System

Abstract

An object of a system according to an embodiment is to quickly propose an appropriate answer in a conversation with a customer.SOLUTION: A system includes a recording part, an analysis part, and a proposal part. The recording unit records a conversation with a customer. The analysis unit analyzes the conversation content recorded by the recording unit. The proposal unit proposes an appropriate answer on the basis of the content analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has made it difficult to provide appropriate responses quickly in conversations with customers, placing a heavy workload on staff.

[0005] The system according to the embodiment aims to quickly suggest appropriate answers in conversations with customers. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, an analysis unit, and a suggestion unit. The recording unit records a conversation with a customer. The analysis unit analyzes the content of the conversation recorded by the recording unit. The suggestion unit suggests an appropriate response based on the content analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly suggest appropriate answers in conversations with customers. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The real-time conversation assistance tool according to the embodiment of the present invention is a system that automatically records conversations with customers, analyzes them using a generation AI, and proposes appropriate responses. This enables the real-time conversation assistance tool to achieve smooth communication with customers and high customer satisfaction.

[0029] A real-time conversation assistance tool according to an embodiment includes a recording unit, an analysis unit, and a suggestion unit. The recording unit records conversations with customers. For example, the recording unit can record telephone conversations. The recording unit can also record face-to-face conversations. The recording unit can also record chat content. For example, the recording unit saves telephone conversations as high-quality audio data. Face-to-face conversations are recorded using a microphone and saved as digital data. Chat content is saved as text data. The analysis unit analyzes the conversation content recorded by the recording unit. For example, the analysis unit converts audio data into text data using speech recognition technology. The analysis unit can also analyze text data using natural language processing technology. The analysis unit can also analyze the intent of a customer's utterance. For example, the analysis unit converts a customer's utterance into text data using speech recognition technology. The analysis unit analyzes the meaning of the text data using natural language processing technology. Context and keywords are extracted to analyze the intent of a customer's utterance. The suggestion unit suggests an appropriate response based on the content analyzed by the analysis unit. For example, the suggestion unit generates an appropriate answer using a generation AI. The suggestion unit can also generate multiple answer candidates and select the optimal answer. The suggestion unit can also suggest answers based on the customer's emotions. For example, the suggestion unit generates a specific answer to a customer's question using a generation AI. Multiple answer candidates are generated, allowing staff to select the optimal answer. Answers are generated based on the customer's emotions, improving customer satisfaction. As a result, the real-time conversation assistance tool according to the embodiment can achieve smooth communication with customers and high customer satisfaction. For example, the staff only need to relay the answer suggested by the generation AI as is, thereby reducing their workload. Customers can obtain quick and accurate information, resulting in high satisfaction. New staff can also become accustomed to their work in a short period of time by responding based on the answers suggested by the generation AI.

[0030] The analysis unit analyzes not only what the customer says, but also background and environmental sounds, allowing for a deeper understanding of the context of the conversation. For example, the analysis unit records the surrounding background and environmental sounds at the same time as the customer says something, and the generation AI analyzes them. For example, if a customer is talking in a cafe, the analysis unit analyzes the sounds of the cafe to determine whether the customer is relaxed. The analysis unit also analyzes the background sounds of the customer's speech to understand the context of the conversation. For example, if a customer is talking in a car, the analysis unit analyzes the sounds of the car to determine that the customer is on the move. The analysis unit also analyzes the environmental sounds of the customer's speech to understand the context of the conversation. For example, if a customer is talking in an office, the analysis unit analyzes the sounds of the office to determine that the customer is at work. This allows for a deeper understanding of the context of the conversation by analyzing not only what the customer says, but also the background and environmental sounds.

[0031] The analysis unit can generate more personalized answers by referencing a customer's past purchase history and inquiry history. For example, the analysis unit references a customer's past purchase history, and the generation AI generates a personalized answer. For example, if a customer asks a question about a product they previously purchased, detailed information about that product is provided. The analysis unit also references the customer's inquiry history, and the generation AI generates a personalized answer. For example, the same response is provided based on the customer's previous inquiry. The analysis unit also combines a customer's past purchase history and inquiry history to generate more personalized answers. For example, if a customer inquires about a product they previously purchased, the analysis unit generates an answer based on detailed information about that product and the content of their previous inquiry. In this way, more personalized answers can be generated by referencing a customer's past purchase history and inquiry history.

[0032] The recording unit can simultaneously analyze the content of chats or emails with customers, enabling multi-channel response. For example, the recording unit analyzes the content of chats with customers in real time, and the generation AI suggests an appropriate response. For example, an answer is provided immediately to a question asked via chat. The recording unit can also analyze the content of emails with customers, and the generation AI suggests an appropriate response. For example, an answer is provided quickly to an inquiry sent via email. The recording unit can also analyze the combined content of chats and emails with customers, enabling multi-channel response. For example, a detailed answer is provided via email to a question asked via chat. In this way, multi-channel response can be achieved by simultaneously analyzing the content of chats and emails with customers.

[0033] The recording unit can translate what customers say in real time, enabling multilingual support. For example, the recording unit translates what customers say in real time, and the generation AI achieves multilingual support. For example, a question asked in English can be answered in Japanese. The recording unit also translates what customers say in real time, smoothing communication with customers who speak different languages. For example, a question asked in Spanish can be answered in English. The recording unit also translates what customers say in real time, enabling support in multiple languages. For example, a question asked in French can be answered in German. This allows for multilingual support by translating what customers say in real time.

[0034] The suggestion unit can automatically generate related questions and collect additional information to gain a deeper understanding of the intention of the customer's utterance. For example, the suggestion unit analyzes the customer's utterance, and the generation AI automatically generates related questions. For example, if a customer says, "Please tell me about returning a product," the suggestion unit generates a follow-up question such as, "Can you tell me the reason for the return?" The suggestion unit also automatically generates related questions and collects additional information to gain a deeper understanding of the intention of the customer's utterance. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit generates a follow-up question such as, "What product do you want to exchange?" The suggestion unit also automatically generates related questions and collects detailed information to gain a deeper understanding of the intention of the customer's utterance. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit generates a follow-up question such as, "Can you tell me more about the product you want repaired?" This makes it possible to automatically generate related questions and collect additional information to gain a deeper understanding of the intention of the customer's utterance.

[0035] The suggestion unit can generate multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, the suggestion unit analyzes customer utterances, and the generation AI generates multiple candidate answers. For example, if a customer says, "Please tell me about returning a product," the suggestion unit generates multiple answers, such as "Return procedures are possible within 30 days of purchase" and "We will provide detailed information on how to return a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit generates multiple answers, such as "Replacement procedures are possible within 30 days of purchase" and "We will provide detailed information on how to exchange a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit generates multiple answers, such as "Repair procedures are possible within 30 days of purchase" and "We will provide detailed information on how to repair a product." In this way, multiple candidate answers to customer utterances are generated, allowing staff to select the optimal answer.

