system

Abstract

The system according to this embodiment aims to provide prompt and accurate responses to customer inquiries. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives inquiries from customers. The analysis unit analyzes the inquiries received by the reception unit. The generation unit generates a response script based on the analysis performed by the analysis unit. The provision unit provides the response script generated by the generation unit to the operator. The learning unit learns the responses of the operators.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to quickly and accurately provide an answer to a customer's inquiry in a call center.

[0005] The system according to the embodiment aims to provide a quick and accurate answer to a customer's inquiry.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives inquiries from customers. The analysis unit analyzes the inquiries received by the reception unit. The generation unit generates a response script based on the analysis performed by the analysis unit. The provision unit provides the response script generated by the generation unit to the operator. The learning unit learns the responses of the operators. [Effects of the Invention]

[0007] The system according to this embodiment can provide quick and accurate responses to customer 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, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied 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 receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The call center system according to an embodiment of the present invention is a system that receives customer inquiries and generates response scripts in real time using AI. This call center system receives customer inquiries, the AI ​​analyzes the inquiries, and generates appropriate response scripts. The generated scripts are provided to operators, who use them as a reference to answer customers. After the operator answers, the AI ​​learns from the answers and improves the accuracy of future answers. This mechanism improves the operational efficiency of the call center and enables even new operators to provide service at the level of veterans. For example, customer inquiries are input to the AI ​​as text data. For example, an inquiry such as "How do I return a product?" is input. Next, the AI ​​analyzes the input inquiry. The AI ​​refers to past inquiry data and FAQ databases to generate the optimal response script. For example, specific steps such as "To return a product, please follow these steps" are generated. The generated response script is provided to the operator. The operator uses the provided script as a reference to answer customers. For example, the operator might answer, "To return a product, first prepare proof of purchase, and then fill out a return request form." After the operator answers, the AI ​​learns from the answers. The AI ​​compares the operator's response with the script it generates to evaluate its accuracy and appropriateness. For example, if the operator's response is accurate, the AI ​​learns from that response and improves the accuracy of future responses. This system improves the operational efficiency of call centers. Even new operators can provide service at the same level as veterans, leading to increased customer satisfaction. Furthermore, by having the AI ​​generate response scripts, the burden on operators is reduced, and appropriate responses to customer harassment become possible. As a result, the call center system can efficiently receive, analyze, generate, provide, and learn from customer inquiries.

[0029] The call center system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives inquiries from customers. Customer inquiries include, but are not limited to, text format, audio format, image format, etc. The reception unit directly receives inquiries in text format, for example. The reception unit can also receive inquiries in audio format after converting them to text format using speech recognition technology. For example, the reception unit converts customer audio into text data using speech recognition technology. The reception unit can also receive inquiries in image format after converting them to text format using image recognition technology. For example, the reception unit converts customer image data into text data using image recognition technology. The analysis unit analyzes the inquiries received by the reception unit. The analysis is performed using, but is not limited to, natural language processing technology or machine learning algorithms. For example, the analysis unit analyzes the inquiry using natural language processing technology. The analysis unit can also analyze the inquiry using machine learning algorithms. For example, the analysis unit analyzes the intent of the inquiry using machine learning algorithms. The generation unit generates a response script based on the content analyzed by the analysis unit. The response script is generated in various formats, such as text, audio, or a template, but is not limited to these examples. For example, the generation unit generates a response script in text format. The generation unit can also generate a response script in audio format. For example, the generation unit generates a response script in audio format using speech synthesis technology. The generation unit can also generate a response script using a template. For example, the generation unit generates a response script based on a pre-prepared template. The provision unit provides the response script generated by the generation unit to the operator. Provision is made in various formats, such as text, audio, or video, but is not limited to these examples. For example, the provision unit provides a response script in text format to the operator. The provision unit can also provide a response script in audio format to the operator.For example, the provisioning unit provides operators with voice-format response scripts using speech synthesis technology. The provisioning unit can also provide operators with video-format response scripts. For example, the provisioning unit provides operators with video-format response scripts. The learning unit learns the content of the operators' responses. Learning is performed using, for example, machine learning algorithms or feedback loops, but is not limited to these examples. For example, the learning unit learns the content of the operators' responses using machine learning algorithms. The learning unit can also learn the content of the operators' responses using feedback loops. For example, the learning unit compares the content of the operators' responses with the generated response scripts and learns from them. As a result, the call center system according to this embodiment can efficiently receive, analyze, generate, provide, and learn response scripts from customers.

[0030] The reception desk receives inquiries from customers. These inquiries may include, but are not limited to, text, audio, and image formats. The reception desk can directly receive inquiries in text format. It can also convert audio inquiries into text format using speech recognition technology. For example, the reception desk can convert customer voices into text data using speech recognition technology. The reception desk can also convert image inquiries into text format using image recognition technology. For example, the reception desk can convert customer image data into text data using image recognition technology. The reception desk employs advanced technologies to efficiently process these diverse inquiry formats. For example, the speech recognition technology uses a deep learning-based speech model that can convert customer speech into text with high accuracy. This allows for rapid processing of inquiries made by telephone as text data. Furthermore, the image recognition technology utilizes computer vision technology to extract text information from images sent by customers. For example, if a customer sends a screenshot of a product label or error message, the system can automatically extract the necessary information from the image and provide it to the reception department as text data. This allows the reception department to quickly and accurately receive customer inquiries and smoothly provide the data to the analysis department.

[0031] The analysis unit analyzes the content of inquiries received by the reception unit. Analysis is performed using, for example, natural language processing techniques and machine learning algorithms, but is not limited to these examples. For instance, the analysis unit may use natural language processing techniques to analyze the content of inquiries. The analysis unit can also use machine learning algorithms to analyze the content of inquiries. For example, the analysis unit may use machine learning algorithms to analyze the intent of the inquiries. The analysis unit utilizes these techniques to analyze customer inquiries in detail and generate foundational data for deriving appropriate answers. Specifically, it uses natural language processing techniques to grammatically analyze customer inquiries and extract keywords and important phrases. This clarifies the subject and intent of the inquiries. Furthermore, by comparing the current inquiry with past inquiry data using machine learning algorithms, it identifies similar inquiry patterns and provides reference information for deriving the optimal answer. For example, if a customer inquires about a product defect, the analysis unit can identify common solutions and methods based on similar past inquiry data and provide them to the generation unit. This allows the analysis unit to quickly and accurately analyze customer inquiries and smoothly provide data to the generation unit.

[0032] The generation unit generates a response script based on the content analyzed by the analysis unit. The response script may be generated in various formats, such as text, audio, or templates, but is not limited to these examples. For example, the generation unit can generate a response script in text format. The generation unit can also generate a response script in audio format. For example, the generation unit can generate a response script in audio format using speech synthesis technology. The generation unit can also generate a response script using templates. For example, the generation unit can generate a response script based on a pre-prepared template. The generation unit utilizes these technologies to quickly generate the optimal response script for customer inquiries. Specifically, when generating a response script in text format, natural language generation technology is used to automatically generate an appropriate response to the customer's inquiry. This eliminates the need for operators to manually create responses, enabling faster responses. Furthermore, when generating a response script in audio format, speech synthesis technology can be used to generate natural-sounding speech. This allows for natural-sounding responses even when customers make inquiries by phone. Additionally, when generating a response script using templates, pre-prepared response templates can be customized according to the customer's inquiry. This enables the provision of fast and consistent responses. The generation unit utilizes these technologies to quickly generate optimal response scripts for customer inquiries and smoothly provide the data to the subsequent delivery unit.

[0033] The provisioning unit provides operators with response scripts generated by the generation unit. The provision may be in various formats, such as text, audio, or video. For example, the provisioning unit may provide operators with text-based response scripts. The provisioning unit may also provide operators with audio-based response scripts. For example, the provisioning unit may provide operators with audio-based response scripts using speech synthesis technology. Furthermore, the provisioning unit may also provide operators with video-based response scripts. For example, the provisioning unit may provide operators with video-based response scripts. The provisioning unit utilizes these technologies to quickly provide operators with the most suitable response scripts. Specifically, when providing text-based response scripts, they are displayed on the operator's screen to allow for quick confirmation of the response. When providing audio-based response scripts, the response is provided audibly to the operator's headset, enabling the operator to communicate the response to the customer in a natural voice. When providing video-based response scripts, the video is displayed on the operator's screen, allowing the operator to visually communicate the response to the customer. This enables the provisioning unit to quickly provide operators with the most suitable response scripts, supporting prompt and accurate responses to customers.

[0034] The learning unit learns the operator's responses. Learning is performed using, for example, machine learning algorithms and feedback loops, but is not limited to these examples. For example, the learning unit can learn the operator's responses using machine learning algorithms. The learning unit can also learn the operator's responses using feedback loops. For example, the learning unit learns by comparing the operator's responses with the generated response scripts. The learning unit utilizes these techniques to continuously learn the operator's responses and improve the overall accuracy and efficiency of the system. Specifically, it uses machine learning algorithms to analyze the operator's responses and evaluate the degree of agreement with the generated response scripts. This allows the learning unit to determine how accurate the operator's responses are and improve the response scripts as needed. Furthermore, feedback loops can be used to collect feedback from operators and use it to improve the system. For example, if an operator makes a modification to the response script, the learning unit can record the modification and reflect it in the generation of subsequent response scripts. In this way, the learning unit can continuously learn the operator's responses and improve the overall accuracy and efficiency of the system.

[0035] The analysis unit includes a reference unit that refers to past inquiry data and an FAQ database. For example, the analysis unit refers to past inquiry data. For example, the analysis unit searches for relevant data from the past inquiry database and uses it for analysis. The analysis unit can also refer to an FAQ database. For example, the analysis unit retrieves relevant information from the FAQ database and uses it for analysis. By referring to past inquiry data and an FAQ database, the accuracy of the analysis is improved. Some or all of the above processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can refer to data using an AI model that takes the past inquiry database and FAQ database as input and outputs relevant data.

[0036] The learning unit includes a comparison unit that compares the operator's response with the generated script. The learning unit compares the operator's response with the generated script, for example. For example, the learning unit compares the operator's response with the generated response script using text matching technology. The learning unit can also compare the operator's response with the generated response script using similarity calculation technology. For example, the learning unit calculates the similarity between the operator's response and the generated response script and compares them. This improves the accuracy of learning by comparing the operator's response with the generated script. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can perform the comparison using an AI model that takes the operator's response and the generated response script as input and outputs a similarity score.

