System

Abstract

An object of a system according to an embodiment is to improve service experience by responding to an inquiry from a customer immediately and on a 24-hour basis.SOLUTION: A system according to an embodiment includes a natural language processing unit, a learning unit, a transfer unit, a translation unit, an aggregation unit, and a feedback analysis unit. The natural language processor uses natural language processing to understand the intent of the customer's question and generate an appropriate answer. The learner evolves to provide optimal answers from past dialogues. The forwarder automatically forwards the complex query to a human operator. The translation unit supports multiple languages, allows a customer to ask a question in his / her native language, and automatically translates the question to provide an answer. The aggregation unit aggregates inquiry leads of a plurality of services into one application. The feedback analyzer automatically analyzes the feedback from the customer and sends it immediately to the product.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies make it difficult to respond to customer inquiries immediately and 24 hours a day, leaving room for improvement in improving the service experience.

[0005] The system according to the embodiment aims to respond to customer inquiries immediately and 24 hours a day, thereby improving the service experience. [Means for solving the problem]

[0006] The system according to the embodiment comprises a natural language processing unit, a learning unit, a transfer unit, a translation unit, an aggregation unit, and a feedback analysis unit. The natural language processing unit uses natural language processing to understand the intent of a customer's question and generate an appropriate answer. The learning unit evolves to provide the optimal answer based on past interactions. The transfer unit automatically transfers complex inquiries to a human operator. The translation unit supports multiple languages, allowing customers to ask questions in their native language and automatically translates the answers to provide them. The aggregation unit aggregates inquiry paths for multiple services into a single app. The feedback analysis unit automatically analyzes customer feedback and immediately sends it to the product. [Effects of the Invention]

[0007] The system according to the embodiment can respond to customer inquiries immediately and 24 hours a day, improving the service experience. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 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, RAM 30, and 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 a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A chatbot system according to an embodiment of the present invention is a system that can respond to customer inquiries instantly and 24 hours a day. It uses natural language processing to understand the intent of customer questions and generate appropriate answers. It also has a learning function that evolves to provide optimal answers based on past interactions. Furthermore, it automatically transfers complex inquiries to a human operator, supports multiple languages, allowing customers to ask questions in their native language and automatically translates the answers. It consolidates inquiries for multiple services into a single app, minimizing service churn. It automatically analyzes customer feedback and immediately sends it to the product, accelerating the quality improvement cycle. This allows the chatbot system to respond to customer inquiries instantly and 24 hours a day, improving the service experience.

[0029] A chatbot system according to an embodiment includes a natural language processing unit, a learning unit, a transfer unit, a translation unit, an aggregation unit, and a feedback analysis unit. The natural language processing unit understands the intent of a customer's question and generates an appropriate answer. For example, the natural language processing unit uses morphological analysis to break down sentences, perform grammatical analysis, and understand the intent of the question through semantic analysis. The natural language processing unit can also use keyword extraction technology to identify important parts of a question and generate an appropriate answer. The learning unit learns from past dialogue data and evolves to provide optimal answers. For example, the learning unit uses a machine learning algorithm to analyze past dialogue data and improve the accuracy of answers. The learning unit can also use a feedback loop to learn from customer feedback and improve the quality of answers. The transfer unit automatically transfers complex inquiries to a human operator. For example, the transfer unit identifies complex inquiries based on the appearance of specific keywords or the length of the inquiry and transfers them to an operator. The transfer unit can also perform rule-based transfer or machine learning transfer. The translation unit supports multiple languages, allowing customers to ask questions in their native language and providing answers through automatic translation. For example, the translation unit uses a machine translation engine to translate questions and generate appropriate answers. The translation unit can also use neural network translation to provide highly accurate translations. The aggregation unit consolidates inquiry leads from multiple services into a single app. For example, the aggregation unit uses an integrated platform to centrally manage inquiries from email, messenger apps, social media, and other sources. The aggregation unit can also aggregate data from each service using API integration. The feedback analysis unit automatically analyzes customer feedback and immediately sends it to the product. For example, the feedback analysis unit uses text mining technology to analyze feedback and perform sentiment analysis. The feedback analysis unit can also immediately send the analysis results to the product team using real-time data transfer. This enables the chatbot system to respond to customer inquiries immediately, 24 hours a day, improving the service experience.For example, customers can make inquiries anytime, anywhere and receive prompt and appropriate responses. Complex inquiries can be transferred to a human operator, improving customer satisfaction. Furthermore, multilingual support allows for international customer service.

[0030] The natural language processing unit can refer to the questioner's past behavioral history and generate a more personalized answer. For example, the natural language processing unit uses a generation AI to refer to the questioner's past behavioral history and generate a more personalized answer. For example, if a question is about a product purchased in the past, an answer specific to that product will be provided. The natural language processing unit can also generate answers tailored to individual preferences based on website browsing history and purchase history. This makes it possible to provide a more personalized answer based on the questioner's past behavioral history.

[0031] The natural language processing unit can automatically collect background information about the question and reflect it in the answer. For example, the natural language processing unit uses a generation AI to automatically collect background information about the question (e.g., related news and trends) and reflect it in the answer. For example, it can provide an answer based on the latest product release information. The natural language processing unit can also collect background information based on past inquiries and related topics and reflect it in the answer. This allows background information about the question to be automatically collected and reflected in the answer.

[0032] The natural language processing unit can analyze image or audio data and generate answers based on multimodal information. For example, a generative AI in the natural language processing unit analyzes image or audio data and generates answers based on multimodal information. For example, it analyzes a photo of a product and provides a detailed answer about the product. The natural language processing unit can also analyze audio recordings and convert them into text data using speech recognition technology to generate answers. This makes it possible to analyze image or audio data and generate answers based on multimodal information.

