system

Abstract

The system according to this embodiment aims to automate and efficiently handle inquiries. [Solution] The system according to the embodiment comprises a learning unit, a response unit, a processing unit, a decision unit, and a suggestion unit. The learning unit learns past inquiry content. The response unit provides automatic responses to text-based inquiries based on the content learned by the learning unit. The processing unit processes unstructured data. The decision unit makes decisions for human handling of inquiries that lead to sales or are complex. The suggestion unit learns past data and suggests products at the appropriate time.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that inquiry response depends on manpower and it is difficult to respond efficiently.

[0005] The system according to the embodiment aims to automate and efficiently perform inquiry response.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning unit, a response unit, a processing unit, a decision unit, and a suggestion unit. The learning unit learns past inquiry content. The response unit provides automatic responses to text-based inquiries based on the content learned by the learning unit. The processing unit processes unstructured data. The decision unit makes decisions for human handling of inquiries that lead to sales or are complex. The suggestion unit learns past data and suggests products at the appropriate time. [Effects of the Invention]

[0007] The system according to this embodiment can automate and efficiently handle inquiries. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The automated inquiry response system according to an embodiment of the present invention is a system that automates and streamlines inquiry response using an AI agent. This automated inquiry response system learns from past inquiries and enables automatic responses to text-based inquiries. As a result, the AI ​​agent automatically handles email-based inquiries, leaving humans only to make the final decision. Humans can handle inquiries that lead to sales or complex inquiries. Furthermore, the AI ​​agent can process unstructured data and evolves to learn from telephone (voice) interactions with customers and provide appropriate responses. In the future, it is planned that telephone support will also be automated in addition to email support. The AI ​​agent also aims to learn from past data and suggest products at the appropriate time. This system will improve the efficiency of inquiry response, making it possible to reduce call center personnel costs and the number of people required to handle inquiries within the company. In addition, while maintaining customer satisfaction, the external sale of the AI ​​agent is also being considered and is planned to be sold to call centers and large corporations. For example, the automated inquiry response system learns from past inquiries and enables automatic responses to text-based inquiries. As a result, the AI ​​agent automatically handles email-based inquiries, leaving humans only to make the final decision. Humans can handle inquiries that lead to sales or are complex. Furthermore, the AI ​​agent can process unstructured data and evolve to learn from customer phone (voice) interactions and provide appropriate responses. In the future, it is planned that not only email but also phone support will be automated. The AI ​​agent also aims to learn from past data and suggest products at the appropriate time. This system will improve the efficiency of inquiry handling, enabling reductions in call center personnel costs and the number of employees handling inquiries within the company. In addition, while maintaining customer satisfaction, the company is also considering selling the AI ​​agent externally, and plans to sell it to call centers and large corporations. As a result, the automated inquiry handling system will improve the efficiency of inquiry handling, enabling reductions in call center personnel costs and the number of employees handling inquiries within the company.

[0029] The automated inquiry handling system according to this embodiment comprises a learning unit, a response unit, a processing unit, a decision unit, and a suggestion unit. The learning unit learns past inquiry content. For example, the learning unit obtains past inquiry content from a database and learns it using a machine learning algorithm. For example, the learning unit can learn inquiry content such as questions, complaints, and feedback from customers. For example, the learning unit analyzes text data using natural language processing technology and extracts features of the inquiry content. The response unit provides an automated response to text-based inquiries based on the content learned by the learning unit. For example, the response unit can provide an automated response to email-based inquiries. For example, the response unit can also respond to customer inquiries in real time using a chatbot. For example, the response unit selects an appropriate template according to the inquiry content and generates an automated response. The processing unit processes unstructured data. For example, the processing unit can learn telephone (voice) interactions with customers and provide an appropriate response. For example, the processing unit converts voice data into text data and analyzes it using natural language processing technology. The processing unit analyzes image and video data, for example, and generates responses tailored to the inquiry. The decision unit makes decisions on whether to assign inquiries that lead to sales or complex inquiries to humans. The decision unit determines, for example, whether a human should handle an inquiry based on its importance and urgency. The decision unit prioritizes assigning sales-oriented inquiries, such as inquiries from highly motivated customers or requests for quotes, to humans. The decision unit also assigns complex inquiries, such as technical questions or issues spanning multiple departments, to humans. The suggestion unit learns from past data and proposes products at the appropriate time. The suggestion unit can propose products at the appropriate time based on customer behavior history and purchase history, for example. The suggestion unit can also propose products in line with specific events or campaigns, for example. The suggestion unit provides personalized product suggestions based on customer interests and preferences, for example.As a result, the automated inquiry handling system according to this embodiment can improve the efficiency of inquiry handling, reduce call center personnel costs, and decrease the number of employees required to handle inquiries within the company.

[0030] The learning unit learns from past inquiries. For example, the learning unit retrieves past inquiries from a database and learns from them using machine learning algorithms. Specifically, the learning unit extracts customer inquiries such as questions, complaints, and feedback from the database and preprocesses this data. Preprocessing includes text normalization, removal of unnecessary information, and tokenization. Next, it analyzes the text data using natural language processing techniques to extract features of the inquiries. For example, it analyzes word frequency, co-occurrence relationships, and contextual information to understand patterns and trends in inquiries. Furthermore, it uses machine learning algorithms to classify and cluster the inquiries, grouping similar inquiries together. This allows the learning unit to efficiently learn the features of inquiries and improve the accuracy of responses to future inquiries. In addition, the learning unit regularly incorporates new data and updates its model to always be able to handle the latest inquiries. For example, if inquiries about new products or services increase, it quickly learns from them to maintain response accuracy. This allows the learning unit to contribute to the efficiency and accuracy of inquiry handling, improving the overall system performance.

[0031] The response unit provides automated responses to text-based inquiries based on the information learned by the learning unit. For example, the response unit can provide automated responses to email-based inquiries. Specifically, the response unit selects an appropriate template based on the characteristics of the inquiry content learned by the learning unit and generates an automated response. For example, it analyzes the content of a customer inquiry, selects the most suitable template, and fills in the necessary information to create a response. The response unit can also respond to customer inquiries in real time using a chatbot. The chatbot uses natural language processing technology to analyze customer input and generate an appropriate response. For example, if a customer asks about how to use a product, the chatbot retrieves information from relevant FAQs and manuals and provides an answer immediately. Furthermore, the response unit selects an appropriate template depending on the content of the inquiry and generates an automated response. For example, it uses a template that includes an apology and solution for complaints, and a template that expresses gratitude for feedback. This allows the response unit to provide quick and appropriate responses, improving customer satisfaction. The response unit also saves a history of responses for later reference. This allows it to provide more appropriate responses based on past responses.

[0032] The processing unit processes unstructured data. For example, the processing unit can learn from telephone (voice) interactions with customers and provide appropriate responses. Specifically, the processing unit uses speech recognition technology to convert voice data into text data. Speech recognition technology analyzes customer utterances in real time and converts them into text data. Next, natural language processing technology is used to analyze the text data and understand the content of the inquiry. For example, if a customer reports a product defect, the processing unit analyzes the content and generates an appropriate response. The processing unit can also analyze image and video data and generate responses according to the content of the inquiry. For example, if a customer sends a photo of a product, the processing unit uses image recognition technology to analyze its content, identify the problem, and suggest solutions. Furthermore, the processing unit can analyze video data and understand the details of the problem indicated by the customer. This allows the processing unit to efficiently process unstructured data such as voice, images, and videos and provide appropriate responses. The processing unit also stores this data so that it can be referenced later. This allows for the provision of more appropriate responses based on past inquiries.