[0036] The suggestion unit can not only respond to customer comments but also suggest related products and services at the same time. For example, the suggestion unit analyzes customer comments and the generation AI simultaneously suggests related products and services. For example, if a customer says, "Please tell me about returning a product," the suggestion unit will provide instructions on the return procedure and suggest an alternative product. The suggestion unit also suggests related products and services along with a response to the customer's comment. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit will provide instructions on the exchange procedure and suggest related products. The suggestion unit also suggests related products and services along with a response to the customer's comment. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit will provide instructions on the repair procedure and suggest related services. This improves customer satisfaction by not only responding to customer comments but also suggesting related products and services at the same time.

[0037] The suggestion unit automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, the suggestion unit automatically records what the customer says, and the generation AI saves information that will be useful for the next inquiry. For example, if a customer says, "Please tell me about returning a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about exchanging a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about repairing a product," that information is recorded and referenced the next time the customer makes an inquiry. In this way, information that will be useful for the next inquiry based on what the customer says is automatically recorded, making future responses smoother.

[0038] The recording unit can summarize what the customer says in real time, allowing staff to understand quickly. For example, the recording unit summarizes what the customer says in real time, and the generation AI provides it to the staff. For example, if a customer gives a long explanation, the main points are summarized briefly and communicated to the staff. The recording unit can also summarize what the customer says in real time, allowing staff to understand quickly. For example, if a customer asks a complex question, the main points are summarized concisely and communicated to the staff. The recording unit can also summarize what the customer says in real time, allowing staff to understand quickly. For example, if a customer gives a detailed explanation, the main points are summarized briefly and communicated to the staff. In this way, the customer's comments can be summarized in real time, allowing staff to understand quickly.

[0039] The suggestion unit can enhance non-verbal communication by having the generation AI suggest appropriate gestures and facial expressions in response to what the customer says. For example, the suggestion unit analyzes the content of what the customer says, and the generation AI suggests appropriate gestures and facial expressions. For example, if a customer expresses gratitude, the suggestion unit suggests that the staff member smile. The suggestion unit also enhances non-verbal communication by having the generation AI suggest appropriate gestures and facial expressions in response to what the customer says. For example, if a customer expresses dissatisfaction, the suggestion unit suggests that the staff member adopt a serious expression. The suggestion unit also enhances non-verbal communication by having the generation AI suggest appropriate gestures and facial expressions in response to what the customer says. For example, if a customer asks a question, the suggestion unit suggests that the staff member nod. In this way, by suggesting appropriate gestures and facial expressions in response to what the customer says, non-verbal communication is enhanced.

[0040] The recording unit allows a generation AI to generate subtitles in real time during video calls with customers, thereby accommodating the hearing impaired. For example, during video calls with customers, the recording unit allows a generation AI to generate subtitles in real time, thereby accommodating the hearing impaired. For example, the recording unit converts what the customer says into text and displays it on a screen. The recording unit also allows a generation AI to generate subtitles in real time during video calls with customers, thereby accommodating the hearing impaired. For example, the recording unit converts what the customer says into text and displays it on a screen. The recording unit also allows a generation AI to generate subtitles in real time during video calls with customers, thereby accommodating the hearing impaired. For example, the recording unit converts what the customer says into text and displays it on a screen. This allows subtitles to be generated in real time during video calls with customers, thereby accommodating the hearing impaired.

[0041] The recording unit translates what the customer says in real time, enabling smoother communication with customers who speak different languages. For example, the recording unit translates what the customer says in real time, allowing the generation AI to smoother communication with customers who speak different languages. For example, a response in Japanese is provided to a question asked in English. The recording unit also translates what the customer says in real time, enabling smoother communication with customers who speak different languages. For example, a response in English is provided to a question asked in Spanish. The recording unit also translates what the customer says in real time, enabling smoother communication with customers who speak different languages. For example, a response in German is provided to a question asked in French. In this way, translating what the customer says in real time enables smoother communication with customers who speak different languages.

[0042] The proposal unit collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. The proposal unit, for example, collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. For example, if a customer gives feedback that the response is slow, a proposal to improve the response speed is made. The proposal unit also collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. For example, if a customer gives feedback that the response is unfriendly, a proposal to improve the quality of the response is made. The proposal unit also collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. For example, if a customer gives feedback that the response is slow, a proposal to improve the response speed is made. In this way, by collecting customer feedback in real time and making improvement proposals on the spot, customer satisfaction is improved.

[0043] The suggestion unit can refer to the customer's past inquiry history and provide a consistent response. The suggestion unit, for example, refers to the customer's past inquiry history, and the generation AI provides a consistent response. For example, the same response is provided based on the content of the customer's previous inquiry. Also, the suggestion unit can refer to the customer's past inquiry history and provide a consistent response. For example, the same response is provided based on the content of the customer's previous inquiry. Also, the suggestion unit can refer to the customer's past inquiry history and provide a consistent response. For example, the same response is provided based on the content of the customer's previous inquiry. In this way, a consistent response is provided by referring to the customer's past inquiry history.

[0044] The suggestion unit can automatically suggest related FAQs and support articles based on what the customer says. For example, the suggestion unit analyzes what the customer says, and the generation AI automatically suggests related FAQs and support articles. For example, if the customer says, "Please tell me about returning a product," the suggestion unit will suggest an FAQ about returns. The suggestion unit also automatically suggests related FAQs and support articles based on what the customer says. For example, if the customer says, "Please tell me about exchanging a product," the suggestion unit will suggest an FAQ about exchanges. The suggestion unit also automatically suggests related FAQs and support articles based on what the customer says. For example, if the customer says, "Please tell me about repairing a product," the suggestion unit will suggest an FAQ about repairs. In this way, customer satisfaction is improved by automatically suggesting related FAQs and support articles based on what the customer says.

[0045] The suggestion unit automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, the suggestion unit automatically records what the customer says, and the generation AI saves information that will be useful for the next inquiry. For example, if a customer says, "Please tell me about returning a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about exchanging a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about repairing a product," that information is recorded and referenced the next time the customer makes an inquiry. In this way, information that will be useful for the next inquiry based on what the customer says is automatically recorded, making future responses smoother.

[0046] The analysis unit analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. The analysis unit, for example, analyzes the staff work logs, and the generation AI makes suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI makes suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI makes suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. In this way, by analyzing the staff work logs and making suggestions for improving work efficiency, work efficiency is achieved.

[0047] The analysis unit can optimize staff schedules and distribute work loads evenly. The analysis unit, for example, analyzes staff schedules, and the generation AI proposes methods to distribute work loads evenly. For example, if work is concentrated on a specific staff member, the generation AI will distribute that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes methods to distribute work loads evenly. For example, if work is concentrated on a specific staff member, the generation AI will distribute that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes methods to distribute work loads evenly. For example, if work is concentrated on a specific staff member, the generation AI will distribute that work to other staff members. In this way, staff schedules are optimized and work loads are distributed evenly, thereby achieving work efficiency.