[0037] The service department includes a support department to assist in responding to customer harassment. The service department provides support for responding to customer harassment, for example. For example, the service department provides operators with appropriate response methods based on specific definitions and criteria of customer harassment. The service department can also provide support messages to operators depending on the customer harassment situation. For example, the service department provides operators with encouraging messages and advice depending on the customer harassment situation. This reduces the burden on operators by supporting their response to customer harassment. Some or all of the above processes in the support department may be performed using AI, for example, or not using AI. For example, the support department can provide support using an AI model that takes the customer harassment situation as input and outputs appropriate response methods.

[0038] The reception department can analyze a customer's past inquiry history and select the most appropriate reception method. For example, the reception department can prioritize inquiries that the customer has frequently made in the past. For example, the reception department can analyze a customer's past inquiry history and prioritize inquiries that the customer has made frequently. The reception department can also provide expert solutions to specific problems based on the customer's past inquiry history. For example, the reception department can analyze a customer's past inquiry history and provide expert solutions to specific problems. The reception department can also reapply solutions that the customer has been satisfied with in the past. For example, the reception department can analyze a customer's past inquiry history and reapply solutions that the customer was satisfied with. This allows the reception department to select the most appropriate reception method by analyzing the customer's past inquiry history. Some or all of the above processes in the reception department may be performed using AI, or not. For example, the reception department can input the customer's past inquiry history into a generating AI and have the generating AI select the most appropriate reception method.

[0039] The reception department can filter inquiries based on the customer's current situation and areas of interest when receiving them. For example, the reception department can prioritize receiving inquiries that are relevant to the customer's current situation. For example, the reception department can analyze the customer's current situation and prioritize receiving relevant inquiries. The reception department can also filter relevant inquiries based on the customer's areas of interest. For example, the reception department can analyze the customer's areas of interest and filter relevant inquiries. The reception department can also select the most appropriate response based on the customer's current situation and areas of interest. For example, the reception department can analyze the customer's current situation and areas of interest and select the most appropriate response. This allows for appropriate responses by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the customer's current situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0040] The reception department can prioritize receiving inquiries that are highly relevant by considering the customer's geographical location. For example, if a customer is in a specific region, the reception department will prioritize receiving inquiries related to that region. For example, the reception department will analyze the customer's geographical location and prioritize receiving inquiries related to that region. The reception department can also select the most appropriate response method based on the customer's geographical location. For example, the reception department will analyze the customer's geographical location and select the most appropriate response method. The reception department can also filter relevant inquiries by considering the customer's geographical location. For example, the reception department will analyze the customer's geographical location and filter relevant inquiries. This allows the reception department to prioritize receiving highly relevant inquiries by considering the customer's geographical location. Some or all of the above processing in the reception department may be performed using AI, for example, or without AI. For example, the reception department can input the customer's geographical location into a generating AI and have the generating AI prioritize receiving highly relevant inquiries.

[0041] The reception department can analyze the customer's social media activity when receiving inquiries and accept relevant content. For example, the reception department can prioritize accepting inquiries that are relevant to the customer's social media activity. The reception department can also analyze the customer's social media activity and select the most appropriate response method. The reception department can also filter relevant inquiries based on the customer's social media activity. For example, the reception department can analyze the customer's social media activity and filter relevant inquiries. This allows the reception department to appropriately accept relevant content by analyzing the customer's social media activity. Some or all of the above processing in the reception department may be performed using AI, or not. For example, the reception department can input the customer's social media activity into a generating AI and have the generating AI handle the acceptance of relevant content.

[0042] The analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry content during the analysis. For example, the analysis unit can perform a detailed analysis on inquiries with high importance. For example, the analysis unit can evaluate the importance of the inquiry content and perform a detailed analysis on those with high importance. The analysis unit can also perform a simplified analysis on inquiries with low importance. For example, the analysis unit can evaluate the importance of the inquiry content and perform a simplified analysis on those with low importance. The analysis unit can also determine the priority of the analysis according to the importance of the inquiry content. For example, the analysis unit can evaluate the importance of the inquiry content and determine the priority. By adjusting the level of detail of the analysis based on the importance of the inquiry content, appropriate analysis results can be provided. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the inquiry content into a generating AI and have the generating AI adjust the level of detail of the analysis.

[0043] The analysis unit can apply different analysis algorithms depending on the category of the inquiry during analysis. For example, the analysis unit can apply a specialized analysis algorithm to technical inquiries. For example, the analysis unit can evaluate the category of the inquiry and apply a specialized analysis algorithm to technical inquiries. The analysis unit can also apply a standard analysis algorithm to general inquiries. For example, the analysis unit can evaluate the category of the inquiry and apply a standard analysis algorithm to general inquiries. The analysis unit can also select the optimal analysis algorithm depending on the category of the inquiry. For example, the analysis unit can evaluate the category of the inquiry and select the optimal analysis algorithm. By applying different analysis algorithms depending on the category of the inquiry, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the inquiry into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0044] The analysis unit can determine the priority of analysis based on when the inquiry content was submitted. For example, the analysis unit may prioritize the analysis of recently submitted inquiries. For example, the analysis unit may evaluate the submission date of the inquiries and prioritize the analysis of recently submitted content. The analysis unit can also analyze older inquiries with normal priority. For example, the analysis unit may evaluate the submission date of the inquiries and analyze older inquiries with normal priority. The analysis unit can also adjust the priority of analysis based on the submission date. For example, the analysis unit may evaluate the submission date of the inquiries and adjust the priority. This enables a quick and appropriate response by determining the priority of analysis based on the submission date of the inquiries. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input the submission date of the inquiries into a generating AI and have the generating AI determine the priority of analysis.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the inquiry content during analysis. For example, the analysis unit may prioritize the analysis of highly relevant inquiry content. For example, the analysis unit may evaluate the relevance of the inquiry content and prioritize the analysis of highly relevant content. The analysis unit can also analyze less relevant inquiry content in the normal order. For example, the analysis unit may evaluate the relevance of the inquiry content and analyze less relevant content in the normal order. The analysis unit can also adjust the order of analysis based on the relevance of the inquiry content. For example, the analysis unit may evaluate the relevance of the inquiry content and adjust the order. By adjusting the order of analysis based on the relevance of the inquiry content, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input the relevance of the inquiry content into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0046] The generation unit can adjust the level of detail of the script based on the importance of the inquiry when generating the response script. For example, the generation unit can generate a detailed script for high-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a detailed script for high-importance inquiries. The generation unit can also generate a simplified script for low-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a simplified script for low-importance inquiries. The generation unit can also adjust the level of detail of the script according to the importance of the inquiry. For example, the generation unit can evaluate the importance of the inquiry and adjust the level of detail. This allows for an appropriate response by adjusting the level of detail of the script based on the importance of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the importance of the inquiry into the generation AI and have the generation AI adjust the level of detail of the script.

[0047] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating response scripts. For example, the generation unit can apply a specialized generation algorithm to technical inquiries. For example, the generation unit can evaluate the category of the inquiry and apply a specialized generation algorithm to technical inquiries. The generation unit can also apply a standard generation algorithm to general inquiries. For example, the generation unit can evaluate the category of the inquiry and apply a standard generation algorithm to general inquiries. The generation unit can also select the optimal generation algorithm depending on the category of the inquiry. For example, the generation unit can evaluate the category of the inquiry and select the optimal generation algorithm. This makes it possible to provide appropriate responses by applying different generation algorithms depending on the category of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the category of the inquiry into a generation AI and have the generation AI execute the application of the generation algorithm.

[0048] The generation unit can determine the priority of response scripts based on when the inquiry was submitted. For example, the generation unit can prioritize generating scripts for recently submitted inquiries. For example, the generation unit can evaluate the submission date of the inquiries and prioritize generating scripts for recently submitted inquiries. The generation unit can also generate scripts for older inquiries with normal priority. For example, the generation unit can evaluate the submission date of the inquiries and generate scripts for older inquiries with normal priority. The generation unit can also adjust the script priority based on the submission date. For example, the generation unit can evaluate the submission date of the inquiries and adjust the priority. This allows for a quick and appropriate response by determining the script priority based on the submission date of the inquiries. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the submission date of the inquiries into a generation AI and have the generation AI determine the script priority.

[0049] The generation unit can adjust the order of the scripts based on the relevance of the inquiry content when generating response scripts. For example, the generation unit can prioritize generating scripts for highly relevant inquiries. For example, the generation unit can evaluate the relevance of the inquiry content and prioritize generating scripts for highly relevant content. The generation unit can also generate scripts in the normal order for less relevant inquiries. For example, the generation unit can evaluate the relevance of the inquiry content and generate scripts in the normal order for less relevant content. The generation unit can also adjust the order of the scripts based on the relevance of the inquiry content. For example, the generation unit can evaluate the relevance of the inquiry content and adjust the order. This allows for appropriate responses by adjusting the order of the scripts based on the relevance of the inquiry content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the relevance of the inquiry content into a generation AI and have the generation AI perform the adjustment of the script order.

[0050] The service provider can select the optimal service method by referring to the operator's past operation history when providing a script. For example, the service provider can prioritize selecting service methods previously used by the operator. For example, the service provider can refer to the operator's past operation history and prioritize selecting service methods previously used. The service provider can also select the optimal service method from the operator's past operation history. For example, the service provider can refer to the operator's past operation history and select the optimal service method. The service provider can also reapply service methods that the operator has previously been satisfied with. For example, the service provider can refer to the operator's past operation history and reapply services that the operator was satisfied with. In this way, the service provider can select the optimal service method by referring to the operator's past operation history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the operator's past operation history into a generating AI and have the generating AI select the optimal service method.

[0051] The service provider can customize the content of the provided script according to the operator's skill level. For example, the service provider can provide a script with detailed explanations to new operators. For example, the service provider can evaluate the operator's skill level and provide a script with detailed explanations to new operators. The service provider can also provide a concise script to veteran operators. For example, the service provider can evaluate the operator's skill level and provide a concise script to veteran operators. The service provider can also adjust the content of the script according to the operator's skill level. For example, the service provider can evaluate the operator's skill level and adjust the content of the script. This allows for appropriate responses by customizing the content of the provided script according to the operator's skill level. Some or all of the above processes in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input the operator's skill level into a generating AI and have the generating AI perform the customization of the provided content.

