system

Abstract

To provide a system that responds to customer requirements promptly and efficiently.SOLUTION: A system according to an embodiment comprises: a reception unit; a summarization unit; a collation unit; a response unit; and a connection unit. The reception unit receives customer requirements. The summarization unit summarizes the requirements received by the reception unit. The collation unit collates the summary generated by the summarization unit with a FAQ database. The response unit provides a primary response on the basis of the result obtained by the collation unit. The connection unit connects to a person in charge when the response unit is unable to provide the primary response.SELECTED DRAWING: Figure 1

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 executed by at least one processor, the method comprising: receiving a user utterance; adding the user utterance to a prompt including an instruction associated with a description related to a character of a chatbot; encoding the prompt; and inputting the encoded prompt to a language model to generate a chatbot utterance responding to the user utterance.

Prior Art Literature

Patent Literature

[0003]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] In the conventional technology, it is difficult to quickly and efficiently respond to customer requirements, and improvement of customer experience is desired.

[0005] The system according to the embodiment aims to quickly and efficiently respond to customer requirements.

Means for Solving the Problem

[0006] The system according to this embodiment comprises a reception unit, a summarization unit, a matching unit, a response unit, and a connection unit. The reception unit receives customer requirements. The summarization unit summarizes the requirements received by the reception unit. The matching unit matches the summary generated by the summarization unit with an FAQ database. The response unit provides an initial response based on the results obtained by the matching unit. The connection unit connects the customer to a relevant person if the response unit is unable to provide an initial response. [Effects of the Invention]

[0007] The system according to this embodiment can respond quickly and efficiently to customer requirements. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] 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.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiment, the referenced communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like.

[0015] In the following embodiment, "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 only A, may be only B, or may be a combination of A and B. In addition, in the present specification, when three or more matters are expressed by connecting with "and / or", the same concept as "A and / or B" applies.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing apparatus 12 and a smart device 14. A server is an example of the data processing apparatus 12.

[0018] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include WAN (Wide Area Network) and / or LAN (Local Area Network), and the like.

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The customer support system according to an embodiment of the present invention is a system that automatically summarizes customer requirements and provides appropriate responses. When a customer calls the call center, a generating AI answers the call and prompts the customer to state their requirements. The generating AI analyzes what the customer says in real time and generates a summary. This summary is compared with an FAQ database, and if a corresponding answer is found, the generating AI provides an initial response on the spot. If there is no corresponding answer in the FAQ database, or if staff assistance is required, the generating AI connects the call to the appropriate person based on the summary. Because the person in charge refers to the summary generated by the generating AI, they can efficiently resolve the issue. This allows customers to receive quick answers without cumbersome operations, improving the customer experience. Furthermore, staff can respond based on summaries, increasing operational efficiency. As a result, the customer support system can automatically summarize customer requirements and provide appropriate responses.

[0029] The customer service system according to this embodiment comprises a reception unit, a summarization unit, a matching unit, a response unit, and a connection unit. The reception unit receives customer requirements. Customer requirements include, but are not limited to, inquiries, complaints, and requests. The reception unit can receive customer requirements using means such as telephone, email, and chat. The summarization unit uses a generation AI to summarize the requirements received by the reception unit. Summarization is performed based on, for example, the length of the text and the importance of the information to be summarized, but is not limited to these examples. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the requirements. The summarization unit can also use a multimodal generation AI to summarize the content of the requirements. The summarization unit can also use a generation AI to extract and summarize important parts of the text. For example, a text generation AI has learned from a large amount of text data and has advanced natural language processing capabilities. A multimodal generation AI can handle multiple modals, such as images and audio, in addition to text. The generation AI uses keyword extraction technology to pick out particularly important information from the requirements and performs summarization based on that. The matching unit compares the summaries generated by the summarization unit with the FAQ database. Matching is performed using methods such as cosine similarity or Jaccard coefficients, but is not limited to these examples. For example, the matching unit calculates the similarity between the summaries and the answers in the FAQ database using cosine similarity. The matching unit can also calculate similarity using Jaccard coefficients. Furthermore, the matching unit can calculate similarity using TF-IDF. For example, as cosine similarity, the matching unit calculates the angle between two vectors in a vector space model, determining that a smaller angle indicates higher similarity. The Jaccard coefficient is the value obtained by dividing the size of the intersection of two sets by the size of the whole, indicating the degree of overlap between the sets. TF-IDF is an index that evaluates the importance of words in a document, and is used to calculate the similarity between the summaries and the answers in the FAQ database. Some or all of the above processing in the matching unit may be performed using AI, or not, for example.For example, the matching unit can calculate similarity using an AI model that takes the summary generated by the summarizing unit and the answers in the FAQ database as input and outputs similarity. The answering unit provides a primary response based on the results obtained by the matching unit. The primary response can be, for example, provided directly from the FAQ database or generated using a generative AI, but is not limited to these examples. For example, the answering unit provides directly from the FAQ database. The answering unit can also generate a response based on the answers in the FAQ database using a generative AI. The answering unit can also generate a response that is not in the FAQ database using a generative AI. For example, the answering unit can generate a response using an AI model that takes the answers in the FAQ database as input and outputs a response. The connection unit connects the customer to a representative if the answering unit cannot provide a primary response. The connection can be, for example, made by means of telephone, email, chat, etc., but is not limited to these examples. For example, the connection unit connects the customer to a representative by telephone. The connection unit can also connect the customer to a representative by email. The connection unit can also connect the customer to a representative by chat. As a result, the customer support system according to this embodiment can automatically summarize customer requirements and provide appropriate responses. Some or all of the processing described above in the connection unit may be performed using AI, for example, or without AI. For example, the connection unit can take the summary generated by the summarization unit as input and perform the connection using an AI model that connects to the person in charge.

[0030] The reception department receives customer requests. These requests include, but are not limited to, inquiries, complaints, and requests. The reception department can receive customer requests using various means, such as telephone, email, and chat. Specifically, telephone requests use an automated voice response system to categorize customer requests and transfer them to the appropriate department. Email requests are automatically analyzed and categorized according to the type and urgency of the request. Chat requests are handled by a chatbot, which provides initial support and transfers the request to a human operator if necessary. This allows the reception department to receive customer requests quickly and efficiently using a variety of methods. The reception department also records customer requests in a database so that subsequent processing departments can refer to them. For example, information such as the customer's name, contact information, request details, and reception date and time are centrally managed, enabling other departments to respond quickly. Furthermore, when receiving customer requests, the reception department can refer to the customer's past inquiry and purchase history to provide more appropriate support. This allows the reception department not only to efficiently receive customer requests but also to contribute to improving customer satisfaction.

[0031] The summarization unit uses generative AI to summarize the requirements received by the reception unit. Summarization is performed based on, for example, the length of the text and the importance of the information to be summarized, but is not limited to these examples. Specifically, the generative AI uses text generation AI (e.g., LLM) to concisely summarize the requirements. Text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. For example, when a long inquiry email is received from a customer, the generative AI analyzes its content, extracts the important points, and generates a short summary. The summarization unit can also summarize the content of the requirements using multimodal generative AI. Multimodal generative AI can handle multiple modals, such as images and audio, in addition to text. For example, when a customer submits an inquiry with an attached image, the multimodal generative AI analyzes the image content, integrates it with the text, and performs a summary. Furthermore, the summarization unit can also use generative AI to extract and summarize important parts of a text. For example, keyword extraction technology can be used to pick out particularly important information from the requirements and perform a summary based on that. This allows the summarization unit to quickly and accurately summarize customer requirements, enabling subsequent processing departments to respond efficiently.

[0032] The matching unit compares the summary generated by the summarization unit with the FAQ database. Matching is performed using methods such as cosine similarity or Jaccard coefficients, but is not limited to these examples. Specifically, the matching unit calculates the similarity between the summary and the answers in the FAQ database using cosine similarity. Cosine similarity calculates the angle between two vectors in a vector space model; a smaller angle indicates higher similarity. The matching unit can also calculate similarity using Jaccard coefficients. Jaccard coefficients are the value obtained by dividing the size of the intersection of two sets by the size of the whole, indicating the degree of overlap between the sets. Furthermore, the matching unit can also calculate similarity using TF-IDF. TF-IDF is an index that evaluates the importance of words in a document, and is used to calculate the similarity between the summary and the answers in the FAQ database. For example, the matching unit can calculate similarity using an AI model that takes the summary generated by the summarization unit and the answers in the FAQ database as input and outputs similarity. The AI ​​model has been trained on a large amount of data and possesses advanced similarity calculation capabilities. This allows the matching unit to quickly and accurately calculate the similarity between the summary and the answers in the FAQ database, and select the optimal answer. Furthermore, based on the similarity calculation results, the matching unit selects the most appropriate answer from the FAQ database and provides it to the subsequent answer unit. This enables the matching unit to build a foundation for providing quick and appropriate answers to customer requirements.