[0033] The decision-making unit makes decisions regarding whether to assign inquiries that lead to sales or are complex to human staff. Specifically, the unit determines whether a human should handle an inquiry based on its importance and urgency. For example, if an inquiry concerns a product purchase or a request for a quote, the unit prioritizes assigning it to a human. It also assigns human staff to complex inquiries, such as technical questions or issues spanning multiple departments. The unit analyzes the content of inquiries and determines whether it exceeds the scope of what the system can automatically respond to. For example, if a customer is seeking a detailed explanation of a specific technical issue, the unit assigns the inquiry to a specialist. The unit also assesses the urgency of inquiries and prioritizes those with high urgency. For example, if a customer is reporting a critical product defect, the unit assigns the inquiry to a human for a quick response. This allows the unit to provide appropriate responses based on the importance and urgency of inquiries, thereby improving customer satisfaction. Furthermore, the unit saves a history of inquiries for later reference. This allows for more appropriate decisions to be made based on past inquiries.

[0034] The recommendation department learns from past data and suggests products at the appropriate time. Specifically, it can suggest products at the right time based on the customer's behavior and purchase history. For example, if a customer frequently views a particular product, the recommendation department will suggest that customer purchase that product. It can also suggest products related to products the customer has previously purchased. For example, if a customer purchases a camera, the recommendation department will suggest accessories suitable for that camera. Furthermore, the recommendation department can suggest products in line with specific events and campaigns. For example, it can suggest special offers to customers in conjunction with Christmas or New Year's sales. The recommendation department also provides personalized product suggestions based on the customer's interests. For example, if a customer is interested in products in a particular category, it will prioritize suggesting products in that category. This allows the recommendation department to make appropriate product suggestions that meet customer needs and increase sales. The recommendation department also saves a history of suggestions for later reference. This allows it to make more appropriate suggestions based on past suggestions. In addition, the recommendation department can collect customer feedback and continuously improve the accuracy and effectiveness of its suggestions. This allows the recommendation department to improve customer satisfaction and maximize sales.

[0035] The response unit can provide automated responses to email-based inquiries. For example, the response unit can provide automated responses to email-based inquiries such as customer questions, complaints, and feedback. For example, the response unit can select an appropriate template according to the content of the inquiry and generate an automated response. The response unit can also analyze the content of the email using natural language processing technology and generate an appropriate response. This enables automated responses to email-based inquiries. Some or all of the above processing in the response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the response unit can input the content of an email-based inquiry into a generative AI and have the generative AI generate a response.

[0036] The processing unit can learn from phone conversations with customers and provide appropriate responses. For example, the processing unit can record phone conversations with customers and convert the audio data into text data. For example, the processing unit can analyze the text data using natural language processing techniques and generate appropriate responses. For example, the processing unit can analyze phone conversations with customers in real time and generate appropriate responses. This enables appropriate responses to phone conversations with customers. Some or all of the above processing in the processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the processing unit can input phone conversations with customers into a generative AI and have the generative AI generate responses.

[0037] The decision-making unit can make decisions regarding inquiries that lead to sales or complex inquiries, determining whether they should be handled by a human. For example, the decision-making unit prioritizes assigning sales-oriented inquiries, such as inquiries from highly motivated customers or requests for quotes, to humans. The decision-making unit also assigns complex inquiries, such as technical questions or issues spanning multiple departments, to humans. This enables decisions regarding inquiries that lead to sales or complex inquiries, determining whether they should be handled by a human. Some or all of the above processing in the decision-making unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the decision-making unit can input the content of an inquiry into a generative AI and have the generative AI make a decision.

[0038] The suggestion unit can learn from past data and suggest products at the appropriate time. For example, the suggestion unit suggests products at the appropriate time based on the customer's behavior history and purchase history. The suggestion unit can also suggest products in line with specific events or campaigns. For example, the suggestion unit makes personalized product suggestions based on the customer's interests and preferences. This makes it possible to suggest products at the appropriate time. Some or all of the above processes in the suggestion unit may be performed using, for example, generative AI, or without generative AI. For example, the suggestion unit can input the customer's behavior history and purchase history into a generative AI and have the generative AI make product suggestions.

[0039] The learning unit can determine learning priorities based on the frequency and importance of past inquiries during the learning process. For example, the learning unit may prioritize learning frequently asked questions. It can also prioritize learning highly important inquiries. For example, the learning unit may determine learning priorities by considering the balance between frequency and importance. This enables efficient learning by determining learning priorities based on the frequency and importance of past inquiries. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input past inquiry content into a generative AI and have the generative AI determine the learning priorities.

[0040] The learning unit can apply different learning algorithms to each category of inquiry during the learning process. For example, the learning unit can apply a technical algorithm to technical inquiries. For example, the learning unit can apply a customer support-specific algorithm to customer support inquiries. For example, the learning unit can apply a sales-specific algorithm to sales-related inquiries. This improves the accuracy of learning by applying different learning algorithms to each category of inquiry. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the inquiry categories into a generative AI and have the generative AI apply different learning algorithms.

[0041] The learning unit can weight the training data based on the submission timing of inquiries during training. For example, the learning unit can prioritize recent inquiries during training. The learning unit can also prioritize seasonal inquiries during training. For example, the learning unit can prioritize inquiries during a specific event period during training. This enables efficient training by weighting the training data based on the submission timing of inquiries. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the submission timing of inquiries into a generative AI and have the generative AI weight the training data.

[0042] The learning unit can improve the accuracy of its learning by referring to relevant literature related to the inquiry during the learning process. For example, the learning unit can learn by referring to relevant technical literature. The learning unit can also learn by referring to relevant customer support literature. The learning unit can learn by referring to relevant sales literature. This allows for more accurate learning by improving the accuracy of learning by referring to relevant literature related to the inquiry. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input relevant literature related to the inquiry into a generative AI to improve the accuracy of the generative AI's learning.

[0043] The response unit can adjust the level of detail in its response based on the importance of the inquiry. For example, the response unit can provide a detailed response to a high-importance inquiry. For example, the response unit can also provide a concise response to a low-importance inquiry. The response unit adjusts the level of detail in its response according to the importance of the inquiry. This allows for efficient responses by adjusting the level of detail in the response based on the importance of the inquiry. Some or all of the above processing in the response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the response unit can input the importance of the inquiry into a generation AI and have the generation AI adjust the level of detail in its response.

[0044] The response unit can apply different response algorithms depending on the category of the inquiry when responding. For example, the response unit can apply a technical response algorithm to a technical inquiry. For example, the response unit can apply a customer support-specific response algorithm to a customer support inquiry. For example, the response unit can apply a sales-specific response algorithm to a sales-related inquiry. This improves the accuracy of the response by applying different response algorithms depending on the category of the inquiry. Some or all of the above processing in the response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the response unit can input the category of the inquiry into a generative AI and cause the generative AI to apply different response algorithms.