[0048] The analysis unit allows the generation AI to propose tools to automate staff work and support the implementation of those tools. The analysis unit, for example, analyzes the work content of staff, and the generation AI proposes automation tools. For example, it proposes a tool to automate data entry work. The analysis unit also analyzes the work content of staff, and the generation AI proposes automation tools. For example, it proposes a tool to automate data entry work. The analysis unit also analyzes the work content of staff, and the generation AI proposes automation tools. For example, it proposes a tool to automate data entry work. In this way, by proposing tools to automate staff work and supporting the implementation, it is possible to achieve work efficiency.

[0049] The analysis unit can analyze the work content of staff in real time and automatically generate a training program for improving efficiency. The analysis unit, for example, analyzes the work content of staff in real time, and the generation AI automatically generates a training program for improving efficiency. For example, if a particular task is taking a long time, it suggests training to improve the efficiency of that task. The analysis unit also analyzes the work content of staff in real time, and the generation AI automatically generates a training program for improving efficiency. For example, if a particular task is taking a long time, it suggests training to improve the efficiency of that task. The analysis unit also analyzes the work content of staff in real time, and the generation AI automatically generates a training program for improving efficiency. For example, if a particular task is taking a long time, it suggests training to improve the efficiency of that task. In this way, by analyzing the work content of staff in real time and automatically generating a training program for improving efficiency, work efficiency is improved.

[0050] The analysis unit can monitor staff members' learning progress in real time and provide individually optimized training programs. For example, the generative AI in the analysis unit monitors staff members' learning progress in real time and provides individually optimized training programs. For example, if a particular skill is lacking, it suggests training to strengthen that skill. The analysis unit can also monitor staff members' learning progress in real time and provide individually optimized training programs. For example, if a particular skill is lacking, it suggests training to strengthen that skill. The analysis unit can also monitor staff members' learning progress in real time and provide individually optimized training programs. For example, if a particular skill is lacking, it suggests training to strengthen that skill. In this way, by monitoring staff members' learning progress in real time and providing individually optimized training programs, it becomes possible for them to debut with short training periods.

[0051] The analysis unit can analyze the staff's past experience and skills and suggest the most appropriate training content. For example, the generation AI in the analysis unit analyzes the staff's past experience and skills and suggests the most appropriate training content. For example, if there is a lack of specific experience, it suggests training to make up for that experience. The analysis unit can also analyze the staff's past experience and skills and suggest the most appropriate training content. For example, if there is a lack of specific experience, it suggests training to make up for that experience. The analysis unit can also analyze the staff's past experience and skills and suggest the most appropriate training content. For example, if there is a lack of specific experience, it suggests training to make up for that experience. In this way, by analyzing the staff's past experience and skills and suggesting the most appropriate training content, it becomes possible for them to make their debut with a short training period.

[0052] The analysis unit can automatically record the training content of staff members and reflect it in future training programs. For example, the generative AI in the analysis unit automatically records the training content of staff members and reflects it in future training programs. For example, if a specific training content is effective, it will reflect that content in the next training. The analysis unit also automatically records the training content of staff members and reflects it in future training programs. For example, if a specific training content is effective, it will reflect that content in the next training. The analysis unit also automatically records the training content of staff members and reflects it in future training programs. For example, if a specific training content is effective, it will reflect that content in the next training. In this way, by automatically recording the training content of staff members and reflecting it in future training programs, it becomes possible for them to debut with a short training period.

[0053] The analysis unit can share the training progress of staff members with other staff members, thereby improving the skills of the entire team. For example, the generation AI shares the training progress of staff members in real time, thereby improving the skills of the entire team. For example, the skills acquired by a specific staff member are shared with other staff members. The analysis unit also shares the training progress of staff members with other staff members, thereby improving the skills of the entire team. For example, the skills acquired by a specific staff member are shared with other staff members. The analysis unit also shares the training progress of staff members with other staff members, thereby improving the skills of the entire team. For example, the skills acquired by a specific staff member are shared with other staff members. In this way, the training progress of staff members can be shared with other staff members, thereby improving the skills of the entire team, making it possible for them to debut with a short training period.

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

[0055] The suggestion unit can not only respond to the customer's comments but also suggest related products and services at the same time. For example, if a customer says, "Please tell me about returning a product," the suggestion unit will provide instructions on the return procedure and suggest an alternative product. The suggestion unit can also respond to the customer's comments and suggest related products and services. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit will provide instructions on the exchange procedure and suggest a related product. The suggestion unit can also respond to the customer's comments and suggest related products and services. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit will provide instructions on the repair procedure and suggest a related service. This not only responds to the customer's comments but also suggests related products and services at the same time, thereby improving customer satisfaction.

[0056] The analysis unit analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. In this way, by analyzing the staff work logs and making suggestions for improving work efficiency, work efficiency is achieved.

[0057] The suggestion unit can generate multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, the generation AI analyzes customer utterances and generates multiple candidate answers. For example, if a customer says, "Please tell me about returning a product," the AI ​​generates multiple answers, such as "Return procedures are possible within 30 days of purchase" and "We will provide detailed information on how to return a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about exchanging a product," the AI ​​generates multiple answers, such as "Replacement procedures are possible within 30 days of purchase" and "We will provide detailed information on how to exchange a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about repairing a product," the AI ​​generates multiple answers, such as "Repair procedures are possible within 30 days of purchase" and "We will provide detailed information on how to repair a product." In this way, multiple candidate answers to customer utterances are generated, allowing staff to select the optimal answer.

[0058] The analysis unit can optimize staff schedules and distribute work loads evenly. For example, it analyzes staff schedules, and the generation AI proposes ways to distribute work loads evenly. For example, if work is concentrated on a specific staff member, it distributes that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes ways to distribute work loads evenly. For example, if work is concentrated on a specific staff member, it distributes that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes ways to distribute work loads evenly. For example, if work is concentrated on a specific staff member, it distributes that work to other staff members. In this way, staff schedules are optimized and work loads are distributed evenly, thereby achieving work efficiency.

[0059] The suggestion unit can automatically suggest related FAQs and support articles based on customer utterances. For example, the generation AI analyzes customer utterances and automatically suggests related FAQs and support articles. For example, if a customer says, "Please tell me about returning a product," the suggestion unit will suggest FAQs related to returns. The suggestion unit also automatically suggests related FAQs and support articles based on customer utterances. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit will suggest FAQs related to exchanges. The suggestion unit also automatically suggests related FAQs and support articles based on customer utterances. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit will suggest FAQs related to repairs. This improves customer satisfaction by automatically suggesting related FAQs and support articles based on customer utterances.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The recording unit records conversations with customers. For example, the recording unit can record telephone conversations, face-to-face conversations, and chat content. Telephone conversations are saved as high-quality audio data, and face-to-face conversations are saved as digital data using a microphone. Chat content is saved as text data. Step 2: The analysis unit analyzes the conversation recorded by the recording unit. For example, the analysis unit converts the voice data into text data using voice recognition technology, and then analyzes the text data using natural language processing technology. It also extracts context and keywords to analyze the intent of the customer's remarks. Step 3: The suggestion unit proposes an appropriate answer based on the content analyzed by the analysis unit. For example, the suggestion unit uses a generation AI to generate an appropriate answer, generating multiple answer candidates and selecting the most appropriate one. It can also propose answers based on the customer's emotions.

