI model such as OpenAI's GPT-3 is used to generate appropriate responses based on the extracted key words. These generated responses are then adjusted to be in a format that is easy for the user to understand.

[0304] The generated response is sent to the user's device via a communication method. This involves forwarding the response via a RESTful API so that it can be received on the user's smartphone or other device. If the user asks, "I want to know the delivery status," the system will immediately respond with something like, "Your current estimated delivery date is tomorrow."

[0305] Furthermore, feedback learning mechanisms allow the server to collect evaluation information from users. This evaluation is used to adjust the generative model to improve the overall system performance. In this process, a database can be built on the cloud to store the evaluation information as data records.

[0306] As a specific example, for an inquiry "Can this product be exchanged?", the model generates a response with a prompt "If it is unused, it can be exchanged at a nearby store". Examples of prompt sentences are expressed as follows. "Please generate a kind Japanese response to the following inquiry: 'Can this product be exchanged?'". By automatically generating such responses, it becomes possible to respond to customers quickly and accurately.

[0307] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The user inputs an inquiry via a smartphone terminal. This input is sent to the server through the RESTful API. The input data is text data of the user's question content.

[0310] Step 2:

[0311] The server analyzes the received inquiry information using the Google Cloud Natural Language API. In the process of analysis, important phrases and intentions are extracted from the inquiry. By this process, keywords and context necessary for response generation are output from the input text data.

[0312] Step 3:

[0313] The server sends a prompt sentence to GPT-3, which is a generative AI model, based on the extracted important phrases. This prompt sentence includes content that requests specific responses related to the user's inquiry. The generative AI model generates appropriate response data based on this prompt sentence.

[0314] Step 4:

[0315] The server analyzes the response data received from GPT-3 and processes it into a user-friendly response format. This processing transforms the text generated by the AI ​​model into an optimized natural language response.

[0316] Step 5:

[0317] The server sends a formatted response to the user's terminal via a communication method. The user's terminal receives this response and displays it as the answer to the query. This allows the user to immediately verify the information provided in the response.

[0318] Step 6:

[0319] Once the interaction is complete, the server collects user feedback and saves it as data for retraining using a feedback learning mechanism. This saved data is then used in a feedback loop to improve the response accuracy of the generated AI model.

[0320] 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.

[0321] The system of this invention is equipped with an advanced response generation function that combines an emotion engine to provide appropriate responses to user inquiries. This allows the system to provide more human-like responses while considering the user's emotions. The system mainly consists of the following elements.

[0322] The server receives inquiry information from users and performs initial analysis through information processing tools. During this process, user sentiment data sent along with the inquiry is also collected.

[0323] The emotion engine analyzes this emotional data to recognize what emotions the user is experiencing. For example, emotions such as "anger," "joy," and "anxiety" may be identified.

[0324] The server adjusts its response generation mechanisms based on the recognized emotions, generating a response that aligns with the user's feelings. This response not only conveys facts but also includes nuances that reflect an understanding of the user's emotions.

[0325] The server sends the generated response to the user via communication means. Emotionally responsive responses demonstrate understanding and consideration for the user, and have the effect of improving satisfaction.

[0326] When an inquiry regarding a specific service is received, the server uses a routing mechanism to assign it to the appropriate person in charge. If the user's emotional state is, for example, "anxiety," the server can assign the inquiry to a person capable of providing appropriate support.

[0327] On the terminal, the assigned staff member can receive details of the assigned inquiry and provide further support tailored to the user's feelings.

[0328] The server uses feedback learning to collect feedback from users and improve the performance of the response generation means and the emotion engine. This feedback increases the accuracy of emotion recognition and the sophistication of responses.

[0329] Specific example

[0330] For example, if a user inquires, "I'm worried because I missed the payment deadline," the server might not simply respond with a businesslike "Here's how to pay," but rather, through its emotional engine, provide a more empathetic response such as, "Don't worry. You can proceed with these steps and use the service with peace of mind." This can give users a greater sense of security and increase their trust in the system.

[0331] The following describes the processing flow.

[0332] Step 1:

[0333] Users enter and submit inquiries through an online customer service interface. In this process, the user's input may include elements that express emotion (e.g., language choice or emojis).

[0334] Step 2:

[0335] The server receives query data from the user, formats the data, and performs basic integrity checks.

[0336] Step 3:

[0337] The server passes the received query to a natural language processing engine for linguistic analysis. This analysis identifies important words and sentence structures.

[0338] Step 4:

[0339] The server uses an emotion engine to recognize the user's emotions from the wording and emojis included in the query data. In this step, specific emotions such as "anger," "joy," and "anxiety" are extracted.

[0340] Step 5:

[0341] Based on the analyzed content and recognized emotions, the server generates an appropriate response using a response generation mechanism. The response will be tailored to the user's emotions.

[0342] Step 6:

[0343] The server sends the generated response to the user via a communication method. The sent response will have nuances that take emotions into consideration and will be tailored to the user's needs.

[0344] Step 7:

[0345] If the inquiry is related to a specific service, the server uses a routing mechanism to automatically route the inquiry to the appropriate person in charge, taking into consideration the perceived emotions.

[0346] Step 8:

[0347] The terminal notifies the business person of the inquiry that has been routed to them, and the business person provides feedback and additional support while keeping the user's feelings in mind.

[0348] Step 9:

[0349] The server collects user feedback and uses that feedback to improve the performance of its response generation methods and emotion engine. This improves the overall response accuracy and emotion recognition capabilities of the system.

[0350] (Example 2)

[0351] 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".

[0352] This invention aims to solve the problem of needing to understand and respond to users' emotions, rather than simply providing administrative responses, when communicating with users. Conventional systems have struggled to respond in a way that considers user emotions, leading to decreased satisfaction. Furthermore, there is a need to improve the quality of responses from business personnel to routed inquiries.

[0353] 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.

[0354] In this invention, the server includes information processing means for receiving inquiry information and emotion data from a user, response generation means using a generative AI model that analyzes the inquiry information and emotion data and generates a response based on the user's emotions, and communication means for transmitting the generated response to the user. This makes it possible to improve the quality of communication and increase user satisfaction by providing responses that include nuances that take into account the user's emotions. Furthermore, it enables appropriate responses based on the user's emotion data for business personnel, thereby improving the quality of service.

[0355] An "information processing device" is a device equipped with the function of receiving inquiry information and sentiment data transmitted by users and performing initial analysis of this data.

[0356] A "generative AI model" is an artificial intelligence program used to generate appropriate and emotionally resonant responses based on user inquiry information and sentiment data.

[0357] A "response generation means" is a means that has the function of generating a response to be provided to the user from analyzed data using a generation AI model.

[0358] "Communication means" refers to a device or method for quickly and effectively transmitting a generated response to a user.

[0359] A "distribution means" is a device or method that has the function of identifying inquiries related to a specific task and distributing those inquiries to the appropriate person in charge of that task.

[0360] "Display means" refers to a visual display device or method for a business person to confirm the details of an assigned inquiry.

[0361] A "feedback learning means" is a device or method for analyzing feedback information received from a user and improving the performance of a generated AI model and a response generation means based on the results.

[0362] This invention provides a system that enables more humane responses to user inquiries. It focuses on effectively processing user inquiry information and emotional data, and generating appropriate responses based on that information.

[0363] In this system, the server functions as an information processing unit, receiving inquiry information and emotion data sent by the user. The received data is then sent to a response generation unit that uses a generative AI model to generate a response tailored to the user's specific emotions and situation. The generative AI model incorporates an emotion analysis algorithm, which allows for the accurate identification of emotions such as "worry" and "joy."

[0364] The generated response is sent from the server to the user via a communication method. The user can receive a warm, considerate response that takes their emotions into account, rather than simply providing purely businesslike information.

[0365] For inquiries related to specific tasks, the server uses a routing mechanism to assign them to the appropriate person in charge. The person in charge then reviews the inquiry details on their terminal and provides support based on analyzed sentiment data. This leads to improved information provision and increased customer satisfaction.