[0045] The response unit can determine the priority of responses based on when the inquiry was submitted. For example, the response unit may prioritize recent inquiries. The response unit may also prioritize seasonal inquiries. For example, the response unit may prioritize inquiries during a specific event period. This enables efficient responses by determining the priority of responses based on when the inquiry was submitted. Some or all of the above processing in the response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the response unit can input the submission date of the inquiry into a generation AI and have the generation AI determine the priority of responses.

[0046] The response unit can adjust the order of responses based on the relevance of the inquiry content when responding. For example, the response unit may prioritize responding to highly relevant inquiries. For example, the response unit may postpone responding to less relevant inquiries. The response unit adjusts the order of responses according to relevance. This allows for efficient responses by adjusting the order of responses based on the relevance of the inquiry content. Some or all of the above processing in the response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the response unit can input the relevance of the inquiry content into a generation AI and have the generation AI adjust the order of responses.

[0047] The processing unit can adjust the level of detail of processing based on the importance of the data when processing unstructured data. For example, the processing unit may prioritize and process highly important data in detail. The processing unit may also process less important data concisely. The processing unit adjusts the level of detail of processing according to importance. This allows for efficient processing by adjusting the level of detail of processing based on the importance of the data. Some or all of the processing described above in the processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the processing unit can input the importance of the data into a generative AI and have the generative AI adjust the level of detail of processing.

[0048] The processing unit can apply different processing algorithms depending on the data category when processing unstructured data. For example, the processing unit can apply a speech processing algorithm to speech data. For example, the processing unit can apply a text processing algorithm to text data. For example, the processing unit can apply an image processing algorithm to image data. By applying different processing algorithms depending on the data category, the accuracy of the processing is improved. Some or all of the processing described above in the processing unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the processing unit can input the data category into a generative AI and cause the generative AI to apply different processing algorithms.

[0049] The processing unit can determine processing priorities based on the data submission date when processing unstructured data. For example, the processing unit may prioritize processing recent data. For example, the processing unit may prioritize processing seasonal data. For example, the processing unit may prioritize processing data during a specific event period. This enables efficient processing by determining processing priorities based on the data submission date. Some or all of the above processing in the processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the processing unit can input the data submission date into a generative AI and have the generative AI determine the processing priorities.

[0050] The processing unit can improve the accuracy of processing by referring to relevant literature when processing unstructured data. For example, the processing unit may refer to relevant technical literature. The processing unit may also refer to relevant customer support literature. The processing unit may also refer to relevant sales literature. By improving the accuracy of processing by referring to relevant literature, more accurate processing becomes possible. Some or all of the above processing in the processing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the processing unit can input relevant literature for the data into a generative AI and improve the accuracy of the processing in the generative AI.

[0051] The decision-making unit can adjust the level of detail in its decision based on the importance of the inquiry. For example, the decision-making unit can make a detailed decision for inquiries of high importance. For example, the decision-making unit can also make a concise decision for inquiries of low importance. The decision-making unit adjusts the level of detail in its decision according to the importance. This allows for efficient decision-making by adjusting the level of detail in the decision based on the importance of the inquiry. Some or all of the above processing in the decision-making unit may be performed using, for example, a generating AI, or without a generating AI. For example, the decision-making unit can input the importance of the inquiry into the generating AI and have the generating AI adjust the level of detail in its decision.

[0052] The decision-making unit can determine the priority of decisions based on when the inquiry content was submitted. For example, the decision-making unit may prioritize recent inquiries. For example, the decision-making unit may prioritize seasonal inquiries. For example, the decision-making unit may prioritize inquiries during a specific event period. This allows for efficient decision-making by determining the priority of decisions based on when the inquiry content was submitted. Some or all of the above processing in the decision-making unit may be performed using, for example, a generating AI, or without a generating AI. For example, the decision-making unit can input the submission dates of inquiries into a generating AI and have the generating AI determine the priority of decisions.

[0053] The proposal unit can adjust the level of detail in its proposals based on the importance of the products. For example, the proposal unit can provide detailed proposals for highly important products. For example, it can also provide concise proposals for less important products. The proposal unit adjusts the level of detail in its proposals according to their importance. This allows for more efficient proposals by adjusting the level of detail based on the importance of the products. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input the importance of the products into the generative AI and have the generative AI adjust the level of detail in its proposals.

[0054] The suggestion unit can apply different suggestion algorithms depending on the product category when making suggestions. For example, the suggestion unit can apply a technical suggestion algorithm to technical products. For example, the suggestion unit can apply a customer support-specific suggestion algorithm to customer support-related products. For example, the suggestion unit can apply a sales-specific suggestion algorithm to sales-related products. By applying different suggestion algorithms depending on the product category, the accuracy of the suggestions is improved. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the product category into a generative AI and have the generative AI apply different suggestion algorithms.

[0055] The proposal department can prioritize proposals based on the timing of product submission. For example, the proposal department may prioritize proposals for recent products. The proposal department may also prioritize proposals for seasonal products. The proposal department may also prioritize proposals for products during a specific event period. This allows for more efficient proposals by prioritizing proposals based on the timing of product submission. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal department can input the product submission timing into a generative AI and have the generative AI determine the priority of proposals.

[0056] The proposal unit can adjust the order of proposals based on the relevance of the products when making a proposal. For example, the proposal unit may prioritize proposals for highly relevant products. For example, the proposal unit may also postpone proposals for less relevant products. The proposal unit adjusts the order of proposals according to relevance. This allows for efficient proposals by adjusting the order of proposals based on the relevance of the products. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input the relevance of the products into a generative AI and have the generative AI adjust the order of proposals.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The automated inquiry response system can further refer to a user's past inquiry history and provide individualized responses. For example, it can respond to users who have made similar inquiries in the past, taking into account previous responses. It can also provide specially considerate responses to users who have previously filed complaints. Users who have previously purchased high-priced items can receive priority service. This enables customized responses for each user, which is expected to improve customer satisfaction.

[0059] The automated inquiry response system can also acquire users' geographical information and provide different responses depending on the region. For example, it can provide region-specific responses to inquiries that frequently occur in a particular area. It can also provide responses that take into account the culture and customs of each region. It can even provide responses that are compatible with the language and dialect of each region. This enables customized responses for each region, which is expected to improve customer satisfaction.

[0060] The automated inquiry response system can further reference the user's purchase history and suggest relevant products. For example, it can suggest new products related to items previously purchased, upgraded versions of previously purchased items, or complementary products to previously purchased items. This enables the suggestion of appropriate products based on the user's purchase history, which is expected to increase sales.

[0061] The automated inquiry response system can also acquire user device information and provide different responses depending on the device. For example, inquiries from smartphones can be answered with responses optimized for smartphones. Inquiries from PCs can be answered with responses optimized for PCs. Inquiries from tablets can be answered with responses optimized for tablets. This enables customized responses for each device, which is expected to improve customer satisfaction.