[0033] The natural language processing unit can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, the generation AI can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, a question about medicine can be answered by providing an answer that reflects the opinions of medical experts. The natural language processing unit can also improve the accuracy of the answer based on reviews by technical experts and business experts. This allows the opinions of experts in different industries to be referred to and the accuracy of the answer to be improved.

[0034] The learning unit learns not only past dialogue data but also other related data, allowing it to provide more accurate answers. For example, the generation AI learns not only past dialogue data but also other related data (e.g., customer purchase history and feedback) to provide more accurate answers. For example, it provides answers tailored to the customer's preferences based on past purchase history. The learning unit can also improve the accuracy of answers based on the customer's profile data and past purchase history. This allows it to provide more accurate answers by learning not only past dialogue data but also other related data.

[0035] The learning unit has a self-evaluation function, which allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, the generative AI has a self-evaluation function, which allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, it compares past answers with customer feedback to evaluate accuracy. The learning unit can also use a self-evaluation algorithm to evaluate the accuracy of answers and customer satisfaction and identify areas for improvement. As a result, the self-evaluation function allows it to evaluate the accuracy of answers and find areas for improvement.

[0036] The learning unit can learn dialogue data from different languages ​​and cultural spheres to improve its global response capabilities. For example, the generation AI can learn dialogue data from different languages ​​and cultural spheres to improve its global response capabilities. For example, it can learn dialogue data from English, Spanish, and other languages ​​to strengthen its multilingual support. The learning unit can also understand the cultural background of a specific country or region and generate answers based on that. This allows it to improve its global response capabilities by learning dialogue data from different languages ​​and cultural spheres.

[0037] The learning unit can work with other AI systems and share learning data with them. For example, the generation AI of the learning unit can work with other AI systems and share learning data with them. For example, data can be shared with AI systems from different companies to improve the accuracy of answers. The learning unit can also work with other AI systems such as chatbots and voice assistants and share learning data. This allows the learning function to be strengthened by working with other AI systems and sharing learning data with them.

[0038] When transferring a complex inquiry, the transfer unit can automatically generate a summary of the inquiry and provide it to the operator. For example, when the generation AI transfers a complex inquiry, the transfer unit can automatically generate a summary of the inquiry and provide it to the operator. For example, the transfer unit can display a summary that concisely summarizes the main points of the inquiry to the operator. The transfer unit can also automatically generate a summary of the inquiry using natural language generation technology. As a result, when transferring a complex inquiry, a summary of the inquiry can be automatically generated and provided to the operator, enabling a quick response.

[0039] The transfer unit can propose multiple solutions to a complex inquiry and allow the customer to select one before transferring it. For example, the transfer unit can present multiple options for resolving a problem and allow the customer to select the optimal solution before transferring the complex inquiry using a generation AI. The transfer unit can also present suggestions from FAQs and past solution cases. This improves customer satisfaction by proposing multiple solutions and allowing the customer to select one before transferring a complex inquiry.

[0040] The forwarding unit can automatically assign complex inquiries to operators with different specialties. For example, when the generation AI forwards a complex inquiry, the forwarding unit automatically assigns it to an operator with a different specialization. For example, technical issues are assigned to a technical support operator, and sales issues are assigned to a sales support operator. The forwarding unit can also perform rule-based assignments or assignments based on machine learning. This allows for the automatic assignment of complex inquiries to operators with different specialties, enabling quick and appropriate responses.

[0041] The forwarding unit can automatically attach relevant documents and FAQs to support the operator's response. For example, when the generation AI forwards a complex inquiry, the forwarding unit automatically attaches relevant documents and FAQs to support the operator's response. For example, it can attach manuals and guidelines related to the inquiry. The forwarding unit can also provide the operator with a list of frequently asked questions and resolution procedures. This allows the automatic attachment of relevant documents and FAQs to support the operator's response and enable quick problem resolution.

[0042] When supporting multiple languages, the translation unit can provide translations that take into account the cultural background and nuances of each language. For example, when the generative AI supports multiple languages, the translation unit provides translations that take into account the cultural background and nuances of each language. For example, when translating from English to Japanese, expressions that reflect cultural differences are used. The translation unit can also translate by taking into account the differences in word usage and nuances in specific cultures. This allows for more natural and appropriate responses by providing translations that take into account the cultural background and nuances of each language.

[0043] The translation unit can cross-reference dialogue data in different languages ​​to maintain consistency in the translation. For example, the generative AI can cross-reference dialogue data in different languages ​​to maintain consistency in the translation. For example, it can compare dialogue data in English and French to provide a consistent translation. The translation unit can also use a glossary or translation memory to maintain consistency in terminology and context between different languages. This allows consistency in the translation to be maintained by cross-referencing dialogue data in different languages.

[0044] The translation unit performs translation in real time, making it possible to facilitate dialogue between different languages. For example, the translation unit uses a generative AI to perform translation in real time, making it possible to facilitate dialogue between different languages. For example, a question in English can be translated into Japanese in real time and an answer can be provided. The translation unit can also perform rapid translation using a real-time translation engine and low-latency communication technology. This allows for real-time translation to facilitate dialogue between different languages, making it possible to respond quickly and appropriately.

[0045] The translation department can refer to the opinions of experts in different languages ​​to improve the quality of the translation. For example, the generation AI can refer to the opinions of experts in different languages ​​to improve the quality of the translation. For example, in a translation from English to Japanese, the opinions of Japanese language experts are reflected. The translation department can also improve the accuracy of the translation based on reviews by translators and linguists. This allows the quality of the translation to be improved by referring to the opinions of experts in different languages.

[0046] When aggregating inquiries from multiple services, the aggregation unit can provide a response that takes into account the characteristics of each service. For example, when the generation AI aggregates inquiries from multiple services, the aggregation unit provides a response that takes into account the characteristics of each service. For example, it provides a detailed response to inquiries made by email and a concise response to inquiries made on social media. The aggregation unit can also customize responses according to the response procedures and characteristics of each service. This makes it possible to provide a more appropriate response when aggregating inquiries from multiple services by providing a response that takes into account the characteristics of each service.