[0366] Furthermore, the server utilizes feedback learning mechanisms to analyze feedback information obtained from users, continuously improving the performance of its generative AI models and response generation methods. This feedback loop ensures that the system is constantly optimized, enabling it to continuously provide responses tailored to user needs.

[0367] For example, if a user inquires, "I'm worried about late fees," the server can perform sentiment analysis and generate a reassuring response that reflects that anxiety. An example of a prompt would be to input a command to the AI ​​model, such as "Generate a response that is empathetic to the user's emotions," which helps the system create a desirable response.

[0368] As described above, the present invention provides specific methods and means for understanding the emotions of users and providing responses that are appropriate to them.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] Users submit inquiries to the system. This input includes text data of the question or request, and, if possible, metadata indicating the user's sentiment. This data is fundamental information for accurately performing subsequent processing within the system.

[0372] Step 2:

[0373] The server receives this query information and sentiment data using information processing tools. The received data is stored in a database. The specific actions performed here are to standardize the data format and prepare the sentiment data for analysis. This input data becomes the material for sentiment analysis and response generation.

[0374] Step 3:

[0375] The server sends query information and sentiment data to the sentiment engine for analysis. The sentiment engine uses natural language processing techniques to identify emotions and outputs labels such as "joy" or "anxiety." The process involves detecting keywords in the text and determining emotions based on the context. This result becomes the data needed to generate the response in the next step.

[0376] Step 4:

[0377] The server uses a generative AI model to generate responses based on analyzed sentiment data. Specifically, it constructs sentences by combining appropriate phrases and expressions based on templates corresponding to sentiment labels. This output is the response text sent back to the user.

[0378] Step 5:

[0379] The server sends the generated response to the user via a communication method. This output is designed to include a more human-like response. Specifically, it delivers text data to the user's device using a data communication protocol.

[0380] Step 6:

[0381] The server receives and analyzes user feedback for feedback learning. A key function here is to store the received feedback as training data and use it to improve the accuracy of the generated AI model. The output results are data that will contribute to improving future response quality.

[0382] (Application Example 2)

[0383] 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."

[0384] Conventional response systems failed to adequately consider user emotions, resulting in uniform and impersonal responses. Furthermore, even assigned staff struggled to provide emotionally responsive responses, highlighting the need for improved user experience. Additionally, there was a lack of mechanisms to continuously improve the overall system performance by fully utilizing feedback.

[0385] 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.

[0386] In this invention, the server includes information processing means for receiving user inquiry information, response generation means for analyzing the inquiry information and generating a response based on its content, and emotion recognition means for analyzing the user's emotion data and generating a response based on that emotion. This enables more human-like responses. Furthermore, by including communication means for transmitting the generated response to the user, and distribution means for identifying inquiries related to a specific service and distributing the inquiry to a business person, business people can provide appropriate support in accordance with the user's emotions. In addition, by providing feedback learning means for collecting user feedback information and emotion data and using them as learning data to improve the performance of the response generation means and emotion recognition means, the overall performance of the system can be continuously improved.

[0387] "Information processing means" refers to a function for receiving inquiry information from users and analyzing it.

[0388] A "response generation means" is a function that generates an appropriate response based on the content of the received inquiry information.

[0389] An "emotion recognition tool" is a function that analyzes the user's emotional data and generates an emotionally conscious response based on the results.

[0390] "Communication means" refers to a function for sending the generated response to the user.

[0391] A "distribution mechanism" is a function that identifies inquiries related to a specific service and distributes them to the appropriate person in charge of that task.

[0392] "Support measures" refer to functions that provide additional information or support for specific inquiries that have been routed to a particular inquiry.

[0393] A "feedback learning method" is a function that collects feedback information and emotional data from users and uses them as learning data to improve the performance of response generation and emotion recognition methods.

[0394] This invention is primarily implemented as a system that provides emotionally conscious responses to user inquiries.

[0395] The server first receives user inquiry information and analyzes it through information processing tools. The received inquiry information also includes the user's emotional data. Specifically, the server uses a speech recognition and text analysis engine (e.g., Google Cloud Speech-to-Text) to convert speech to text, and then uses an emotional analysis engine (e.g., IBM Watson Tone Analyzer) to identify emotions from the text. During this process, emotions such as "anxiety," "joy," and "anger" are recognized.

[0396] Based on the emotional information analyzed by the emotion recognition means, the server adjusts the response generation means to generate a response that matches the user's emotions. A generation AI model (e.g., the OpenAI GPT model) is used for response generation, and specific and emotionally resonant responses are generated through prompts. The generated response is sent to the user via the communication means.

[0397] For example, if a user makes an inquiry expressing concern such as, "I'm worried about security before making a large payment," the server will recognize the user's anxiety and respond with, "Don't worry, your transaction is protected by a high level of security. Also, if you have any questions, support is available immediately."

[0398] Examples of prompts for a generative AI model include the following:

[0399] "User inquiry: 'I'm worried about security, so I'd like to confirm before making a large payment.' AI response: Generate a response here that includes consideration to alleviate the user's concerns."

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] The server receives voice inquiries from users. The input here is the user's voice data, and the server uses a speech recognition engine to convert this voice data into text data. Specifically, this involves digitizing the voice collected by the microphone and sending it to Google Cloud Speech-to-Text.

[0403] Step 2:

[0404] The server passes the converted text data to the sentiment analysis engine. To recognize emotions from the input text, it calls the IBM Watson Tone Analyzer to identify the emotion labels in the text (e.g., "anxiety," "joy," "anger," etc.). This specifically involves sending the text data to the analysis engine and applying the sentiment classification algorithm.

[0405] Step 3:

[0406] The server invokes a response generation engine based on the recognized emotion data. Here, the OpenAI GPT generative AI model is used to form a prompt. This prompt contains instructions for generating a response that takes a specific emotion into account. Specifically, this involves constructing a prompt based on emotion labels and inputting it into the AI ​​model.

[0407] Step 4:

[0408] The server sends the generated response to the user. The text output obtained from the response generation engine is transmitted to the user's terminal via communication means. This specific operation involves transferring data over the network and displaying or playing it on the user's device.

[0409] Step 5:

[0410] User feedback is sent to the server. This feedback may include evaluations of the response quality and additional sentiment information. This input is processed by a feedback learning mechanism to improve the performance of the response generation mechanism and the sentiment recognition mechanism. Specifically, this involves collecting evaluation data and using it for analysis to improve the system.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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".

[0427] The system of this invention enables users to make inquiries through an online contact point. This system responds to user requests by analyzing received inquiries, generating appropriate responses, and sending them back. It also has a function to automatically route inquiries that are deemed necessary by the business staff.

[0428] This system consists of multiple components. It primarily includes information processing means, response generation means, communication means, sorting means, support means, and feedback learning means. The detailed configuration is as follows:

[0429] The server receives inquiries from users and processes their content using information processing tools.

[0430] The server analyzes the key keywords in the query and generates an appropriate response using a response generation system. This response is generated using natural language processing and is in a format that is easy for the user to understand.

[0431] Once a response is generated, the server sends that response to the user via the communication means.

[0432] If the inquiry concerns a specific service or is complex, the server uses a routing mechanism to automatically assign the inquiry to the appropriate person.

[0433] The terminal processes the assigned inquiries and, if necessary, allows business personnel to provide additional support directly using support tools.

[0434] The server collects feedback information from users and uses it to improve the response generation system through feedback learning. This process improves the overall response accuracy of the system.

[0435] Specific example

[0436] For example, if a user submits an inquiry through the online system stating, "I want to change my data plan," the server receives this inquiry. The information processing system recognizes the key phrase "data plan," and the response generation system generates a response such as, "You can change your data plan online or in-store. Would you like to be connected to a representative near you for detailed instructions?" This response is then sent to the user via the communication system. If necessary, this inquiry is automatically routed to a terminal, allowing a business representative to provide specific assistance.

[0437] Thus, the present invention offers the advantages of enabling users to receive prompt and accurate support, as well as reducing the burden on those responsible for operations.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The user enters their question through an online interface and submits it.