[0052] The service provider can select the optimal service delivery method by considering the operator's geographical location information when providing scripts. For example, if the operator is in a specific region, the service provider can provide a script relevant to that region. For example, the service provider can analyze the operator's geographical location information and provide a script relevant to that region. The service provider can also select the optimal service delivery method based on the operator's geographical location information. For example, the service provider can analyze the operator's geographical location information and select the optimal service delivery method. The service provider can also provide relevant scripts considering the operator's geographical location information. For example, the service provider can analyze the operator's geographical location information and provide relevant scripts. This allows the service provider to select the optimal service delivery method by considering the operator's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the operator's geographical location information into a generating AI and have the generating AI select the optimal service delivery method.

[0053] The service provider can analyze the operator's social media activity and adjust the content of the service when providing scripts. For example, the service provider can provide relevant scripts based on the operator's social media activity. For example, the service provider can analyze the operator's social media activity and provide relevant scripts. The service provider can also analyze the operator's social media activity and select the optimal delivery method. For example, the service provider can analyze the operator's social media activity and select the optimal delivery method. The service provider can also adjust the content of the service based on the operator's social media activity. For example, the service provider can analyze the operator's social media activity and adjust the content of the service. This allows for appropriate adjustment of the content of the service by analyzing the operator's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the operator's social media activity into a generating AI and have the generating AI perform the adjustment of the content of the service.

[0054] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. For example, the learning unit can select the optimal learning algorithm by referring to past learning data. The learning unit can also optimize the learning algorithm by analyzing past learning data. For example, the learning unit can analyze past learning data and optimize the learning algorithm. The learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. For example, the learning unit can improve the accuracy of the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0055] The learning unit can customize the learning content by analyzing the operator's response history during the learning process. For example, the learning unit can customize the learning content based on the operator's response history. For example, the learning unit can analyze the operator's response history and customize the learning content. The learning unit can also analyze the operator's response history and select the optimal learning content. For example, the learning unit can analyze the operator's response history and select the optimal learning content. The learning unit can also refer to the operator's response history and adjust the learning content. For example, the learning unit refers to the operator's response history and adjusts the learning content. This allows for appropriate customization of the learning content by analyzing the operator's response history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the operator's response history into a generating AI and have the generating AI perform the customization of the learning content.

[0056] The learning unit can weight the training data based on the submission date of the inquiry during training. For example, the learning unit can give higher weight to recently submitted inquiries. For example, the learning unit can evaluate the submission date of the inquiry and give higher weight to recently submitted inquiries. The learning unit can also give lower weight to older inquiries. For example, the learning unit can evaluate the submission date of the inquiry and give lower weight to older inquiries. The learning unit can also adjust the weighting of the training data based on the submission date. For example, the learning unit can evaluate the submission date of the inquiry and adjust the weighting. This enables appropriate training by weighting the training data based on the submission date of the inquiry. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the submission date of the inquiry into a generating AI and have the generating AI perform the weighting of the training data.

[0057] The learning unit can adjust the learning content according to the operator's skill level during the learning process. For example, the learning unit can provide basic learning content to new operators. For example, the learning unit can evaluate the operator's skill level and provide basic learning content to new operators. The learning unit can also provide advanced learning content to veteran operators. For example, the learning unit can evaluate the operator's skill level and provide advanced learning content to veteran operators. The learning unit can also adjust the learning content according to the operator's skill level. For example, the learning unit can evaluate the operator's skill level and adjust the learning content. This allows for appropriate learning by adjusting the learning content according to the operator's skill level. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the operator's skill level into a generating AI and have the generating AI perform the adjustment of the learning content.

[0058] The reference unit can analyze past query data and select the optimal reference method when referencing data. For example, the reference unit can select the optimal reference method based on past query data. For example, the reference unit can analyze past query data and select the optimal reference method. The reference unit can also analyze past query data and optimize the reference method. For example, the reference unit can analyze past query data and optimize the reference method. The reference unit can also refer to past query data and select the optimal reference method. For example, the reference unit can refer to past query data and select the optimal reference method. In this way, the optimal reference method can be selected by analyzing past query data. Some or all of the above processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can input past query data into a generating AI and have the generating AI perform the selection of the optimal reference method.

[0059] The reference unit can apply different reference algorithms depending on the category of the query content during the reference process. For example, the reference unit can apply a specialized reference algorithm to technical queries. For instance, the reference unit evaluates the category of the query content and applies a specialized reference algorithm to technical content. The reference unit can also apply a standard reference algorithm to general queries. For example, the reference unit evaluates the category of the query content and applies a standard reference algorithm to general content. The reference unit can also select the optimal reference algorithm depending on the category of the query content. For example, the reference unit evaluates the category of the query content and selects the optimal reference algorithm. This enables appropriate data retrieval by applying different reference algorithms depending on the category of the query content. Some or all of the above processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can input the category of the query content into a generating AI and have the generating AI execute the application of the reference algorithm.

[0060] The comparison unit can select the optimal comparison method by analyzing the operator's response history during the comparison process. For example, the comparison unit can select the optimal comparison method based on the operator's response history. For example, the comparison unit can analyze the operator's response history and select the optimal comparison method. The comparison unit can also optimize the comparison method by analyzing the operator's response history. For example, the comparison unit can analyze the operator's response history and optimize the comparison method. The comparison unit can also select the optimal comparison method by referring to the operator's response history. For example, the comparison unit can refer to the operator's response history and select the optimal comparison method. In this way, the optimal comparison method can be selected by analyzing the operator's response history. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without using AI. For example, the comparison unit can input the operator's response history into a generating AI and have the generating AI select the optimal comparison method.

[0061] The comparison unit can apply different comparison algorithms depending on the category of the inquiry during the comparison process. For example, the comparison unit can apply a specialized comparison algorithm to technical inquiries. For instance, the comparison unit evaluates the category of the inquiry and applies a specialized comparison algorithm to technical inquiries. The comparison unit can also apply a standard comparison algorithm to general inquiries. For example, the comparison unit evaluates the category of the inquiry and applies a standard comparison algorithm to general inquiries. The comparison unit can also select the optimal comparison algorithm depending on the category of the inquiry. For example, the comparison unit evaluates the category of the inquiry and selects the optimal comparison algorithm. This enables appropriate comparisons by applying different comparison algorithms depending on the category of the inquiry. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input the category of the inquiry into a generating AI and have the generating AI execute the application of the comparison algorithm.

[0062] The support department can select the optimal support method by referring to the operator's past interaction history when providing support. For example, the support department selects the optimal support method based on the operator's past interaction history. For example, the support department selects the optimal support method by referring to the operator's past interaction history. The support department can also optimize the support method by analyzing the operator's past interaction history. For example, the support department analyzes the operator's past interaction history and optimizes the support method. The support department can also select the optimal support method by referring to the operator's past interaction history. For example, the support department selects the optimal support method by referring to the operator's past interaction history. This allows the support department to select the optimal support method by referring to the operator's past interaction history. Some or all of the above processing in the support department may be performed using AI, for example, or without using AI. For example, the support department inputs the operator's past interaction history into a generating AI and has the generating AI select the optimal support method. This allows the support department to select the optimal support method by referring to the operator's past interaction history. Some or all of the above-described processes in the support department may be performed using AI, for example, or without AI. For example, the support department can input the operator's past interaction history into a generating AI and have the generating AI select the optimal support method.

[0063] The support department can customize the support provided according to the operator's skill level. For example, the support department can provide detailed support to new operators. For example, the support department can evaluate the operator's skill level and provide detailed support to new operators. The support department can also provide concise support to veteran operators. For example, the support department can evaluate the operator's skill level and provide concise support to veteran operators. The support department can also adjust the support content according to the operator's skill level. For example, the support department can evaluate the operator's skill level and adjust the support content. This allows for appropriate support by customizing the support content according to the operator's skill level. Some or all of the above processes in the support department may be performed using AI, for example, or without AI. For example, the support department can input the operator's skill level into a generating AI and have the generating AI perform the customization of the support content.

[0064] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0065] The reception department can analyze a customer's past inquiry history and select the most appropriate reception method. For example, it can prioritize inquiries that customers have frequently made in the past. It can also provide expert support for specific issues based on the customer's past inquiry history. Furthermore, it can reapply a service that the customer was previously satisfied with. In this way, the optimal reception method can be selected by analyzing the customer's past inquiry history. Some or all of the above processes in the reception department may be performed using AI, or they may not.

[0066] The analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry content during the analysis. For example, it can perform a detailed analysis on high-importance inquiries and a simplified analysis on low-importance inquiries. Furthermore, it can determine the priority of the analysis according to the importance of the inquiry content. By adjusting the level of detail of the analysis based on the importance of the inquiry content, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without using AI.

[0067] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating response scripts. For example, a specialized generation algorithm can be applied to technical inquiries. A standard generation algorithm can also be applied to general inquiries. Furthermore, the optimal generation algorithm can be selected depending on the category of the inquiry. This allows for appropriate responses by applying different generation algorithms depending on the category of the inquiry. Some or all of the above-described processes in the generation unit may be performed using AI, or they may not be performed using AI.

[0068] The delivery unit can select the optimal delivery method by referring to the operator's past operation history when providing a script. For example, it can prioritize selecting a delivery method previously used by the operator. It can also select the optimal delivery method from the operator's past operation history. Furthermore, it can reapply a delivery method that the operator was previously satisfied with. In this way, the optimal delivery method can be selected by referring to the operator's past operation history. Some or all of the above processing in the delivery unit may be performed using AI, or it may be performed without using AI.