[0047] The aggregation unit can automatically set the priority of inquiries and respond efficiently. For example, the generation AI of the aggregation unit can automatically set the priority of inquiries and respond efficiently. For example, inquiries with a high level of urgency can be given priority. The aggregation unit can also set priorities based on the urgency of the inquiry and the importance of the customer. This allows for automatic priority setting of inquiries and efficient response, enabling quick and appropriate responses.

[0048] The aggregation unit can automatically link data between different services and provide a consistent response. For example, the generation AI in the aggregation unit automatically links data between different services and provides a consistent response. For example, it can integrate email and chat inquiries and provide a consistent response. The aggregation unit can also link data between different services using API integration or database integration. This makes it possible to automatically link data between different services and provide a consistent response.

[0049] The aggregation unit can integrate the inquiry history of each service to get a complete picture of the customer. For example, the generation AI can integrate the inquiry history of each service to get a complete picture of the customer. For example, it can comprehensively understand the customer's problems based on past inquiry history. The aggregation unit can also get a complete picture of the customer based on the customer's profile and past behavioral history. In this way, by integrating the inquiry history of each service, a complete picture of the customer can be obtained, enabling more appropriate responses.

[0050] The feedback analysis unit can provide the analysis results of customer feedback to the product team in real time, facilitating rapid quality improvements. For example, the feedback analysis unit uses a generative AI to provide the analysis results of customer feedback to the product team in real time, facilitating rapid quality improvements. For example, the content of the feedback can be immediately notified to the product team, allowing improvement measures to be implemented quickly. The feedback analysis unit can also provide the analysis results to the product team using real-time data transfer or API integration. This allows rapid quality improvements by providing the analysis results of customer feedback to the product team in real time.

[0051] The feedback analysis unit can refer to the background information of customer feedback and make more specific improvement proposals. For example, the generation AI can refer to the background information of customer feedback (for example, the customer's past behavioral history) and make more specific improvement proposals. For example, it can propose improvement measures based on past purchase history. The feedback analysis unit can also refer to background information and make improvement proposals based on past inquiries and related topics. This makes it possible to make more specific improvement proposals by referring to the background information of customer feedback.

[0052] The feedback analysis department can share the results of customer feedback analysis with different departments to promote company-wide quality improvement. For example, the feedback analysis department can share the results of customer feedback analysis with different departments (e.g., marketing, development) to promote company-wide quality improvement. For example, it can provide feedback to the marketing department to improve promotion strategies. The feedback analysis department can also share feedback with the technical department and customer support department to improve products and services. In this way, by sharing the results of customer feedback analysis with different departments, company-wide quality improvement is possible.

[0053] The feedback analysis unit can integrate the results of customer feedback analysis with other data sets to make comprehensive quality improvements. For example, the feedback analysis unit integrates the results of customer feedback analysis by the generative AI with other data sets (e.g., sales data, customer satisfaction surveys) to make comprehensive quality improvements. For example, it compares sales data with feedback to identify areas for improvement. The feedback analysis unit can also make comprehensive quality improvements based on customer data and sales data. This makes it possible to make comprehensive quality improvements by integrating the results of customer feedback analysis with other data sets.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The natural language processing unit can refer to the questioner's past behavioral history to generate a more personalized answer. For example, if a question is about a product purchased in the past, an answer specific to that product will be provided. The natural language processing unit can also generate answers tailored to individual preferences based on website browsing history and purchase history. This makes it possible to provide a more personalized answer based on the questioner's past behavioral history.

[0056] The natural language processing unit can automatically collect background information about the question and reflect it in the answer. For example, the generation AI can automatically collect background information about the question (such as related news and trends) and reflect it in the answer. For example, it can provide an answer based on the latest product release information. The natural language processing unit can also collect background information based on past inquiries and related topics and reflect it in the answer. This allows background information about the question to be automatically collected and reflected in the answer.

[0057] The natural language processor can analyze image or audio data and generate answers based on multimodal information. For example, a generative AI can analyze image or audio data and generate answers based on multimodal information. For example, it can analyze a photo of a product and provide a detailed answer about the product. The natural language processor can also analyze audio recordings and convert them into text data using speech recognition technology to generate answers. This allows it to analyze image or audio data and generate answers based on multimodal information.

[0058] The natural language processing unit can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, the generation AI can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, answers that reflect the opinions of medical experts are provided for questions about medicine. The natural language processing unit can also improve the accuracy of the answer based on reviews by technical experts and business experts. This allows the opinions of experts in different industries to be referred to and the accuracy of the answer improved.

[0059] The learning unit learns not only past dialogue data but also other related data, allowing it to provide more accurate answers. For example, the generation AI learns not only past dialogue data but also other related data (e.g., customer purchase history and feedback) to provide more accurate answers. For example, it provides answers that match the customer's preferences based on past purchase history. The learning unit can also improve the accuracy of answers based on the customer's profile data and past purchase history. This allows it to provide more accurate answers by learning not only past dialogue data but also other related data.

[0060] The learning unit has a self-evaluation function that allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, the generation AI has a self-evaluation function that allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, it compares past answers with customer feedback to evaluate accuracy. The learning unit can also use a self-evaluation algorithm to evaluate the accuracy of answers and customer satisfaction and identify areas for improvement. As a result, the self-evaluation function allows it to evaluate the accuracy of answers and find areas for improvement.