[0033] The response unit provides an initial response based on the results obtained by the verification unit. This initial response may be provided directly from the FAQ database or generated using a generative AI, but is not limited to these examples. Specifically, the response unit provides directly from the FAQ database. For example, if an existing answer in the FAQ database is appropriate to a customer inquiry, that answer is provided directly. The response unit can also generate an answer based on the FAQ database using a generative AI. For example, if an answer in the FAQ database is only partially applicable, the generative AI will generate a more specific and appropriate answer based on that answer. Furthermore, the response unit can also generate an answer that is not in the FAQ database using a generative AI. For example, if a customer inquiry is new and no corresponding answer exists in the FAQ database, the generative AI will generate a new answer based on past data and related information. This allows the response unit to provide a quick and appropriate response to customer requirements. Additionally, the response unit can record the history of the answers provided in a database and utilize it for future inquiry handling. This allows the response unit to improve the efficiency and quality of customer service.

[0034] The connection unit connects to a representative when the answering unit cannot provide an initial response. Connections are made using methods such as phone, email, and chat, but are not limited to these. Specifically, the connection unit connects to a representative via phone. For example, if a customer inquiry is complex and cannot be handled by an initial response, the connection unit automatically transfers the call to a representative. The connection unit can also connect to a representative via email. For example, it can summarize the customer's inquiry and send it to the representative via email to facilitate a quick response. Furthermore, the connection unit can connect to a representative via chat. For example, a chatbot can provide an initial response and, if necessary, transfer the chat to a human operator. This allows the connection unit to respond quickly and appropriately to customer requirements. Additionally, the connection unit can record connection history to representatives in a database, which can be used for future inquiry handling. For example, by referring to past connection history, similar inquiries can be handled quickly. The connection unit can also optimize connections using AI. For example, it can use an AI model that takes a summary generated by the summarizing unit as input to select the most suitable representative and connect them. This allows the connection section to improve the efficiency and quality of customer service.

[0035] The summarization unit includes an algorithm for generating summaries. The summarization unit generates summaries using, for example, natural language processing techniques. For example, the summarization unit generates summaries using text generation AI (e.g., LLM). The summarization unit can also generate summaries using machine learning algorithms. For example, the summarization unit generates summaries using supervised learning. The summarization unit can also generate summaries using unsupervised learning. For example, the summarization unit generates summaries using clustering algorithms. This allows the summarization unit to improve the accuracy of summary generation. Some or all of the above processing in the summarization unit may be performed using, for example, AI, or without AI. For example, the summarization unit can generate summaries using an AI model that takes a summary generation algorithm as input and outputs summaries.

[0036] The matching unit has the structure of an FAQ database. The structure of the FAQ database includes, but is not limited to, the database schema and data storage method. For example, the FAQ database can be built using a relational database. Alternatively, the FAQ database can be built using a NoSQL database. For example, the FAQ database can be built using a key-value store. Alternatively, the FAQ database can be built using a document store. For example, the FAQ database has tables that store question-answer pairs as the database schema. Data storage methods include storing questions and answers in text format or in JSON format. This allows the FAQ database to be used efficiently. Some or all of the above processing in the FAQ database may be performed using, for example, AI, or not using AI. For example, the FAQ database structure can be constructed using an AI model that takes the database schema as input and outputs the data storage method.

[0037] The customer service system includes an encryption unit for privacy protection. The encryption unit encrypts customer data using, for example, an encryption algorithm. For instance, the encryption unit might use AES (Advanced Encryption Standard) to encrypt data. Alternatively, the encryption unit could use RSA (Rivest-Shamir-Adleman) to encrypt data. For example, the encryption unit could encrypt data using AES and the encryption key using RSA. Furthermore, the encryption unit could encrypt data using a hybrid encryption method. For example, the encryption unit could encrypt data by combining symmetric-key and public-key cryptography. This ensures customer privacy. Some or all of the above processing in the encryption unit may be performed using, for example, AI, or not. For example, the encryption unit could encrypt data using an AI model that takes an encryption algorithm as input and outputs encrypted data.

[0038] The customer service system includes a method for notifying the assigned staff member. This method may include, but is not limited to, email notifications, push notifications, and SMS notifications. For example, the notification method could be email to the staff member. Alternatively, the notification method could use push notifications. For example, a smartphone app could be used to send push notifications. Alternatively, SMS could be used to send urgent notifications to the staff member. This enables rapid notification to the staff member. Some or all of the above-described processes in the notification method may be performed using, for example, AI, or not. For example, the notification method could use an AI model that takes the notification method as input and outputs the notification content.

[0039] The reception desk can analyze a customer's past inquiry history and select the most appropriate response method. For example, the reception desk can use a generating AI to select an appropriate response method based on the content of inquiries the customer has frequently made in the past. The reception desk can also identify specific patterns from the customer's past inquiry history and the generating AI can respond based on those patterns. Furthermore, the reception desk can prioritize suggesting response methods (voice, text, etc.) that the customer has used in the past. This enables the most appropriate response based on past inquiry history. Some or all of the above processes in the reception desk may be performed using AI, or not. For example, the reception desk can input the customer's past inquiry history data into the generating AI and have the generating AI select the most appropriate response method.

[0040] The reception desk can filter customers based on their current situation and areas of interest during the reception process. For example, when a customer describes their current situation, the generating AI can use that information to perform appropriate filtering. The reception desk can also have the generating AI prioritize questions relevant to the customer's areas of interest. Furthermore, the reception desk can have the generating AI select an appropriate response method depending on the customer's current situation. This enables appropriate filtering according to the customer's situation and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input data on the customer's current situation and areas of interest into the generating AI and have the generating AI perform the filtering.

[0041] The reception desk can prioritize receiving requests based on the customer's geographical location information. For example, if a customer is in a specific region, the reception desk will prioritize requests related to that region. The reception desk can also use the customer's geographical location information to have a generating AI select an appropriate response method. Furthermore, if the customer is on the move, the generating AI can update the geographical location information in real time and receive appropriate requests. This enables the reception of appropriate requests based on geographical location information. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the customer's geographical location information into a generating AI and have the generating AI perform the request reception.

[0042] The reception department can analyze the customer's social media activity and receive relevant requirements at the time of reception. For example, the reception department can use a generative AI to prioritize receiving relevant requirements based on the customer's social media activity. The reception department can also use a generative AI to select an appropriate response method based on what the customer has mentioned on social media. Furthermore, the reception department can analyze the customer's social media activity and use a generative AI to receive relevant requirements. This enables the reception of appropriate requirements based on social media activity. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input customer social media activity data into a generative AI and have the generative AI perform the requirement reception.

[0043] The summarization unit can adjust the level of detail of a summary based on the importance of the requirements during summary generation. For example, the summarization unit can generate a detailed summary using the generating AI for high-importance requirements. It can also generate a concise summary using the generating AI for low-importance requirements. Furthermore, the summarization unit can adjust the level of detail of the summary using the generating AI according to the importance of the requirements. This enables appropriate summaries tailored to the importance of the requirements. Some or all of the above processing in the summarization unit may be performed using AI, or without AI. For example, the summarization unit can input requirement importance data into the generating AI and have the generating AI adjust the level of detail of the summary.

[0044] The summarization unit can apply different summarization algorithms depending on the category of requirements when generating summaries. For example, the summarization unit can apply a specialized summarization algorithm to technical requirements using a generating AI. Alternatively, the summarization unit can apply a simpler summarization algorithm to general requirements using a generating AI. Furthermore, the summarization unit can select the optimal summarization algorithm based on the category of requirements using a generating AI. This enables appropriate summaries tailored to the category of requirements. Some or all of the above-described processes in the summarization unit may be performed using AI, or not. For example, the summarization unit can input requirement category data into the generating AI and have the generating AI apply the summarization algorithm.

[0045] The summarization unit can determine the priority of summaries based on the submission date of the requirements when generating summaries. For example, the generation AI may prioritize summarizing recently submitted requirements. The summarization unit can also delay the generation of summaries for older requirements. Furthermore, the generation AI can determine the priority of summaries according to the submission date of the requirements. This enables appropriate summary prioritization based on submission date. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input requirement submission date data into the generation AI and have the generation AI perform the determination of summary priority.

[0046] The summarization unit can adjust the order of summaries based on the relevance of the requirements during summary generation. For example, the generation AI can prioritize summarizing highly relevant requirements. The summarization unit can also postpone summarizing less relevant requirements. Furthermore, the generation AI can adjust the order of summaries according to the relevance of the requirements. This enables appropriate ordering of summaries based on relevance. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input requirement relevance data into the generation AI and have the generation AI adjust the order of summaries.