[0441] Step 2:

[0442] The server receives query data from users, formats that data, and performs basic consistency checks.

[0443] Step 3:

[0444] The server passes the received query to a natural language processing engine, which analyzes important keywords and sentence structure.

[0445] Step 4:

[0446] Based on the analysis results, the server generates an appropriate response using a response generation mechanism. The response is combined with information templates as needed and formatted into a user-friendly format.

[0447] Step 5:

[0448] The server sends the generated response to the user via a communication method.

[0449] Step 6:

[0450] The server classifies the inquiry content and determines whether it is a general inquiry or an inquiry related to a specific service.

[0451] Step 7:

[0452] If the server determines that an inquiry is related to a specific service, it uses a routing mechanism to automatically assign the inquiry to a terminal.

[0453] Step 8:

[0454] The terminal notifies the business representative of the inquiry, and the business representative provides support to the user directly as needed.

[0455] Step 9:

[0456] The server collects user feedback and uses feedback learning mechanisms to improve the response generation algorithm. This process contributes to improving the overall system performance.

[0457] (Example 1)

[0458] 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."

[0459] The challenge lies in providing prompt and accurate responses to a wide range of online user inquiries while simultaneously reducing the burden on employees and continuously improving the overall accuracy of responses.

[0460] 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.

[0461] In this invention, the server includes information processing means for receiving inquiry information from a user, natural language processing means for analyzing the inquiry information and generating a response based on its content, and data transmission means for sending the generated response to the user. This makes it possible to respond to inquiries quickly.

[0462] "Information processing means" refers to a device or program that has the function of organizing and analyzing inquiry information received from a user.

[0463] "Natural language processing means" refers to a device or program that uses natural language processing technology to generate an appropriate response based on query information.

[0464] "Data transmission means" refers to a device or program that has a communication function for transmitting the generated response to the user.

[0465] "Inquiry management means" refers to a device or program that has the function of identifying inquiries related to a specific task and assigning said inquiries to the appropriate person performing the task.

[0466] A "data adaptation means" is a device or program that has the function of using feedback information collected from users as learning data to improve response generation capabilities.

[0467] "Support execution means" refers to a device or program that has the function of providing additional information or support in response to specific inquiries assigned to employees.

[0468] This invention provides a system that receives user inquiries through an online contact point and processes them quickly and appropriately. The system primarily operates with a server, utilizing information processing means, natural language processing means, data transmission means, inquiry management means, and data adaptation means.

[0469] The server uses information processing tools when receiving inquiries from users. The data of the received inquiries is stored on the server, and natural language processing libraries (e.g., NLTK and spaCy) are utilized. This allows for the analysis of the input text, including tokenization of important terms and syntactic analysis. Furthermore, a generative AI model (e.g., GPT-3) is used as a natural language processing tool to generate an appropriate response based on the prompt. A specific example of a prompt would be, "Please explain how to easily change the data plan using the online system."

[0470] The generated response is sent to the user by the server's data transmission mechanism. The data transmission mechanism uses the HTTP protocol and returns the response via the client-side user interface.

[0471] Furthermore, if the inquiry relates to a specific task, the server uses an inquiry management system to assign the inquiry to the appropriate person in charge of that task. The person in charge can then use their terminal to provide additional information and support to the user through specific software (e.g., a CRM system).

[0472] The server uses user feedback as a data adaptation tool and leverages it to improve response generation. This continuously improves the overall accuracy and efficiency of the system.

[0473] This configuration allows the system to respond promptly to diverse user needs, reduce the burden on employees, and maintain a high level of response quality.

[0474] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0475] Step 1:

[0476] Users enter and submit inquiries through an online form. The input is in the form of natural language questions. The data entered by the user is sent to the server as an HTTP request.

[0477] Step 2:

[0478] The server analyzes the query received from the user using information processing tools. At this stage, the received query data is converted into tokens, and part-of-speech tagging and syntactic analysis are performed using a natural language processing library. As a result of the analysis, important words and phrases are extracted, which become the input for the next response generation process.

[0479] Step 3:

[0480] The server uses natural language processing techniques based on the analyzed data to generate responses via a generative AI model. Specifically, it inputs data, including prompts, into a model such as GPT-3, and generates responses accordingly. The output responses are temporarily stored on the server as a reply to the user.

[0481] Step 4:

[0482] The server sends the generated response to the user using a data transmission method. Here, the response data is sent back to the user's device via an HTTP response. The user can instantly view this response on their device.

[0483] Step 5:

[0484] When an inquiry related to a specific task arises, the server uses an inquiry management system to assign the inquiry to the appropriate person in charge. The management system analyzes the content of the inquiry, identifies the person or team to whom it can be assigned, and notifies the person in charge of that information on their terminal.

[0485] Step 6:

[0486] The terminal provides additional information and support to business users through business software such as CRM systems in response to inquiries received by business personnel. This allows business personnel to respond directly to users as needed.

[0487] Step 7:

[0488] During the feedback phase, the server receives post-use feedback information from users and uses it to improve the response generation system through data adaptation mechanisms. The feedback obtained in this process is utilized as training data for the generation AI model, improving the overall response accuracy of the system.

[0489] (Application Example 1)

[0490] 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."

[0491] Responding to customer inquiries in online stores requires prompt and accurate responses. However, the large number of inquiries regarding purchasing procedures, return procedures, and delivery status increases the burden on staff, leading to delays and incorrect answers. This can result in decreased customer satisfaction and negatively impact the store's credibility.

[0492] 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.

[0493] In this invention, the server includes information processing means for receiving inquiry information from users, natural language generation means for analyzing the inquiry information and generating a response based on its content, and communication means for transmitting the generated response to the user. This enables the automatic processing of inquiries regarding purchasing procedures, return procedures, and delivery status confirmation procedures, reducing the burden on business staff and providing users with prompt and accurate support.

[0494] "Information processing means" refers to a device or program that has the function of collecting and analyzing inquiry information received from users.

[0495] A "natural language generation means" is a program or device that generates a response in a format easily understood by the user, based on analyzed query information.

[0496] "Communication means" refers to a device or program that uses a network interface or protocol to transmit a generated response to a user.

[0497] A "distribution tool" is a program or device that has the function of automatically identifying inquiries related to a specific task and assigning them to the person in charge of that task.

[0498] A "feedback learning method" is a program or device that collects evaluation information from users and uses it to improve the performance of a natural language generation method.

[0499] To implement this invention, several important functions must be implemented on the server. First, the server utilizes information processing means via an API to receive user inquiry information. For example, the Flask framework in Python can be used for this processing. The received inquiry information is parsed using the Google Cloud Natural Language API to extract important words and intents.

[0500] Next, as a means of natural language generation, a generative AI model such as OpenAI's GPT-3 is used to generate appropriate responses based on the extracted key words. These generated responses are then adjusted to be in a format that is easy for the user to understand.

[0501] The generated response is sent to the user's device via a communication method. This involves forwarding the response via a RESTful API so that it can be received on the user's smartphone or other device. If the user asks, "I want to know the delivery status," the system will immediately respond with something like, "Your current estimated delivery date is tomorrow."

[0502] Furthermore, feedback learning mechanisms allow the server to collect evaluation information from users. This evaluation is used to adjust the generative model to improve the overall system performance. In this process, a database can be built on the cloud to store the evaluation information as data records.

[0503] As a concrete example, in response to the inquiry, "Is it possible to exchange this product?", the model generates a response with the prompt, "If unused, it can be exchanged at your nearest store." An example of a prompt statement is expressed as follows: "Generate a simple Japanese response to the following inquiry: 'Is it possible to exchange this product?'" Automatic generation of such responses enables quick and accurate responses to customers.

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] Users enter their inquiries via their smartphones. This input is sent to the server via a RESTful API. The input data consists of text data of the user's question.

[0507] Step 2:

[0508] The server analyzes the received query information using the Google Cloud Natural Language API. During the analysis process, it extracts important keywords and intent from the query. This process outputs the keywords and context necessary for generating a response from the input text data.