[0069] The learning unit can customize the learning content by analyzing the operator's response history during the learning process. For example, it can customize the learning content based on the operator's response history. It can also select the optimal learning content by analyzing the operator's response history. Furthermore, it can adjust the learning content by referring to the operator's response history. In this way, the learning content can be appropriately customized by analyzing the operator's response history. Some or all of the above processes in the learning unit may be performed using AI, or they may not be performed using AI.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The reception desk receives customer inquiries. These inquiries can be in text, audio, or image formats. For example, the reception desk uses speech recognition technology to convert audio inquiries into text and image recognition technology to convert image inquiries into text. Step 2: The analysis unit analyzes the content of the inquiry received by the reception unit. The analysis is performed using natural language processing technology and machine learning algorithms. For example, the analysis unit uses natural language processing technology to analyze the content of the inquiry and machine learning algorithms to analyze the intent of the inquiry. Step 3: The generation unit generates a response script based on the analysis performed by the analysis unit. The response script can be generated in various formats, such as text, audio, or a template. For example, the generation unit can generate an audio response script using speech synthesis technology, or generate a response script based on a pre-prepared template. Step 4: The providing unit provides the operator with the response script generated by the generating unit. The provision can be in various formats, such as text, audio, or video. For example, the providing unit may provide the operator with an audio response script using speech synthesis technology, or a video response script. Step 5: The learning unit learns from the operator's responses. Learning is performed using machine learning algorithms and feedback loops. For example, the learning unit learns by comparing the operator's responses with the generated response scripts.

[0072] (Example of form 2) The call center system according to an embodiment of the present invention is a system that receives customer inquiries and generates response scripts in real time using AI. This call center system receives customer inquiries, the AI ​​analyzes the inquiries, and generates appropriate response scripts. The generated scripts are provided to operators, who use them as a reference to answer customers. After the operator answers, the AI ​​learns from the answers and improves the accuracy of future answers. This mechanism improves the operational efficiency of the call center and enables even new operators to provide service at the level of veterans. For example, customer inquiries are input to the AI ​​as text data. For example, an inquiry such as "How do I return a product?" is input. Next, the AI ​​analyzes the input inquiry. The AI ​​refers to past inquiry data and FAQ databases to generate the optimal response script. For example, specific steps such as "To return a product, please follow these steps" are generated. The generated response script is provided to the operator. The operator uses the provided script as a reference to answer customers. For example, the operator might answer, "To return a product, first prepare proof of purchase, and then fill out a return request form." After the operator answers, the AI ​​learns from the answers. The AI ​​compares the operator's response with the script it generates to evaluate its accuracy and appropriateness. For example, if the operator's response is accurate, the AI ​​learns from that response and improves the accuracy of future responses. This system improves the operational efficiency of call centers. Even new operators can provide service at the same level as veterans, leading to increased customer satisfaction. Furthermore, by having the AI ​​generate response scripts, the burden on operators is reduced, and appropriate responses to customer harassment become possible. As a result, the call center system can efficiently receive, analyze, generate, provide, and learn from customer inquiries.

[0073] The call center system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives inquiries from customers. Customer inquiries include, but are not limited to, text format, audio format, image format, etc. The reception unit directly receives inquiries in text format, for example. The reception unit can also receive inquiries in audio format after converting them to text format using speech recognition technology. For example, the reception unit converts customer audio into text data using speech recognition technology. The reception unit can also receive inquiries in image format after converting them to text format using image recognition technology. For example, the reception unit converts customer image data into text data using image recognition technology. The analysis unit analyzes the inquiries received by the reception unit. The analysis is performed using, but is not limited to, natural language processing technology or machine learning algorithms. For example, the analysis unit analyzes the inquiry using natural language processing technology. The analysis unit can also analyze the inquiry using machine learning algorithms. For example, the analysis unit analyzes the intent of the inquiry using machine learning algorithms. The generation unit generates a response script based on the content analyzed by the analysis unit. The response script is generated in various formats, such as text, audio, or a template, but is not limited to these examples. For example, the generation unit generates a response script in text format. The generation unit can also generate a response script in audio format. For example, the generation unit generates a response script in audio format using speech synthesis technology. The generation unit can also generate a response script using a template. For example, the generation unit generates a response script based on a pre-prepared template. The provision unit provides the response script generated by the generation unit to the operator. Provision is made in various formats, such as text, audio, or video, but is not limited to these examples. For example, the provision unit provides a response script in text format to the operator. The provision unit can also provide a response script in audio format to the operator.For example, the provisioning unit provides operators with voice-format response scripts using speech synthesis technology. The provisioning unit can also provide operators with video-format response scripts. For example, the provisioning unit provides operators with video-format response scripts. The learning unit learns the content of the operators' responses. Learning is performed using, for example, machine learning algorithms or feedback loops, but is not limited to these examples. For example, the learning unit learns the content of the operators' responses using machine learning algorithms. The learning unit can also learn the content of the operators' responses using feedback loops. For example, the learning unit compares the content of the operators' responses with the generated response scripts and learns from them. As a result, the call center system according to this embodiment can efficiently receive, analyze, generate, provide, and learn response scripts from customers.

[0074] The reception desk receives inquiries from customers. These inquiries may include, but are not limited to, text, audio, and image formats. The reception desk can directly receive inquiries in text format. It can also convert audio inquiries into text format using speech recognition technology. For example, the reception desk can convert customer voices into text data using speech recognition technology. The reception desk can also convert image inquiries into text format using image recognition technology. For example, the reception desk can convert customer image data into text data using image recognition technology. The reception desk employs advanced technologies to efficiently process these diverse inquiry formats. For example, the speech recognition technology uses a deep learning-based speech model that can convert customer speech into text with high accuracy. This allows for rapid processing of inquiries made by telephone as text data. Furthermore, the image recognition technology utilizes computer vision technology to extract text information from images sent by customers. For example, if a customer sends a screenshot of a product label or error message, the system can automatically extract the necessary information from the image and provide it to the reception department as text data. This allows the reception department to quickly and accurately receive customer inquiries and smoothly provide the data to the analysis department.

[0075] The analysis unit analyzes the content of inquiries received by the reception unit. Analysis is performed using, for example, natural language processing techniques and machine learning algorithms, but is not limited to these examples. For instance, the analysis unit may use natural language processing techniques to analyze the content of inquiries. The analysis unit can also use machine learning algorithms to analyze the content of inquiries. For example, the analysis unit may use machine learning algorithms to analyze the intent of the inquiries. The analysis unit utilizes these techniques to analyze customer inquiries in detail and generate foundational data for deriving appropriate answers. Specifically, it uses natural language processing techniques to grammatically analyze customer inquiries and extract keywords and important phrases. This clarifies the subject and intent of the inquiries. Furthermore, by comparing the current inquiry with past inquiry data using machine learning algorithms, it identifies similar inquiry patterns and provides reference information for deriving the optimal answer. For example, if a customer inquires about a product defect, the analysis unit can identify common solutions and methods based on similar past inquiry data and provide them to the generation unit. This allows the analysis unit to quickly and accurately analyze customer inquiries and smoothly provide data to the generation unit.

[0076] The generation unit generates a response script based on the content analyzed by the analysis unit. The response script may be generated in various formats, such as text, audio, or templates, but is not limited to these examples. For example, the generation unit can generate a response script in text format. The generation unit can also generate a response script in audio format. For example, the generation unit can generate a response script in audio format using speech synthesis technology. The generation unit can also generate a response script using templates. For example, the generation unit can generate a response script based on a pre-prepared template. The generation unit utilizes these technologies to quickly generate the optimal response script for customer inquiries. Specifically, when generating a response script in text format, natural language generation technology is used to automatically generate an appropriate response to the customer's inquiry. This eliminates the need for operators to manually create responses, enabling faster responses. Furthermore, when generating a response script in audio format, speech synthesis technology can be used to generate natural-sounding speech. This allows for natural-sounding responses even when customers make inquiries by phone. Additionally, when generating a response script using templates, pre-prepared response templates can be customized according to the customer's inquiry. This enables the provision of fast and consistent responses. The generation unit utilizes these technologies to quickly generate optimal response scripts for customer inquiries and smoothly provide the data to the subsequent delivery unit.

[0077] The provisioning unit provides operators with response scripts generated by the generation unit. The provision may be in various formats, such as text, audio, or video. For example, the provisioning unit may provide operators with text-based response scripts. The provisioning unit may also provide operators with audio-based response scripts. For example, the provisioning unit may provide operators with audio-based response scripts using speech synthesis technology. Furthermore, the provisioning unit may also provide operators with video-based response scripts. For example, the provisioning unit may provide operators with video-based response scripts. The provisioning unit utilizes these technologies to quickly provide operators with the most suitable response scripts. Specifically, when providing text-based response scripts, they are displayed on the operator's screen to allow for quick confirmation of the response. When providing audio-based response scripts, the response is provided audibly to the operator's headset, enabling the operator to communicate the response to the customer in a natural voice. When providing video-based response scripts, the video is displayed on the operator's screen, allowing the operator to visually communicate the response to the customer. This enables the provisioning unit to quickly provide operators with the most suitable response scripts, supporting prompt and accurate responses to customers.

[0078] The learning unit learns the operator's responses. Learning is performed using, for example, machine learning algorithms and feedback loops, but is not limited to these examples. For example, the learning unit can learn the operator's responses using machine learning algorithms. The learning unit can also learn the operator's responses using feedback loops. For example, the learning unit learns by comparing the operator's responses with the generated response scripts. The learning unit utilizes these techniques to continuously learn the operator's responses and improve the overall accuracy and efficiency of the system. Specifically, it uses machine learning algorithms to analyze the operator's responses and evaluate the degree of agreement with the generated response scripts. This allows the learning unit to determine how accurate the operator's responses are and improve the response scripts as needed. Furthermore, feedback loops can be used to collect feedback from operators and use it to improve the system. For example, if an operator makes a modification to the response script, the learning unit can record the modification and reflect it in the generation of subsequent response scripts. In this way, the learning unit can continuously learn the operator's responses and improve the overall accuracy and efficiency of the system.

[0079] The analysis unit includes a reference unit that refers to past inquiry data and an FAQ database. For example, the analysis unit refers to past inquiry data. For example, the analysis unit searches for relevant data from the past inquiry database and uses it for analysis. The analysis unit can also refer to an FAQ database. For example, the analysis unit retrieves relevant information from the FAQ database and uses it for analysis. By referring to past inquiry data and an FAQ database, the accuracy of the analysis is improved. Some or all of the above processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can refer to data using an AI model that takes the past inquiry database and FAQ database as input and outputs relevant data.

[0080] The learning unit includes a comparison unit that compares the operator's response with the generated script. The learning unit compares the operator's response with the generated script, for example. For example, the learning unit compares the operator's response with the generated response script using text matching technology. The learning unit can also compare the operator's response with the generated response script using similarity calculation technology. For example, the learning unit calculates the similarity between the operator's response and the generated response script and compares them. This improves the accuracy of learning by comparing the operator's response with the generated script. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can perform the comparison using an AI model that takes the operator's response and the generated response script as input and outputs a similarity score.