[0061] The learning unit can learn dialogue data from different languages ​​and cultures to improve its global response capabilities. For example, the generation AI can learn dialogue data from different languages ​​and cultures to improve its global response capabilities. For example, it can learn dialogue data from languages ​​such as English and Spanish to strengthen its multilingual support. The learning unit can also understand the cultural background of a specific country or region and generate answers based on that. This allows it to improve its global response capabilities by learning dialogue data from different languages ​​and cultures.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The natural language processing unit understands the intent of the customer's question and generates an appropriate answer. For example, it uses morphological analysis to break down the sentence, performs grammatical analysis, and understands the intent of the question through semantic analysis. It also uses keyword extraction technology to identify important parts of the question and generate an appropriate answer. Step 2: The learning unit learns from past dialogue data and evolves to provide optimal answers. For example, it uses machine learning algorithms to analyze past dialogue data and improve the accuracy of answers. It also uses a feedback loop to learn from customer feedback and improve the quality of answers. Step 3: The forwarding unit automatically forwards complex queries to a human operator. For example, it can identify complex queries based on the occurrence of specific keywords or the length of the query, and forward them to a human operator. It can also use rule-based forwarding or machine learning. Step 4: The translation department supports multiple languages, allowing customers to ask questions in their native language and providing answers through automatic translation. For example, it uses a machine translation engine to translate questions and generate appropriate answers. It can also use neural network translation to provide highly accurate translations. Step 5: The aggregation unit aggregates inquiries from multiple services into a single app. For example, an integrated platform can be used to centrally manage inquiries from email, messenger apps, social media, etc. Data from each service can also be aggregated using API integration. Step 6: The feedback analysis department automatically analyzes customer feedback and immediately sends it to the product. For example, it can use text mining technology to analyze the feedback and perform sentiment analysis. It can also use real-time data transfer to immediately send the analysis results to the product team.

[0064] (Example 2) A chatbot system according to an embodiment of the present invention is a system that can respond to customer inquiries instantly and 24 hours a day. It uses natural language processing to understand the intent of customer questions and generate appropriate answers. It also has a learning function that evolves to provide optimal answers based on past interactions. Furthermore, it automatically transfers complex inquiries to a human operator, supports multiple languages, allowing customers to ask questions in their native language and automatically translates the answers. It consolidates inquiries for multiple services into a single app, minimizing service churn. It automatically analyzes customer feedback and immediately sends it to the product, accelerating the quality improvement cycle. This allows the chatbot system to respond to customer inquiries instantly and 24 hours a day, improving the service experience.

[0065] A chatbot system according to an embodiment includes a natural language processing unit, a learning unit, a transfer unit, a translation unit, an aggregation unit, and a feedback analysis unit. The natural language processing unit understands the intent of a customer's question and generates an appropriate answer. For example, the natural language processing unit uses morphological analysis to break down sentences, perform grammatical analysis, and understand the intent of the question through semantic analysis. The natural language processing unit can also use keyword extraction technology to identify important parts of a question and generate an appropriate answer. The learning unit learns from past dialogue data and evolves to provide optimal answers. For example, the learning unit uses a machine learning algorithm to analyze past dialogue data and improve the accuracy of answers. The learning unit can also use a feedback loop to learn from customer feedback and improve the quality of answers. The transfer unit automatically transfers complex inquiries to a human operator. For example, the transfer unit identifies complex inquiries based on the appearance of specific keywords or the length of the inquiry and transfers them to an operator. The transfer unit can also perform rule-based transfer or machine learning transfer. The translation unit supports multiple languages, allowing customers to ask questions in their native language and providing answers through automatic translation. For example, the translation unit uses a machine translation engine to translate questions and generate appropriate answers. The translation unit can also use neural network translation to provide highly accurate translations. The aggregation unit consolidates inquiry leads from multiple services into a single app. For example, the aggregation unit uses an integrated platform to centrally manage inquiries from email, messenger apps, social media, and other sources. The aggregation unit can also aggregate data from each service using API integration. The feedback analysis unit automatically analyzes customer feedback and immediately sends it to the product. For example, the feedback analysis unit uses text mining technology to analyze feedback and perform sentiment analysis. The feedback analysis unit can also immediately send the analysis results to the product team using real-time data transfer. This enables the chatbot system to respond to customer inquiries immediately, 24 hours a day, improving the service experience.For example, customers can make inquiries anytime, anywhere and receive prompt and appropriate responses. Complex inquiries can be transferred to a human operator, improving customer satisfaction. Furthermore, multilingual support allows for international customer service.

[0066] The natural language processing unit can infer a customer's emotions and generate a response that corresponds to those emotions. For example, the natural language processing unit uses a generation AI emotion estimation function to analyze a customer's emotions and generate a response that corresponds to those emotions. For example, if a customer is angry, a calm and polite response can be generated to ease the customer's dissatisfaction. The natural language processing unit can also perform text mining using an emotion analysis algorithm to infer a customer's emotions. This makes it possible to provide an appropriate response that corresponds to the customer's emotions.

[0067] The natural language processing unit can refer to the questioner's past behavioral history and generate a more personalized answer. For example, the natural language processing unit uses a generation AI to refer to the questioner's past behavioral history and generate a more personalized answer. For example, if a question is about a product purchased in the past, an answer specific to that product will be provided. The natural language processing unit can also generate answers tailored to individual preferences based on website browsing history and purchase history. This makes it possible to provide a more personalized answer based on the questioner's past behavioral history.

[0068] The natural language processing unit can automatically collect background information about the question and reflect it in the answer. For example, the natural language processing unit uses a generation AI to automatically collect background information about the question (e.g., related news and trends) and reflect it in the answer. For example, it can provide an answer based on the latest product release information. The natural language processing unit can also collect background information based on past inquiries and related topics and reflect it in the answer. This allows background information about the question to be automatically collected and reflected in the answer.

[0069] The natural language processing unit can analyze image or audio data and generate answers based on multimodal information. For example, a generative AI in the natural language processing unit analyzes image or audio data and generates answers based on multimodal information. For example, it analyzes a photo of a product and provides a detailed answer about the product. The natural language processing unit can also analyze audio recordings and convert them into text data using speech recognition technology to generate answers. This makes it possible to analyze image or audio data and generate answers based on multimodal information.