[0509] Step 3:

[0510] The server sends a prompt message to the generative AI model, GPT-3, based on the extracted key keywords. This prompt message contains specific instructions related to the user's inquiry. The generative AI model then generates appropriate response data based on this prompt message.

[0511] Step 4:

[0512] The server analyzes the response data received from GPT-3 and processes it into a user-friendly response format. This processing transforms the text generated by the AI ​​model into an optimized natural language response.

[0513] Step 5:

[0514] The server sends a formatted response to the user's terminal via a communication method. The user's terminal receives this response and displays it as the answer to the query. This allows the user to immediately verify the information provided in the response.

[0515] Step 6:

[0516] Once the interaction is complete, the server collects user feedback and saves it as data for retraining using a feedback learning mechanism. This saved data is then used in a feedback loop to improve the response accuracy of the generated AI model.

[0517] 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.

[0518] The system of this invention is equipped with an advanced response generation function that combines an emotion engine to provide appropriate responses to user inquiries. This allows the system to provide more human-like responses while considering the user's emotions. The system mainly consists of the following elements.

[0519] The server receives inquiry information from users and performs initial analysis through information processing tools. During this process, user sentiment data sent along with the inquiry is also collected.

[0520] The emotion engine analyzes this emotional data to recognize what emotions the user is experiencing. For example, emotions such as "anger," "joy," and "anxiety" may be identified.

[0521] The server adjusts its response generation mechanisms based on the recognized emotions, generating a response that aligns with the user's feelings. This response not only conveys facts but also includes nuances that reflect an understanding of the user's emotions.

[0522] The server sends the generated response to the user via communication means. Emotionally responsive responses demonstrate understanding and consideration for the user, and have the effect of improving satisfaction.

[0523] When an inquiry regarding a specific service is received, the server uses a routing mechanism to assign it to the appropriate person in charge. If the user's emotional state is, for example, "anxiety," the server can assign the inquiry to a person capable of providing appropriate support.

[0524] On the terminal, the assigned staff member can receive details of the assigned inquiry and provide further support tailored to the user's feelings.

[0525] The server uses feedback learning to collect feedback from users and improve the performance of the response generation means and the emotion engine. This feedback increases the accuracy of emotion recognition and the sophistication of responses.

[0526] Specific example

[0527] For example, if a user inquires, "I'm worried because I missed the payment deadline," the server might not simply respond with a businesslike "Here's how to pay," but rather, through its emotional engine, provide a more empathetic response such as, "Don't worry. You can proceed with these steps and use the service with peace of mind." This can give users a greater sense of security and increase their trust in the system.

[0528] The following describes the processing flow.

[0529] Step 1:

[0530] Users enter and submit inquiries through an online customer service interface. In this process, the user's input may include elements that express emotion (e.g., language choice or emojis).

[0531] Step 2:

[0532] The server receives query data from the user, formats the data, and performs basic integrity checks.

[0533] Step 3:

[0534] The server passes the received query to a natural language processing engine for linguistic analysis. This analysis identifies important words and sentence structures.

[0535] Step 4:

[0536] The server uses an emotion engine to recognize the user's emotions from the wording and emojis included in the query data. In this step, specific emotions such as "anger," "joy," and "anxiety" are extracted.

[0537] Step 5:

[0538] Based on the analyzed content and recognized emotions, the server generates an appropriate response using a response generation mechanism. The response will be tailored to the user's emotions.

[0539] Step 6:

[0540] The server sends the generated response to the user via a communication method. The sent response will have nuances that take emotions into consideration and will be tailored to the user's needs.

[0541] Step 7:

[0542] If the inquiry is related to a specific service, the server uses a routing mechanism to automatically route the inquiry to the appropriate person in charge, taking into consideration the perceived emotions.

[0543] Step 8:

[0544] The terminal notifies the business person of the inquiry that has been routed to them, and the business person provides feedback and additional support while keeping the user's feelings in mind.

[0545] Step 9:

[0546] The server collects user feedback and uses that feedback to improve the performance of its response generation methods and emotion engine. This improves the overall response accuracy and emotion recognition capabilities of the system.

[0547] (Example 2)

[0548] 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."

[0549] This invention aims to solve the problem of needing to understand and respond to users' emotions, rather than simply providing administrative responses, when communicating with users. Conventional systems have struggled to respond in a way that considers user emotions, leading to decreased satisfaction. Furthermore, there is a need to improve the quality of responses from business personnel to routed inquiries.

[0550] 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.

[0551] In this invention, the server includes information processing means for receiving inquiry information and emotion data from a user, response generation means using a generative AI model that analyzes the inquiry information and emotion data and generates a response based on the user's emotions, and communication means for transmitting the generated response to the user. This makes it possible to improve the quality of communication and increase user satisfaction by providing responses that include nuances that take into account the user's emotions. Furthermore, it enables appropriate responses based on the user's emotion data for business personnel, thereby improving the quality of service.

[0552] An "information processing device" is a device equipped with the function of receiving inquiry information and sentiment data transmitted by users and performing initial analysis of this data.

[0553] A "generative AI model" is an artificial intelligence program used to generate appropriate and emotionally resonant responses based on user inquiry information and sentiment data.

[0554] A "response generation means" is a means that has the function of generating a response to be provided to the user from analyzed data using a generation AI model.

[0555] "Communication means" refers to a device or method for quickly and effectively transmitting a generated response to a user.

[0556] A "distribution means" is a device or method that has the function of identifying inquiries related to a specific task and distributing those inquiries to the appropriate person in charge of that task.

[0557] "Display means" refers to a visual display device or method for a business person to confirm the details of an assigned inquiry.

[0558] A "feedback learning means" is a device or method for analyzing feedback information received from a user and improving the performance of a generated AI model and a response generation means based on the results.

[0559] This invention provides a system that enables more humane responses to user inquiries. It focuses on effectively processing user inquiry information and emotional data, and generating appropriate responses based on that information.

[0560] In this system, the server functions as an information processing unit, receiving inquiry information and emotion data sent by the user. The received data is then sent to a response generation unit that uses a generative AI model to generate a response tailored to the user's specific emotions and situation. The generative AI model incorporates an emotion analysis algorithm, which allows for the accurate identification of emotions such as "worry" and "joy."

[0561] The generated response is sent from the server to the user via a communication method. The user can receive a warm, considerate response that takes their emotions into account, rather than simply providing purely businesslike information.

[0562] For inquiries related to specific tasks, the server uses a routing mechanism to assign them to the appropriate person in charge. The person in charge then reviews the inquiry details on their terminal and provides support based on analyzed sentiment data. This leads to improved information provision and increased customer satisfaction.

[0563] Furthermore, the server utilizes feedback learning mechanisms to analyze feedback information obtained from users, continuously improving the performance of its generative AI models and response generation methods. This feedback loop ensures that the system is constantly optimized, enabling it to continuously provide responses tailored to user needs.

[0564] For example, if a user inquires, "I'm worried about late fees," the server can perform sentiment analysis and generate a reassuring response that reflects that anxiety. An example of a prompt would be to input a command to the AI ​​model, such as "Generate a response that is empathetic to the user's emotions," which helps the system create a desirable response.

[0565] As described above, the present invention provides specific methods and means for understanding the emotions of users and providing responses that are appropriate to them.

[0566] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0567] Step 1:

[0568] Users submit inquiries to the system. This input includes text data of the question or request, and, if possible, metadata indicating the user's sentiment. This data is fundamental information for accurately performing subsequent processing within the system.

[0569] Step 2:

[0570] The server receives this query information and sentiment data using information processing tools. The received data is stored in a database. The specific actions performed here are to standardize the data format and prepare the sentiment data for analysis. This input data becomes the material for sentiment analysis and response generation.

[0571] Step 3:

[0572] The server sends query information and sentiment data to the sentiment engine for analysis. The sentiment engine uses natural language processing techniques to identify emotions and outputs labels such as "joy" or "anxiety." The process involves detecting keywords in the text and determining emotions based on the context. This result becomes the data needed to generate the response in the next step.