[0047] The matching unit can improve the accuracy of the matching process based on the interrelationships of the requirements. For example, the matching unit can analyze the interrelationships of the requirements, and the generating AI can prioritize matching the relevant requirements. The matching unit can also consider the interrelationships of the requirements, allowing the generating AI to improve the accuracy of the matching process. Furthermore, the matching unit can allow the generating AI to select the optimal matching method based on the interrelationships of the requirements. This enables appropriate matching based on the interrelationships of the requirements. Some or all of the above-described processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input the interrelationship data of the requirements into the generating AI and have the generating AI perform the matching accuracy improvement.

[0048] The matching unit can perform matching based on the attribute information of the requirements submitter during the matching process. For example, the matching unit's generating AI can select an appropriate matching method based on the submitter's attribute information. The matching unit can also improve the accuracy of the matching by considering the submitter's attribute information and enabling the generating AI to do so. Furthermore, the matching unit can apply optimal matching criteria based on the submitter's attribute information and enable appropriate matching based on the submitter's attribute information. Some or all of the above-described processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input the submitter's attribute information data into the generating AI and have the generating AI perform the matching.

[0049] The matching unit can perform matching based on the geographical distribution of requirements. For example, the matching unit's generating AI can select an appropriate matching method based on the geographical distribution of requirements. The matching unit can also improve the accuracy of matching by considering the geographical distribution of requirements and enabling the generating AI to do so. Furthermore, the matching unit can apply optimal matching criteria based on the geographical distribution of requirements and enable appropriate matching based on geographical distribution. Some or all of the above-described processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input geographical distribution data of requirements into the generating AI and have the generating AI perform the matching.

[0050] The matching unit can improve the accuracy of the matching by referring to relevant literature during the matching process. For example, the matching unit's generating AI can select an appropriate matching method based on the relevant literature. The matching unit can also improve the accuracy of the matching by referring to the relevant literature and allowing the generating AI to do so. Furthermore, the matching unit can apply optimal matching criteria based on the relevant literature and allowing the generating AI to do so. This enables appropriate matching based on relevant literature. Some or all of the above processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input relevant literature data into the generating AI and have the generating AI perform the matching accuracy improvement.

[0051] The response unit can adjust the level of detail in its response based on the importance of the requirements. For example, the AI ​​can provide a detailed response to high-importance requirements. The AI ​​can also provide a concise response to low-importance requirements. Furthermore, the AI ​​can adjust the level of detail in the response according to the importance of the requirements. This enables appropriate responses according to the importance of the requirements. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input requirement importance data into the AI ​​and have the AI ​​adjust the level of detail in the response.

[0052] The response unit can apply different response algorithms depending on the category of the requirement when providing a response. For example, the response unit can use a specialized response algorithm generated by the generation AI for technical requirements. Alternatively, the response unit can use a simpler response algorithm generated by the generation AI for general requirements. Furthermore, the response unit can use the generation AI to select the optimal response algorithm depending on the category of the requirement. This enables appropriate responses according to the category of the requirement. Some or all of the above processing in the response unit may be performed using AI, or not. For example, the response unit can input requirement category data into the generation AI and have the generation AI apply the response algorithm.

[0053] The response unit can determine the priority of responses based on the submission date of the requirements. For example, the response unit's generating AI may prioritize responses to recently submitted requirements. The response unit can also delay responses to older requirements. Furthermore, the response unit can have the generating AI determine the priority of responses based on the submission date of the requirements. This enables appropriate prioritization of responses based on submission date. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input requirement submission date data into the generating AI and have the generating AI determine the priority of responses.

[0054] The response unit can adjust the order of responses based on the relevance of the requirements when providing a response. For example, the response unit can prioritize providing responses to highly relevant requirements using its generating AI. The response unit can also postpone providing responses to less relevant requirements using its generating AI. Furthermore, the response unit can adjust the order of responses using its generating AI according to the relevance of the requirements. This enables appropriate ordering of responses based on relevance. Some or all of the above processing in the response unit may be performed using AI, or not. For example, the response unit can input requirement relevance data into the generating AI and have the generating AI adjust the order of responses.

[0055] The connection unit can determine connection priorities based on the importance of the requirements during connection. For example, it can prioritize connecting to the responsible person for high-priority requirements. It can also connect to low-priority requirements using the normal procedure. Furthermore, the connection unit can adjust the connection priority according to the importance of the requirements. This enables appropriate connection prioritization according to the importance of the requirements. Some or all of the above processing in the connection unit may be performed using AI, for example, or not using AI. For example, the connection unit can input requirement importance data into a generating AI and have the generating AI perform the determination of connection priorities.

[0056] The connection unit can apply different connection methods depending on the category of requirements during connection. For example, the connection unit can connect to a specialist for technical requirements. It can also connect to a regular person for general requirements. Furthermore, the connection unit can select the optimal connection method depending on the category of requirements. This enables appropriate connections according to the category of requirements. Some or all of the above processing in the connection unit may be performed using AI, for example, or without AI. For example, the connection unit can input requirement category data into a generating AI and have the generating AI apply the connection method.

[0057] The connection unit can determine connection priorities based on the submission date of the requirements at the time of connection. For example, the connection unit will prioritize connecting to the responsible person for recently submitted requirements. The connection unit can also connect to older requirements using the normal procedure. Furthermore, the connection unit can adjust the connection priority according to the submission date of the requirements. This enables appropriate connection prioritization based on submission date. Some or all of the above processing in the connection unit may be performed using AI, for example, or not using AI. For example, the connection unit can input requirement submission date data into a generating AI and have the generating AI perform the determination of connection priorities.

[0058] The connection unit can adjust the order of connections based on the relevance of the requirements during the connection process. For example, the connection unit can prioritize connecting to the appropriate person for highly relevant requirements. It can also connect to less relevant requirements using the normal procedure. Furthermore, the connection unit can adjust the order of connections according to the relevance of the requirements. This enables appropriate connection ordering based on relevance. Some or all of the above processing in the connection unit may be performed using AI, for example, or without AI. For example, the connection unit can input requirement relevance data into a generating AI and have the generating AI perform the adjustment of the connection order.

[0059] The encryption unit can adjust the level of detail of encryption based on the importance of the requirements during encryption. For example, the encryption unit can apply detailed encryption to high-importance requirements. It can also apply simplified encryption to low-importance requirements. Furthermore, the encryption unit can adjust the level of detail of encryption according to the importance of the requirements. This enables appropriate encryption according to the importance of the requirements. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input requirement importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of encryption.

[0060] The encryption unit can determine the encryption priority based on the submission date of the requirements during encryption. For example, the encryption unit may prioritize encryption of recently submitted requirements. It can also encrypt older requirements using the standard procedure. Furthermore, the encryption unit can adjust the encryption priority according to the submission date of the requirements. This enables appropriate encryption prioritization based on the submission date. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input requirement submission date data into a generating AI and have the generating AI determine the encryption priority.

[0061] The notification method can adjust the level of detail of notifications based on the importance of the requirements. For example, the notification method can provide detailed notifications for high-importance requirements, and concise notifications for low-importance requirements. Furthermore, the notification method can adjust the level of detail of notifications according to the importance of the requirements. This enables appropriate notifications according to the importance of the requirements. Some or all of the above processing in the notification method may be performed using AI, for example, or not using AI. For example, the notification method can input requirement importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the notifications.

[0062] The notification method can prioritize notifications based on the submission date of the requirements. For example, it can prioritize notifications for recently submitted requirements. It can also send notifications for older requirements using the standard procedure. Furthermore, it can adjust the priority of notifications according to the submission date of the requirements. This enables appropriate notification prioritization based on submission date. Some or all of the above processing in the notification method may be performed using AI, for example, or not using AI. For example, the notification method can input requirement submission date data into a generating AI and have the generating AI determine the notification priority.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The customer service system can further analyze a customer's past purchase history and incorporate it into the summaries generated by the summarization unit. For example, if a customer has requirements related to products or services they have purchased in the past, the summarization unit can include that information in the summary. It can also generate summaries based on information if a customer frequently purchases products from a particular brand or category. Furthermore, it can identify specific trends and patterns from the customer's purchase history and adjust the summary accordingly. This enables more accurate summaries based on the customer's past purchase history.

[0065] The customer service system can further analyze customers' social media activity and reflect this in the summaries generated by the summarization department. For example, it can include what customers have mentioned or topics they are interested in on social media. It can also generate summaries based on information such as customers frequently using specific hashtags or keywords. Furthermore, it can identify specific trends and patterns from customers' social media activity and adjust the summaries accordingly. This enables more accurate summaries based on customers' social media activity.

[0066] The customer service system can further analyze the customer's geographical location and reflect this in the summaries generated by the summarization unit. For example, if a customer is in a specific region, the summary can include information relevant to that region. Furthermore, if a customer is on the move, the system can update their geographical location in real time and generate summaries based on that information. It can also identify specific trends and patterns from the customer's geographical location and adjust the summaries accordingly. This enables more accurate summaries based on the customer's geographical location.