[0062] The automated inquiry response system can further reference user behavior history and provide responses based on behavioral patterns. For example, it can provide quick responses to users who frequently make inquiries. It can also provide responses optimized for users who make inquiries at specific times of the day. Users interested in specific topics can be provided with information related to those topics. This enables appropriate responses based on user behavior history, which is expected to improve customer satisfaction.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The learning unit learns from past inquiries. For example, the learning unit retrieves past inquiries from a database and learns from them using machine learning algorithms. The learning unit can learn from customer inquiries such as questions, complaints, and feedback. The learning unit analyzes text data using natural language processing technology and extracts features of the inquiries. Step 2: The response unit automatically responds to text-based inquiries based on what it has learned from the learning unit. The response unit can also automatically respond to email-based inquiries. The response unit can also respond to customer inquiries in real time using a chatbot. The response unit selects the appropriate template according to the content of the inquiry and generates an automated response. Step 3: The processing unit processes unstructured data. The processing unit learns from phone (voice) interactions with customers and can provide appropriate responses. The processing unit converts voice data into text data and analyzes it using natural language processing techniques. The processing unit analyzes image and video data and generates responses tailored to the inquiries. Step 4: The decision-making unit makes decisions on whether to assign sales-generating and complex inquiries to humans. The decision-making unit determines whether a human should handle an inquiry based on its importance and urgency. The decision-making unit prioritizes assigning sales-generating inquiries, such as inquiries from highly motivated customers and requests for quotes, to humans. The decision-making unit also assigns complex inquiries, such as technical questions and issues spanning multiple departments, to humans. Step 5: The recommendation team learns from past data and suggests products at the right time. The recommendation team can suggest products at the right time based on the customer's behavior and purchase history. The recommendation team can also suggest products to coincide with specific events or campaigns. The recommendation team provides personalized product suggestions based on the customer's interests and preferences.

[0065] (Example of form 2) The automated inquiry response system according to an embodiment of the present invention is a system that automates and streamlines inquiry response using an AI agent. This automated inquiry response system learns from past inquiries and enables automatic responses to text-based inquiries. As a result, the AI ​​agent automatically handles email-based inquiries, leaving humans only to make the final decision. Humans can handle inquiries that lead to sales or complex inquiries. Furthermore, the AI ​​agent can process unstructured data and evolves to learn from telephone (voice) interactions with customers and provide appropriate responses. In the future, it is planned that telephone support will also be automated in addition to email support. The AI ​​agent also aims to learn from past data and suggest products at the appropriate time. This system will improve the efficiency of inquiry response, making it possible to reduce call center personnel costs and the number of people required to handle inquiries within the company. In addition, while maintaining customer satisfaction, the external sale of the AI ​​agent is also being considered and is planned to be sold to call centers and large corporations. For example, the automated inquiry response system learns from past inquiries and enables automatic responses to text-based inquiries. As a result, the AI ​​agent automatically handles email-based inquiries, leaving humans only to make the final decision. Humans can handle inquiries that lead to sales or are complex. Furthermore, the AI ​​agent can process unstructured data and evolve to learn from customer phone (voice) interactions and provide appropriate responses. In the future, it is planned that not only email but also phone support will be automated. The AI ​​agent also aims to learn from past data and suggest products at the appropriate time. This system will improve the efficiency of inquiry handling, enabling reductions in call center personnel costs and the number of employees handling inquiries within the company. In addition, while maintaining customer satisfaction, the company is also considering selling the AI ​​agent externally, and plans to sell it to call centers and large corporations. As a result, the automated inquiry handling system will improve the efficiency of inquiry handling, enabling reductions in call center personnel costs and the number of employees handling inquiries within the company.

[0066] The automated inquiry handling system according to this embodiment comprises a learning unit, a response unit, a processing unit, a decision unit, and a suggestion unit. The learning unit learns past inquiry content. For example, the learning unit obtains past inquiry content from a database and learns it using a machine learning algorithm. For example, the learning unit can learn inquiry content such as questions, complaints, and feedback from customers. For example, the learning unit analyzes text data using natural language processing technology and extracts features of the inquiry content. The response unit provides an automated response to text-based inquiries based on the content learned by the learning unit. For example, the response unit can provide an automated response to email-based inquiries. For example, the response unit can also respond to customer inquiries in real time using a chatbot. For example, the response unit selects an appropriate template according to the inquiry content and generates an automated response. The processing unit processes unstructured data. For example, the processing unit can learn telephone (voice) interactions with customers and provide an appropriate response. For example, the processing unit converts voice data into text data and analyzes it using natural language processing technology. The processing unit analyzes image and video data, for example, and generates responses tailored to the inquiry. The decision unit makes decisions on whether to assign inquiries that lead to sales or complex inquiries to humans. The decision unit determines, for example, whether a human should handle an inquiry based on its importance and urgency. The decision unit prioritizes assigning sales-oriented inquiries, such as inquiries from highly motivated customers or requests for quotes, to humans. The decision unit also assigns complex inquiries, such as technical questions or issues spanning multiple departments, to humans. The suggestion unit learns from past data and proposes products at the appropriate time. The suggestion unit can propose products at the appropriate time based on customer behavior history and purchase history, for example. The suggestion unit can also propose products in line with specific events or campaigns, for example. The suggestion unit provides personalized product suggestions based on customer interests and preferences, for example.As a result, the automated inquiry handling system according to this embodiment can improve the efficiency of inquiry handling, reduce call center personnel costs, and decrease the number of employees required to handle inquiries within the company.

[0067] The learning unit learns from past inquiries. For example, the learning unit retrieves past inquiries from a database and learns from them using machine learning algorithms. Specifically, the learning unit extracts customer inquiries such as questions, complaints, and feedback from the database and preprocesses this data. Preprocessing includes text normalization, removal of unnecessary information, and tokenization. Next, it analyzes the text data using natural language processing techniques to extract features of the inquiries. For example, it analyzes word frequency, co-occurrence relationships, and contextual information to understand patterns and trends in inquiries. Furthermore, it uses machine learning algorithms to classify and cluster the inquiries, grouping similar inquiries together. This allows the learning unit to efficiently learn the features of inquiries and improve the accuracy of responses to future inquiries. In addition, the learning unit regularly incorporates new data and updates its model to always be able to handle the latest inquiries. For example, if inquiries about new products or services increase, it quickly learns from them to maintain response accuracy. This allows the learning unit to contribute to the efficiency and accuracy of inquiry handling, improving the overall system performance.

[0068] The response unit provides automated responses to text-based inquiries based on the information learned by the learning unit. For example, the response unit can provide automated responses to email-based inquiries. Specifically, the response unit selects an appropriate template based on the characteristics of the inquiry content learned by the learning unit and generates an automated response. For example, it analyzes the content of a customer inquiry, selects the most suitable template, and fills in the necessary information to create a response. The response unit can also respond to customer inquiries in real time using a chatbot. The chatbot uses natural language processing technology to analyze customer input and generate an appropriate response. For example, if a customer asks about how to use a product, the chatbot retrieves information from relevant FAQs and manuals and provides an answer immediately. Furthermore, the response unit selects an appropriate template depending on the content of the inquiry and generates an automated response. For example, it uses a template that includes an apology and solution for complaints, and a template that expresses gratitude for feedback. This allows the response unit to provide quick and appropriate responses, improving customer satisfaction. The response unit also saves a history of responses for later reference. This allows it to provide more appropriate responses based on past responses.