[0573] Step 4:

[0574] The server uses a generative AI model to generate responses based on analyzed sentiment data. Specifically, it constructs sentences by combining appropriate phrases and expressions based on templates corresponding to sentiment labels. This output is the response text sent back to the user.

[0575] Step 5:

[0576] The server sends the generated response to the user via a communication method. This output is designed to include a more human-like response. Specifically, it delivers text data to the user's device using a data communication protocol.

[0577] Step 6:

[0578] The server receives and analyzes user feedback for feedback learning. A key function here is to store the received feedback as training data and use it to improve the accuracy of the generated AI model. The output results are data that will contribute to improving future response quality.

[0579] (Application Example 2)

[0580] 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."

[0581] Conventional response systems failed to adequately consider user emotions, resulting in uniform and impersonal responses. Furthermore, even assigned staff struggled to provide emotionally responsive responses, highlighting the need for improved user experience. Additionally, there was a lack of mechanisms to continuously improve the overall system performance by fully utilizing feedback.

[0582] 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.

[0583] In this invention, the server includes information processing means for receiving user inquiry information, response generation means for analyzing the inquiry information and generating a response based on its content, and emotion recognition means for analyzing the user's emotion data and generating a response based on that emotion. This enables more human-like responses. Furthermore, by including communication means for transmitting the generated response to the user, and distribution means for identifying inquiries related to a specific service and distributing the inquiry to a business person, business people can provide appropriate support in accordance with the user's emotions. In addition, by providing feedback learning means for collecting user feedback information and emotion data and using them as learning data to improve the performance of the response generation means and emotion recognition means, the overall performance of the system can be continuously improved.

[0584] "Information processing means" refers to a function for receiving inquiry information from users and analyzing it.

[0585] A "response generation means" is a function that generates an appropriate response based on the content of the received inquiry information.

[0586] An "emotion recognition tool" is a function that analyzes the user's emotional data and generates an emotionally conscious response based on the results.

[0587] "Communication means" refers to a function for sending the generated response to the user.

[0588] A "distribution mechanism" is a function that identifies inquiries related to a specific service and distributes them to the appropriate person in charge of that task.

[0589] "Support measures" refer to functions that provide additional information or support for specific inquiries that have been routed to a particular inquiry.

[0590] A "feedback learning method" is a function that collects feedback information and emotional data from users and uses them as learning data to improve the performance of response generation and emotion recognition methods.

[0591] This invention is primarily implemented as a system that provides emotionally conscious responses to user inquiries.

[0592] The server first receives user inquiry information and analyzes it through information processing tools. The received inquiry information also includes the user's emotional data. Specifically, the server uses a speech recognition and text analysis engine (e.g., Google Cloud Speech-to-Text) to convert speech to text, and then uses an emotional analysis engine (e.g., IBM Watson Tone Analyzer) to identify emotions from the text. During this process, emotions such as "anxiety," "joy," and "anger" are recognized.

[0593] Based on the emotional information analyzed by the emotion recognition means, the server adjusts the response generation means to generate a response that matches the user's emotions. A generation AI model (e.g., the OpenAI GPT model) is used for response generation, and specific and emotionally resonant responses are generated through prompts. The generated response is sent to the user via the communication means.

[0594] For example, if a user makes an inquiry expressing concern such as, "I'm worried about security before making a large payment," the server will recognize the user's anxiety and respond with, "Don't worry, your transaction is protected by a high level of security. Also, if you have any questions, support is available immediately."

[0595] Examples of prompts for a generative AI model include the following:

[0596] "User inquiry: 'I'm worried about security, so I'd like to confirm before making a large payment.' AI response: Generate a response here that includes consideration to alleviate the user's concerns."

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1:

[0599] The server receives voice inquiries from users. The input here is the user's voice data, and the server uses a speech recognition engine to convert this voice data into text data. Specifically, this involves digitizing the voice collected by the microphone and sending it to Google Cloud Speech-to-Text.

[0600] Step 2:

[0601] The server passes the converted text data to the sentiment analysis engine. To recognize emotions from the input text, it calls the IBM Watson Tone Analyzer to identify the emotion labels in the text (e.g., "anxiety," "joy," "anger," etc.). This specifically involves sending the text data to the analysis engine and applying the sentiment classification algorithm.

[0602] Step 3:

[0603] The server invokes a response generation engine based on the recognized emotion data. Here, the OpenAI GPT generative AI model is used to form a prompt. This prompt contains instructions for generating a response that takes a specific emotion into account. Specifically, this involves constructing a prompt based on emotion labels and inputting it into the AI ​​model.

[0604] Step 4:

[0605] The server sends the generated response to the user. The text output obtained from the response generation engine is transmitted to the user's terminal via communication means. This specific operation involves transferring data over the network and displaying or playing it on the user's device.

[0606] Step 5:

[0607] User feedback is sent to the server. This feedback may include evaluations of the response quality and additional sentiment information. This input is processed by a feedback learning mechanism to improve the performance of the response generation mechanism and the sentiment recognition mechanism. Specifically, this involves collecting evaluation data and using it for analysis to improve the system.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] [Fourth Embodiment]

[0612] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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".

[0625] The system of this invention enables users to make inquiries through an online contact point. This system responds to user requests by analyzing received inquiries, generating appropriate responses, and sending them back. It also has a function to automatically route inquiries that are deemed necessary by the business staff.

[0626] This system consists of multiple components. It primarily includes information processing means, response generation means, communication means, sorting means, support means, and feedback learning means. The detailed configuration is as follows:

[0627] The server receives inquiries from users and processes their content using information processing tools.

[0628] The server analyzes the key keywords in the query and generates an appropriate response using a response generation system. This response is generated using natural language processing and is in a format that is easy for the user to understand.

[0629] Once a response is generated, the server sends that response to the user via the communication means.

[0630] If the inquiry concerns a specific service or is complex, the server uses a routing mechanism to automatically assign the inquiry to the appropriate person.

[0631] The terminal processes the assigned inquiries and, if necessary, allows business personnel to provide additional support directly using support tools.

[0632] The server collects feedback information from users and uses it to improve the response generation system through feedback learning. This process improves the overall response accuracy of the system.

[0633] Specific example

[0634] For example, if a user submits an inquiry through the online system stating, "I want to change my data plan," the server receives this inquiry. The information processing system recognizes the key phrase "data plan," and the response generation system generates a response such as, "You can change your data plan online or in-store. Would you like to be connected to a representative near you for detailed instructions?" This response is then sent to the user via the communication system. If necessary, this inquiry is automatically routed to a terminal, allowing a business representative to provide specific assistance.

[0635] Thus, the present invention offers the advantages of enabling users to receive prompt and accurate support, as well as reducing the burden on those responsible for operations.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] The user enters their question through an online interface and submits it.

[0639] Step 2:

[0640] The server receives query data from users, formats that data, and performs basic consistency checks.

[0641] Step 3:

[0642] The server passes the received query to a natural language processing engine, which analyzes important keywords and sentence structure.

[0643] Step 4:

[0644] Based on the analysis results, the server generates an appropriate response using a response generation mechanism. The response is combined with information templates as needed and formatted into a user-friendly format.

[0645] Step 5:

[0646] The server sends the generated response to the user via a communication method.

[0647] Step 6:

[0648] The server classifies the inquiry content and determines whether it is a general inquiry or an inquiry related to a specific service.

[0649] Step 7:

[0650] If the server determines that an inquiry is related to a specific service, it uses a routing mechanism to automatically assign the inquiry to a terminal.

[0651] Step 8:

[0652] The terminal notifies the business representative of the inquiry, and the business representative provides support to the user directly as needed.

[0653] Step 9:

[0654] The server collects user feedback and uses feedback learning mechanisms to improve the response generation algorithm. This process contributes to improving the overall system performance.

[0655] (Example 1)

[0656] 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".

[0657] The challenge lies in providing prompt and accurate responses to a wide range of online user inquiries while simultaneously reducing the burden on employees and continuously improving the overall accuracy of responses.

[0658] 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.