[0062] (Example 2) The real-time conversation assistance tool according to the embodiment of the present invention is a system that automatically records conversations with customers, analyzes them using a generation AI, and proposes appropriate responses. This enables the real-time conversation assistance tool to achieve smooth communication with customers and high customer satisfaction.

[0063] A real-time conversation assistance tool according to an embodiment includes a recording unit, an analysis unit, and a suggestion unit. The recording unit records conversations with customers. For example, the recording unit can record telephone conversations. The recording unit can also record face-to-face conversations. The recording unit can also record chat content. For example, the recording unit saves telephone conversations as high-quality audio data. Face-to-face conversations are recorded using a microphone and saved as digital data. Chat content is saved as text data. The analysis unit analyzes the conversation content recorded by the recording unit. For example, the analysis unit converts audio data into text data using speech recognition technology. The analysis unit can also analyze text data using natural language processing technology. The analysis unit can also analyze the intent of a customer's utterance. For example, the analysis unit converts a customer's utterance into text data using speech recognition technology. The analysis unit analyzes the meaning of the text data using natural language processing technology. Context and keywords are extracted to analyze the intent of a customer's utterance. The suggestion unit suggests an appropriate response based on the content analyzed by the analysis unit. For example, the suggestion unit generates an appropriate answer using a generation AI. The suggestion unit can also generate multiple answer candidates and select the optimal answer. The suggestion unit can also suggest answers based on the customer's emotions. For example, the suggestion unit generates a specific answer to a customer's question using a generation AI. Multiple answer candidates are generated, allowing staff to select the optimal answer. Answers are generated based on the customer's emotions, improving customer satisfaction. As a result, the real-time conversation assistance tool according to the embodiment can achieve smooth communication with customers and high customer satisfaction. For example, the staff only need to relay the answer suggested by the generation AI as is, thereby reducing their workload. Customers can obtain quick and accurate information, resulting in high satisfaction. New staff can also become accustomed to their work in a short period of time by responding based on the answers suggested by the generation AI.

[0064] The analysis unit analyzes not only what the customer says, but also background and environmental sounds, allowing for a deeper understanding of the context of the conversation. For example, the analysis unit records the surrounding background and environmental sounds at the same time as the customer says something, and the generation AI analyzes them. For example, if a customer is talking in a cafe, the analysis unit analyzes the sounds of the cafe to determine whether the customer is relaxed. The analysis unit also analyzes the background sounds of the customer's speech to understand the context of the conversation. For example, if a customer is talking in a car, the analysis unit analyzes the sounds of the car to determine that the customer is on the move. The analysis unit also analyzes the environmental sounds of the customer's speech to understand the context of the conversation. For example, if a customer is talking in an office, the analysis unit analyzes the sounds of the office to determine that the customer is at work. This allows for a deeper understanding of the context of the conversation by analyzing not only what the customer says, but also the background and environmental sounds.

[0065] The analysis unit can generate more personalized answers by referencing a customer's past purchase history and inquiry history. For example, the analysis unit references a customer's past purchase history, and the generation AI generates a personalized answer. For example, if a customer asks a question about a product they previously purchased, detailed information about that product is provided. The analysis unit also references the customer's inquiry history, and the generation AI generates a personalized answer. For example, the same response is provided based on the customer's previous inquiry. The analysis unit also combines a customer's past purchase history and inquiry history to generate more personalized answers. For example, if a customer inquires about a product they previously purchased, the analysis unit generates an answer based on detailed information about that product and the content of their previous inquiry. In this way, more personalized answers can be generated by referencing a customer's past purchase history and inquiry history.

[0066] The analysis unit can use the emotion estimation function to analyze the emotional state of the customer and suggest a response that corresponds to that emotion. The analysis unit, for example, analyzes the customer's utterances and uses the emotion estimation function to identify the customer's emotional state. For example, if the customer is angry, it suggests a calm response that corresponds to that emotion. The analysis unit can also analyze the customer's facial expressions and use the emotion estimation function to identify the customer's emotional state. For example, if the customer is smiling when speaking, it suggests a friendly response that corresponds to that emotion. The analysis unit can also analyze the customer's voice and use the emotion estimation function to identify the customer's emotional state. For example, if the customer is nervous, it suggests a reassuring response that corresponds to that emotion. In this way, customer satisfaction can be improved by analyzing the customer's emotional state and suggesting a response that corresponds to that emotion.

[0067] The recording unit can simultaneously analyze the content of chats or emails with customers, enabling multi-channel response. For example, the recording unit analyzes the content of chats with customers in real time, and the generation AI suggests an appropriate response. For example, an answer is provided immediately to a question asked via chat. The recording unit can also analyze the content of emails with customers, and the generation AI suggests an appropriate response. For example, an answer is provided quickly to an inquiry sent via email. The recording unit can also analyze the combined content of chats and emails with customers, enabling multi-channel response. For example, a detailed answer is provided via email to a question asked via chat. In this way, multi-channel response can be achieved by simultaneously analyzing the content of chats and emails with customers.

[0068] The recording unit can translate what customers say in real time, enabling multilingual support. For example, the recording unit translates what customers say in real time, and the generation AI achieves multilingual support. For example, a question asked in English can be answered in Japanese. The recording unit also translates what customers say in real time, smoothing communication with customers who speak different languages. For example, a question asked in Spanish can be answered in English. The recording unit also translates what customers say in real time, enabling support in multiple languages. For example, a question asked in French can be answered in German. This allows for multilingual support by translating what customers say in real time.

[0069] The analysis unit can use the emotion estimation function to suggest music and videos that correspond to the customer's emotions, thereby providing a relaxing environment. The analysis unit, for example, analyzes the customer's emotional state and uses the emotion estimation function to suggest relaxing music. For example, if the customer is feeling stressed, relaxing music is played. The analysis unit also analyzes the customer's emotional state and uses the emotion estimation function to suggest relaxing videos. For example, if the customer is tired, relaxing nature videos are played. The analysis unit also analyzes the customer's emotional state and uses the emotion estimation function to suggest a combination of relaxing music and videos. For example, if the customer is tense, relaxing music and videos are played simultaneously. In this way, a relaxing environment can be provided by suggesting music and videos that correspond to the customer's emotions.

