System

Abstract

An object of a system according to an embodiment is to analyze a conversation with a customer in real time and propose an appropriate answer.SOLUTION: A system includes a recording part, an analysis part, a proposal part, and a history storage part. The recording unit records a conversation with a customer. The analysis unit analyzes the voice data recorded by the recording unit. The proposal unit proposes an answer on the basis of an analysis result obtained by the analysis unit. The history storage unit stores a history of the answer and the conversation proposed by the proposal 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] With conventional technology, it is difficult to analyze conversations with customers in real time and suggest appropriate responses, leaving room for improvement in operational efficiency.

[0005] The system according to the embodiment aims to analyze conversations with customers in real time and propose appropriate responses. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, an analysis unit, a proposal unit, and a history storage unit. The recording unit records conversations with customers. The analysis unit analyzes the voice data recorded by the recording unit. The proposal unit proposes answers based on the analysis results obtained by the analysis unit. The history storage unit stores the answers proposed by the proposal unit and the history of the conversation. [Effects of the Invention]

[0007] The system according to the embodiment can analyze conversations with customers in real time and suggest appropriate responses. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) A real-time conversation assistance tool according to an embodiment of the present invention is a system that records conversations with customers, analyzes them using a generation AI, and proposes appropriate responses. The real-time conversation assistance tool records conversations with customers, analyzes them using a generation AI, and proposes appropriate responses, thereby achieving smooth communication and high customer satisfaction. Furthermore, the real-time conversation assistance tool can reduce the workload of staff and improve work efficiency. For example, the real-time conversation assistance tool records a conversation when a conversation with a customer begins. The recorded voice data is analyzed in real time by a generation AI. The generation AI understands the content of the conversation and proposes an appropriate response. For example, if a customer asks about how to use a product, the generation AI proposes the optimal response to that question. The response proposed by the generation AI is then displayed on the staff member's screen. The staff member reviews the proposed response, modifies it if necessary, and then responds to the customer. This allows the staff member to quickly and accurately answer customer questions. Furthermore, the real-time conversation assistance tool can save the conversation history and refer to it later. This allows the staff member to review past conversation content and improve the quality of customer service. Furthermore, analyzing the conversation history can help identify customer needs and trends and use this information to improve services. This allows the real-time conversation assistance tool to achieve smooth communication with customers, providing high customer satisfaction, while also reducing the workload of staff and improving work efficiency.

[0029] A real-time conversation assistance tool according to an embodiment includes a recording unit, an analysis unit, a suggestion unit, and a history storage unit. The recording unit records a conversation with a customer. The conversation with a customer may include, but is not limited to, a telephone conversation, a chat conversation, or a face-to-face conversation. The recording unit may automatically start recording when the conversation starts. The recording unit may also use noise canceling technology to improve the quality of the recording. For example, the recording unit may analyze ambient sounds and remove noise. The analysis unit may use a generation AI to analyze the audio data recorded by the recording unit. The analysis may be performed using, for example, speech recognition technology or natural language processing technology, but is not limited to, examples. For example, the analysis unit may convert the audio data into text data and understand the content of the conversation. The analysis unit may also perform contextual analysis and semantic analysis. For example, the analysis unit may understand the context by taking into account the context of the conversation. The suggestion unit uses the generation AI to suggest an appropriate answer based on the analysis results obtained by the analysis unit. The suggestion may be performed using, for example, a suggestion algorithm, but is not limited to, examples. For example, the suggestion unit may suggest an optimal answer to a customer's question. The suggestion unit can also display the content of the suggestion on the staff member's screen. For example, the suggestion unit can display the proposed answer on the staff member's screen so that the staff member can confirm it. The history storage unit stores the answers proposed by the suggestion unit and the conversation history. The history storage can be, for example, in text format or audio format, but is not limited to such examples. For example, the history storage unit stores the conversation history as text data. The history storage unit can also make the stored history available for later reference. For example, the history storage unit has a function for searching and referencing past conversation content. This enables the real-time conversation assistance tool according to the embodiment to achieve smooth communication with customers and provide high customer satisfaction. Some or all of the above-described processes in the recording unit, analysis unit, suggestion unit, and history storage unit may be performed using, or without, AI. For example, the recording unit can input recorded audio data to a generation AI and cause the generation AI to analyze the audio data. The analysis unit can suggest an appropriate answer based on the data analyzed by the generation AI.The suggestion unit can display the answers proposed by the generation AI on the staff member's screen, and the history storage unit can later refer to the history saved by the generation AI.