[0070] The natural language processing unit can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, the generation AI can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, a question about medicine can be answered by providing an answer that reflects the opinions of medical experts. The natural language processing unit can also improve the accuracy of the answer based on reviews by technical experts and business experts. This allows the opinions of experts in different industries to be referred to and the accuracy of the answer to be improved.

[0071] The natural language processing unit can use the emotion estimation function to adjust the tone and style of the response according to the emotion of the questioner. For example, the generation AI in the natural language processing unit uses the emotion estimation function to analyze the emotion of the questioner and adjust the tone and style of the response according to the emotion. For example, if the customer is angry, the natural language processing unit can provide a response in a calm and polite tone. The natural language processing unit can also perform text mining using an emotion analysis algorithm to adjust the tone and style according to the emotion of the questioner. This makes it possible to adjust the tone and style of the response according to the emotion of the questioner.

[0072] The learning unit learns not only past dialogue data but also other related data, allowing it to provide more accurate answers. For example, the generation AI learns not only past dialogue data but also other related data (e.g., customer purchase history and feedback) to provide more accurate answers. For example, it provides answers tailored to the customer's preferences based on past purchase history. The learning unit can also improve the accuracy of answers based on the customer's profile data and past purchase history. This allows it to provide more accurate answers by learning not only past dialogue data but also other related data.

[0073] The learning unit has a self-evaluation function, which allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, the generative AI has a self-evaluation function, which allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, it compares past answers with customer feedback to evaluate accuracy. The learning unit can also use a self-evaluation algorithm to evaluate the accuracy of answers and customer satisfaction and identify areas for improvement. As a result, the self-evaluation function allows it to evaluate the accuracy of answers and find areas for improvement.

[0074] The learning unit incorporates an emotion estimation function, learns the emotional reactions of customers in past interactions, and can provide the optimal response based on the emotion. For example, the generation AI incorporates an emotion estimation function, learns the emotional reactions of customers in past interactions, and provides the optimal response based on the emotion. For example, it learns responses that pleased customers in past interactions and uses them in similar situations. The learning unit can also use an emotion analysis algorithm to analyze past interaction data and generate responses based on the customer's emotions. In this way, by incorporating the emotion estimation function, it is possible to learn the emotional reactions of customers in past interactions and provide the optimal response based on the emotion.

[0075] The learning unit can learn dialogue data from different languages ​​and cultural spheres to improve its global response capabilities. For example, the generation AI can learn dialogue data from different languages ​​and cultural spheres to improve its global response capabilities. For example, it can learn dialogue data from English, Spanish, and other languages ​​to strengthen its multilingual support. The learning unit can also understand the cultural background of a specific country or region and generate answers based on that. This allows it to improve its global response capabilities by learning dialogue data from different languages ​​and cultural spheres.

[0076] The learning unit can work with other AI systems and share learning data with them. For example, the generation AI of the learning unit can work with other AI systems and share learning data with them. For example, data can be shared with AI systems from different companies to improve the accuracy of answers. The learning unit can also work with other AI systems such as chatbots and voice assistants and share learning data. This allows the learning function to be strengthened by working with other AI systems and sharing learning data with them.

[0077] The learning unit can use the emotion estimation function to adjust the tone and style of the response based on the learning data and provide the optimal response according to the customer's emotions. For example, the generation AI can use the emotion estimation function to adjust the tone and style of the response based on the learning data and provide the optimal response according to the customer's emotions. For example, if the customer is angry, the learning unit can provide a response in a calm and polite tone. The learning unit can also use an emotion analysis algorithm to analyze the learning data and adjust the tone and style according to the customer's emotions. This allows the emotion estimation function to adjust the tone and style of the response based on the learning data and provide the optimal response according to the customer's emotions.

[0078] When transferring a complex inquiry, the transfer unit can automatically generate a summary of the inquiry and provide it to the operator. For example, when the generation AI transfers a complex inquiry, the transfer unit can automatically generate a summary of the inquiry and provide it to the operator. For example, the transfer unit can display a summary that concisely summarizes the main points of the inquiry to the operator. The transfer unit can also automatically generate a summary of the inquiry using natural language generation technology. As a result, when transferring a complex inquiry, a summary of the inquiry can be automatically generated and provided to the operator, enabling a quick response.

[0079] The transfer unit can propose multiple solutions to a complex inquiry and allow the customer to select one before transferring it. For example, the transfer unit can present multiple options for resolving a problem and allow the customer to select the optimal solution before transferring the complex inquiry using a generation AI. The transfer unit can also present suggestions from FAQs and past solution cases. This improves customer satisfaction by proposing multiple solutions and allowing the customer to select one before transferring a complex inquiry.

[0080] The transfer unit can use the emotion estimation function to analyze the customer's emotions and provide the emotion information to the operator. For example, the transfer unit uses the generation AI to analyze the customer's emotions using the emotion estimation function and provides the emotion information to the operator. For example, if the customer is angry, the transfer unit conveys that information to the operator. The transfer unit can also use an emotion analysis algorithm to analyze the customer's emotions and provide an emotion score to the operator. This allows for a more appropriate response by analyzing the customer's emotions using the emotion estimation function and providing the emotion information to the operator.

[0081] The forwarding unit can automatically assign complex inquiries to operators with different specialties. For example, when the generation AI forwards a complex inquiry, the forwarding unit automatically assigns it to an operator with a different specialization. For example, technical issues are assigned to a technical support operator, and sales issues are assigned to a sales support operator. The forwarding unit can also perform rule-based assignments or assignments based on machine learning. This allows for the automatic assignment of complex inquiries to operators with different specialties, enabling quick and appropriate responses.