[0070] The suggestion unit can automatically generate related questions and collect additional information to gain a deeper understanding of the intention of the customer's utterance. For example, the suggestion unit analyzes the customer's utterance, and the generation AI automatically generates related questions. For example, if a customer says, "Please tell me about returning a product," the suggestion unit generates a follow-up question such as, "Can you tell me the reason for the return?" The suggestion unit also automatically generates related questions and collects additional information to gain a deeper understanding of the intention of the customer's utterance. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit generates a follow-up question such as, "What product do you want to exchange?" The suggestion unit also automatically generates related questions and collects detailed information to gain a deeper understanding of the intention of the customer's utterance. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit generates a follow-up question such as, "Can you tell me more about the product you want repaired?" This makes it possible to automatically generate related questions and collect additional information to gain a deeper understanding of the intention of the customer's utterance.

[0071] The suggestion unit can generate multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, the suggestion unit analyzes customer utterances, and the generation AI generates multiple candidate answers. For example, if a customer says, "Please tell me about returning a product," the suggestion unit generates multiple answers, such as "Return procedures are possible within 30 days of purchase" and "We will provide detailed information on how to return a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit generates multiple answers, such as "Replacement procedures are possible within 30 days of purchase" and "We will provide detailed information on how to exchange a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit generates multiple answers, such as "Repair procedures are possible within 30 days of purchase" and "We will provide detailed information on how to repair a product." In this way, multiple candidate answers to customer utterances are generated, allowing staff to select the optimal answer.

[0072] The suggestion unit can use the emotion estimation function to suggest answers with adjusted tone and expression according to the customer's emotions. The suggestion unit, for example, analyzes the customer's emotional state and suggests answers with adjusted tone and expression using the emotion estimation function. For example, if the customer is angry, it suggests an answer with a calm and polite tone. The suggestion unit also analyzes the customer's emotional state and suggests answers with adjusted tone and expression using the emotion estimation function. For example, if the customer is sad, it suggests an answer with a gentle tone. The suggestion unit also analyzes the customer's emotional state and suggests answers with adjusted tone and expression using the emotion estimation function. For example, if the customer is happy, it suggests an answer with a bright tone. In this way, by suggesting answers with adjusted tone and expression according to the customer's emotions, customer satisfaction is improved.

[0073] The suggestion unit can not only respond to customer comments but also suggest related products and services at the same time. For example, the suggestion unit analyzes customer comments and the generation AI simultaneously suggests related products and services. For example, if a customer says, "Please tell me about returning a product," the suggestion unit will provide instructions on the return procedure and suggest an alternative product. The suggestion unit also suggests related products and services along with a response to the customer's comment. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit will provide instructions on the exchange procedure and suggest related products. The suggestion unit also suggests related products and services along with a response to the customer's comment. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit will provide instructions on the repair procedure and suggest related services. This improves customer satisfaction by not only responding to customer comments but also suggesting related products and services at the same time.

[0074] The suggestion unit automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, the suggestion unit automatically records what the customer says, and the generation AI saves information that will be useful for the next inquiry. For example, if a customer says, "Please tell me about returning a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about exchanging a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about repairing a product," that information is recorded and referenced the next time the customer makes an inquiry. In this way, information that will be useful for the next inquiry based on what the customer says is automatically recorded, making future responses smoother.

[0075] The suggestion unit can improve customer satisfaction by automatically generating a follow-up message according to the customer's emotions using the emotion estimation function. The suggestion unit, for example, analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is angry, it sends a calm and polite follow-up message. The suggestion unit also analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is sad, it sends a kind follow-up message. The suggestion unit also analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is happy, it sends a cheerful follow-up message. In this way, customer satisfaction is improved by automatically generating a follow-up message according to the customer's emotions.

[0076] The recording unit can summarize what the customer says in real time, allowing staff to understand quickly. For example, the recording unit summarizes what the customer says in real time, and the generation AI provides it to the staff. For example, if a customer gives a long explanation, the main points are summarized briefly and communicated to the staff. The recording unit can also summarize what the customer says in real time, allowing staff to understand quickly. For example, if a customer asks a complex question, the main points are summarized concisely and communicated to the staff. The recording unit can also summarize what the customer says in real time, allowing staff to understand quickly. For example, if a customer gives a detailed explanation, the main points are summarized briefly and communicated to the staff. In this way, the customer's comments can be summarized in real time, allowing staff to understand quickly.

[0077] The suggestion unit can enhance non-verbal communication by having the generation AI suggest appropriate gestures and facial expressions in response to what the customer says. For example, the suggestion unit analyzes the content of what the customer says, and the generation AI suggests appropriate gestures and facial expressions. For example, if a customer expresses gratitude, the suggestion unit suggests that the staff member smile. The suggestion unit also enhances non-verbal communication by having the generation AI suggest appropriate gestures and facial expressions in response to what the customer says. For example, if a customer expresses dissatisfaction, the suggestion unit suggests that the staff member adopt a serious expression. The suggestion unit also enhances non-verbal communication by having the generation AI suggest appropriate gestures and facial expressions in response to what the customer says. For example, if a customer asks a question, the suggestion unit suggests that the staff member nod. In this way, by suggesting appropriate gestures and facial expressions in response to what the customer says, non-verbal communication is enhanced.

[0078] The suggestion unit can use the emotion estimation function to suggest a communication style that corresponds to the customer's emotions. The suggestion unit, for example, analyzes the customer's emotional state and suggests an appropriate communication style using the emotion estimation function. For example, if the customer is angry, it suggests a calm and polite communication style. The suggestion unit also analyzes the customer's emotional state and suggests an appropriate communication style using the emotion estimation function. For example, if the customer is sad, it suggests a gentle communication style. The suggestion unit also analyzes the customer's emotional state and suggests an appropriate communication style using the emotion estimation function. For example, if the customer is happy, it suggests a cheerful communication style. In this way, customer satisfaction is improved by suggesting a communication style that corresponds to the customer's emotions.

[0079] The recording unit allows a generation AI to generate subtitles in real time during video calls with customers, thereby accommodating the hearing impaired. For example, during video calls with customers, the recording unit allows a generation AI to generate subtitles in real time, thereby accommodating the hearing impaired. For example, the recording unit converts what the customer says into text and displays it on a screen. The recording unit also allows a generation AI to generate subtitles in real time during video calls with customers, thereby accommodating the hearing impaired. For example, the recording unit converts what the customer says into text and displays it on a screen. The recording unit also allows a generation AI to generate subtitles in real time during video calls with customers, thereby accommodating the hearing impaired. For example, the recording unit converts what the customer says into text and displays it on a screen. This allows subtitles to be generated in real time during video calls with customers, thereby accommodating the hearing impaired.