[0081] The service department includes a support department to assist in responding to customer harassment. The service department provides support for responding to customer harassment, for example. For example, the service department provides operators with appropriate response methods based on specific definitions and criteria of customer harassment. The service department can also provide support messages to operators depending on the customer harassment situation. For example, the service department provides operators with encouraging messages and advice depending on the customer harassment situation. This reduces the burden on operators by supporting their response to customer harassment. Some or all of the above processes in the support department may be performed using AI, for example, or not using AI. For example, the support department can provide support using an AI model that takes the customer harassment situation as input and outputs appropriate response methods.

[0082] The reception desk can estimate the customer's emotions and prioritize inquiries based on those emotions. For example, if the customer is angry, the reception desk will process the inquiry with the highest priority. For example, if the reception desk estimates the customer's emotions and detects anger, it will process the inquiry with the highest priority. The reception desk can also raise the priority of inquiries if the customer is anxious in order to respond quickly. For example, if the reception desk estimates the customer's emotions and detects anxiety, it will raise the priority of the inquiry. The reception desk can also process inquiries with the normal priority if the customer is relaxed. For example, if the reception desk estimates the customer's emotions and detects relaxation, it will process the inquiry with the normal priority. This allows for quick and appropriate responses by prioritizing inquiries based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes at the reception desk may be performed using AI, for example, or without AI. For example, the reception desk may input customer text data into a generating AI and have the generating AI perform sentiment estimation.

[0083] The reception department can analyze a customer's past inquiry history and select the most appropriate reception method. For example, the reception department can prioritize inquiries that the customer has frequently made in the past. For example, the reception department can analyze a customer's past inquiry history and prioritize inquiries that the customer has made frequently. The reception department can also provide expert solutions to specific problems based on the customer's past inquiry history. For example, the reception department can analyze a customer's past inquiry history and provide expert solutions to specific problems. The reception department can also reapply solutions that the customer has been satisfied with in the past. For example, the reception department can analyze a customer's past inquiry history and reapply solutions that the customer was satisfied with. This allows the reception department to select the most appropriate reception method by analyzing the customer's past inquiry history. Some or all of the above processes in the reception department may be performed using AI, or not. For example, the reception department can input the customer's past inquiry history into a generating AI and have the generating AI select the most appropriate reception method.

[0084] The reception department can filter inquiries based on the customer's current situation and areas of interest when receiving them. For example, the reception department can prioritize receiving inquiries that are relevant to the customer's current situation. For example, the reception department can analyze the customer's current situation and prioritize receiving relevant inquiries. The reception department can also filter relevant inquiries based on the customer's areas of interest. For example, the reception department can analyze the customer's areas of interest and filter relevant inquiries. The reception department can also select the most appropriate response based on the customer's current situation and areas of interest. For example, the reception department can analyze the customer's current situation and areas of interest and select the most appropriate response. This allows for appropriate responses by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the customer's current situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0085] The reception desk can estimate the customer's emotions and adjust the timing of the reception based on the estimated emotions. For example, if the customer is angry, the reception desk can process the customer quickly. For example, if the reception desk estimates the customer's emotions and detects anger, it can process the customer quickly. The reception desk can also adjust the timing of the reception to respond quickly if the customer is feeling anxious. For example, if the reception desk estimates the customer's emotions and detects anxiety, it can adjust the timing of the reception. The reception desk can also respond at the normal time if the customer is relaxed. For example, if the reception desk estimates the customer's emotions and detects relaxation, it can respond at the normal time of the reception. This allows for a quick and appropriate response by adjusting the timing of the reception based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input customer text data into a generative AI and have the AI ​​perform emotion estimation.

[0086] The reception department can prioritize receiving inquiries that are highly relevant by considering the customer's geographical location. For example, if a customer is in a specific region, the reception department will prioritize receiving inquiries related to that region. For example, the reception department will analyze the customer's geographical location and prioritize receiving inquiries related to that region. The reception department can also select the most appropriate response method based on the customer's geographical location. For example, the reception department will analyze the customer's geographical location and select the most appropriate response method. The reception department can also filter relevant inquiries by considering the customer's geographical location. For example, the reception department will analyze the customer's geographical location and filter relevant inquiries. This allows the reception department to prioritize receiving highly relevant inquiries by considering the customer's geographical location. Some or all of the above processing in the reception department may be performed using AI, for example, or without AI. For example, the reception department can input the customer's geographical location into a generating AI and have the generating AI prioritize receiving highly relevant inquiries.

[0087] The reception department can analyze the customer's social media activity when receiving inquiries and accept relevant content. For example, the reception department can prioritize accepting inquiries that are relevant to the customer's social media activity. The reception department can also analyze the customer's social media activity and select the most appropriate response method. The reception department can also filter relevant inquiries based on the customer's social media activity. For example, the reception department can analyze the customer's social media activity and filter relevant inquiries. This allows the reception department to appropriately accept relevant content by analyzing the customer's social media activity. Some or all of the above processing in the reception department may be performed using AI, or not. For example, the reception department can input the customer's social media activity into a generating AI and have the generating AI handle the acceptance of relevant content.

[0088] The analysis unit can estimate the customer's emotions and adjust the expression of the analysis based on the estimated emotions. For example, if the customer is angry, the analysis unit will use a simple and clear expression. For example, if the analysis unit estimates the customer's emotions and detects anger, it will use a simple and clear expression. The analysis unit can also use a reassuring expression if the customer is feeling anxious. For example, if the analysis unit estimates the customer's emotions and detects anxiety, it will use a reassuring expression. The analysis unit can also use a detailed expression if the customer is relaxed. For example, if the analysis unit estimates the customer's emotions and detects relaxation, it will use a detailed expression. This allows for the provision of appropriate analysis results by adjusting the expression of the analysis based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input customer text data into a generating AI and have the generating AI perform emotion estimation.

[0089] The analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry content during the analysis. For example, the analysis unit can perform a detailed analysis on inquiries with high importance. For example, the analysis unit can evaluate the importance of the inquiry content and perform a detailed analysis on those with high importance. The analysis unit can also perform a simplified analysis on inquiries with low importance. For example, the analysis unit can evaluate the importance of the inquiry content and perform a simplified analysis on those with low importance. The analysis unit can also determine the priority of the analysis according to the importance of the inquiry content. For example, the analysis unit can evaluate the importance of the inquiry content and determine the priority. By adjusting the level of detail of the analysis based on the importance of the inquiry content, appropriate analysis results can be provided. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the inquiry content into a generating AI and have the generating AI adjust the level of detail of the analysis.

[0090] The analysis unit can apply different analysis algorithms depending on the category of the inquiry during analysis. For example, the analysis unit can apply a specialized analysis algorithm to technical inquiries. For example, the analysis unit can evaluate the category of the inquiry and apply a specialized analysis algorithm to technical inquiries. The analysis unit can also apply a standard analysis algorithm to general inquiries. For example, the analysis unit can evaluate the category of the inquiry and apply a standard analysis algorithm to general inquiries. The analysis unit can also select the optimal analysis algorithm depending on the category of the inquiry. For example, the analysis unit can evaluate the category of the inquiry and select the optimal analysis algorithm. By applying different analysis algorithms depending on the category of the inquiry, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the inquiry into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0091] The analysis unit can estimate the customer's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the customer is angry, the analysis unit can perform a short, concise analysis. For example, if the analysis unit estimates the customer's emotions and detects anger, it can perform a short, concise analysis. The analysis unit can also perform a detailed analysis if the customer is feeling anxious. For example, if the analysis unit estimates the customer's emotions and detects anxiety, it can perform a detailed analysis. The analysis unit can also perform an analysis of normal length if the customer is relaxed. For example, if the analysis unit estimates the customer's emotions and detects relaxation, it can perform an analysis of normal length. By adjusting the length of the analysis based on the customer's emotions, appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input customer text data into a generating AI and have the generating AI perform emotion estimation.

[0092] The analysis unit can determine the priority of analysis based on when the inquiry content was submitted. For example, the analysis unit may prioritize the analysis of recently submitted inquiries. For example, the analysis unit may evaluate the submission date of the inquiries and prioritize the analysis of recently submitted content. The analysis unit can also analyze older inquiries with normal priority. For example, the analysis unit may evaluate the submission date of the inquiries and analyze older inquiries with normal priority. The analysis unit can also adjust the priority of analysis based on the submission date. For example, the analysis unit may evaluate the submission date of the inquiries and adjust the priority. This enables a quick and appropriate response by determining the priority of analysis based on the submission date of the inquiries. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input the submission date of the inquiries into a generating AI and have the generating AI determine the priority of analysis.

[0093] The analysis unit can adjust the order of analysis based on the relevance of the inquiry content during analysis. For example, the analysis unit may prioritize the analysis of highly relevant inquiry content. For example, the analysis unit may evaluate the relevance of the inquiry content and prioritize the analysis of highly relevant content. The analysis unit can also analyze less relevant inquiry content in the normal order. For example, the analysis unit may evaluate the relevance of the inquiry content and analyze less relevant content in the normal order. The analysis unit can also adjust the order of analysis based on the relevance of the inquiry content. For example, the analysis unit may evaluate the relevance of the inquiry content and adjust the order. By adjusting the order of analysis based on the relevance of the inquiry content, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input the relevance of the inquiry content into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0094] The generation unit can estimate the customer's emotions and adjust the wording of the response script based on the estimated emotions. For example, if the customer is angry, the generation unit will use a simple and clear expression. For example, if the generation unit estimates the customer's emotions and detects anger, it will use a simple and clear expression. The generation unit can also use a reassuring expression if the customer is feeling anxious. For example, if the generation unit estimates the customer's emotions and detects anxiety, it will use a reassuring expression. The generation unit can also use a detailed expression if the customer is relaxed. For example, if the generation unit estimates the customer's emotions and detects relaxation, it will use a detailed expression. This allows for appropriate responses by adjusting the wording of the response script based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer text data into a generation AI and have the generation AI perform sentiment estimation.