[0069] The processing unit processes unstructured data. For example, the processing unit can learn from telephone (voice) interactions with customers and provide appropriate responses. Specifically, the processing unit uses speech recognition technology to convert voice data into text data. Speech recognition technology analyzes customer utterances in real time and converts them into text data. Next, natural language processing technology is used to analyze the text data and understand the content of the inquiry. For example, if a customer reports a product defect, the processing unit analyzes the content and generates an appropriate response. The processing unit can also analyze image and video data and generate responses according to the content of the inquiry. For example, if a customer sends a photo of a product, the processing unit uses image recognition technology to analyze its content, identify the problem, and suggest solutions. Furthermore, the processing unit can analyze video data and understand the details of the problem indicated by the customer. This allows the processing unit to efficiently process unstructured data such as voice, images, and videos and provide appropriate responses. The processing unit also stores this data so that it can be referenced later. This allows for the provision of more appropriate responses based on past inquiries.

[0070] The decision-making unit makes decisions regarding whether to assign inquiries that lead to sales or are complex to human staff. Specifically, the unit determines whether a human should handle an inquiry based on its importance and urgency. For example, if an inquiry concerns a product purchase or a request for a quote, the unit prioritizes assigning it to a human. It also assigns human staff to complex inquiries, such as technical questions or issues spanning multiple departments. The unit analyzes the content of inquiries and determines whether it exceeds the scope of what the system can automatically respond to. For example, if a customer is seeking a detailed explanation of a specific technical issue, the unit assigns the inquiry to a specialist. The unit also assesses the urgency of inquiries and prioritizes those with high urgency. For example, if a customer is reporting a critical product defect, the unit assigns the inquiry to a human for a quick response. This allows the unit to provide appropriate responses based on the importance and urgency of inquiries, thereby improving customer satisfaction. Furthermore, the unit saves a history of inquiries for later reference. This allows for more appropriate decisions to be made based on past inquiries.

[0071] The recommendation department learns from past data and suggests products at the appropriate time. Specifically, it can suggest products at the right time based on the customer's behavior and purchase history. For example, if a customer frequently views a particular product, the recommendation department will suggest that customer purchase that product. It can also suggest products related to products the customer has previously purchased. For example, if a customer purchases a camera, the recommendation department will suggest accessories suitable for that camera. Furthermore, the recommendation department can suggest products in line with specific events and campaigns. For example, it can suggest special offers to customers in conjunction with Christmas or New Year's sales. The recommendation department also provides personalized product suggestions based on the customer's interests. For example, if a customer is interested in products in a particular category, it will prioritize suggesting products in that category. This allows the recommendation department to make appropriate product suggestions that meet customer needs and increase sales. The recommendation department also saves a history of suggestions for later reference. This allows it to make more appropriate suggestions based on past suggestions. In addition, the recommendation department can collect customer feedback and continuously improve the accuracy and effectiveness of its suggestions. This allows the recommendation department to improve customer satisfaction and maximize sales.

[0072] The response unit can provide automated responses to email-based inquiries. For example, the response unit can provide automated responses to email-based inquiries such as customer questions, complaints, and feedback. For example, the response unit can select an appropriate template according to the content of the inquiry and generate an automated response. The response unit can also analyze the content of the email using natural language processing technology and generate an appropriate response. This enables automated responses to email-based inquiries. Some or all of the above processing in the response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the response unit can input the content of an email-based inquiry into a generative AI and have the generative AI generate a response.

[0073] The processing unit can learn from phone conversations with customers and provide appropriate responses. For example, the processing unit can record phone conversations with customers and convert the audio data into text data. For example, the processing unit can analyze the text data using natural language processing techniques and generate appropriate responses. For example, the processing unit can analyze phone conversations with customers in real time and generate appropriate responses. This enables appropriate responses to phone conversations with customers. Some or all of the above processing in the processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the processing unit can input phone conversations with customers into a generative AI and have the generative AI generate responses.

[0074] The decision-making unit can make decisions regarding inquiries that lead to sales or complex inquiries, determining whether they should be handled by a human. For example, the decision-making unit prioritizes assigning sales-oriented inquiries, such as inquiries from highly motivated customers or requests for quotes, to humans. The decision-making unit also assigns complex inquiries, such as technical questions or issues spanning multiple departments, to humans. This enables decisions regarding inquiries that lead to sales or complex inquiries, determining whether they should be handled by a human. Some or all of the above processing in the decision-making unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the decision-making unit can input the content of an inquiry into a generative AI and have the generative AI make a decision.

[0075] The suggestion unit can learn from past data and suggest products at the appropriate time. For example, the suggestion unit suggests products at the appropriate time based on the customer's behavior history and purchase history. The suggestion unit can also suggest products in line with specific events or campaigns. For example, the suggestion unit makes personalized product suggestions based on the customer's interests and preferences. This makes it possible to suggest products at the appropriate time. Some or all of the above processes in the suggestion unit may be performed using, for example, generative AI, or without generative AI. For example, the suggestion unit can input the customer's behavior history and purchase history into a generative AI and have the generative AI make product suggestions.

[0076] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will prioritize learning response data that helps reduce stress. For example, if the user is relaxed, the learning unit can also learn response data that includes detailed explanations. For example, if the user is in a hurry, the learning unit will prioritize learning data that requires a quick response. This allows for more appropriate learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the learning unit may be performed using a generative AI, or not using a generative AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI select training data.

[0077] The learning unit can determine learning priorities based on the frequency and importance of past inquiries during the learning process. For example, the learning unit may prioritize learning frequently asked questions. It can also prioritize learning highly important inquiries. For example, the learning unit may determine learning priorities by considering the balance between frequency and importance. This enables efficient learning by determining learning priorities based on the frequency and importance of past inquiries. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input past inquiry content into a generative AI and have the generative AI determine the learning priorities.

[0078] The learning unit can apply different learning algorithms to each category of inquiry during the learning process. For example, the learning unit can apply a technical algorithm to technical inquiries. For example, the learning unit can apply a customer support-specific algorithm to customer support inquiries. For example, the learning unit can apply a sales-specific algorithm to sales-related inquiries. This improves the accuracy of learning by applying different learning algorithms to each category of inquiry. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the inquiry categories into a generative AI and have the generative AI apply different learning algorithms.

[0079] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency. For example, if the user is relaxed, the learning unit can increase the learning frequency. For example, if the user is in a hurry, the learning unit can optimize the learning frequency. This allows for more appropriate learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the learning unit may be performed using a generative AI, or not using a generative AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI adjust the learning frequency.

[0080] The learning unit can weight the training data based on the submission timing of inquiries during training. For example, the learning unit can prioritize recent inquiries during training. The learning unit can also prioritize seasonal inquiries during training. For example, the learning unit can prioritize inquiries during a specific event period during training. This enables efficient training by weighting the training data based on the submission timing of inquiries. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the submission timing of inquiries into a generative AI and have the generative AI weight the training data.