[0067] The customer support system can further analyze a customer's past inquiry history and reflect this in the summaries generated by the summarization unit. For example, it can include the content and solutions of past inquiries by the customer in the summary. It can also generate summaries based on information if a customer frequently inquires about specific problems or questions. Furthermore, it can identify specific trends and patterns from the customer's inquiry history and adjust the summary accordingly. This enables more accurate summaries based on the customer's past inquiry history.

[0068] The customer service system can further analyze the customer's current situation and areas of interest, and reflect this in the summaries generated by the summarization unit. For example, when a customer describes their current situation, that information can be included in the summary. It can also include relevant information based on the customer's areas of interest. Furthermore, it can identify specific trends and patterns from the customer's current situation and areas of interest, and adjust the summary accordingly. This enables more accurate summaries based on the customer's current situation and areas of interest.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The reception desk receives customer requests. These requests may include inquiries, complaints, and requests. The reception desk can receive customer requests via telephone, email, chat, or other means. Step 2: The summarization unit uses a generation AI to summarize the requirements received by the reception unit. The summarization is based on the length of the text and the importance of the information to be summarized. The generation AI uses a text generation AI (e.g., LLM) or a multimodal generation AI to concisely summarize the requirements. Step 3: The matching unit compares the summaries generated by the summarization unit with the FAQ database. The matching is performed using methods such as cosine similarity, Jaccard coefficients, and TF-IDF. The matching unit uses these methods to calculate the similarity between the summaries and the answers in the FAQ database. Step 4: The response unit provides a preliminary response based on the results obtained by the verification unit. The preliminary response can be provided either by directly using the answer from the FAQ database or by generating an answer using a generation AI. Step 5: The connection unit connects the caller to a representative if the response unit is unable to provide an initial response. The connection is made using methods such as telephone, email, or chat.

[0071] (Example of form 2) The customer support system according to an embodiment of the present invention is a system that automatically summarizes customer requirements and provides appropriate responses. When a customer calls the call center, a generating AI answers the call and prompts the customer to state their requirements. The generating AI analyzes what the customer says in real time and generates a summary. This summary is compared with an FAQ database, and if a corresponding answer is found, the generating AI provides an initial response on the spot. If there is no corresponding answer in the FAQ database, or if staff assistance is required, the generating AI connects the call to the appropriate person based on the summary. Because the person in charge refers to the summary generated by the generating AI, they can efficiently resolve the issue. This allows customers to receive quick answers without cumbersome operations, improving the customer experience. Furthermore, staff can respond based on summaries, increasing operational efficiency. As a result, the customer support system can automatically summarize customer requirements and provide appropriate responses.

[0072] The customer service system according to this embodiment comprises a reception unit, a summarization unit, a matching unit, a response unit, and a connection unit. The reception unit receives customer requirements. Customer requirements include, but are not limited to, inquiries, complaints, and requests. The reception unit can receive customer requirements using means such as telephone, email, and chat. The summarization unit uses a generation AI to summarize the requirements received by the reception unit. Summarization is performed based on, for example, the length of the text and the importance of the information to be summarized, but is not limited to these examples. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the requirements. The summarization unit can also use a multimodal generation AI to summarize the content of the requirements. The summarization unit can also use a generation AI to extract and summarize important parts of the text. For example, a text generation AI has learned from a large amount of text data and has advanced natural language processing capabilities. A multimodal generation AI can handle multiple modals, such as images and audio, in addition to text. The generation AI uses keyword extraction technology to pick out particularly important information from the requirements and performs summarization based on that. The matching unit compares the summaries generated by the summarization unit with the FAQ database. Matching is performed using methods such as cosine similarity or Jaccard coefficients, but is not limited to these examples. For example, the matching unit calculates the similarity between the summaries and the answers in the FAQ database using cosine similarity. The matching unit can also calculate similarity using Jaccard coefficients. Furthermore, the matching unit can calculate similarity using TF-IDF. For example, as cosine similarity, the matching unit calculates the angle between two vectors in a vector space model, determining that a smaller angle indicates higher similarity. The Jaccard coefficient is the value obtained by dividing the size of the intersection of two sets by the size of the whole, indicating the degree of overlap between the sets. TF-IDF is an index that evaluates the importance of words in a document, and is used to calculate the similarity between the summaries and the answers in the FAQ database. Some or all of the above processing in the matching unit may be performed using AI, or not, for example.For example, the matching unit can calculate similarity using an AI model that takes the summary generated by the summarizing unit and the answers in the FAQ database as input and outputs similarity. The answering unit provides a primary response based on the results obtained by the matching unit. The primary response can be, for example, provided directly from the FAQ database or generated using a generative AI, but is not limited to these examples. For example, the answering unit provides directly from the FAQ database. The answering unit can also generate a response based on the answers in the FAQ database using a generative AI. The answering unit can also generate a response that is not in the FAQ database using a generative AI. For example, the answering unit can generate a response using an AI model that takes the answers in the FAQ database as input and outputs a response. The connection unit connects the customer to a representative if the answering unit cannot provide a primary response. The connection can be, for example, made by means of telephone, email, chat, etc., but is not limited to these examples. For example, the connection unit connects the customer to a representative by telephone. The connection unit can also connect the customer to a representative by email. The connection unit can also connect the customer to a representative by chat. As a result, the customer support system according to this embodiment can automatically summarize customer requirements and provide appropriate responses. Some or all of the processing described above in the connection unit may be performed using AI, for example, or without AI. For example, the connection unit can take the summary generated by the summarization unit as input and perform the connection using an AI model that connects to the person in charge.

[0073] The reception department receives customer requests. These requests include, but are not limited to, inquiries, complaints, and requests. The reception department can receive customer requests using various means, such as telephone, email, and chat. Specifically, telephone requests use an automated voice response system to categorize customer requests and transfer them to the appropriate department. Email requests are automatically analyzed and categorized according to the type and urgency of the request. Chat requests are handled by a chatbot, which provides initial support and transfers the request to a human operator if necessary. This allows the reception department to receive customer requests quickly and efficiently using a variety of methods. The reception department also records customer requests in a database so that subsequent processing departments can refer to them. For example, information such as the customer's name, contact information, request details, and reception date and time are centrally managed, enabling other departments to respond quickly. Furthermore, when receiving customer requests, the reception department can refer to the customer's past inquiry and purchase history to provide more appropriate support. This allows the reception department not only to efficiently receive customer requests but also to contribute to improving customer satisfaction.

[0074] The summarization unit uses generative AI to summarize the requirements received by the reception unit. Summarization is performed based on, for example, the length of the text and the importance of the information to be summarized, but is not limited to these examples. Specifically, the generative AI uses text generation AI (e.g., LLM) to concisely summarize the requirements. Text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. For example, when a long inquiry email is received from a customer, the generative AI analyzes its content, extracts the important points, and generates a short summary. The summarization unit can also summarize the content of the requirements using multimodal generative AI. Multimodal generative AI can handle multiple modals, such as images and audio, in addition to text. For example, when a customer submits an inquiry with an attached image, the multimodal generative AI analyzes the image content, integrates it with the text, and performs a summary. Furthermore, the summarization unit can also use generative AI to extract and summarize important parts of a text. For example, keyword extraction technology can be used to pick out particularly important information from the requirements and perform a summary based on that. This allows the summarization unit to quickly and accurately summarize customer requirements, enabling subsequent processing departments to respond efficiently.

[0075] The matching unit compares the summary generated by the summarization unit with the FAQ database. Matching is performed using methods such as cosine similarity or Jaccard coefficients, but is not limited to these examples. Specifically, the matching unit calculates the similarity between the summary and the answers in the FAQ database using cosine similarity. Cosine similarity calculates the angle between two vectors in a vector space model; a smaller angle indicates higher similarity. The matching unit can also calculate similarity using Jaccard coefficients. Jaccard coefficients are the value obtained by dividing the size of the intersection of two sets by the size of the whole, indicating the degree of overlap between the sets. Furthermore, the matching unit can also calculate similarity using TF-IDF. TF-IDF is an index that evaluates the importance of words in a document, and is used to calculate the similarity between the summary and the answers in the FAQ database. For example, the matching unit can calculate similarity using an AI model that takes the summary generated by the summarization unit and the answers in the FAQ database as input and outputs similarity. The AI ​​model has been trained on a large amount of data and possesses advanced similarity calculation capabilities. This allows the matching unit to quickly and accurately calculate the similarity between the summary and the answers in the FAQ database, and select the optimal answer. Furthermore, based on the similarity calculation results, the matching unit selects the most appropriate answer from the FAQ database and provides it to the subsequent answer unit. This enables the matching unit to build a foundation for providing quick and appropriate answers to customer requirements.