[0095] The generation unit can adjust the level of detail of the script based on the importance of the inquiry when generating the response script. For example, the generation unit can generate a detailed script for high-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a detailed script for high-importance inquiries. The generation unit can also generate a simplified script for low-importance inquiries. For example, the generation unit can evaluate the importance of the inquiry and generate a simplified script for low-importance inquiries. The generation unit can also adjust the level of detail of the script according to the importance of the inquiry. For example, the generation unit can evaluate the importance of the inquiry and adjust the level of detail. This allows for an appropriate response by adjusting the level of detail of the script based on the importance of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the importance of the inquiry into the generation AI and have the generation AI adjust the level of detail of the script.

[0096] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating response scripts. For example, the generation unit can apply a specialized generation algorithm to technical inquiries. For example, the generation unit can evaluate the category of the inquiry and apply a specialized generation algorithm to technical inquiries. The generation unit can also apply a standard generation algorithm to general inquiries. For example, the generation unit can evaluate the category of the inquiry and apply a standard generation algorithm to general inquiries. The generation unit can also select the optimal generation algorithm depending on the category of the inquiry. For example, the generation unit can evaluate the category of the inquiry and select the optimal generation algorithm. This makes it possible to provide appropriate responses by applying different generation algorithms depending on the category of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the category of the inquiry into a generation AI and have the generation AI execute the application of the generation algorithm.

[0097] The generation unit can estimate the customer's emotions and adjust the length of the response script based on the estimated emotions. For example, if the customer is angry, the generation unit can generate a short, concise script. For example, if the generation unit estimates the customer's emotions and detects anger, it can generate a short, concise script. The generation unit can also generate a detailed script if the customer is feeling anxious. For example, if the generation unit estimates the customer's emotions and detects anxiety, it can generate a detailed script. The generation unit can also generate a script of normal length if the customer is relaxed. For example, if the generation unit estimates the customer's emotions and detects relaxation, it can generate a script of normal length. This allows for appropriate responses by adjusting the length of the response script based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input customer text data into a generation AI and have the generation AI perform sentiment estimation.

[0098] The generation unit can determine the priority of response scripts based on when the inquiry was submitted. For example, the generation unit can prioritize generating scripts for recently submitted inquiries. For example, the generation unit can evaluate the submission date of the inquiries and prioritize generating scripts for recently submitted inquiries. The generation unit can also generate scripts for older inquiries with normal priority. For example, the generation unit can evaluate the submission date of the inquiries and generate scripts for older inquiries with normal priority. The generation unit can also adjust the script priority based on the submission date. For example, the generation unit can evaluate the submission date of the inquiries and adjust the priority. This allows for a quick and appropriate response by determining the script priority based on the submission date of the inquiries. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the submission date of the inquiries into a generation AI and have the generation AI determine the script priority.

[0099] The generation unit can adjust the order of the scripts based on the relevance of the inquiry content when generating response scripts. For example, the generation unit can prioritize generating scripts for highly relevant inquiries. For example, the generation unit can evaluate the relevance of the inquiry content and prioritize generating scripts for highly relevant content. The generation unit can also generate scripts in the normal order for less relevant inquiries. For example, the generation unit can evaluate the relevance of the inquiry content and generate scripts in the normal order for less relevant content. The generation unit can also adjust the order of the scripts based on the relevance of the inquiry content. For example, the generation unit can evaluate the relevance of the inquiry content and adjust the order. This allows for appropriate responses by adjusting the order of the scripts based on the relevance of the inquiry content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the relevance of the inquiry content into a generation AI and have the generation AI perform the adjustment of the script order.

[0100] The service provider can estimate the customer's emotions and adjust the way the script is delivered based on the estimated emotions. For example, if the customer is angry, the service provider can quickly deliver the script. For example, if the service provider estimates the customer's emotions and detects anger, it can quickly deliver the script. The service provider can also deliver the script in a reassuring way if the customer is feeling anxious. For example, if the service provider estimates the customer's emotions and detects anxiety, it can deliver the script in a reassuring way. The service provider can also deliver the script in a normal way if the customer is relaxed. For example, if the service provider estimates the customer's emotions and detects relaxation, it can deliver the script in a normal way. This allows for appropriate responses by adjusting the way the script is delivered based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input customer text data into a generating AI and have the AI ​​perform sentiment estimation.

[0101] The service provider can select the optimal service method by referring to the operator's past operation history when providing a script. For example, the service provider can prioritize selecting service methods previously used by the operator. For example, the service provider can refer to the operator's past operation history and prioritize selecting service methods previously used. The service provider can also select the optimal service method from the operator's past operation history. For example, the service provider can refer to the operator's past operation history and select the optimal service method. The service provider can also reapply service methods that the operator has previously been satisfied with. For example, the service provider can refer to the operator's past operation history and reapply services that the operator was satisfied with. In this way, the service provider can select the optimal service method by referring to the operator's past operation history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the operator's past operation history into a generating AI and have the generating AI select the optimal service method.

[0102] The service provider can customize the content of the provided script according to the operator's skill level. For example, the service provider can provide a script with detailed explanations to new operators. For example, the service provider can evaluate the operator's skill level and provide a script with detailed explanations to new operators. The service provider can also provide a concise script to veteran operators. For example, the service provider can evaluate the operator's skill level and provide a concise script to veteran operators. The service provider can also adjust the content of the script according to the operator's skill level. For example, the service provider can evaluate the operator's skill level and adjust the content of the script. This allows for appropriate responses by customizing the content of the provided script according to the operator's skill level. Some or all of the above processes in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input the operator's skill level into a generating AI and have the generating AI perform the customization of the provided content.

[0103] The service provider can estimate the customer's emotions and adjust the timing of script delivery based on the estimated emotions. For example, if the customer is angry, the service provider can quickly deliver the script. For example, if the service provider estimates the customer's emotions and detects anger, it can quickly deliver the script. The service provider can also quickly deliver the script if the customer is feeling anxious. For example, if the service provider estimates the customer's emotions and detects anxiety, it can quickly deliver the script. The service provider can also deliver the script at the normal time if the customer is relaxed. For example, if the service provider estimates the customer's emotions and detects relaxation, it can deliver the script at the normal time. This allows for a quick and appropriate response by adjusting the timing of script delivery based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input customer text data into a generating AI and have the AI ​​perform sentiment estimation.

[0104] The service provider can select the optimal service delivery method by considering the operator's geographical location information when providing scripts. For example, if the operator is in a specific region, the service provider can provide a script relevant to that region. For example, the service provider can analyze the operator's geographical location information and provide a script relevant to that region. The service provider can also select the optimal service delivery method based on the operator's geographical location information. For example, the service provider can analyze the operator's geographical location information and select the optimal service delivery method. The service provider can also provide relevant scripts considering the operator's geographical location information. For example, the service provider can analyze the operator's geographical location information and provide relevant scripts. This allows the service provider to select the optimal service delivery method by considering the operator's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the operator's geographical location information into a generating AI and have the generating AI select the optimal service delivery method.

[0105] The service provider can analyze the operator's social media activity and adjust the content of the service when providing scripts. For example, the service provider can provide relevant scripts based on the operator's social media activity. For example, the service provider can analyze the operator's social media activity and provide relevant scripts. The service provider can also analyze the operator's social media activity and select the optimal delivery method. For example, the service provider can analyze the operator's social media activity and select the optimal delivery method. The service provider can also adjust the content of the service based on the operator's social media activity. For example, the service provider can analyze the operator's social media activity and adjust the content of the service. This allows for appropriate adjustment of the content of the service by analyzing the operator's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the operator's social media activity into a generating AI and have the generating AI perform the adjustment of the content of the service.

[0106] The learning unit can estimate customer emotions and select training data based on the estimated customer emotions. For example, if a customer is angry, the learning unit will prioritize selecting training data related to that response. For example, if an angry customer is detected, the learning unit will prioritize selecting training data related to that response. The learning unit can also prioritize selecting training data related to an anxious customer. For example, if an anxious customer is detected, the learning unit will prioritize selecting training data related to that response. The learning unit can also select normal training data if a customer is relaxed. For example, if an anxious customer is detected, the learning unit will select normal training data. This allows for appropriate learning by selecting training data based on customer emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, 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 learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input customer text data into a generating AI and have the generating AI perform emotion estimation.

[0107] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. For example, the learning unit can select the optimal learning algorithm by referring to past learning data. The learning unit can also optimize the learning algorithm by analyzing past learning data. For example, the learning unit can analyze past learning data and optimize the learning algorithm. The learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. For example, the learning unit can improve the accuracy of the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0108] The learning unit can customize the learning content by analyzing the operator's response history during the learning process. For example, the learning unit can customize the learning content based on the operator's response history. For example, the learning unit can analyze the operator's response history and customize the learning content. The learning unit can also analyze the operator's response history and select the optimal learning content. For example, the learning unit can analyze the operator's response history and select the optimal learning content. The learning unit can also refer to the operator's response history and adjust the learning content. For example, the learning unit refers to the operator's response history and adjusts the learning content. This allows for appropriate customization of the learning content by analyzing the operator's response history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the operator's response history into a generating AI and have the generating AI perform the customization of the learning content.

[0109] The learning unit can estimate the customer's emotions and adjust the learning frequency based on the estimated emotions. For example, if the customer is angry, the learning unit can increase the learning frequency. For example, if the learning unit estimates the customer's emotions and detects anger, it can increase the learning frequency. The learning unit can also increase the learning frequency if the customer is feeling anxious. For example, if the learning unit estimates the customer's emotions and detects anxiety, it can increase the learning frequency. The learning unit can also learn at the normal learning frequency if the customer is relaxed. For example, if the learning unit estimates the customer's emotions and detects relaxation, it can learn at the normal learning frequency. This allows for appropriate learning by adjusting the learning frequency based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input customer text data into a generating AI and have the generating AI perform sentiment estimation.

[0110] The learning unit can weight the training data based on the submission date of the inquiry during training. For example, the learning unit can give higher weight to recently submitted inquiries. For example, the learning unit can evaluate the submission date of the inquiry and give higher weight to recently submitted inquiries. The learning unit can also give lower weight to older inquiries. For example, the learning unit can evaluate the submission date of the inquiry and give lower weight to older inquiries. The learning unit can also adjust the weighting of the training data based on the submission date. For example, the learning unit can evaluate the submission date of the inquiry and adjust the weighting. This enables appropriate training by weighting the training data based on the submission date of the inquiry. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the submission date of the inquiry into a generating AI and have the generating AI perform the weighting of the training data.