[0081] The learning unit can improve the accuracy of its learning by referring to relevant literature related to the inquiry during the learning process. For example, the learning unit can learn by referring to relevant technical literature. The learning unit can also learn by referring to relevant customer support literature. The learning unit can learn by referring to relevant sales literature. This allows for more accurate learning by improving the accuracy of learning by referring to relevant literature related to the inquiry. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input relevant literature related to the inquiry into a generative AI to improve the accuracy of the generative AI's learning.

[0082] The response unit can estimate the user's emotions and adjust the way it expresses its response based on the estimated emotions. For example, if the user is stressed, the response unit will respond in a gentle manner. For example, if the user is relaxed, the response unit may provide a response that includes a detailed explanation. For example, if the user is in a hurry, the response unit will provide a concise response. This allows for a more appropriate response by adjusting the way it expresses its response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the processing described above in the response unit may be performed using a generative AI, or not using a generative AI. For example, the response unit can input user emotion data into a generative AI and have the generative AI adjust the way it expresses its response.

[0083] The response unit can adjust the level of detail in its response based on the importance of the inquiry. For example, the response unit can provide a detailed response to a high-importance inquiry. For example, the response unit can also provide a concise response to a low-importance inquiry. The response unit adjusts the level of detail in its response according to the importance of the inquiry. This allows for efficient responses by adjusting the level of detail in the response based on the importance of the inquiry. Some or all of the above processing in the response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the response unit can input the importance of the inquiry into a generation AI and have the generation AI adjust the level of detail in its response.

[0084] The response unit can apply different response algorithms depending on the category of the inquiry when responding. For example, the response unit can apply a technical response algorithm to a technical inquiry. For example, the response unit can apply a customer support-specific response algorithm to a customer support inquiry. For example, the response unit can apply a sales-specific response algorithm to a sales-related inquiry. This improves the accuracy of the response by applying different response algorithms depending on the category of the inquiry. Some or all of the above processing in the response unit may be performed using, for example, a generative AI, or without a generative AI. For example, the response unit can input the category of the inquiry into a generative AI and cause the generative AI to apply different response algorithms.

[0085] The response unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is stressed, the response unit will provide a short response. For example, if the user is relaxed, the response unit may provide a longer response. For example, if the user is in a hurry, the response unit will provide a response of the optimal length. By adjusting the length of the response based on the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the response unit may be performed using a generative AI, or not using a generative AI. For example, the response unit can input user emotion data into a generative AI and have the generative AI adjust the length of the response.

[0086] The response unit can determine the priority of responses based on when the inquiry was submitted. For example, the response unit may prioritize recent inquiries. The response unit may also prioritize seasonal inquiries. For example, the response unit may prioritize inquiries during a specific event period. This enables efficient responses by determining the priority of responses based on when the inquiry was submitted. Some or all of the above processing in the response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the response unit can input the submission date of the inquiry into a generation AI and have the generation AI determine the priority of responses.

[0087] The response unit can adjust the order of responses based on the relevance of the inquiry content when responding. For example, the response unit may prioritize responding to highly relevant inquiries. For example, the response unit may postpone responding to less relevant inquiries. The response unit adjusts the order of responses according to relevance. This allows for efficient responses by adjusting the order of responses based on the relevance of the inquiry content. Some or all of the above processing in the response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the response unit can input the relevance of the inquiry content into a generation AI and have the generation AI adjust the order of responses.

[0088] The processing unit can estimate the user's emotions and adjust how it processes unstructured data based on the estimated emotions. For example, if the user is stressed, the processing unit may perform rapid processing. For example, if the user is relaxed, the processing unit may perform detailed processing. For example, if the user is in a hurry, the processing unit may apply the most appropriate processing method. This allows for more appropriate processing by adjusting how unstructured data is processed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the processing unit may be performed using a generative AI, or not using a generative AI. For example, the processing unit can input user emotion data into a generative AI and have the generative AI adjust how it processes unstructured data.

[0089] The processing unit can adjust the level of detail of processing based on the importance of the data when processing unstructured data. For example, the processing unit may prioritize and process highly important data in detail. The processing unit may also process less important data concisely. The processing unit adjusts the level of detail of processing according to importance. This allows for efficient processing by adjusting the level of detail of processing based on the importance of the data. Some or all of the processing described above in the processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the processing unit can input the importance of the data into a generative AI and have the generative AI adjust the level of detail of processing.

[0090] The processing unit can apply different processing algorithms depending on the data category when processing unstructured data. For example, the processing unit can apply a speech processing algorithm to speech data. For example, the processing unit can apply a text processing algorithm to text data. For example, the processing unit can apply an image processing algorithm to image data. By applying different processing algorithms depending on the data category, the accuracy of the processing is improved. Some or all of the processing described above in the processing unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the processing unit can input the data category into a generative AI and cause the generative AI to apply different processing algorithms.

[0091] The processing unit can estimate the user's emotions and determine the processing priority of unstructured data based on the estimated user emotions. For example, if the user is stressed, the processing unit will prioritize processing. If the user is relaxed, the processing unit may process the data with the normal priority. If the user is in a hurry, the processing unit will process the data quickly. This allows for more appropriate processing by determining the processing priority of unstructured data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the processing unit may be performed using a generative AI, or not using a generative AI. For example, the processing unit can input user emotion data into a generative AI and have the generative AI determine the processing priority of unstructured data.

[0092] The processing unit can determine processing priorities based on the data submission date when processing unstructured data. For example, the processing unit may prioritize processing recent data. For example, the processing unit may prioritize processing seasonal data. For example, the processing unit may prioritize processing data during a specific event period. This enables efficient processing by determining processing priorities based on the data submission date. Some or all of the above processing in the processing unit may be performed using, for example, a generative AI, or without a generative AI. For example, the processing unit can input the data submission date into a generative AI and have the generative AI determine the processing priorities.

[0093] The processing unit can improve the accuracy of processing by referring to relevant literature when processing unstructured data. For example, the processing unit may refer to relevant technical literature. The processing unit may also refer to relevant customer support literature. The processing unit may also refer to relevant sales literature. By improving the accuracy of processing by referring to relevant literature, more accurate processing becomes possible. Some or all of the above processing in the processing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the processing unit can input relevant literature for the data into a generative AI and improve the accuracy of the processing in the generative AI.

[0094] The decision unit can estimate the user's emotions and adjust the decision criteria based on the estimated emotions. For example, if the user is stressed, the decision unit can make a quick decision. For example, if the user is relaxed, the decision unit can also make a detailed decision. For example, if the user is in a hurry, the decision unit can apply the optimal decision criteria. This allows for more appropriate decisions by adjusting the decision criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the decision unit may be performed using a generative AI, or not using a generative AI. For example, the decision unit can input user emotion data into a generative AI and have the generative AI adjust the decision criteria.

[0095] The decision-making unit can adjust the level of detail in its decision based on the importance of the inquiry. For example, the decision-making unit can make a detailed decision for inquiries of high importance. For example, the decision-making unit can also make a concise decision for inquiries of low importance. The decision-making unit adjusts the level of detail in its decision according to the importance. This allows for efficient decision-making by adjusting the level of detail in the decision based on the importance of the inquiry. Some or all of the above processing in the decision-making unit may be performed using, for example, a generating AI, or without a generating AI. For example, the decision-making unit can input the importance of the inquiry into the generating AI and have the generating AI adjust the level of detail in its decision.