[0080] The recording unit translates what the customer says in real time, enabling smoother communication with customers who speak different languages. For example, the recording unit translates what the customer says in real time, allowing the generation AI to smoother communication with customers who speak different languages. For example, a response in Japanese is provided to a question asked in English. The recording unit also translates what the customer says in real time, enabling smoother communication with customers who speak different languages. For example, a response in English is provided to a question asked in Spanish. The recording unit also translates what the customer says in real time, enabling smoother communication with customers who speak different languages. For example, a response in German is provided to a question asked in French. In this way, translating what the customer says in real time enables smoother communication with customers who speak different languages.

[0081] The suggestion unit can provide a relaxing environment by automatically changing a background image or theme according to the customer's emotions using the emotion estimation function. The suggestion unit, for example, analyzes the customer's emotional state and automatically changes a relaxing background image using the emotion estimation function. For example, if the customer is feeling stressed, a relaxing landscape image is displayed. The suggestion unit also analyzes the customer's emotional state and automatically changes a relaxing background image using the emotion estimation function. For example, if the customer is tired, a relaxing natural landscape image is displayed. The suggestion unit also analyzes the customer's emotional state and automatically changes a relaxing background image using the emotion estimation function. For example, if the customer is tense, a relaxing landscape image is displayed. In this way, a relaxing environment is provided by automatically changing a background image or theme according to the customer's emotions.

[0082] The proposal unit collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. The proposal unit, for example, collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. For example, if a customer gives feedback that the response is slow, a proposal to improve the response speed is made. The proposal unit also collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. For example, if a customer gives feedback that the response is unfriendly, a proposal to improve the quality of the response is made. The proposal unit also collects customer feedback in real time, allowing the generation AI to make improvement proposals on the spot. For example, if a customer gives feedback that the response is slow, a proposal to improve the response speed is made. In this way, by collecting customer feedback in real time and making improvement proposals on the spot, customer satisfaction is improved.

[0083] The suggestion unit can refer to the customer's past inquiry history and provide a consistent response. The suggestion unit, for example, refers to the customer's past inquiry history, and the generation AI provides a consistent response. For example, the same response is provided based on the content of the customer's previous inquiry. Also, the suggestion unit can refer to the customer's past inquiry history and provide a consistent response. For example, the same response is provided based on the content of the customer's previous inquiry. Also, the suggestion unit can refer to the customer's past inquiry history and provide a consistent response. For example, the same response is provided based on the content of the customer's previous inquiry. In this way, a consistent response is provided by referring to the customer's past inquiry history.

[0084] The suggestion unit can use the emotion estimation function to suggest benefits and services according to the customer's emotions. The suggestion unit, for example, analyzes the customer's emotional state and suggests benefits and services using the emotion estimation function. For example, if the customer is angry, it suggests a special discount or service. The suggestion unit also analyzes the customer's emotional state and suggests benefits and services using the emotion estimation function. For example, if the customer is sad, it suggests a special discount or service. The suggestion unit also analyzes the customer's emotional state and suggests benefits and services using the emotion estimation function. For example, if the customer is happy, it suggests a special discount or service. In this way, customer satisfaction is improved by suggesting benefits and services according to the customer's emotions.

[0085] The suggestion unit can automatically suggest related FAQs and support articles based on what the customer says. For example, the suggestion unit analyzes what the customer says, and the generation AI automatically suggests related FAQs and support articles. For example, if the customer says, "Please tell me about returning a product," the suggestion unit will suggest an FAQ about returns. The suggestion unit also automatically suggests related FAQs and support articles based on what the customer says. For example, if the customer says, "Please tell me about exchanging a product," the suggestion unit will suggest an FAQ about exchanges. The suggestion unit also automatically suggests related FAQs and support articles based on what the customer says. For example, if the customer says, "Please tell me about repairing a product," the suggestion unit will suggest an FAQ about repairs. In this way, customer satisfaction is improved by automatically suggesting related FAQs and support articles based on what the customer says.

[0086] The suggestion unit automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, the suggestion unit automatically records what the customer says, and the generation AI saves information that will be useful for the next inquiry. For example, if a customer says, "Please tell me about returning a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about exchanging a product," that information is recorded and referenced the next time the customer makes an inquiry. The suggestion unit also automatically records information that will be useful for the next inquiry based on what the customer says, making future responses smoother. For example, if a customer says, "Please tell me about repairing a product," that information is recorded and referenced the next time the customer makes an inquiry. In this way, information that will be useful for the next inquiry based on what the customer says is automatically recorded, making future responses smoother.

[0087] The suggestion unit can improve customer satisfaction by automatically generating a follow-up message according to the customer's emotions using the emotion estimation function. The suggestion unit, for example, analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is angry, it sends a calm and polite follow-up message. The suggestion unit also analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is sad, it sends a kind follow-up message. The suggestion unit also analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is happy, it sends a cheerful follow-up message. In this way, customer satisfaction is improved by automatically generating a follow-up message according to the customer's emotions.

[0088] The analysis unit analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. The analysis unit, for example, analyzes the staff work logs, and the generation AI makes suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI makes suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI makes suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. In this way, by analyzing the staff work logs and making suggestions for improving work efficiency, work efficiency is achieved.

[0089] The analysis unit can optimize staff schedules and distribute work loads evenly. The analysis unit, for example, analyzes staff schedules, and the generation AI proposes methods to distribute work loads evenly. For example, if work is concentrated on a specific staff member, the generation AI will distribute that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes methods to distribute work loads evenly. For example, if work is concentrated on a specific staff member, the generation AI will distribute that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes methods to distribute work loads evenly. For example, if work is concentrated on a specific staff member, the generation AI will distribute that work to other staff members. In this way, staff schedules are optimized and work loads are distributed evenly, thereby achieving work efficiency.

[0090] The analysis unit can monitor the stress levels of staff members using the emotion estimation function and suggest appropriate break times. The analysis unit, for example, analyzes the emotional state of staff members and monitors their stress levels using the emotion estimation function. For example, if staff members are feeling stressed, it suggests appropriate break times. The analysis unit also analyzes the emotional state of staff members and monitors their stress levels using the emotion estimation function. For example, if staff members are feeling stressed, it suggests appropriate break times. The analysis unit also analyzes the emotional state of staff members and monitors their stress levels using the emotion estimation function. For example, if staff members are feeling stressed, it suggests appropriate break times. In this way, by monitoring the stress levels of staff members and suggesting appropriate break times, work efficiency is improved.

[0091] The analysis unit allows the generation AI to propose tools to automate staff work and support the implementation of those tools. The analysis unit, for example, analyzes the work content of staff, and the generation AI proposes automation tools. For example, it proposes a tool to automate data entry work. The analysis unit also analyzes the work content of staff, and the generation AI proposes automation tools. For example, it proposes a tool to automate data entry work. The analysis unit also analyzes the work content of staff, and the generation AI proposes automation tools. For example, it proposes a tool to automate data entry work. In this way, by proposing tools to automate staff work and supporting the implementation, it is possible to achieve work efficiency.