[0076] The response unit provides an initial response based on the results obtained by the verification unit. This initial response may be provided directly from the FAQ database or generated using a generative AI, but is not limited to these examples. Specifically, the response unit provides directly from the FAQ database. For example, if an existing answer in the FAQ database is appropriate to a customer inquiry, that answer is provided directly. The response unit can also generate an answer based on the FAQ database using a generative AI. For example, if an answer in the FAQ database is only partially applicable, the generative AI will generate a more specific and appropriate answer based on that answer. Furthermore, the response unit can also generate an answer that is not in the FAQ database using a generative AI. For example, if a customer inquiry is new and no corresponding answer exists in the FAQ database, the generative AI will generate a new answer based on past data and related information. This allows the response unit to provide a quick and appropriate response to customer requirements. Additionally, the response unit can record the history of the answers provided in a database and utilize it for future inquiry handling. This allows the response unit to improve the efficiency and quality of customer service.

[0077] The connection unit connects to a representative when the answering unit cannot provide an initial response. Connections are made using methods such as phone, email, and chat, but are not limited to these. Specifically, the connection unit connects to a representative via phone. For example, if a customer inquiry is complex and cannot be handled by an initial response, the connection unit automatically transfers the call to a representative. The connection unit can also connect to a representative via email. For example, it can summarize the customer's inquiry and send it to the representative via email to facilitate a quick response. Furthermore, the connection unit can connect to a representative via chat. For example, a chatbot can provide an initial response and, if necessary, transfer the chat to a human operator. This allows the connection unit to respond quickly and appropriately to customer requirements. Additionally, the connection unit can record connection history to representatives in a database, which can be used for future inquiry handling. For example, by referring to past connection history, similar inquiries can be handled quickly. The connection unit can also optimize connections using AI. For example, it can use an AI model that takes a summary generated by the summarizing unit as input to select the most suitable representative and connect them. This allows the connection section to improve the efficiency and quality of customer service.

[0078] The summarization unit includes an algorithm for generating summaries. The summarization unit generates summaries using, for example, natural language processing techniques. For example, the summarization unit generates summaries using text generation AI (e.g., LLM). The summarization unit can also generate summaries using machine learning algorithms. For example, the summarization unit generates summaries using supervised learning. The summarization unit can also generate summaries using unsupervised learning. For example, the summarization unit generates summaries using clustering algorithms. This allows the summarization unit to improve the accuracy of summary generation. Some or all of the above processing in the summarization unit may be performed using, for example, AI, or without AI. For example, the summarization unit can generate summaries using an AI model that takes a summary generation algorithm as input and outputs summaries.

[0079] The matching unit has the structure of an FAQ database. The structure of the FAQ database includes, but is not limited to, the database schema and data storage method. For example, the FAQ database can be built using a relational database. Alternatively, the FAQ database can be built using a NoSQL database. For example, the FAQ database can be built using a key-value store. Alternatively, the FAQ database can be built using a document store. For example, the FAQ database has tables that store question-answer pairs as the database schema. Data storage methods include storing questions and answers in text format or in JSON format. This allows the FAQ database to be used efficiently. Some or all of the above processing in the FAQ database may be performed using, for example, AI, or not using AI. For example, the FAQ database structure can be constructed using an AI model that takes the database schema as input and outputs the data storage method.

[0080] The customer service system includes an encryption unit for privacy protection. The encryption unit encrypts customer data using, for example, an encryption algorithm. For instance, the encryption unit might use AES (Advanced Encryption Standard) to encrypt data. Alternatively, the encryption unit could use RSA (Rivest-Shamir-Adleman) to encrypt data. For example, the encryption unit could encrypt data using AES and the encryption key using RSA. Furthermore, the encryption unit could encrypt data using a hybrid encryption method. For example, the encryption unit could encrypt data by combining symmetric-key and public-key cryptography. This ensures customer privacy. Some or all of the above processing in the encryption unit may be performed using, for example, AI, or not. For example, the encryption unit could encrypt data using an AI model that takes an encryption algorithm as input and outputs encrypted data.

[0081] The customer service system includes a method for notifying the assigned staff member. This method may include, but is not limited to, email notifications, push notifications, and SMS notifications. For example, the notification method could be email to the staff member. Alternatively, the notification method could use push notifications. For example, a smartphone app could be used to send push notifications. Alternatively, SMS could be used to send urgent notifications to the staff member. This enables rapid notification to the staff member. Some or all of the above-described processes in the notification method may be performed using, for example, AI, or not. For example, the notification method could use an AI model that takes the notification method as input and outputs the notification content.

[0082] The reception desk can estimate the customer's emotions and adjust its response based on the estimated emotions. For example, if the customer is stressed, the generating AI can respond in a calm voice and ask simple questions. If the customer is relaxed, the generating AI can respond in a friendly voice and ask more detailed questions. Furthermore, if the customer is in a hurry, the generating AI can ask short questions to quickly elicit their requirements. This enables appropriate responses tailored to the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input customer voice data into a generating AI and have the generating AI perform emotion estimation.

[0083] The reception desk can analyze a customer's past inquiry history and select the most appropriate response method. For example, the reception desk can use a generating AI to select an appropriate response method based on the content of inquiries the customer has frequently made in the past. The reception desk can also identify specific patterns from the customer's past inquiry history and the generating AI can respond based on those patterns. Furthermore, the reception desk can prioritize suggesting response methods (voice, text, etc.) that the customer has used in the past. This enables the most appropriate response based on past inquiry history. Some or all of the above processes in the reception desk may be performed using AI, or not. For example, the reception desk can input the customer's past inquiry history data into the generating AI and have the generating AI select the most appropriate response method.

[0084] The reception desk can filter customers based on their current situation and areas of interest during the reception process. For example, when a customer describes their current situation, the generating AI can use that information to perform appropriate filtering. The reception desk can also have the generating AI prioritize questions relevant to the customer's areas of interest. Furthermore, the reception desk can have the generating AI select an appropriate response method depending on the customer's current situation. This enables appropriate filtering according to the customer's situation and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input data on the customer's current situation and areas of interest into the generating AI and have the generating AI perform the filtering.

[0085] The reception desk can estimate the customer's emotions and prioritize the requests to be received based on those emotions. For example, if a customer has an urgent request, the generative AI will prioritize that request. The reception desk can also have the generative AI treat the customer's request equally if the customer is relaxed. Furthermore, if the customer is stressed, the generative AI can prioritize that request to ensure a quick response. This enables prioritization of requests according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input customer voice data into the generative AI and have the generative AI determine the priority of the requests.

[0086] The reception desk can prioritize receiving requests based on the customer's geographical location information. For example, if a customer is in a specific region, the reception desk will prioritize requests related to that region. The reception desk can also use the customer's geographical location information to have a generating AI select an appropriate response method. Furthermore, if the customer is on the move, the generating AI can update the geographical location information in real time and receive appropriate requests. This enables the reception of appropriate requests based on geographical location information. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the customer's geographical location information into a generating AI and have the generating AI perform the request reception.

[0087] The reception department can analyze the customer's social media activity and receive relevant requirements at the time of reception. For example, the reception department can use a generative AI to prioritize receiving relevant requirements based on the customer's social media activity. The reception department can also use a generative AI to select an appropriate response method based on what the customer has mentioned on social media. Furthermore, the reception department can analyze the customer's social media activity and use a generative AI to receive relevant requirements. This enables the reception of appropriate requirements based on social media activity. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input customer social media activity data into a generative AI and have the generative AI perform the requirement reception.

[0088] The summarization unit can estimate the customer's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the customer is stressed, the summarization unit's generating AI can produce a simple and easy-to-understand summary. If the customer is relaxed, the generating AI can also produce a detailed summary. Furthermore, if the customer is in a hurry, the generating AI can produce a short and to-the-point summary. This enables appropriate summaries tailored to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input customer voice data into the generating AI and have the generating AI adjust the way the summary is presented.

[0089] The summarization unit can adjust the level of detail of a summary based on the importance of the requirements during summary generation. For example, the summarization unit can generate a detailed summary using the generating AI for high-importance requirements. It can also generate a concise summary using the generating AI for low-importance requirements. Furthermore, the summarization unit can adjust the level of detail of the summary using the generating AI according to the importance of the requirements. This enables appropriate summaries tailored to the importance of the requirements. Some or all of the above processing in the summarization unit may be performed using AI, or without AI. For example, the summarization unit can input requirement importance data into the generating AI and have the generating AI adjust the level of detail of the summary.

[0090] The summarization unit can apply different summarization algorithms depending on the category of requirements when generating summaries. For example, the summarization unit can apply a specialized summarization algorithm to technical requirements using a generating AI. Alternatively, the summarization unit can apply a simpler summarization algorithm to general requirements using a generating AI. Furthermore, the summarization unit can select the optimal summarization algorithm based on the category of requirements using a generating AI. This enables appropriate summaries tailored to the category of requirements. Some or all of the above-described processes in the summarization unit may be performed using AI, or not. For example, the summarization unit can input requirement category data into the generating AI and have the generating AI apply the summarization algorithm.