[0096] The decision-making unit can estimate the user's emotions and determine the priority of decisions based on the estimated emotions. For example, the decision-making unit will prioritize decisions when the user is stressed. For example, the decision-making unit can also make decisions with normal priority when the user is relaxed. For example, the decision-making unit will make quick decisions when the user is in a hurry. This allows for more appropriate decisions by prioritizing decisions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the decision-making unit may be performed using a generative AI, or not using a generative AI. For example, the decision-making unit can input user emotion data into a generative AI and have the generative AI determine the priority of decisions.

[0097] The decision-making unit can determine the priority of decisions based on when the inquiry content was submitted. For example, the decision-making unit may prioritize recent inquiries. For example, the decision-making unit may prioritize seasonal inquiries. For example, the decision-making unit may prioritize inquiries during a specific event period. This allows for efficient decision-making by determining the priority of decisions based on when the inquiry content was submitted. Some or all of the above processing in the decision-making unit may be performed using, for example, a generating AI, or without a generating AI. For example, the decision-making unit can input the submission dates of inquiries into a generating AI and have the generating AI determine the priority of decisions.

[0098] The suggestion unit can estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, if the user is stressed, the suggestion unit will present suggestions in a gentle manner. If the user is relaxed, the suggestion unit may also present suggestions with detailed explanations. If the user is in a hurry, the suggestion unit will present concise suggestions. By adjusting the way suggestions are presented based on the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using a generative AI, or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the way it presents suggestions.

[0099] The proposal unit can adjust the level of detail in its proposals based on the importance of the products. For example, the proposal unit can provide detailed proposals for highly important products. For example, it can also provide concise proposals for less important products. The proposal unit adjusts the level of detail in its proposals according to their importance. This allows for more efficient proposals by adjusting the level of detail based on the importance of the products. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input the importance of the products into the generative AI and have the generative AI adjust the level of detail in its proposals.

[0100] The suggestion unit can apply different suggestion algorithms depending on the product category when making suggestions. For example, the suggestion unit can apply a technical suggestion algorithm to technical products. For example, the suggestion unit can apply a customer support-specific suggestion algorithm to customer support-related products. For example, the suggestion unit can apply a sales-specific suggestion algorithm to sales-related products. By applying different suggestion algorithms depending on the product category, the accuracy of the suggestions is improved. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the product category into a generative AI and have the generative AI apply different suggestion algorithms.

[0101] The suggestion unit can estimate the user's emotions and adjust the length of the suggestion based on the estimated emotions. For example, if the user is stressed, the suggestion unit will make a short suggestion. For example, if the user is relaxed, the suggestion unit may make a longer suggestion. For example, if the user is in a hurry, the suggestion unit will make a suggestion of the optimal length. By adjusting the length of the suggestion based on the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the processing described above in the suggestion unit may be performed using a generative AI, or not using a generative AI. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the length of the suggestion.

[0102] The proposal department can prioritize proposals based on the timing of product submission. For example, the proposal department may prioritize proposals for recent products. The proposal department may also prioritize proposals for seasonal products. The proposal department may also prioritize proposals for products during a specific event period. This allows for more efficient proposals by prioritizing proposals based on the timing of product submission. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal department can input the product submission timing into a generative AI and have the generative AI determine the priority of proposals.

[0103] The proposal unit can adjust the order of proposals based on the relevance of the products when making a proposal. For example, the proposal unit may prioritize proposals for highly relevant products. For example, the proposal unit may also postpone proposals for less relevant products. The proposal unit adjusts the order of proposals according to relevance. This allows for efficient proposals by adjusting the order of proposals based on the relevance of the products. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input the relevance of the products into a generative AI and have the generative AI adjust the order of proposals.

[0104] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0105] The automated inquiry response system can also estimate the user's emotions and adjust the tone of its response based on those emotions. For example, if the user is angry, the system can respond in a calm and composed tone. If the user is sad, the system can respond in a gentle tone. If the user is happy, the system can respond in a cheerful tone. This allows for responses in an appropriate tone according to the user's emotions, which is expected to improve customer satisfaction.

[0106] The automated inquiry response system can further refer to a user's past inquiry history and provide individualized responses. For example, it can respond to users who have made similar inquiries in the past, taking into account previous responses. It can also provide specially considerate responses to users who have previously filed complaints. Users who have previously purchased high-priced items can receive priority service. This enables customized responses for each user, which is expected to improve customer satisfaction.

[0107] The automated inquiry response system can further estimate the user's emotions and adjust the response based on those emotions. For example, if the user is feeling anxious, the system can respond with reassuring content. If the user is excited, the system can respond with content that encourages calmness. If the user is satisfied, the system can respond with content that further enhances that satisfaction. This enables responses that are appropriate to the user's emotions, and is expected to improve customer satisfaction.

[0108] The automated inquiry response system can also acquire users' geographical information and provide different responses depending on the region. For example, it can provide region-specific responses to inquiries that frequently occur in a particular area. It can also provide responses that take into account the culture and customs of each region. It can even provide responses that are compatible with the language and dialect of each region. This enables customized responses for each region, which is expected to improve customer satisfaction.

[0109] The automated inquiry response system can also estimate the user's emotions and adjust the timing of its response based on those emotions. For example, if the user is in a hurry, the system can respond quickly. If the user is relaxed, the system can respond at a slower pace. If the user is stressed, the system can respond at an appropriate time. This enables responses at the right time according to the user's emotions, which is expected to improve customer satisfaction.

[0110] The automated inquiry response system can further reference the user's purchase history and suggest relevant products. For example, it can suggest new products related to items previously purchased, upgraded versions of previously purchased items, or complementary products to previously purchased items. This enables the suggestion of appropriate products based on the user's purchase history, which is expected to increase sales.

[0111] The automated inquiry response system can further estimate the user's emotions and adjust the response format based on those emotions. For example, if the user is stressed, the response system can respond in a concise format. If the user is relaxed, the response system can respond in a detailed format. If the user is in a hurry, the response system can respond in the most appropriate format. This enables responses in an appropriate format according to the user's emotions, which is expected to improve customer satisfaction.

[0112] The automated inquiry response system can also acquire user device information and provide different responses depending on the device. For example, inquiries from smartphones can be answered with responses optimized for smartphones. Inquiries from PCs can be answered with responses optimized for PCs. Inquiries from tablets can be answered with responses optimized for tablets. This enables customized responses for each device, which is expected to improve customer satisfaction.

[0113] The automated inquiry response system can further estimate the user's emotions and adjust the frequency of responses based on those emotions. For example, if the user is stressed, the response unit can reduce the frequency of responses. If the user is relaxed, the response unit can increase the frequency of responses. If the user is in a hurry, the response unit can respond at the optimal frequency. This enables responses at an appropriate frequency according to the user's emotions, which is expected to improve customer satisfaction.

[0114] The automated inquiry response system can further reference user behavior history and provide responses based on behavioral patterns. For example, it can provide quick responses to users who frequently make inquiries. It can also provide responses optimized for users who make inquiries at specific times of the day. Users interested in specific topics can be provided with information related to those topics. This enables appropriate responses based on user behavior history, which is expected to improve customer satisfaction.