[0092] The analysis unit can analyze the work content of staff in real time and automatically generate a training program for improving efficiency. The analysis unit, for example, analyzes the work content of staff in real time, and the generation AI automatically generates a training program for improving efficiency. For example, if a particular task is taking a long time, it suggests training to improve the efficiency of that task. The analysis unit also analyzes the work content of staff in real time, and the generation AI automatically generates a training program for improving efficiency. For example, if a particular task is taking a long time, it suggests training to improve the efficiency of that task. The analysis unit also analyzes the work content of staff in real time, and the generation AI automatically generates a training program for improving efficiency. For example, if a particular task is taking a long time, it suggests training to improve the efficiency of that task. In this way, by analyzing the work content of staff in real time and automatically generating a training program for improving efficiency, work efficiency is improved.

[0093] The analysis unit can use the emotion estimation function to suggest motivation improvement measures according to the emotions of the staff. The analysis unit, for example, analyzes the emotional state of the staff and suggests motivation improvement measures using the emotion estimation function. For example, if the staff is tired, it suggests a break to refresh them. The analysis unit also analyzes the emotional state of the staff and suggests motivation improvement measures using the emotion estimation function. For example, if the staff is feeling stressed, it suggests an activity to relieve stress. The analysis unit also analyzes the emotional state of the staff and suggests motivation improvement measures using the emotion estimation function. For example, if the staff is losing motivation, it suggests goal setting to increase motivation. In this way, by suggesting motivation improvement measures according to the emotions of the staff, work efficiency is improved.

[0094] The analysis unit can monitor staff members' learning progress in real time and provide individually optimized training programs. For example, the generative AI in the analysis unit monitors staff members' learning progress in real time and provides individually optimized training programs. For example, if a particular skill is lacking, it suggests training to strengthen that skill. The analysis unit can also monitor staff members' learning progress in real time and provide individually optimized training programs. For example, if a particular skill is lacking, it suggests training to strengthen that skill. The analysis unit can also monitor staff members' learning progress in real time and provide individually optimized training programs. For example, if a particular skill is lacking, it suggests training to strengthen that skill. In this way, by monitoring staff members' learning progress in real time and providing individually optimized training programs, it becomes possible for them to debut with short training periods.

[0095] The analysis unit can analyze the staff's past experience and skills and suggest the most appropriate training content. For example, the generation AI in the analysis unit analyzes the staff's past experience and skills and suggests the most appropriate training content. For example, if there is a lack of specific experience, it suggests training to make up for that experience. The analysis unit can also analyze the staff's past experience and skills and suggest the most appropriate training content. For example, if there is a lack of specific experience, it suggests training to make up for that experience. The analysis unit can also analyze the staff's past experience and skills and suggest the most appropriate training content. For example, if there is a lack of specific experience, it suggests training to make up for that experience. In this way, by analyzing the staff's past experience and skills and suggesting the most appropriate training content, it becomes possible for them to make their debut with a short training period.

[0096] The analysis unit can use the emotion estimation function to provide real-time feedback to increase staff motivation to learn. The analysis unit, for example, analyzes the emotional state of the staff and uses the emotion estimation function to provide real-time feedback to increase motivation to learn. For example, if the staff is tired, it provides words of encouragement. The analysis unit also analyzes the emotional state of the staff and uses the emotion estimation function to provide real-time feedback to increase motivation to learn. For example, if the staff is feeling stressed, it suggests an activity to refresh them. The analysis unit also analyzes the emotional state of the staff and uses the emotion estimation function to provide real-time feedback to increase motivation to learn. For example, if the staff is losing motivation, it suggests goal setting to increase motivation. In this way, by providing real-time feedback to increase staff motivation to learn, it is possible to make a debut with short training periods.

[0097] The analysis unit can automatically record the training content of staff members and reflect it in future training programs. For example, the generative AI in the analysis unit automatically records the training content of staff members and reflects it in future training programs. For example, if a specific training content is effective, it will reflect that content in the next training. The analysis unit also automatically records the training content of staff members and reflects it in future training programs. For example, if a specific training content is effective, it will reflect that content in the next training. The analysis unit also automatically records the training content of staff members and reflects it in future training programs. For example, if a specific training content is effective, it will reflect that content in the next training. In this way, by automatically recording the training content of staff members and reflecting it in future training programs, it becomes possible for them to debut with a short training period.

[0098] The analysis unit can share the training progress of staff members with other staff members, thereby improving the skills of the entire team. For example, the generation AI shares the training progress of staff members in real time, thereby improving the skills of the entire team. For example, the skills acquired by a specific staff member are shared with other staff members. The analysis unit also shares the training progress of staff members with other staff members, thereby improving the skills of the entire team. For example, the skills acquired by a specific staff member are shared with other staff members. The analysis unit also shares the training progress of staff members with other staff members, thereby improving the skills of the entire team. For example, the skills acquired by a specific staff member are shared with other staff members. In this way, the training progress of staff members can be shared with other staff members, thereby improving the skills of the entire team, making it possible for them to debut with a short training period.

[0099] The analysis unit can use the emotion estimation function to adjust the training content and methods according to the staff's emotions, thereby achieving effective learning. The analysis unit, for example, analyzes the emotional state of the staff and uses the emotion estimation function to adjust the training content and methods. For example, if the staff is tired, it suggests a break to refresh itself. The analysis unit also analyzes the emotional state of the staff and uses the emotion estimation function to adjust the training content and methods. For example, if the staff is feeling stressed, it suggests an activity to relieve stress. The analysis unit also analyzes the emotional state of the staff and uses the emotion estimation function to adjust the training content and methods. For example, if the staff is losing motivation, it suggests goal setting to increase motivation. In this way, by adjusting the training content and methods according to the staff's emotions, effective learning is achieved, allowing them to debut with a short training period.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The suggestion unit can not only respond to the customer's comments but also suggest related products and services at the same time. For example, if a customer says, "Please tell me about returning a product," the suggestion unit will provide instructions on the return procedure and suggest an alternative product. The suggestion unit can also respond to the customer's comments and suggest related products and services. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit will provide instructions on the exchange procedure and suggest a related product. The suggestion unit can also respond to the customer's comments and suggest related products and services. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit will provide instructions on the repair procedure and suggest a related service. This not only responds to the customer's comments but also suggests related products and services at the same time, thereby improving customer satisfaction.

[0102] The analysis unit analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. The analysis unit also analyzes the staff work logs, and the generation AI can make suggestions for improving work efficiency. For example, if a particular task is taking a long time, it will suggest ways to make that task more efficient. In this way, by analyzing the staff work logs and making suggestions for improving work efficiency, work efficiency is achieved.