[0111] The learning unit can adjust the learning content according to the operator's skill level during the learning process. For example, the learning unit can provide basic learning content to new operators. For example, the learning unit can evaluate the operator's skill level and provide basic learning content to new operators. The learning unit can also provide advanced learning content to veteran operators. For example, the learning unit can evaluate the operator's skill level and provide advanced learning content to veteran operators. The learning unit can also adjust the learning content according to the operator's skill level. For example, the learning unit can evaluate the operator's skill level and adjust the learning content. This allows for appropriate learning by adjusting the learning content according to the operator's skill level. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the operator's skill level into a generating AI and have the generating AI perform the adjustment of the learning content.

[0112] The reference unit can estimate the customer's emotions and determine the priority of the data to reference based on the estimated emotions. For example, if the customer is angry, the reference unit will prioritize the reference of relevant data. For example, if the reference unit estimates the customer's emotions and detects anger, it will prioritize the reference of relevant data. The reference unit can also prioritize the reference of reassuring data if the customer is feeling anxious. For example, if the reference unit estimates the customer's emotions and detects anxiety, it will prioritize the reference of reassuring data. The reference unit can also reference data in the normal priority order if the customer is relaxed. For example, if the reference unit estimates the customer's emotions and detects relaxation, it will prioritize the reference of data in the normal priority order. This allows for appropriate data retrieval by determining the priority of the data to reference based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, 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 reference unit may be performed using AI, for example, or without AI. For example, the reference unit can input customer text data into a generating AI and have the generating AI perform sentiment estimation.

[0113] The reference unit can analyze past query data and select the optimal reference method when referencing data. For example, the reference unit can select the optimal reference method based on past query data. For example, the reference unit can analyze past query data and select the optimal reference method. The reference unit can also analyze past query data and optimize the reference method. For example, the reference unit can analyze past query data and optimize the reference method. The reference unit can also refer to past query data and select the optimal reference method. For example, the reference unit can refer to past query data and select the optimal reference method. In this way, the optimal reference method can be selected by analyzing past query data. Some or all of the above processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can input past query data into a generating AI and have the generating AI perform the selection of the optimal reference method.

[0114] The reference unit can estimate the customer's emotions and adjust the display method of the reference data based on the estimated emotions. For example, if the customer is angry, the reference unit uses a simple and clear display method. For example, if the reference unit estimates the customer's emotions and detects anger, it uses a simple and clear display method. The reference unit can also use a reassuring display method if the customer is feeling anxious. For example, if the reference unit estimates the customer's emotions and detects anxiety, it uses a reassuring display method. The reference unit can also use a display method that includes detailed information if the customer is relaxed. For example, if the reference unit estimates the customer's emotions and detects relaxation, it uses a display method that includes detailed information. This allows for appropriate data display by adjusting the display method of the reference data based on the customer's emotions. Emotion estimation is implemented using an emotion estimation function, for example, an emotion engine or generative AI. This allows for appropriate support by adjusting the support content based on the customer's emotions. Emotion estimation is implemented using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the reference unit may be performed using AI, for example, or not using AI. For example, the reference unit may input customer text data into the generative AI and have the generative AI perform sentiment estimation.

[0115] The reference unit can apply different reference algorithms depending on the category of the query content during the reference process. For example, the reference unit can apply a specialized reference algorithm to technical queries. For instance, the reference unit evaluates the category of the query content and applies a specialized reference algorithm to technical content. The reference unit can also apply a standard reference algorithm to general queries. For example, the reference unit evaluates the category of the query content and applies a standard reference algorithm to general content. The reference unit can also select the optimal reference algorithm depending on the category of the query content. For example, the reference unit evaluates the category of the query content and selects the optimal reference algorithm. This enables appropriate data retrieval by applying different reference algorithms depending on the category of the query content. Some or all of the above processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can input the category of the query content into a generating AI and have the generating AI execute the application of the reference algorithm.

[0116] The comparison unit can estimate the customer's emotions and adjust the comparison criteria based on the estimated emotions. For example, if the customer is angry, the comparison unit uses simple and clear criteria. For example, if the comparison unit estimates the customer's emotions and detects anger, it uses simple and clear criteria. The comparison unit can also use reassuring criteria if the customer is feeling anxious. For example, if the comparison unit estimates the customer's emotions and detects anxiety, it uses reassuring criteria. The comparison unit can also use detailed criteria if the customer is relaxed. For example, if the comparison unit estimates the customer's emotions and detects relaxation, it uses detailed criteria. This allows for appropriate comparisons by adjusting the comparison criteria based on the customer's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input customer text data into a generating AI and have the generating AI perform sentiment estimation.

[0117] The comparison unit can select the optimal comparison method by analyzing the operator's response history during the comparison process. For example, the comparison unit can select the optimal comparison method based on the operator's response history. For example, the comparison unit can analyze the operator's response history and select the optimal comparison method. The comparison unit can also optimize the comparison method by analyzing the operator's response history. For example, the comparison unit can analyze the operator's response history and optimize the comparison method. The comparison unit can also select the optimal comparison method by referring to the operator's response history. For example, the comparison unit can refer to the operator's response history and select the optimal comparison method. In this way, the optimal comparison method can be selected by analyzing the operator's response history. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without using AI. For example, the comparison unit can input the operator's response history into a generating AI and have the generating AI select the optimal comparison method.

[0118] The comparison unit can estimate the customer's emotions and adjust the display method of the comparison results based on the estimated emotions. For example, if the customer is angry, the comparison unit uses a simple and clear display method. For example, if the comparison unit estimates the customer's emotions and detects anger, it uses a simple and clear display method. The comparison unit can also use a reassuring display method if the customer is feeling anxious. For example, if the comparison unit estimates the customer's emotions and detects anxiety, it uses a reassuring display method. The comparison unit can also use a display method that includes detailed information if the customer is relaxed. For example, if the comparison unit estimates the customer's emotions and detects relaxation, it uses a display method that includes detailed information. This allows for appropriate display by adjusting the display method of the comparison results based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input customer text data into a generating AI and have the generating AI perform sentiment estimation.

[0119] The comparison unit can apply different comparison algorithms depending on the category of the inquiry during the comparison process. For example, the comparison unit can apply a specialized comparison algorithm to technical inquiries. For instance, the comparison unit evaluates the category of the inquiry and applies a specialized comparison algorithm to technical inquiries. The comparison unit can also apply a standard comparison algorithm to general inquiries. For example, the comparison unit evaluates the category of the inquiry and applies a standard comparison algorithm to general inquiries. The comparison unit can also select the optimal comparison algorithm depending on the category of the inquiry. For example, the comparison unit evaluates the category of the inquiry and selects the optimal comparison algorithm. This enables appropriate comparisons by applying different comparison algorithms depending on the category of the inquiry. Some or all of the above processing in the comparison unit may be performed using AI, for example, or without AI. For example, the comparison unit can input the category of the inquiry into a generating AI and have the generating AI execute the application of the comparison algorithm.

[0120] The support unit can estimate the customer's emotions and adjust the support content based on the estimated emotions. For example, if the customer is angry, the support unit can provide support to respond quickly. For example, if the support unit estimates the customer's emotions and detects anger, it can provide support to respond quickly. The support unit can also provide reassuring support if the customer is feeling anxious. For example, if the support unit estimates the customer's emotions and detects anxiety, it can provide reassuring support. The support unit can also provide normal support if the customer is relaxed. For example, if the support unit estimates the customer's emotions and detects relaxation, it can provide normal support. This allows for appropriate support by adjusting the support content based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support department can input customer text data into a generative AI and have the AI ​​perform emotion estimation.

[0121] The support department can select the optimal support method by referring to the operator's past interaction history when providing support. For example, the support department selects the optimal support method based on the operator's past interaction history. For example, the support department selects the optimal support method by referring to the operator's past interaction history. The support department can also optimize the support method by analyzing the operator's past interaction history. For example, the support department analyzes the operator's past interaction history and optimizes the support method. The support department can also select the optimal support method by referring to the operator's past interaction history. For example, the support department selects the optimal support method by referring to the operator's past interaction history. This allows the support department to select the optimal support method by referring to the operator's past interaction history. Some or all of the above processing in the support department may be performed using AI, for example, or without using AI. For example, the support department inputs the operator's past interaction history into a generating AI and has the generating AI select the optimal support method. This allows the support department to select the optimal support method by referring to the operator's past interaction history. Some or all of the above-described processes in the support department may be performed using AI, for example, or without AI. For example, the support department can input the operator's past interaction history into a generating AI and have the generating AI select the optimal support method.

[0122] The support unit can estimate the customer's emotions and determine the priority of support based on the estimated emotions. For example, if the customer is angry, the support unit will prioritize support. For example, if the support unit estimates the customer's emotions and detects anger, it will prioritize support. The support unit can also prioritize support if the customer is feeling anxious. For example, if the support unit estimates the customer's emotions and detects anxiety, it will prioritize support. The support unit can also provide support at the normal priority if the customer is relaxed. For example, if the support unit estimates the customer's emotions and detects relaxation, it will provide support at the normal priority. This allows for appropriate support by determining the priority of support based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support department can input customer text data into a generative AI and have the AI ​​perform emotion estimation.

[0123] The support department can customize the support provided according to the operator's skill level. For example, the support department can provide detailed support to new operators. For example, the support department can evaluate the operator's skill level and provide detailed support to new operators. The support department can also provide concise support to veteran operators. For example, the support department can evaluate the operator's skill level and provide concise support to veteran operators. The support department can also adjust the support content according to the operator's skill level. For example, the support department can evaluate the operator's skill level and adjust the support content. This allows for appropriate support by customizing the support content according to the operator's skill level. Some or all of the above processes in the support department may be performed using AI, for example, or without AI. For example, the support department can input the operator's skill level into a generating AI and have the generating AI perform the customization of the support content.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The analysis unit can estimate the customer's emotions and determine the priority of analysis based on the estimated emotions. For example, if the customer is angry, the analysis unit will prioritize analyzing that inquiry. If the customer is feeling anxious, the priority can be increased to allow for faster analysis. Furthermore, if the customer is relaxed, the analysis can be performed with the normal priority. This enables a quick and appropriate response by prioritizing analysis based on the customer's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above-described processes in the analysis unit may be performed using AI or not.