[0115] The following briefly describes the processing flow for example form 2.

[0116] Step 1: The learning unit learns from past inquiries. For example, the learning unit retrieves past inquiries from a database and learns from them using machine learning algorithms. The learning unit can learn from customer inquiries such as questions, complaints, and feedback. The learning unit analyzes text data using natural language processing technology and extracts features of the inquiries. Step 2: The response unit automatically responds to text-based inquiries based on what it has learned from the learning unit. The response unit can also automatically respond to email-based inquiries. The response unit can also respond to customer inquiries in real time using a chatbot. The response unit selects the appropriate template according to the content of the inquiry and generates an automated response. Step 3: The processing unit processes unstructured data. The processing unit learns from phone (voice) interactions with customers and can provide appropriate responses. The processing unit converts voice data into text data and analyzes it using natural language processing techniques. The processing unit analyzes image and video data and generates responses tailored to the inquiries. Step 4: The decision-making unit makes decisions on whether to assign sales-generating and complex inquiries to humans. The decision-making unit determines whether a human should handle an inquiry based on its importance and urgency. The decision-making unit prioritizes assigning sales-generating inquiries, such as inquiries from highly motivated customers and requests for quotes, to humans. The decision-making unit also assigns complex inquiries, such as technical questions and issues spanning multiple departments, to humans. Step 5: The recommendation team learns from past data and suggests products at the right time. The recommendation team can suggest products at the right time based on the customer's behavior and purchase history. The recommendation team can also suggest products to coincide with specific events or campaigns. The recommendation team provides personalized product suggestions based on the customer's interests and preferences.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0119] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0120] Each of the multiple elements described above, including the learning unit, response unit, processing unit, decision unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which acquires past inquiry content from the database 24 and learns using a machine learning algorithm. The response unit is implemented by the control unit 46A of the smart device 14, which automatically responds to email-based inquiries. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns telephone (voice) interactions with customers and provides appropriate responses. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12, which determines whether a human should handle the inquiry based on its importance and urgency. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12, which proposes products based on the customer's behavior history and purchase history. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0121] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0122] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0124] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0125] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0127] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0128] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0129] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0130] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0131] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0135] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements described above, including the learning unit, response unit, processing unit, decision unit, and suggestion unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which acquires past inquiry content from the database 24 and learns using a machine learning algorithm. The response unit is implemented by the control unit 46A of the smart glasses 214, which automatically responds to email-based inquiries. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns telephone (voice) interactions with customers and provides appropriate responses. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12, which determines whether a human should handle the inquiry based on its importance and urgency. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, which suggests products based on the customer's behavior history and purchase history. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0137] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0138] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0149] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0151] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the learning unit, response unit, processing unit, decision unit, and suggestion unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which acquires past inquiry content from the database 24 and learns using a machine learning algorithm. The response unit is implemented by the control unit 46A of the headset terminal 314 and provides automatic responses to email-based inquiries. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns telephone (voice) interactions with customers and provides appropriate responses. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12, which determines whether a human should handle the inquiry based on its importance and urgency. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, which suggests products based on the customer's behavioral history and purchase history. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0153] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0154] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0161] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0162] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0163] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0164] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0165] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0166] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0167] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0168] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0169] Each of the multiple elements described above, including the learning unit, response unit, processing unit, decision unit, and proposal unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which acquires past inquiry content from the database 24 and learns using a machine learning algorithm. The response unit is implemented by the control unit 46A of the robot 414, which automatically responds to email-based inquiries. The processing unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns telephone (voice) interactions with customers and provides appropriate responses. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12, which determines whether a human should handle the inquiry based on its importance and urgency. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12, which proposes products based on the customer's behavioral history and purchase history. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0170] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0171] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0172] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0173] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0174] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0175] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0176] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0177] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0178] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0179] 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.

[0180] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0181] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0182] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0183] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0184] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0185] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0186] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0187] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0188] (Note 1) A learning section that studies past inquiries, A response unit that automatically responds to text-based inquiries based on the content learned by the learning unit, A processing unit for processing unstructured data, A decision-making unit for handling inquiries that lead to sales or are complex, It includes a proposal unit that learns from past data and suggests products at the appropriate time. A system characterized by the following features. (Note 2) The response unit is Automate responses to email-based inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned processing unit, Learn from customer phone conversations and provide appropriate responses. The system described in Appendix 1, characterized by the features described herein. (Note 4) The unit that makes the determination said, This involves making decisions for people to handle inquiries that lead to sales or are complex. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, Learn from past data and suggest products at the appropriate time. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, During the learning process, learning priorities are determined based on the frequency and importance of past inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, During training, different learning algorithms are applied to each category of inquiry content. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, During training, the training data is weighted based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, During the learning process, we improve the accuracy of the learning by referring to relevant literature related to the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 12) The response unit is It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The response unit is When responding, adjust the level of detail in the response based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 14) The response unit is When responding, apply a different response algorithm depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 15) The response unit is It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The response unit is When responding, we will prioritize responses based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The response unit is When responding, the order of responses will be adjusted based on the relevance of the inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned processing unit, It estimates user sentiment and adjusts how unstructured data is processed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned processing unit, When processing unstructured data, adjust the level of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned processing unit, When processing unstructured data, different processing algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned processing unit, It estimates user sentiment and prioritizes the processing of unstructured data based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned processing unit, When processing unstructured data, prioritize processing based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned processing unit, When processing unstructured data, referencing relevant literature improves the accuracy of the processing. The system described in Appendix 1, characterized by the features described herein. (Note 24) The unit that makes the determination said, It estimates the user's emotions and adjusts the decision criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The unit that makes the determination said, When making a decision, adjust the level of detail based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 26) The unit that makes the determination said, It estimates the user's emotions and determines the priority of decisions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The unit that makes the determination said, When making a decision, we will prioritize the decision based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned proposal section is, When making a proposal, adjust the level of detail in the proposal based on the importance of the product. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned proposal section is, When making suggestions, different suggestion algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned proposal section is, When submitting proposals, prioritize them based on when the products are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned proposal section is, When making proposals, adjust the order of proposals based on the relevance of the products. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning section that studies past inquiries, A response unit that automatically responds to text-based inquiries based on the content learned by the learning unit, A processing unit for processing unstructured data, A decision-making unit for handling inquiries that lead to sales or are complex, It includes a proposal unit that learns from past data and suggests products at the appropriate time. A system characterized by the following features.

2. The response unit is Automate responses to email-based inquiries. The system according to feature 1.

3. The aforementioned processing unit, Learn from customer phone conversations and provide appropriate responses. The system according to feature 1.

4. The unit that makes the determination said, This involves making decisions for people to handle inquiries that lead to sales or are complex. The system according to feature 1.

5. The aforementioned proposal section is, Learn from past data and suggest products at the appropriate time. The system according to feature 1.

6. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

7. The aforementioned learning unit, During the learning process, learning priorities are determined based on the frequency and importance of past inquiries. The system according to feature 1.

8. The aforementioned learning unit, During training, different learning algorithms are applied to each category of inquiry content. The system according to feature 1.

Images