[0091] The summarization unit can estimate the customer's emotions and adjust the length of the summary based on the estimated emotions. For example, if the customer is stressed, the summarization unit's generating AI can produce a short, concise summary. If the customer is relaxed, the generating AI can produce a more detailed summary. Furthermore, if the customer is in a hurry, the generating AI can produce a short, concise summary. This allows for an appropriate summary length according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input customer voice data into the generating AI and have the generating AI adjust the length of the summary.

[0092] The summarization unit can determine the priority of summaries based on the submission date of the requirements when generating summaries. For example, the generation AI may prioritize summarizing recently submitted requirements. The summarization unit can also delay the generation of summaries for older requirements. Furthermore, the generation AI can determine the priority of summaries according to the submission date of the requirements. This enables appropriate summary prioritization based on submission date. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input requirement submission date data into the generation AI and have the generation AI perform the determination of summary priority.

[0093] The summarization unit can adjust the order of summaries based on the relevance of the requirements during summary generation. For example, the generation AI can prioritize summarizing highly relevant requirements. The summarization unit can also postpone summarizing less relevant requirements. Furthermore, the generation AI can adjust the order of summaries according to the relevance of the requirements. This enables appropriate ordering of summaries based on relevance. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input requirement relevance data into the generation AI and have the generation AI adjust the order of summaries.

[0094] The matching unit can estimate the customer's emotions and adjust the matching criteria based on the estimated emotions. For example, if the customer is stressed, the matching unit can have the generative AI apply simple matching criteria. If the customer is relaxed, the matching unit can have the generative AI apply more detailed matching criteria. Furthermore, if the customer is in a hurry, the matching unit can have the generative AI apply criteria for quick matching. This enables appropriate matching criteria according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the matching unit may be performed using AI or not using AI. For example, the matching unit can input customer voice data into the generative AI and have the generative AI perform the adjustment of the matching criteria.

[0095] The matching unit can improve the accuracy of the matching process based on the interrelationships of the requirements. For example, the matching unit can analyze the interrelationships of the requirements, and the generating AI can prioritize matching the relevant requirements. The matching unit can also consider the interrelationships of the requirements, allowing the generating AI to improve the accuracy of the matching process. Furthermore, the matching unit can allow the generating AI to select the optimal matching method based on the interrelationships of the requirements. This enables appropriate matching based on the interrelationships of the requirements. Some or all of the above-described processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input the interrelationship data of the requirements into the generating AI and have the generating AI perform the matching accuracy improvement.

[0096] The matching unit can perform matching based on the attribute information of the requirements submitter during the matching process. For example, the matching unit's generating AI can select an appropriate matching method based on the submitter's attribute information. The matching unit can also improve the accuracy of the matching by considering the submitter's attribute information and enabling the generating AI to do so. Furthermore, the matching unit can apply optimal matching criteria based on the submitter's attribute information and enable appropriate matching based on the submitter's attribute information. Some or all of the above-described processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input the submitter's attribute information data into the generating AI and have the generating AI perform the matching.

[0097] The matching unit can estimate the customer's emotions and adjust the order in which the matching results are displayed based on the estimated emotions. For example, if the customer is stressed, the matching unit can have the generating AI prioritize displaying important results. If the customer is relaxed, the matching unit can also have the generating AI display detailed results in a sequential manner. Furthermore, if the customer is in a hurry, the matching unit can adjust the order to allow the generating AI to display results quickly. This enables an appropriate display order of matching results according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the matching unit may be performed using AI, or not. For example, the matching unit can input customer voice data into the generating AI and have the generating AI adjust the display order of the matching results.

[0098] The matching unit can perform matching based on the geographical distribution of requirements. For example, the matching unit's generating AI can select an appropriate matching method based on the geographical distribution of requirements. The matching unit can also improve the accuracy of matching by considering the geographical distribution of requirements and enabling the generating AI to do so. Furthermore, the matching unit can apply optimal matching criteria based on the geographical distribution of requirements and enable appropriate matching based on geographical distribution. Some or all of the above-described processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input geographical distribution data of requirements into the generating AI and have the generating AI perform the matching.

[0099] The matching unit can improve the accuracy of the matching by referring to relevant literature during the matching process. For example, the matching unit's generating AI can select an appropriate matching method based on the relevant literature. The matching unit can also improve the accuracy of the matching by referring to the relevant literature and allowing the generating AI to do so. Furthermore, the matching unit can apply optimal matching criteria based on the relevant literature and allowing the generating AI to do so. This enables appropriate matching based on relevant literature. Some or all of the above processes in the matching unit may be performed using AI, for example, or without AI. For example, the matching unit can input relevant literature data into the generating AI and have the generating AI perform the matching accuracy improvement.

[0100] The response unit can estimate the customer's emotions and adjust the way the response is expressed based on the estimated emotions. For example, if the customer is stressed, the generating AI can provide a simple and easy-to-understand response. If the customer is relaxed, the generating AI can provide a more detailed response. Furthermore, if the customer is in a hurry, the generating AI can provide a short and concise response. This enables appropriate responses tailored to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input customer voice data into the generating AI and have the generating AI adjust the way the response is expressed.

[0101] The response unit can adjust the level of detail in its response based on the importance of the requirements. For example, the AI ​​can provide a detailed response to high-importance requirements. The AI ​​can also provide a concise response to low-importance requirements. Furthermore, the AI ​​can adjust the level of detail in the response according to the importance of the requirements. This enables appropriate responses according to the importance of the requirements. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input requirement importance data into the AI ​​and have the AI ​​adjust the level of detail in the response.

[0102] The response unit can apply different response algorithms depending on the category of the requirement when providing a response. For example, the response unit can use a specialized response algorithm generated by the generation AI for technical requirements. Alternatively, the response unit can use a simpler response algorithm generated by the generation AI for general requirements. Furthermore, the response unit can use the generation AI to select the optimal response algorithm depending on the category of the requirement. This enables appropriate responses according to the category of the requirement. Some or all of the above processing in the response unit may be performed using AI, or not. For example, the response unit can input requirement category data into the generation AI and have the generation AI apply the response algorithm.

[0103] The response unit can estimate the customer's emotions and adjust the length of the response based on the estimated emotions. For example, if the customer is stressed, the response unit's generating AI can provide a short, to-the-point response. If the customer is relaxed, the response unit's generating AI can provide a more detailed response. Furthermore, if the customer is in a hurry, the response unit's generating AI can provide a short, concise response. This allows for an appropriate response length according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input customer voice data into the generating AI and have the generating AI adjust the length of the response.

[0104] The response unit can determine the priority of responses based on the submission date of the requirements. For example, the response unit's generating AI may prioritize responses to recently submitted requirements. The response unit can also delay responses to older requirements. Furthermore, the response unit can have the generating AI determine the priority of responses based on the submission date of the requirements. This enables appropriate prioritization of responses based on submission date. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input requirement submission date data into the generating AI and have the generating AI determine the priority of responses.

[0105] The response unit can adjust the order of responses based on the relevance of the requirements when providing a response. For example, the response unit can prioritize providing responses to highly relevant requirements using its generating AI. The response unit can also postpone providing responses to less relevant requirements using its generating AI. Furthermore, the response unit can adjust the order of responses using its generating AI according to the relevance of the requirements. This enables appropriate ordering of responses based on relevance. Some or all of the above processing in the response unit may be performed using AI, or not. For example, the response unit can input requirement relevance data into the generating AI and have the generating AI adjust the order of responses.

[0106] The connection unit can estimate the customer's emotions and adjust the connection method based on the estimated emotions. For example, if the customer is stressed, the connection unit can quickly connect them to a representative. If the customer is relaxed, the connection unit can also connect them using the normal procedure. Furthermore, if the customer is in a hurry, the connection unit can connect them to a representative via the shortest route. This enables an appropriate connection method according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the connection unit may be performed using AI or not using AI. For example, the connection unit can input customer voice data into the generative AI and have the generative AI adjust the connection method.

[0107] The connection unit can determine connection priorities based on the importance of the requirements during connection. For example, it can prioritize connecting to the responsible person for high-priority requirements. It can also connect to low-priority requirements using the normal procedure. Furthermore, the connection unit can adjust the connection priority according to the importance of the requirements. This enables appropriate connection prioritization according to the importance of the requirements. Some or all of the above processing in the connection unit may be performed using AI, for example, or not using AI. For example, the connection unit can input requirement importance data into a generating AI and have the generating AI perform the determination of connection priorities.

[0108] The connection unit can apply different connection methods depending on the category of requirements during connection. For example, the connection unit can connect to a specialist for technical requirements. It can also connect to a regular person for general requirements. Furthermore, the connection unit can select the optimal connection method depending on the category of requirements. This enables appropriate connections according to the category of requirements. Some or all of the above processing in the connection unit may be performed using AI, for example, or without AI. For example, the connection unit can input requirement category data into a generating AI and have the generating AI apply the connection method.