[0126] The delivery unit can estimate the customer's emotions and adjust the way the script is delivered based on the estimated emotions. For example, if the customer is angry, the script can be delivered quickly. If the customer is feeling anxious, the script can be delivered in a reassuring way. Furthermore, if the customer is relaxed, the script can be delivered in a normal manner. This allows for appropriate responses by adjusting the way the script is delivered based on the customer's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Some or all of the above processing in the delivery unit may be performed using AI or not.

[0127] The learning unit can estimate the customer's emotions and select training data based on the estimated emotions. For example, if the customer is angry, it can prioritize selecting training data related to that emotion. Similarly, if the customer is anxious, it can prioritize selecting training data related to that emotion. Furthermore, if the customer is relaxed, it can select normal training data. This allows for appropriate learning by selecting training data based on the customer's emotions. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above processing in the learning unit may be performed using AI or not.

[0128] The generation unit can estimate the customer's emotions and adjust the wording of the response script based on the estimated emotions. For example, if the customer is angry, a simple and clear wording can be used. If the customer is feeling anxious, a reassuring wording can be used. Furthermore, if the customer is relaxed, a wording that includes detailed information can be used. By adjusting the wording of the response script based on the customer's emotions, an appropriate response can be provided. Emotion estimation is achieved using an emotion engine or a generation AI. Some or all of the above processing in the generation unit may be performed using AI or not.

[0129] The support unit can estimate the customer's emotions and adjust the support provided based on those emotions. For example, if the customer is angry, it can provide support to address the situation quickly. If the customer is feeling anxious, it can provide support to reassure them. Furthermore, if the customer is relaxed, it can provide standard support. By adjusting the support based on the customer's emotions, appropriate support becomes possible. Emotion estimation is achieved using an emotion engine or generative AI. Some or all of the above-described processes in the support unit may be performed using AI or not.

[0130] The reception department can analyze a customer's past inquiry history and select the most appropriate reception method. For example, it can prioritize inquiries that customers have frequently made in the past. It can also provide expert support for specific issues based on the customer's past inquiry history. Furthermore, it can reapply a service that the customer was previously satisfied with. In this way, the optimal reception method can be selected by analyzing the customer's past inquiry history. Some or all of the above processes in the reception department may be performed using AI, or they may not.

[0131] The analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry content during the analysis. For example, it can perform a detailed analysis on high-importance inquiries and a simplified analysis on low-importance inquiries. Furthermore, it can determine the priority of the analysis according to the importance of the inquiry content. By adjusting the level of detail of the analysis based on the importance of the inquiry content, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without using AI.

[0132] The generation unit can apply different generation algorithms depending on the category of the inquiry when generating response scripts. For example, a specialized generation algorithm can be applied to technical inquiries. A standard generation algorithm can also be applied to general inquiries. Furthermore, the optimal generation algorithm can be selected depending on the category of the inquiry. This allows for appropriate responses by applying different generation algorithms depending on the category of the inquiry. Some or all of the above-described processes in the generation unit may be performed using AI, or they may not be performed using AI.

[0133] The delivery unit can select the optimal delivery method by referring to the operator's past operation history when providing a script. For example, it can prioritize selecting a delivery method previously used by the operator. It can also select the optimal delivery method from the operator's past operation history. Furthermore, it can reapply a delivery method that the operator was previously satisfied with. In this way, the optimal delivery method can be selected by referring to the operator's past operation history. Some or all of the above processing in the delivery unit may be performed using AI, or it may be performed without using AI.

[0134] The learning unit can customize the learning content by analyzing the operator's response history during the learning process. For example, it can customize the learning content based on the operator's response history. It can also select the optimal learning content by analyzing the operator's response history. Furthermore, it can adjust the learning content by referring to the operator's response history. In this way, the learning content can be appropriately customized by analyzing the operator's response history. Some or all of the above processes in the learning unit may be performed using AI, or they may not be performed using AI.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The reception desk receives customer inquiries. These inquiries can be in text, audio, or image formats. For example, the reception desk uses speech recognition technology to convert audio inquiries into text and image recognition technology to convert image inquiries into text. Step 2: The analysis unit analyzes the content of the inquiry received by the reception unit. The analysis is performed using natural language processing technology and machine learning algorithms. For example, the analysis unit uses natural language processing technology to analyze the content of the inquiry and machine learning algorithms to analyze the intent of the inquiry. Step 3: The generation unit generates a response script based on the analysis performed by the analysis unit. The response script can be generated in various formats, such as text, audio, or a template. For example, the generation unit can generate an audio response script using speech synthesis technology, or generate a response script based on a pre-prepared template. Step 4: The providing unit provides the operator with the response script generated by the generating unit. The provision can be in various formats, such as text, audio, or video. For example, the providing unit may provide the operator with an audio response script using speech synthesis technology, or a video response script. Step 5: The learning unit learns from the operator's responses. Learning is performed using machine learning algorithms and feedback loops. For example, the learning unit learns by comparing the operator's responses with the generated response scripts.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the reception device 38 of the smart device 14 and receives inquiries from customers. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received inquiries. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a response script based on the analyzed content. The provision unit is implemented by the output device 40 of the smart device 14 and provides the generated response script to the operator. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the operator's responses. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the smart glasses 214 and receives inquiries from customers. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the received inquiries. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates a response script based on the analyzed content. The provision unit is implemented, for example, by the speaker 240 of the smart glasses 214 and provides the generated response script to the operator. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and learns the operator's responses. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and receives inquiries from customers. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the received inquiries. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates a response script based on the analyzed content. The provision unit is implemented by, for example, the speaker 240 of the headset terminal 314 and provides the generated response script to the operator. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns the operator's responses. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0178] 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).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.).

[0186] 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.

[0187] 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.

[0188] 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.

[0189] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the robot 414 and receives inquiries from customers. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the received inquiries. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates a response script based on the analyzed content. The provision unit is implemented by, for example, the speaker 240 of the robot 414 and provides the generated response script to the operator. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns the operator's responses. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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."

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] (Note 1) The reception department handles customer inquiries, An analysis unit that analyzes the content of inquiries received by the aforementioned reception unit, A generation unit generates a response script based on the content analyzed by the analysis unit, A providing unit that provides the response script generated by the generation unit to the operator, The system includes a learning unit that learns the content of the operator's response. A system characterized by the following features. (Note 2) The aforementioned analysis unit, It includes a reference section that accesses past inquiry data and FAQ databases. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned learning unit, It includes a comparison section that compares the operator's response with the generated script. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, We have a support department to assist in dealing with customer harassment. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is The system estimates customer emotions and prioritizes inquiries based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is Analyze the customer's past inquiry history and select the most suitable contact method. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When receiving an inquiry, filtering is performed based on the customer's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We estimate the customer's emotions and adjust the timing of the reception based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving inquiries, the system prioritizes receiving inquiries that are highly relevant, taking into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving an inquiry, the system analyzes the customer's social media activity and accepts relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, We estimate customer emotions and adjust the way the analysis is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, the level of detail of the analysis is adjusted based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, It estimates customer emotions and adjusts the length of the analysis based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During the analysis, the priority of the analysis will be determined based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the query content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is The system estimates customer emotions and adjusts the wording of the response script based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating response scripts, adjust the level of detail in the script based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating response scripts, different generation algorithms are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is The system estimates customer emotions and adjusts the length of the response script based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating response scripts, the script priority is determined based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is When generating response scripts, the order of the scripts is adjusted based on the relevance of the inquiry content. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, We estimate customer emotions and adjust how the script is delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing scripts, the system selects the optimal delivery method by referring to the operator's past operation history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing scripts, customize the content according to the operator's skill level. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, It estimates customer emotions and adjusts the timing of script delivery based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing scripts, the optimal delivery method will be selected considering the operator's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When providing scripts, we analyze the operator's social media activity and adjust the content accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, The system estimates customer emotions and selects training data based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned learning unit, During training, the training content is customized by analyzing the operator's response history. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned learning unit, It estimates customer emotions and adjusts the learning frequency based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) 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 34) The aforementioned learning unit, During training, the learning content is adjusted according to the operator's skill level. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned reference section is, The system estimates customer emotions and prioritizes the data to reference based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned reference section is, When referencing data, the system analyzes past query data to select the optimal referencing method. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned reference section is, It estimates customer sentiment and adjusts how reference data is displayed based on the estimated customer sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned reference section is, When referencing, different referencing algorithms are applied depending on the category of the query content. The system described in Appendix 2, characterized by the features described herein. (Note 39) The comparison unit is, Estimate customer sentiment and adjust the comparison criteria based on the estimated customer sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 40) The comparison unit is, During the comparison process, the operator's response history is analyzed to select the optimal comparison method. The system described in Appendix 3, characterized by the features described herein. (Note 41) The comparison unit is, It estimates customer sentiment and adjusts how comparison results are displayed based on the estimated customer sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 42) The comparison unit is, When making comparisons, different comparison algorithms are applied depending on the category of the inquiry. The system described in Appendix 3, characterized by the features described herein. (Note 43) The aforementioned support unit, We estimate the customer's emotions and adjust the support provided based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned support unit, When providing support, the operator's past response history is referenced to select the most appropriate support method. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned support unit, Estimate customer emotions and prioritize support based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned support unit, During support, the support content is customized according to the operator's skill level. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0209] 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. The reception department handles customer inquiries, An analysis unit that analyzes the content of inquiries received by the aforementioned reception unit, A generation unit generates a response script based on the content analyzed by the analysis unit, A providing unit that provides the response script generated by the generation unit to the operator, The system includes a learning unit that learns the content of the operator's response. A system characterized by the following features.

2. The aforementioned analysis unit, It includes a reference section that accesses past inquiry data and FAQ databases. The system according to feature 1.

3. The aforementioned learning unit, It includes a comparison section that compares the operator's response with the generated script. The system according to feature 1.

4. The aforementioned supply unit is, We have a support department to assist in dealing with customer harassment. The system according to feature 1.

5. The aforementioned reception unit is The system estimates customer emotions and prioritizes inquiries based on those estimated emotions. The system according to feature 1.

6. The aforementioned reception unit is Analyze the customer's past inquiry history and select the most suitable contact method. The system according to feature 1.

7. The aforementioned reception unit is When receiving an inquiry, filtering is performed based on the customer's current situation and areas of interest. The system according to feature 1.

8. The aforementioned reception unit is We estimate the customer's emotions and adjust the timing of the reception based on those estimated emotions. The system according to feature 1.

Images