[0082] The forwarding unit can automatically attach relevant documents and FAQs to support the operator's response. For example, when the generation AI forwards a complex inquiry, the forwarding unit automatically attaches relevant documents and FAQs to support the operator's response. For example, it can attach manuals and guidelines related to the inquiry. The forwarding unit can also provide the operator with a list of frequently asked questions and resolution procedures. This allows the automatic attachment of relevant documents and FAQs to support the operator's response and enable quick problem resolution.

[0083] The transfer unit can use the emotion estimation function to suggest to the operator a response method that is appropriate to the customer's emotions when transferring a complex inquiry. For example, the transfer unit uses the generation AI emotion estimation function to analyze the customer's emotions when transferring a complex inquiry and suggest a response method to the operator. For example, if the customer is angry, it will suggest a calm and polite response. The transfer unit can also use an emotion analysis algorithm to provide the operator with response procedures and scripts that are appropriate to the customer's emotions. This allows the emotion estimation function to suggest to the operator a response method that is appropriate to the customer's emotions when transferring a complex inquiry, enabling a more appropriate response.

[0084] When supporting multiple languages, the translation unit can provide translations that take into account the cultural background and nuances of each language. For example, when the generative AI supports multiple languages, the translation unit provides translations that take into account the cultural background and nuances of each language. For example, when translating from English to Japanese, expressions that reflect cultural differences are used. The translation unit can also translate by taking into account the differences in word usage and nuances in specific cultures. This allows for more natural and appropriate responses by providing translations that take into account the cultural background and nuances of each language.

[0085] The translation unit can cross-reference dialogue data in different languages ​​to maintain consistency in the translation. For example, the generative AI can cross-reference dialogue data in different languages ​​to maintain consistency in the translation. For example, it can compare dialogue data in English and French to provide a consistent translation. The translation unit can also use a glossary or translation memory to maintain consistency in terminology and context between different languages. This allows consistency in the translation to be maintained by cross-referencing dialogue data in different languages.

[0086] The translation unit can incorporate an emotion estimation function and adjust the translated response so that it appropriately corresponds to the customer's emotions. For example, the generation AI in the translation unit can incorporate an emotion estimation function and adjust the translated response so that it appropriately corresponds to the customer's emotions. For example, if the customer is angry, the translation unit can provide a translation with a calm and polite tone. The translation unit can also use an emotion analysis algorithm to adjust the tone and style of the translated response. In this way, by incorporating an emotion estimation function and adjusting the translated response so that it appropriately corresponds to the customer's emotions, it is possible to provide a response that is more empathetic.

[0087] The translation unit performs translation in real time, making it possible to facilitate dialogue between different languages. For example, the translation unit uses a generative AI to perform translation in real time, making it possible to facilitate dialogue between different languages. For example, a question in English can be translated into Japanese in real time and an answer can be provided. The translation unit can also perform rapid translation using a real-time translation engine and low-latency communication technology. This allows for real-time translation to facilitate dialogue between different languages, making it possible to respond quickly and appropriately.

[0088] The translation department can refer to the opinions of experts in different languages ​​to improve the quality of the translation. For example, the generation AI can refer to the opinions of experts in different languages ​​to improve the quality of the translation. For example, in a translation from English to Japanese, the opinions of Japanese language experts are reflected. The translation department can also improve the accuracy of the translation based on reviews by translators and linguists. This allows the quality of the translation to be improved by referring to the opinions of experts in different languages.

[0089] The translation unit can use the emotion estimation function to adjust the translation style according to the customer's emotions when providing multilingual support. For example, the generation AI can use the emotion estimation function to adjust the translation style according to the customer's emotions when providing multilingual support. For example, if the customer is angry, a translation with a calm and polite tone is provided. The translation unit can also adjust the translation style using an emotion analysis algorithm. In this way, by using the emotion estimation function to adjust the translation style according to the customer's emotions when providing multilingual support, it is possible to provide answers that are more relatable.

[0090] When aggregating inquiries from multiple services, the aggregation unit can provide a response that takes into account the characteristics of each service. For example, when the generation AI aggregates inquiries from multiple services, the aggregation unit provides a response that takes into account the characteristics of each service. For example, it provides a detailed response to inquiries made by email and a concise response to inquiries made on social media. The aggregation unit can also customize responses according to the response procedures and characteristics of each service. This makes it possible to provide a more appropriate response when aggregating inquiries from multiple services by providing a response that takes into account the characteristics of each service.

[0091] The aggregation unit can automatically set the priority of inquiries and respond efficiently. For example, the generation AI of the aggregation unit can automatically set the priority of inquiries and respond efficiently. For example, inquiries with a high level of urgency can be given priority. The aggregation unit can also set priorities based on the urgency of the inquiry and the importance of the customer. This allows for automatic priority setting of inquiries and efficient response, enabling quick and appropriate responses.

[0092] The aggregation unit can use the emotion estimation function to analyze customer emotions and adjust response priorities. For example, the generation AI in the aggregation unit uses the emotion estimation function to analyze customer emotions and adjust response priorities. For example, if a customer is angry, the aggregation unit prioritizes the response. The aggregation unit can also use an emotion analysis algorithm to change priorities based on the customer's emotions. This makes it possible to analyze customer emotions using the emotion estimation function and adjust response priorities, enabling more appropriate responses.

[0093] The aggregation unit can automatically link data between different services and provide a consistent response. For example, the generation AI in the aggregation unit automatically links data between different services and provides a consistent response. For example, it can integrate email and chat inquiries and provide a consistent response. The aggregation unit can also link data between different services using API integration or database integration. This makes it possible to automatically link data between different services and provide a consistent response.

[0094] The aggregation unit can integrate the inquiry history of each service to get a complete picture of the customer. For example, the generation AI can integrate the inquiry history of each service to get a complete picture of the customer. For example, it can comprehensively understand the customer's problems based on past inquiry history. The aggregation unit can also get a complete picture of the customer based on the customer's profile and past behavioral history. In this way, by integrating the inquiry history of each service, a complete picture of the customer can be obtained, enabling more appropriate responses.