[0109] The connection unit can estimate the customer's emotions and adjust the order of connections based on the estimated emotions. For example, if the customer is stressed, the connection unit can quickly connect them to a representative. If the customer is relaxed, the connection unit can also connect them using the normal procedure. Furthermore, if the customer is in a hurry, the connection unit can connect them to a representative via the shortest route. This enables appropriate connection ordering according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the connection unit may be performed using AI or not using AI. For example, the connection unit can input customer voice data into a generative AI and have the generative AI adjust the order of connections.

[0110] The connection unit can determine connection priorities based on the submission date of the requirements at the time of connection. For example, the connection unit will prioritize connecting to the responsible person for recently submitted requirements. The connection unit can also connect to older requirements using the normal procedure. Furthermore, the connection unit can adjust the connection priority according to the submission date of the requirements. This enables appropriate connection prioritization based on submission date. Some or all of the above processing in the connection unit may be performed using AI, for example, or not using AI. For example, the connection unit can input requirement submission date data into a generating AI and have the generating AI perform the determination of connection priorities.

[0111] The connection unit can adjust the order of connections based on the relevance of the requirements during the connection process. For example, the connection unit can prioritize connecting to the appropriate person for highly relevant requirements. It can also connect to less relevant requirements using the normal procedure. Furthermore, the connection unit can adjust the order of connections according to the relevance of the requirements. This enables appropriate connection ordering based on relevance. Some or all of the above processing in the connection unit may be performed using AI, for example, or without AI. For example, the connection unit can input requirement relevance data into a generating AI and have the generating AI perform the adjustment of the connection order.

[0112] The encryption unit can estimate the customer's emotions and adjust the encryption strength based on the estimated emotions. For example, if the customer is stressed, the encryption unit can apply high-strength encryption. It can also apply normal encryption if the customer is relaxed. Furthermore, if the customer is in a hurry, the encryption unit can adjust the strength to perform encryption quickly. This allows for appropriate encryption strength according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the encryption unit may be performed using AI, or not. For example, the encryption unit can input customer voice data into a generative AI and have the generative AI adjust the encryption strength.

[0113] The encryption unit can adjust the level of detail of encryption based on the importance of the requirements during encryption. For example, the encryption unit can apply detailed encryption to high-importance requirements. It can also apply simplified encryption to low-importance requirements. Furthermore, the encryption unit can adjust the level of detail of encryption according to the importance of the requirements. This enables appropriate encryption according to the importance of the requirements. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input requirement importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of encryption.

[0114] The encryption unit can estimate the customer's emotions and determine encryption priorities based on those estimated emotions. For example, if the customer is stressed, the encryption unit will prioritize encryption. If the customer is relaxed, the encryption unit can also perform encryption using the normal procedure. Furthermore, if the customer is in a hurry, the encryption unit can adjust the priority to perform encryption quickly. This enables appropriate encryption prioritization according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the encryption unit may be performed using AI or not. For example, the encryption unit can input customer voice data into the generative AI and have the generative AI determine the encryption priorities.

[0115] The encryption unit can determine the encryption priority based on the submission date of the requirements during encryption. For example, the encryption unit may prioritize encryption of recently submitted requirements. It can also encrypt older requirements using the standard procedure. Furthermore, the encryption unit can adjust the encryption priority according to the submission date of the requirements. This enables appropriate encryption prioritization based on the submission date. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input requirement submission date data into a generating AI and have the generating AI determine the encryption priority.

[0116] The notification method can estimate the customer's emotions and adjust the notification method based on those emotions. For example, if the customer is stressed, the notification method can provide a simple and easy-to-understand notification. If the customer is relaxed, it can provide a more detailed notification. Furthermore, if the customer is in a hurry, the notification method can be adjusted to provide a quick notification. This enables appropriate notifications tailored to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the notification method may be performed using AI or not. For example, the notification method can input customer voice data into a generative AI and have the generative AI adjust the notification method.

[0117] The notification method can adjust the level of detail of notifications based on the importance of the requirements. For example, the notification method can provide detailed notifications for high-importance requirements, and concise notifications for low-importance requirements. Furthermore, the notification method can adjust the level of detail of notifications according to the importance of the requirements. This enables appropriate notifications according to the importance of the requirements. Some or all of the above processing in the notification method may be performed using AI, for example, or not using AI. For example, the notification method can input requirement importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the notifications.

[0118] The notification method can estimate the customer's emotions and determine the priority of notifications based on those emotions. For example, if the customer is stressed, the notification method will prioritize notifications. If the customer is relaxed, the notification method can also proceed with the normal procedure. Furthermore, if the customer is in a hurry, the notification method can adjust the priority to deliver notifications quickly. This enables appropriate notification prioritization according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the notification method may be performed using AI or not. For example, the notification method can input customer voice data into a generative AI and have the generative AI determine the priority of notifications.

[0119] The notification method can prioritize notifications based on the submission date of the requirements. For example, it can prioritize notifications for recently submitted requirements. It can also send notifications for older requirements using the standard procedure. Furthermore, it can adjust the priority of notifications according to the submission date of the requirements. This enables appropriate notification prioritization based on submission date. Some or all of the above processing in the notification method may be performed using AI, for example, or not using AI. For example, the notification method can input requirement submission date data into a generating AI and have the generating AI determine the notification priority.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The customer service system can further analyze a customer's past purchase history and incorporate it into the summaries generated by the summarization unit. For example, if a customer has requirements related to products or services they have purchased in the past, the summarization unit can include that information in the summary. It can also generate summaries based on information if a customer frequently purchases products from a particular brand or category. Furthermore, it can identify specific trends and patterns from the customer's purchase history and adjust the summary accordingly. This enables more accurate summaries based on the customer's past purchase history.

[0122] The customer service system can further analyze customers' social media activity and reflect this in the summaries generated by the summarization department. For example, it can include what customers have mentioned or topics they are interested in on social media. It can also generate summaries based on information such as customers frequently using specific hashtags or keywords. Furthermore, it can identify specific trends and patterns from customers' social media activity and adjust the summaries accordingly. This enables more accurate summaries based on customers' social media activity.

[0123] The customer service system can further analyze the customer's geographical location and reflect this in the summaries generated by the summarization unit. For example, if a customer is in a specific region, the summary can include information relevant to that region. Furthermore, if a customer is on the move, the system can update their geographical location in real time and generate summaries based on that information. It can also identify specific trends and patterns from the customer's geographical location and adjust the summaries accordingly. This enables more accurate summaries based on the customer's geographical location.

[0124] The customer support system can further analyze a customer's past inquiry history and reflect this in the summaries generated by the summarization unit. For example, it can include the content and solutions of past inquiries by the customer in the summary. It can also generate summaries based on information if a customer frequently inquires about specific problems or questions. Furthermore, it can identify specific trends and patterns from the customer's inquiry history and adjust the summary accordingly. This enables more accurate summaries based on the customer's past inquiry history.

[0125] The customer service system can further analyze the customer's current situation and areas of interest, and reflect this in the summaries generated by the summarization unit. For example, when a customer describes their current situation, that information can be included in the summary. It can also include relevant information based on the customer's areas of interest. Furthermore, it can identify specific trends and patterns from the customer's current situation and areas of interest, and adjust the summary accordingly. This enables more accurate summaries based on the customer's current situation and areas of interest.

[0126] The reception desk can estimate the customer's emotions and adjust its response based on that estimation. For example, if the customer is stressed, the generating AI will respond in a calm voice and ask simple questions. If the customer is relaxed, the generating AI can respond in a friendly voice and ask more detailed questions. Furthermore, if the customer is in a hurry, the generating AI can ask short questions to quickly elicit their requirements. This enables appropriate responses tailored to the customer's emotions.

[0127] The summarization function can estimate the customer's emotions and adjust the way the summary is presented based on those emotions. For example, if the customer is stressed, the generating AI will produce a simple and easy-to-understand summary. If the customer is relaxed, the generating AI can produce a detailed summary. Furthermore, if the customer is in a hurry, the generating AI can produce a short and to-the-point summary. This enables the creation of appropriate summaries tailored to the customer's emotions.

[0128] The matching unit can estimate the customer's emotions and adjust the matching criteria based on those emotions. For example, if the customer is stressed, the generating AI can apply simple matching criteria. If the customer is relaxed, the generating AI can apply more detailed matching criteria. Furthermore, if the customer is in a hurry, the generating AI can apply criteria for quick matching. This enables appropriate matching criteria tailored to the customer's emotions.

[0129] The response unit can estimate the customer's emotions and adjust the way the response is expressed based on those emotions. For example, if the customer is stressed, the generating AI will provide a simple and easy-to-understand response. If the customer is relaxed, the generating AI can provide a more detailed response. Furthermore, if the customer is in a hurry, the generating AI can provide a short and to-the-point response. This enables appropriate responses tailored to the customer's emotions.