[0103] The suggestion unit can generate multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, the generation AI analyzes customer utterances and generates multiple candidate answers. For example, if a customer says, "Please tell me about returning a product," the AI ​​generates multiple answers, such as "Return procedures are possible within 30 days of purchase" and "We will provide detailed information on how to return a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about exchanging a product," the AI ​​generates multiple answers, such as "Replacement procedures are possible within 30 days of purchase" and "We will provide detailed information on how to exchange a product." The suggestion unit also generates multiple candidate answers to customer utterances, allowing staff to select the optimal answer. For example, if a customer says, "Please tell me about repairing a product," the AI ​​generates multiple answers, such as "Repair procedures are possible within 30 days of purchase" and "We will provide detailed information on how to repair a product." In this way, multiple candidate answers to customer utterances are generated, allowing staff to select the optimal answer.

[0104] The analysis unit can optimize staff schedules and distribute work loads evenly. For example, it analyzes staff schedules, and the generation AI proposes ways to distribute work loads evenly. For example, if work is concentrated on a specific staff member, it distributes that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes ways to distribute work loads evenly. For example, if work is concentrated on a specific staff member, it distributes that work to other staff members. The analysis unit also analyzes staff schedules, and the generation AI proposes ways to distribute work loads evenly. For example, if work is concentrated on a specific staff member, it distributes that work to other staff members. In this way, staff schedules are optimized and work loads are distributed evenly, thereby achieving work efficiency.

[0105] The suggestion unit can automatically suggest related FAQs and support articles based on customer utterances. For example, the generation AI analyzes customer utterances and automatically suggests related FAQs and support articles. For example, if a customer says, "Please tell me about returning a product," the suggestion unit will suggest FAQs related to returns. The suggestion unit also automatically suggests related FAQs and support articles based on customer utterances. For example, if a customer says, "Please tell me about exchanging a product," the suggestion unit will suggest FAQs related to exchanges. The suggestion unit also automatically suggests related FAQs and support articles based on customer utterances. For example, if a customer says, "Please tell me about repairing a product," the suggestion unit will suggest FAQs related to repairs. This improves customer satisfaction by automatically suggesting related FAQs and support articles based on customer utterances.

[0106] The suggestion unit can use the emotion estimation function to suggest answers with adjusted tone and expression according to the customer's emotions. For example, the suggestion unit analyzes the customer's emotional state and uses the emotion estimation function to suggest answers with adjusted tone and expression. For example, if the customer is angry, it suggests an answer with a calm and polite tone. The suggestion unit also analyzes the customer's emotional state and uses the emotion estimation function to suggest answers with adjusted tone and expression. For example, if the customer is sad, it suggests an answer with a gentle tone. The suggestion unit also analyzes the customer's emotional state and uses the emotion estimation function to suggest answers with adjusted tone and expression. For example, if the customer is happy, it suggests an answer with a bright tone. In this way, by suggesting answers with adjusted tone and expression according to the customer's emotions, customer satisfaction is improved.

[0107] The analysis unit can use the emotion estimation function to suggest music and videos that correspond to the customer's emotions, thereby providing a relaxing environment. For example, the analysis unit analyzes the customer's emotional state and uses the emotion estimation function to suggest relaxing music. For example, if the customer is feeling stressed, relaxing music is played. The analysis unit also analyzes the customer's emotional state and uses the emotion estimation function to suggest relaxing videos. For example, if the customer is tired, relaxing nature videos are played. The analysis unit also analyzes the customer's emotional state and uses the emotion estimation function to suggest a combination of relaxing music and videos. For example, if the customer is tense, relaxing music and videos are played simultaneously. In this way, a relaxing environment can be provided by suggesting music and videos that correspond to the customer's emotions.

[0108] The suggestion unit can use the emotion estimation function to automatically generate a follow-up message according to the customer's emotions, thereby improving customer satisfaction. For example, the suggestion unit analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is angry, a calm and polite follow-up message is sent. The suggestion unit also analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is sad, a kind follow-up message is sent. The suggestion unit also analyzes the customer's emotional state and automatically generates a follow-up message using the emotion estimation function. For example, if the customer is happy, a cheerful follow-up message is sent. In this way, customer satisfaction is improved by automatically generating a follow-up message according to the customer's emotions.

[0109] The suggestion unit can use the emotion estimation function to suggest benefits and services according to the customer's emotions. For example, the suggestion unit analyzes the customer's emotional state and uses the emotion estimation function to suggest benefits and services. For example, if the customer is angry, a special discount or service is suggested. The suggestion unit can also analyze the customer's emotional state and use the emotion estimation function to suggest benefits and services. For example, if the customer is sad, a special discount or service is suggested. The suggestion unit can also analyze the customer's emotional state and use the emotion estimation function to suggest benefits and services. For example, if the customer is happy, a special discount or service is suggested. In this way, customer satisfaction can be improved by suggesting benefits and services according to the customer's emotions.

[0110] The analysis unit can monitor the stress levels of staff using the emotion estimation function and suggest appropriate break times. For example, it analyzes the emotional state of staff and monitors their stress levels using the emotion estimation function. For example, if staff are feeling stressed, it suggests appropriate break times. The analysis unit can also analyze the emotional state of staff and monitor their stress levels using the emotion estimation function. For example, if staff are feeling stressed, it suggests appropriate break times. The analysis unit can also analyze the emotional state of staff and monitor their stress levels using the emotion estimation function. For example, if staff are feeling stressed, it suggests appropriate break times. In this way, by monitoring staff stress levels and suggesting appropriate break times, work efficiency is improved.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The recording unit records conversations with customers. For example, the recording unit can record telephone conversations, face-to-face conversations, and chat content. Telephone conversations are saved as high-quality audio data, and face-to-face conversations are saved as digital data using a microphone. Chat content is saved as text data. Step 2: The analysis unit analyzes the conversation recorded by the recording unit. For example, the analysis unit converts the voice data into text data using voice recognition technology, and then analyzes the text data using natural language processing technology. It also extracts context and keywords to analyze the intent of the customer's remarks. Step 3: The suggestion unit proposes an appropriate answer based on the content analyzed by the analysis unit. For example, the suggestion unit uses a generation AI to generate an appropriate answer, generating multiple answer candidates and selecting the most appropriate one. It can also propose answers based on the customer's emotions.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0141] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0157] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0165] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0170] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0171] 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.

[0172] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0173] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0174] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0175] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0178] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0180] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A recording unit that records conversations with customers; an analysis unit that analyzes the content of the conversation recorded by the recording unit; a suggestion unit that proposes an appropriate answer based on the content analyzed by the analysis unit. A system characterized by:

2. The recording unit The content of chats or emails with the customer is also analyzed at the same time, enabling multi-channel responses.

2. The system of claim 1.

3. The proposal unit Automatically generate relevant questions and gather additional information to better understand the intent of the customer's statements 2. The system of claim 1.

4. The recording unit Summarize what the customer said in real time, allowing staff to quickly understand 2. The system of claim 1.

5. The analysis unit Analyze staff work logs and use AI to suggest ways to improve work efficiency 2. The system of claim 1.

6. The analysis unit Analyzing the emotional state of the customer and suggesting responses according to the emotion 2. The system of claim 1.

Images