[0030] The history storage unit can store the conversation history. The history storage unit stores the conversation history in, for example, text format or audio format. For example, the history storage unit stores the content of the conversation as text data. The history storage unit can also store the audio data of the conversation as is. For example, the history storage unit stores recorded audio data so that it can be played back later. By storing the conversation history, it can be referenced later, improving the quality of customer service. Some or all of the above-described processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can later reference the history stored by the generation AI.

[0031] The real-time conversation assistance tool further includes a history analysis unit that analyzes the conversation history stored by the history storage unit. The history analysis unit analyzes the conversation history stored by the history storage unit. The history analysis is performed using, for example, data mining technology or statistical analysis, but is not limited to these examples. For example, the history analysis unit identifies customer needs and trends based on the stored conversation history. The history analysis unit can also use the analysis of the conversation history to improve services. For example, the history analysis unit identifies customer needs and identifies areas for improvement in services. In this way, analyzing the conversation history can identify customer needs and trends and be used to improve services. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can identify customer needs and trends based on the history stored by the generation AI.

[0032] The real-time conversation assistance tool further includes a staff screen display unit that displays the answer proposed by the suggestion unit on the staff screen. The staff screen display unit displays the answer proposed by the suggestion unit on the staff screen. The screen display is performed, for example, based on the type of information to be displayed and the display layout, but is not limited to such examples. For example, the staff screen display unit displays the proposed answer on the staff screen so that the staff can confirm it. The staff screen display unit can also customize the type of information to be displayed. For example, the staff screen display unit displays the answer to the customer's question in detail. The staff screen display unit can also adjust the display layout to improve visibility. For example, the staff screen display unit displays the answer in an easy-to-read format. This allows the staff to confirm the proposed answer and quickly and accurately answer the customer's question. Some or all of the above-described processing in the staff screen display unit may be performed, for example, using AI or without AI. For example, the staff screen display unit can display the answer proposed by the generation AI on the staff screen.

[0033] The analysis unit can understand the content of the conversation and suggest an appropriate response. The analysis unit, for example, uses a generation AI to understand the content of the conversation. For example, the analysis unit converts audio data into text data and understands the content of the conversation. The analysis unit can also perform contextual analysis and semantic analysis. For example, the analysis unit understands the context by taking into account the context of the conversation. This allows the analysis unit to understand the content of the conversation and suggest a more appropriate response. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can suggest an appropriate response based on data analyzed by the generation AI.

[0034] The suggestion unit can suggest an optimal answer to a customer's question. The suggestion unit can, for example, use a generation AI to suggest an optimal answer to a customer's question. For example, the suggestion unit can use a suggestion algorithm to suggest an optimal answer to a customer's question. The suggestion unit can also display the content of the suggestion on the staff member's screen. For example, the suggestion unit can display the suggested answer on the staff member's screen so that the staff member can check it. This makes it possible to improve customer satisfaction by suggesting an optimal answer to a customer's question. Some or all of the above-mentioned processing in the suggestion unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the suggestion unit can display an answer suggested by the generation AI on the staff member's screen.

[0035] The recording unit can automatically remove background noise during recording. For example, the recording unit analyzes the surrounding environmental sounds when recording starts and removes noise. For example, the recording unit filters sudden noise that occurs during conversation in real time. The recording unit can also remove noise from the recorded data through post-processing after recording ends. This removes background noise, thereby improving the quality of the recording. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can perform noise removal using generation AI.

[0036] The recording unit can adjust the quality of the recording based on the importance of the conversation during recording. The recording unit adjusts the quality of the recording based on, for example, the importance of the conversation. For example, the recording unit records at high quality if the content of the conversation is important. The recording unit can also record at standard quality if the content of the conversation is general. The recording unit can also record at low quality if the content of the conversation is less important. In this way, by adjusting the quality of the recording according to the importance of the conversation, important conversations can be recorded at high quality. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can evaluate the importance of the conversation using a generation AI and adjust the quality of the recording.

[0037] The recording unit can integrate and record audio from multiple audio input sources during recording. For example, the recording unit simultaneously records and integrates audio from multiple microphones. For example, the recording unit integrates audio from different devices in real time during a conversation. The recording unit can also integrate multiple audio data into a single file after recording. This enables more comprehensive recording by integrating audio from multiple audio input sources. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can integrate multiple audio data using generative AI.