[0095] The aggregation unit can use the emotion estimation function to suggest a response method that matches the customer's emotions when aggregating inquiries from multiple services. For example, the aggregation unit uses the emotion estimation function to analyze the customer's emotions when aggregating inquiries from multiple services, and suggests a response method. For example, if the customer is angry, it suggests a calm and polite response. The aggregation unit can also use an emotion analysis algorithm to suggest response procedures or scripts that match the customer's emotions. This makes it possible to use the emotion estimation function to suggest a response method that matches the customer's emotions when aggregating inquiries from multiple services, enabling more appropriate responses.

[0096] When analyzing customer feedback, the feedback analysis unit can take into account the emotional aspects of the feedback and make improvement suggestions based on emotions. For example, when the generation AI analyzes customer feedback, the feedback analysis unit can take into account the emotional aspects of the feedback and make improvement suggestions based on emotions. For example, the feedback analysis unit can propose specific improvement measures for feedback in which a customer expresses dissatisfaction. The feedback analysis unit can also use an emotion analysis algorithm to analyze the emotional aspects of feedback and make improvement suggestions. In this way, by taking into account the emotional aspects of customer feedback and making improvement suggestions based on emotions, customer satisfaction can be improved.

[0097] The feedback analysis unit can provide the analysis results of customer feedback to the product team in real time, facilitating rapid quality improvements. For example, the feedback analysis unit uses a generative AI to provide the analysis results of customer feedback to the product team in real time, facilitating rapid quality improvements. For example, the content of the feedback can be immediately notified to the product team, allowing improvement measures to be implemented quickly. The feedback analysis unit can also provide the analysis results to the product team using real-time data transfer or API integration. This allows rapid quality improvements by providing the analysis results of customer feedback to the product team in real time.

[0098] The feedback analysis unit can refer to the background information of customer feedback and make more specific improvement proposals. For example, the generation AI can refer to the background information of customer feedback (for example, the customer's past behavioral history) and make more specific improvement proposals. For example, it can propose improvement measures based on past purchase history. The feedback analysis unit can also refer to background information and make improvement proposals based on past inquiries and related topics. This makes it possible to make more specific improvement proposals by referring to the background information of customer feedback.

[0099] The feedback analysis department can share the results of customer feedback analysis with different departments to promote company-wide quality improvement. For example, the feedback analysis department can share the results of customer feedback analysis with different departments (e.g., marketing, development) to promote company-wide quality improvement. For example, it can provide feedback to the marketing department to improve promotion strategies. The feedback analysis department can also share feedback with the technical department and customer support department to improve products and services. In this way, by sharing the results of customer feedback analysis with different departments, company-wide quality improvement is possible.

[0100] The feedback analysis unit can integrate the results of customer feedback analysis with other data sets to make comprehensive quality improvements. For example, the feedback analysis unit integrates the results of customer feedback analysis by the generative AI with other data sets (e.g., sales data, customer satisfaction surveys) to make comprehensive quality improvements. For example, it compares sales data with feedback to identify areas for improvement. The feedback analysis unit can also make comprehensive quality improvements based on customer data and sales data. This makes it possible to make comprehensive quality improvements by integrating the results of customer feedback analysis with other data sets.

[0101] The feedback analysis unit can use the emotion estimation function to analyze the emotional aspects of customer feedback and make improvement suggestions based on the emotions. For example, the generation AI can use the emotion estimation function to analyze the emotional aspects of customer feedback and make improvement suggestions based on the emotions. For example, the feedback analysis unit can propose specific improvement measures for feedback in which a customer expresses dissatisfaction. The feedback analysis unit can also use an emotion analysis algorithm to analyze the emotional aspects of feedback and make improvement suggestions. In this way, customer satisfaction can be improved by using the emotion estimation function to analyze the emotional aspects of customer feedback and making improvement suggestions based on the emotions.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] The natural language processing unit can refer to the questioner's past behavioral history to generate a more personalized answer. For example, if a question is about a product purchased in the past, an answer specific to that product will be provided. The natural language processing unit can also generate answers tailored to individual preferences based on website browsing history and purchase history. This makes it possible to provide a more personalized answer based on the questioner's past behavioral history.

[0104] The natural language processing unit can automatically collect background information about the question and reflect it in the answer. For example, the generation AI can automatically collect background information about the question (such as related news and trends) and reflect it in the answer. For example, it can provide an answer based on the latest product release information. The natural language processing unit can also collect background information based on past inquiries and related topics and reflect it in the answer. This allows background information about the question to be automatically collected and reflected in the answer.

[0105] The natural language processor can analyze image or audio data and generate answers based on multimodal information. For example, a generative AI can analyze image or audio data and generate answers based on multimodal information. For example, it can analyze a photo of a product and provide a detailed answer about the product. The natural language processor can also analyze audio recordings and convert them into text data using speech recognition technology to generate answers. This allows it to analyze image or audio data and generate answers based on multimodal information.

[0106] The natural language processing unit can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, the generation AI can refer to the opinions of experts in different industries to improve the accuracy of the answer. For example, answers that reflect the opinions of medical experts are provided for questions about medicine. The natural language processing unit can also improve the accuracy of the answer based on reviews by technical experts and business experts. This allows the opinions of experts in different industries to be referred to and the accuracy of the answer improved.

[0107] The natural language processing unit can use the emotion estimation function to adjust the tone and style of the response according to the emotion of the questioner. For example, the generation AI can use the emotion estimation function to analyze the emotion of the questioner and adjust the tone and style of the response according to that emotion. For example, if the customer is angry, it can provide a response in a calm and polite tone. The natural language processing unit can also perform text mining using an emotion analysis algorithm to adjust the tone and style according to the emotion of the questioner. This makes it possible to adjust the tone and style of the response according to the emotion of the questioner.