[0659] In this invention, the server includes information processing means for receiving inquiry information from a user, natural language processing means for analyzing the inquiry information and generating a response based on its content, and data transmission means for sending the generated response to the user. This makes it possible to respond to inquiries quickly.

[0660] "Information processing means" refers to a device or program that has the function of organizing and analyzing inquiry information received from a user.

[0661] "Natural language processing means" refers to a device or program that uses natural language processing technology to generate an appropriate response based on query information.

[0662] "Data transmission means" refers to a device or program that has a communication function for transmitting the generated response to the user.

[0663] "Inquiry management means" refers to a device or program that has the function of identifying inquiries related to a specific task and assigning said inquiries to the appropriate person performing the task.

[0664] A "data adaptation means" is a device or program that has the function of using feedback information collected from users as learning data to improve response generation capabilities.

[0665] "Support execution means" refers to a device or program that has the function of providing additional information or support in response to specific inquiries assigned to employees.

[0666] This invention provides a system that receives user inquiries through an online contact point and processes them quickly and appropriately. The system primarily operates with a server, utilizing information processing means, natural language processing means, data transmission means, inquiry management means, and data adaptation means.

[0667] The server uses information processing tools when receiving inquiries from users. The data of the received inquiries is stored on the server, and natural language processing libraries (e.g., NLTK and spaCy) are utilized. This allows for the analysis of the input text, including tokenization of important terms and syntactic analysis. Furthermore, a generative AI model (e.g., GPT-3) is used as a natural language processing tool to generate an appropriate response based on the prompt. A specific example of a prompt would be, "Please explain how to easily change the data plan using the online system."

[0668] The generated response is sent to the user by the server's data transmission mechanism. The data transmission mechanism uses the HTTP protocol and returns the response via the client-side user interface.

[0669] Furthermore, if the inquiry relates to a specific task, the server uses an inquiry management system to assign the inquiry to the appropriate person in charge of that task. The person in charge can then use their terminal to provide additional information and support to the user through specific software (e.g., a CRM system).

[0670] The server uses user feedback as a data adaptation tool and leverages it to improve response generation. This continuously improves the overall accuracy and efficiency of the system.

[0671] This configuration allows the system to respond promptly to diverse user needs, reduce the burden on employees, and maintain a high level of response quality.

[0672] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0673] Step 1:

[0674] Users enter and submit inquiries through an online form. The input is in the form of natural language questions. The data entered by the user is sent to the server as an HTTP request.

[0675] Step 2:

[0676] The server analyzes the query received from the user using information processing tools. At this stage, the received query data is converted into tokens, and part-of-speech tagging and syntactic analysis are performed using a natural language processing library. As a result of the analysis, important words and phrases are extracted, which become the input for the next response generation process.

[0677] Step 3:

[0678] The server uses natural language processing techniques based on the analyzed data to generate responses via a generative AI model. Specifically, it inputs data, including prompts, into a model such as GPT-3, and generates responses accordingly. The output responses are temporarily stored on the server as a reply to the user.

[0679] Step 4:

[0680] The server sends the generated response to the user using a data transmission method. Here, the response data is sent back to the user's device via an HTTP response. The user can instantly view this response on their device.

[0681] Step 5:

[0682] When an inquiry related to a specific task arises, the server uses an inquiry management system to assign the inquiry to the appropriate person in charge. The management system analyzes the content of the inquiry, identifies the person or team to whom it can be assigned, and notifies the person in charge of that information on their terminal.

[0683] Step 6:

[0684] The terminal provides additional information and support to business users through business software such as CRM systems in response to inquiries received by business personnel. This allows business personnel to respond directly to users as needed.

[0685] Step 7:

[0686] During the feedback phase, the server receives post-use feedback information from users and uses it to improve the response generation system through data adaptation mechanisms. The feedback obtained in this process is utilized as training data for the generation AI model, improving the overall response accuracy of the system.

[0687] (Application Example 1)

[0688] 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".

[0689] Responding to customer inquiries in online stores requires prompt and accurate responses. However, the large number of inquiries regarding purchasing procedures, return procedures, and delivery status increases the burden on staff, leading to delays and incorrect answers. This can result in decreased customer satisfaction and negatively impact the store's credibility.

[0690] 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.

[0691] In this invention, the server includes information processing means for receiving inquiry information from users, natural language generation means for analyzing the inquiry information and generating a response based on its content, and communication means for transmitting the generated response to the user. This enables the automatic processing of inquiries regarding purchasing procedures, return procedures, and delivery status confirmation procedures, reducing the burden on business staff and providing users with prompt and accurate support.

[0692] "Information processing means" refers to a device or program that has the function of collecting and analyzing inquiry information received from users.

[0693] A "natural language generation means" is a program or device that generates a response in a format easily understood by the user, based on analyzed query information.

[0694] "Communication means" refers to a device or program that uses a network interface or protocol to transmit a generated response to a user.

[0695] A "distribution tool" is a program or device that has the function of automatically identifying inquiries related to a specific task and assigning them to the person in charge of that task.

[0696] A "feedback learning method" is a program or device that collects evaluation information from users and uses it to improve the performance of a natural language generation method.

[0697] To implement this invention, several important functions must be implemented on the server. First, the server utilizes information processing means via an API to receive user inquiry information. For example, the Flask framework in Python can be used for this processing. The received inquiry information is parsed using the Google Cloud Natural Language API to extract important words and intents.

[0698] Next, as a means of natural language generation, a generative AI model such as OpenAI's GPT-3 is used to generate appropriate responses based on the extracted key words. These generated responses are then adjusted to be in a format that is easy for the user to understand.

[0699] The generated response is sent to the user's device via a communication method. This involves forwarding the response via a RESTful API so that it can be received on the user's smartphone or other device. If the user asks, "I want to know the delivery status," the system will immediately respond with something like, "Your current estimated delivery date is tomorrow."

[0700] Furthermore, feedback learning mechanisms allow the server to collect evaluation information from users. This evaluation is used to adjust the generative model to improve the overall system performance. In this process, a database can be built on the cloud to store the evaluation information as data records.

[0701] As a concrete example, in response to the inquiry, "Is it possible to exchange this product?", the model generates a response with the prompt, "If unused, it can be exchanged at your nearest store." An example of a prompt statement is expressed as follows: "Generate a simple Japanese response to the following inquiry: 'Is it possible to exchange this product?'" Automatic generation of such responses enables quick and accurate responses to customers.

[0702] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0703] Step 1:

[0704] Users enter their inquiries via their smartphones. This input is sent to the server via a RESTful API. The input data consists of text data of the user's question.

[0705] Step 2:

[0706] The server analyzes the received query information using the Google Cloud Natural Language API. During the analysis process, it extracts important keywords and intent from the query. This process outputs the keywords and context necessary for generating a response from the input text data.

[0707] Step 3:

[0708] The server sends a prompt message to the generative AI model, GPT-3, based on the extracted key keywords. This prompt message contains specific instructions related to the user's inquiry. The generative AI model then generates appropriate response data based on this prompt message.

[0709] Step 4:

[0710] The server analyzes the response data received from GPT-3 and processes it into a user-friendly response format. This processing transforms the text generated by the AI ​​model into an optimized natural language response.

[0711] Step 5:

[0712] The server sends a formatted response to the user's terminal via a communication method. The user's terminal receives this response and displays it as the answer to the query. This allows the user to immediately verify the information provided in the response.

[0713] Step 6:

[0714] Once the interaction is complete, the server collects user feedback and saves it as data for retraining using a feedback learning mechanism. This saved data is then used in a feedback loop to improve the response accuracy of the generated AI model.

[0715] 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.

[0716] The system of this invention is equipped with an advanced response generation function that combines an emotion engine to provide appropriate responses to user inquiries. This allows the system to provide more human-like responses while considering the user's emotions. The system mainly consists of the following elements.

[0717] The server receives inquiry information from users and performs initial analysis through information processing tools. During this process, user sentiment data sent along with the inquiry is also collected.