[0130] The connection unit can estimate the customer's emotions and adjust the connection method based on those estimates. For example, if the customer is stressed, it will connect them quickly to a representative. If the customer is relaxed, it can connect them using the standard procedure. Furthermore, if the customer is in a hurry, it can connect them to a representative via the shortest route. This enables the appropriate connection method according to the customer's emotions.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The reception desk receives customer requests. These requests may include inquiries, complaints, and requests. The reception desk can receive customer requests via telephone, email, chat, or other means. Step 2: The summarization unit uses a generation AI to summarize the requirements received by the reception unit. The summarization is based on the length of the text and the importance of the information to be summarized. The generation AI uses a text generation AI (e.g., LLM) or a multimodal generation AI to concisely summarize the requirements. Step 3: The matching unit compares the summaries generated by the summarization unit with the FAQ database. The matching is performed using methods such as cosine similarity, Jaccard coefficients, and TF-IDF. The matching unit uses these methods to calculate the similarity between the summaries and the answers in the FAQ database. Step 4: The response unit provides a preliminary response based on the results obtained by the verification unit. The preliminary response can be provided either by directly using the answer from the FAQ database or by generating an answer using a generation AI. Step 5: The connection unit connects the caller to a representative if the response unit is unable to provide an initial response. The connection is made using methods such as telephone, email, or chat.

[0133] 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.

[0134] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0135] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements described above, including the reception unit, summarization unit, matching unit, response unit, and connection unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives customer requirements. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and summarizes the requirements using generation AI. The matching unit is implemented by the identification processing unit 290 of the data processing unit 12 and matches the summary with an FAQ database. The response unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides an initial response. The connection unit is implemented by the control unit 46A of the smart device 14 and connects to the person in charge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] 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.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0140] 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.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0142] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] 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.

[0144] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the reception unit, summarization unit, matching unit, response unit, and connection unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives customer requirements. The summarization unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and summarizes the requirements using generation AI. The matching unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and matches the summary with an FAQ database. The response unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and provides an initial response. The connection unit is implemented, for example, by the control unit 46A of the smart glasses 214 and connects to the person in charge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] 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.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0156] 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.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0158] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] 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.

[0160] 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.

[0161] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0162] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0163] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] 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.

[0166] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] Each of the multiple elements described above, including the reception unit, summarization unit, verification unit, response unit, and connection unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives customer requirements. The summarization unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and summarizes the requirements using generation AI. The verification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and verifies the summary against the FAQ database. The response unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and provides an initial response. The connection unit is implemented by, for example, the control unit 46A of the headset terminal 314 and connects to the person in charge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0172] 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.

[0173] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0174] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] 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.

[0176] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0177] 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.

[0178] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0179] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0180] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0181] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0182] 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.

[0183] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0185] Each of the multiple elements described above, including the reception unit, summarization unit, matching unit, response unit, and connection unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives customer requirements. The summarization unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and summarizes the requirements using generation AI. The matching unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and matches the summary with an FAQ database. The response unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and provides an initial response. The connection unit is implemented by, for example, the control unit 46A of the robot 414 and connects to the person in charge. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0186] 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.

[0187] Figure 9 shows the 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.

[0188] 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.

[0189] 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.

[0190] 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, and motorcycles, 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 based, for example, 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.

[0191] 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."

[0192] 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.

[0193] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0202] 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 other things 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.

[0203] 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.

[0204] (Note 1) A reception desk that handles customer requirements, A summarization unit that summarizes the requirements received by the reception unit, A matching unit compares the summary generated by the summarization unit with an FAQ database. A response unit that provides a primary response based on the results obtained by the verification unit, A system comprising: a connection unit that connects to a person in charge if the aforementioned response unit cannot provide an initial response. (Note 2) Features an algorithm for generating summaries. The system described in Appendix 1, characterized by the features described herein. (Note 3) Features an FAQ database structure The system described in Appendix 1, characterized by the features described herein. (Note 4) Equipped with an encryption section for privacy protection. The system described in Appendix 1, characterized by the features described herein. (Note 5) Provide a method for notifying the person in charge. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is A system that estimates customer emotions and adjusts its response method based on those estimated emotions. (Note 7) The aforementioned reception unit is A system that analyzes a customer's past inquiry history and selects the appropriate response method. (Note 8) The aforementioned reception unit is During registration, filtering is performed based on the customer's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is A system that estimates customer emotions and determines the priority of requests to be accepted based on those estimated emotions. (Note 10) The aforementioned reception unit is A system that prioritizes requests based on the customer's geographical location information during the registration process. (Note 11) The aforementioned reception unit is At the time of registration, we analyze the customer's social media activity and collect relevant requirements. The system described in Appendix 1, characterized by the features described herein. (Note 12) The summary section above is, A system that estimates customer emotions and adjusts the way summaries are presented based on those estimated emotions. (Note 13) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 14) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the category of requirements. The system described in Appendix 1, characterized by the features described herein. (Note 15) The summary section above is, A system that estimates customer emotions and adjusts the length of summaries based on those estimated emotions. (Note 16) The summary section above is, When generating summaries, prioritize the summaries based on when the requirements were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The summary section above is, When generating summaries, adjust the order of summaries based on the relevance of the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned verification unit is A system that estimates customer emotions and adjusts matching criteria based on those estimated emotions. (Note 19) The aforementioned verification unit is A system that improves the accuracy of matching based on the interrelationships of requirements during the matching process. (Note 20) The aforementioned verification unit is A system that performs matching based on the attribute information of the person submitting the requirements during the matching process. (Note 21) The aforementioned verification unit is A system that estimates customer emotions and adjusts the order in which matching results are displayed based on the estimated customer emotions. (Note 22) The aforementioned verification unit is A system that performs matching based on the geographical distribution of requirements during the matching process. (Note 23) The aforementioned verification unit is A system that improves the accuracy of matching based on relevant literature for the requirements during the matching process. (Note 24) The aforementioned response section is, A system that estimates customer emotions and adjusts the way responses are expressed based on those estimated emotions. (Note 25) The aforementioned response section is, When responding, adjust the level of detail in your response based on the importance of the requirement. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned response section is, When responding, different response algorithms are applied depending on the category of the requirement. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned response section is, A system that estimates customer emotions and adjusts the length of responses based on those estimated emotions. (Note 28) The aforementioned response section is, When responding, prioritize responses based on when the requirements were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned response section is, When responding, adjust the order of your answers based on the relevance of the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned connection part is A system that estimates customer emotions and adjusts the connection method based on those estimated emotions. (Note 31) The aforementioned connection part is When connecting, the connection priority is determined based on the importance of the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned connection part is When connecting, apply different connection methods depending on the category of requirements. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned connection part is A system that estimates customer emotions and adjusts the order of connections based on those estimated emotions. (Note 34) The aforementioned connection part is When connecting, priority is determined based on when the requirements were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned connection part is When connecting, the order of connections is adjusted based on the relevance of the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 36) The encryption unit is A system that estimates customer emotions and adjusts the encryption strength based on those estimated emotions. (Note 37) The encryption unit is During encryption, adjust the level of encryption granularity based on the importance of the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 38) The encryption unit is A system that estimates customer emotions and determines encryption priorities based on those estimated emotions. (Note 39) The encryption unit is During encryption, the priority of encryption is determined based on when the requirements were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned notification method is: A system that estimates customer emotions and adjusts notification methods based on those estimated emotions. (Note 41) The aforementioned notification method is: When sending notifications, adjust the level of detail based on the importance of the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned notification method is: A system that estimates customer emotions and determines notification priorities based on those estimated emotions. (Note 43) The aforementioned notification method is: When notifying, we will prioritize notifications based on when the requirements were submitted. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception unit that receives requirements through dialogue between the customer's terminal and the generating AI, A summarization unit that summarizes the requirements received by the reception unit, A matching unit searches for answers stored in the FAQ database as pairs of questions similar to the summary by comparing the summary generated by the summarization unit with the FAQ database. If a response is obtained as a result of the verification by the verification unit, the response unit provides the response to the terminal used by the customer, If no answer is obtained as a result of the verification by the verification unit, the system includes a connection unit that forwards the inquiry regarding the requirements to a terminal used by the operator. The reception unit inputs user input, either text or voice, from a terminal used by the customer to the generating AI, causing the generating AI to estimate the customer's emotions. If the estimated category of the customer's emotions is relaxed, the generating AI generates a question of a first length to elicit the requirements from the customer during the dialogue. If the category of the customer's emotions is urgent, the generating AI generates a question of a second length, shorter than the first length, to elicit the requirements from the customer during the dialogue.

2. The summary is generated by the generation AI by inputting the requirements received by the reception unit into the generation AI. The system according to feature 1.

Images