[0108] The learning unit learns not only past dialogue data but also other related data, allowing it to provide more accurate answers. For example, the generation AI learns not only past dialogue data but also other related data (e.g., customer purchase history and feedback) to provide more accurate answers. For example, it provides answers that match the customer's preferences based on past purchase history. The learning unit can also improve the accuracy of answers based on the customer's profile data and past purchase history. This allows it to provide more accurate answers by learning not only past dialogue data but also other related data.

[0109] The learning unit has a self-evaluation function that allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, the generation AI has a self-evaluation function that allows it to evaluate the accuracy of its own answers and find areas for improvement. For example, it compares past answers with customer feedback to evaluate accuracy. The learning unit can also use a self-evaluation algorithm to evaluate the accuracy of answers and customer satisfaction and identify areas for improvement. As a result, the self-evaluation function allows it to evaluate the accuracy of answers and find areas for improvement.

[0110] The learning unit incorporates an emotion estimation function, learns the emotional reactions of customers in past interactions, and can provide the optimal response based on those emotions. For example, a generation AI incorporates an emotion estimation function, learns the emotional reactions of customers in past interactions, and provides the optimal response based on those emotions. For example, it learns responses that pleased customers in past interactions and uses them in similar situations. The learning unit can also use an emotion analysis algorithm to analyze past interaction data and generate responses based on the customer's emotions. In this way, by incorporating an emotion estimation function, it can learn the emotional reactions of customers in past interactions and provide the optimal response based on those emotions.

[0111] The learning unit can learn dialogue data from different languages ​​and cultures to improve its global response capabilities. For example, the generation AI can learn dialogue data from different languages ​​and cultures to improve its global response capabilities. For example, it can learn dialogue data from languages ​​such as English and Spanish to strengthen its multilingual support. The learning unit can also understand the cultural background of a specific country or region and generate answers based on that. This allows it to improve its global response capabilities by learning dialogue data from different languages ​​and cultures.

[0112] The learning unit can use the emotion estimation function to adjust the tone and style of the response based on the learning data and provide the optimal response according to the customer's emotions. For example, the generation AI can use the emotion estimation function to adjust the tone and style of the response based on the learning data and provide the optimal response according to the customer's emotions. For example, if the customer is angry, it can provide a response in a calm and polite tone. The learning unit can also use an emotion analysis algorithm to analyze the learning data and adjust the tone and style according to the customer's emotions. This allows the emotion estimation function to adjust the tone and style of the response based on the learning data and provide the optimal response according to the customer's emotions.

[0113] The processing flow of the second embodiment will be briefly explained below.

[0114] Step 1: The natural language processing unit understands the intent of the customer's question and generates an appropriate answer. For example, it uses morphological analysis to break down the sentence, performs grammatical analysis, and understands the intent of the question through semantic analysis. It also uses keyword extraction technology to identify important parts of the question and generate an appropriate answer. Step 2: The learning unit learns from past dialogue data and evolves to provide optimal answers. For example, it uses machine learning algorithms to analyze past dialogue data and improve the accuracy of answers. It also uses a feedback loop to learn from customer feedback and improve the quality of answers. Step 3: The forwarding unit automatically forwards complex queries to a human operator. For example, it can identify complex queries based on the occurrence of specific keywords or the length of the query, and forward them to a human operator. It can also use rule-based forwarding or machine learning. Step 4: The translation department supports multiple languages, allowing customers to ask questions in their native language and providing answers through automatic translation. For example, it uses a machine translation engine to translate questions and generate appropriate answers. It can also use neural network translation to provide highly accurate translations. Step 5: The aggregation unit aggregates inquiries from multiple services into a single app. For example, an integrated platform can be used to centrally manage inquiries from email, messenger apps, social media, etc. Data from each service can also be aggregated using API integration. Step 6: The feedback analysis department automatically analyzes customer feedback and immediately sends it to the product. For example, it can use text mining technology to analyze the feedback and perform sentiment analysis. It can also use real-time data transfer to immediately send the analysis results to the product team.

[0115] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0116] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 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.

[0120] The data processing device 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, RAM 30, and 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 a WAN and / or a LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0129] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 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, RAM 30, and 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 a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0143] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0144] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 7, a 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.

[0150] The data processing device 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, RAM 30, and 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 a WAN and / or a LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0156] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0157] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0158] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0159] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0160] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0161] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0162] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0164] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] 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.

[0174] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0176] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0180] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a natural language processing unit that uses natural language processing to understand the intent of a customer's question and generate an appropriate answer; A learning section that evolves to provide optimal answers based on past conversations, A transfer unit that automatically transfers complex inquiries to a human operator; A translation department that supports multiple languages, allowing customers to ask questions in their native language and automatically translates the answers to provide answers; An aggregation unit that aggregates inquiries for multiple services into one app; A feedback analysis unit that automatically analyzes customer feedback and immediately transmits it to the product. A system characterized by:

2. The natural language processing unit Analyze image or audio data and generate answers based on multimodal information 2. The system of claim 1.

3. The learning unit The system learns not only the past dialogue data but also the other related data to provide the answer with higher accuracy.

2. The system of claim 1.

4. The transfer unit When transferring the complex inquiry, a summary of the inquiry is automatically generated and provided to the operator.

2. The system of claim 1.

5. The translation unit When providing multilingual support, we provide translations that take into account the cultural background and nuances of each language.

2. The system of claim 1.

6. The collecting unit is Analyze the customer's emotions using emotion estimation and adjust response priorities 2. The system of claim 1.

7. The feedback analysis unit When analyzing customer feedback, consider the emotional aspects of said feedback and make emotion-based improvement suggestions 2. The system of claim 1.

Images