[0718] The emotion engine analyzes this emotional data to recognize what emotions the user is experiencing. For example, emotions such as "anger," "joy," and "anxiety" may be identified.

[0719] The server adjusts its response generation mechanisms based on the recognized emotions, generating a response that aligns with the user's feelings. This response not only conveys facts but also includes nuances that reflect an understanding of the user's emotions.

[0720] The server sends the generated response to the user via communication means. Emotionally responsive responses demonstrate understanding and consideration for the user, and have the effect of improving satisfaction.

[0721] When an inquiry regarding a specific service is received, the server uses a routing mechanism to assign it to the appropriate person in charge. If the user's emotional state is, for example, "anxiety," the server can assign the inquiry to a person capable of providing appropriate support.

[0722] On the terminal, the assigned staff member can receive details of the assigned inquiry and provide further support tailored to the user's feelings.

[0723] The server uses feedback learning to collect feedback from users and improve the performance of the response generation means and the emotion engine. This feedback increases the accuracy of emotion recognition and the sophistication of responses.

[0724] Specific example

[0725] For example, if a user inquires, "I'm worried because I missed the payment deadline," the server might not simply respond with a businesslike "Here's how to pay," but rather, through its emotional engine, provide a more empathetic response such as, "Don't worry. You can proceed with these steps and use the service with peace of mind." This can give users a greater sense of security and increase their trust in the system.

[0726] The following describes the processing flow.

[0727] Step 1:

[0728] Users enter and submit inquiries through an online customer service interface. In this process, the user's input may include elements that express emotion (e.g., language choice or emojis).

[0729] Step 2:

[0730] The server receives query data from the user, formats the data, and performs basic integrity checks.

[0731] Step 3:

[0732] The server passes the received query to a natural language processing engine for linguistic analysis. This analysis identifies important words and sentence structures.

[0733] Step 4:

[0734] The server uses an emotion engine to recognize the user's emotions from the wording and emojis included in the query data. In this step, specific emotions such as "anger," "joy," and "anxiety" are extracted.

[0735] Step 5:

[0736] Based on the analyzed content and recognized emotions, the server generates an appropriate response using a response generation mechanism. The response will be tailored to the user's emotions.

[0737] Step 6:

[0738] The server sends the generated response to the user via a communication method. The sent response will have nuances that take emotions into consideration and will be tailored to the user's needs.

[0739] Step 7:

[0740] If the inquiry is related to a specific service, the server uses a routing mechanism to automatically route the inquiry to the appropriate person in charge, taking into consideration the perceived emotions.

[0741] Step 8:

[0742] The terminal notifies the business person of the inquiry that has been routed to them, and the business person provides feedback and additional support while keeping the user's feelings in mind.

[0743] Step 9:

[0744] The server collects user feedback and uses that feedback to improve the performance of its response generation methods and emotion engine. This improves the overall response accuracy and emotion recognition capabilities of the system.

[0745] (Example 2)

[0746] 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".

[0747] This invention aims to solve the problem of needing to understand and respond to users' emotions, rather than simply providing administrative responses, when communicating with users. Conventional systems have struggled to respond in a way that considers user emotions, leading to decreased satisfaction. Furthermore, there is a need to improve the quality of responses from business personnel to routed inquiries.

[0748] 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.

[0749] In this invention, the server includes information processing means for receiving inquiry information and emotion data from a user, response generation means using a generative AI model that analyzes the inquiry information and emotion data and generates a response based on the user's emotions, and communication means for transmitting the generated response to the user. This makes it possible to improve the quality of communication and increase user satisfaction by providing responses that include nuances that take into account the user's emotions. Furthermore, it enables appropriate responses based on the user's emotion data for business personnel, thereby improving the quality of service.

[0750] An "information processing device" is a device equipped with the function of receiving inquiry information and sentiment data transmitted by users and performing initial analysis of this data.

[0751] A "generative AI model" is an artificial intelligence program used to generate appropriate and emotionally resonant responses based on user inquiry information and sentiment data.

[0752] A "response generation means" is a means that has the function of generating a response to be provided to the user from analyzed data using a generation AI model.

[0753] "Communication means" refers to a device or method for quickly and effectively transmitting a generated response to a user.

[0754] A "distribution means" is a device or method that has the function of identifying inquiries related to a specific task and distributing those inquiries to the appropriate person in charge of that task.

[0755] "Display means" refers to a visual display device or method for a business person to confirm the details of an assigned inquiry.

[0756] A "feedback learning means" is a device or method for analyzing feedback information received from a user and improving the performance of a generated AI model and a response generation means based on the results.

[0757] This invention provides a system that enables more humane responses to user inquiries. It focuses on effectively processing user inquiry information and emotional data, and generating appropriate responses based on that information.

[0758] In this system, the server functions as an information processing unit, receiving inquiry information and emotion data sent by the user. The received data is then sent to a response generation unit that uses a generative AI model to generate a response tailored to the user's specific emotions and situation. The generative AI model incorporates an emotion analysis algorithm, which allows for the accurate identification of emotions such as "worry" and "joy."

[0759] The generated response is sent from the server to the user via a communication method. The user can receive a warm, considerate response that takes their emotions into account, rather than simply providing purely businesslike information.

[0760] For inquiries related to specific tasks, the server uses a routing mechanism to assign them to the appropriate person in charge. The person in charge then reviews the inquiry details on their terminal and provides support based on analyzed sentiment data. This leads to improved information provision and increased customer satisfaction.

[0761] Furthermore, the server utilizes feedback learning mechanisms to analyze feedback information obtained from users, continuously improving the performance of its generative AI models and response generation methods. This feedback loop ensures that the system is constantly optimized, enabling it to continuously provide responses tailored to user needs.

[0762] For example, if a user inquires, "I'm worried about late fees," the server can perform sentiment analysis and generate a reassuring response that reflects that anxiety. An example of a prompt would be to input a command to the AI ​​model, such as "Generate a response that is empathetic to the user's emotions," which helps the system create a desirable response.

[0763] As described above, the present invention provides specific methods and means for understanding the emotions of users and providing responses that are appropriate to them.

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] Users submit inquiries to the system. This input includes text data of the question or request, and, if possible, metadata indicating the user's sentiment. This data is fundamental information for accurately performing subsequent processing within the system.

[0767] Step 2:

[0768] The server receives this query information and sentiment data using information processing tools. The received data is stored in a database. The specific actions performed here are to standardize the data format and prepare the sentiment data for analysis. This input data becomes the material for sentiment analysis and response generation.

[0769] Step 3:

[0770] The server sends query information and sentiment data to the sentiment engine for analysis. The sentiment engine uses natural language processing techniques to identify emotions and outputs labels such as "joy" or "anxiety." The process involves detecting keywords in the text and determining emotions based on the context. This result becomes the data needed to generate the response in the next step.

[0771] Step 4:

[0772] The server uses a generative AI model to generate responses based on analyzed sentiment data. Specifically, it constructs sentences by combining appropriate phrases and expressions based on templates corresponding to sentiment labels. This output is the response text sent back to the user.

[0773] Step 5:

[0774] The server sends the generated response to the user via a communication method. This output is designed to include a more human-like response. Specifically, it delivers text data to the user's device using a data communication protocol.

[0775] Step 6:

[0776] The server receives and analyzes user feedback for feedback learning. A key function here is to store the received feedback as training data and use it to improve the accuracy of the generated AI model. The output results are data that will contribute to improving future response quality.

[0777] (Application Example 2)

[0778] 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".

[0779] Conventional response systems failed to adequately consider user emotions, resulting in uniform and impersonal responses. Furthermore, even assigned staff struggled to provide emotionally responsive responses, highlighting the need for improved user experience. Additionally, there was a lack of mechanisms to continuously improve the overall system performance by fully utilizing feedback.

[0780] 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.

[0781] In this invention, the server includes information processing means for receiving user inquiry information, response generation means for analyzing the inquiry information and generating a response based on its content, and emotion recognition means for analyzing the user's emotion data and generating a response based on that emotion. This enables more human-like responses. Furthermore, by including communication means for transmitting the generated response to the user, and distribution means for identifying inquiries related to a specific service and distributing the inquiry to a business person, business people can provide appropriate support in accordance with the user's emotions. In addition, by providing feedback learning means for collecting user feedback information and emotion data and using them as learning data to improve the performance of the response generation means and emotion recognition means, the overall performance of the system can be continuously improved.

[0782] "Information processing means" refers to a function for receiving inquiry information from users and analyzing it.

[0783] A "response generation means" is a function that generates an appropriate response based on the content of the received inquiry information.

[0784] An "emotion recognition tool" is a function that analyzes the user's emotional data and generates an emotionally conscious response based on the results.

[0785] "Communication means" refers to a function for sending the generated response to the user.

[0786] A "distribution mechanism" is a function that identifies inquiries related to a specific service and distributes them to the appropriate person in charge of that task.

[0787] "Support measures" refer to functions that provide additional information or support for specific inquiries that have been routed to a particular inquiry.

[0788] A "feedback learning method" is a function that collects feedback information and emotional data from users and uses them as learning data to improve the performance of response generation and emotion recognition methods.

[0789] This invention is primarily implemented as a system that provides emotionally conscious responses to user inquiries.

[0790] The server first receives user inquiry information and analyzes it through information processing tools. The received inquiry information also includes the user's emotional data. Specifically, the server uses a speech recognition and text analysis engine (e.g., Google Cloud Speech-to-Text) to convert speech to text, and then uses an emotional analysis engine (e.g., IBM Watson Tone Analyzer) to identify emotions from the text. During this process, emotions such as "anxiety," "joy," and "anger" are recognized.

[0791] Based on the emotional information analyzed by the emotion recognition means, the server adjusts the response generation means to generate a response that matches the user's emotions. A generation AI model (e.g., the OpenAI GPT model) is used for response generation, and specific and emotionally resonant responses are generated through prompts. The generated response is sent to the user via the communication means.

[0792] For example, if a user makes an inquiry expressing concern such as, "I'm worried about security before making a large payment," the server will recognize the user's anxiety and respond with, "Don't worry, your transaction is protected by a high level of security. Also, if you have any questions, support is available immediately."

[0793] Examples of prompts for a generative AI model include the following:

[0794] "User inquiry: 'I'm worried about security, so I'd like to confirm before making a large payment.' AI response: Generate a response here that includes consideration to alleviate the user's concerns."

[0795] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0796] Step 1:

[0797] The server receives voice inquiries from users. The input here is the user's voice data, and the server uses a speech recognition engine to convert this voice data into text data. Specifically, this involves digitizing the voice collected by the microphone and sending it to Google Cloud Speech-to-Text.

[0798] Step 2:

[0799] The server passes the converted text data to the sentiment analysis engine. To recognize emotions from the input text, it calls the IBM Watson Tone Analyzer to identify the emotion labels in the text (e.g., "anxiety," "joy," "anger," etc.). This specifically involves sending the text data to the analysis engine and applying the sentiment classification algorithm.

[0800] Step 3:

[0801] The server invokes a response generation engine based on the recognized emotion data. Here, the OpenAI GPT generative AI model is used to form a prompt. This prompt contains instructions for generating a response that takes a specific emotion into account. Specifically, this involves constructing a prompt based on emotion labels and inputting it into the AI ​​model.

[0802] Step 4:

[0803] The server sends the generated response to the user. The text output obtained from the response generation engine is transmitted to the user's terminal via communication means. This specific operation involves transferring data over the network and displaying or playing it on the user's device.

[0804] Step 5:

[0805] User feedback is sent to the server. This feedback may include evaluations of the response quality and additional sentiment information. This input is processed by a feedback learning mechanism to improve the performance of the response generation mechanism and the sentiment recognition mechanism. Specifically, this involves collecting evaluation data and using it for analysis to improve the system.

[0806] 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.

[0807] 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.

[0808] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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."

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] Information processing means for receiving inquiry information from users,

[0830] A response generation means that analyzes the aforementioned inquiry information and generates a response based on its content,

[0831] A communication means for sending the generated response to the user,

[0832] A distribution means for identifying inquiries related to a specific service and distributing those inquiries to the appropriate personnel,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, characterized in that it includes a support mechanism for providing additional information or support in response to specific inquiries assigned to business personnel.

[0836] (Claim 3)

[0837] The system according to claim 1, further comprising a feedback learning means for collecting user feedback information and using it as learning data to improve the performance of the response generation means.

[0838] "Example 1"

[0839] (Claim 1)

[0840] Information processing means for receiving inquiry information from users,

[0841] A natural language processing means that analyzes the aforementioned inquiry information and generates a response based on its content,

[0842] A data transmission means for sending the generated response to the user,

[0843] An inquiry management system that identifies inquiries related to specific tasks and assigns those inquiries to the person performing the task,

[0844] A data adaptation means that collects feedback information from users and uses it as training data to improve the capabilities of the response generation means,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, characterized in that it includes a means for providing additional information or support in response to specific inquiries assigned to employees.

[0848] (Claim 3)

[0849] The system according to claim 1, characterized in that the natural language processing means generates a response using a generative AI model.

[0850] "Application Example 1"

[0851] (Claim 1)

[0852] Information processing means for receiving inquiry information from users,

[0853] A natural language generation means that analyzes the aforementioned inquiry information and generates a response based on its content,

[0854] A communication means for sending the generated response to the user,

[0855] A distribution means that identifies inquiries related to specific tasks and distributes those inquiries to the person in charge of those tasks,

[0856] A means of automatically processing inquiries regarding purchasing procedures, return procedures, and delivery status confirmation procedures,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, characterized in that it includes means for providing additional information or support in response to specific inquiries assigned to business personnel.

[0860] (Claim 3)

[0861] The system according to claim 1, characterized by comprising a feedback learning means that collects evaluation information from users and uses it as learning data to improve the performance of a natural language generation means.

[0862] "Example 2 of combining an emotion engine"

[0863] (Claim 1)

[0864] Information processing means for receiving inquiry information and sentiment data from users,

[0865] A response generation means using a generative AI model that analyzes the aforementioned inquiry information and emotion data and generates a response based on the user's emotions,

[0866] A communication means for sending the generated response to the user,

[0867] A distribution means that identifies inquiries related to specific tasks and distributes those inquiries to the person in charge of those tasks,

[0868] A display method that shows the details of inquiries assigned to the person in charge of the task,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, characterized in that it provides additional information or support based on analyzed sentiment data in response to specific inquiries assigned to business personnel.

[0872] (Claim 3)

[0873] The system according to claim 1, characterized in that it collects feedback information from users and uses it as training data to improve the performance of the response generation means and emotion data analysis using a generative AI model.

[0874] "Application example 2 when combining with an emotional engine"

[0875] (Claim 1)

[0876] Information processing means for receiving inquiry information from users,

[0877] A response generation means that analyzes the aforementioned inquiry information and generates a response based on its content,

[0878] An emotion recognition means that analyzes user emotion data and generates a response based on that emotion,

[0879] A communication means for sending the generated response to the user,

[0880] A distribution means for identifying inquiries related to a specific service and distributing those inquiries to the appropriate personnel,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, characterized in that it includes a support mechanism for providing additional information or support tailored to the user's emotions in response to specific inquiries assigned to business personnel.

[0884] (Claim 3)

[0885] The system according to claim 1, further comprising a feedback learning means that collects user feedback information and emotion data and uses them as learning data to improve the performance of the response generation means and the emotion recognition means. [Explanation of Symbols]

[0886] 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. Information processing means for receiving inquiry information from users, A response generation means that analyzes the aforementioned inquiry information and generates a response based on its content, A communication means for sending the generated response to the user, A distribution means for identifying inquiries related to a specific service and distributing those inquiries to the appropriate personnel, A system that includes this.

2. The system according to claim 1, characterized in that it includes a support means for providing additional information or support in response to specific inquiries assigned to business personnel.

3. The system according to claim 1, further comprising a feedback learning means for collecting user feedback information and using it as learning data to improve the performance of the response generation means.

Images