[0038] The recording unit can customize recording settings taking into account the user's geographical location information when recording. The recording unit customizes the recording settings taking into account the user's geographical location information, for example. For example, the recording unit records with standard settings when the user is in a quiet place. The recording unit can also enhance noise cancellation when the user is in a noisy place. The recording unit can also adjust recording sensitivity when the user is moving. This allows for more appropriate recording by customizing the recording settings based on the user's geographical location information. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can analyze the user's geographical location information using generation AI and customize the recording settings.

[0039] The recording unit can optimize recording settings by referring to the user's past conversation history when recording. The recording unit, for example, optimizes recording settings by referring to the user's past conversation history. For example, the recording unit suggests optimal recording settings based on the settings of conversations previously recorded by the user. The recording unit can also adjust the intensity of noise canceling based on the user's past conversation history. The recording unit can also analyze the user's past conversation history and optimize recording sensitivity. In this way, the recording settings can be optimized by referring to the user's past conversation history. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can analyze the user's past conversation history using a generation AI and optimize the recording settings.

[0040] When recording, the recording unit can analyze the user's social media activity and prioritize recording relevant conversations. For example, the recording unit can analyze the user's social media activity and prioritize recording relevant conversations. For example, the recording unit can prioritize recording conversations related to topics the user frequently mentions on social media. The recording unit can also predict important conversations from the user's social media activity and prioritize recording them. The recording unit can also prioritize recording conversations with the user's social media friends. In this way, by prioritizing recording relevant conversations based on the user's social media activity, important conversations can be recorded without missing them. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can analyze the user's social media activity using generation AI and prioritize recording relevant conversations.

[0041] During analysis, the analysis unit can enhance the natural language processing algorithm for understanding the context of the conversation. For example, the analysis unit can enhance the algorithm for understanding the context by taking into account the context of the conversation. For example, the analysis unit can enhance the algorithm for understanding the technical terms and slang used in the conversation. The analysis unit can also track changes in the topic of the conversation and enhance the algorithm for understanding the context. This can improve the accuracy of the analysis by enhancing the algorithm for understanding the context of the conversation. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using a generation AI or without using a generation AI. For example, the analysis unit can enhance the algorithm for understanding the context of the conversation by a generation AI.

[0042] During analysis, the analysis unit can apply different analysis methods depending on the category of the conversation. For example, in the case of technical conversation, the analysis unit applies an analysis method that emphasizes technical terminology. For example, in the case of casual conversation, the analysis unit applies an analysis method that emphasizes slang and colloquial expressions. In addition, in the case of business conversation, the analysis unit can also apply an analysis method that emphasizes formal expressions. In this way, by applying an analysis method depending on the category of the conversation, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can apply different analysis methods depending on the category of the conversation using a generation AI.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past conversation history. The analysis unit can improve the accuracy of the analysis by, for example, referring to the user's past conversation history. For example, the analysis unit can improve the analysis accuracy for a specific topic based on the user's past conversation history. The analysis unit can also learn frequently used expressions from the user's past conversation history to improve the analysis accuracy. The analysis unit can also analyze the user's past conversation history to improve the accuracy of understanding context. In this way, the analysis accuracy can be improved by referring to the user's past conversation history. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can improve the analysis accuracy by referring to the user's past conversation history using a generation AI.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the conversation. The analysis unit determines the priority of analysis based on, for example, the time of submission of the conversation. For example, the analysis unit prioritizes analysis of the most recent conversation. The analysis unit can also postpone conversations that were submitted earlier. The analysis unit can also automatically adjust the order of analysis based on the time of submission. In this way, by determining the priority of analysis based on the time of submission of the conversation, it is possible to prioritize analysis of the most recent conversation. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the time of submission of the conversation using a generation AI and determine the priority of analysis.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversations. For example, the analysis unit prioritizes analysis of highly relevant conversations. For example, the analysis unit postpones analysis of less relevant conversations. The analysis unit can also automatically adjust the order of analysis based on the relevance of the conversations. In this way, by adjusting the order of analysis based on the relevance of the conversations, highly relevant conversations can be analyzed with priority. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the relevance of the conversations using a generation AI and adjust the order of analysis.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis results according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit displays analysis results that use a lot of technical terms. For example, if the user has general knowledge, the analysis unit displays analysis results that use less technical terms. The analysis unit can also automatically adjust the use of technical terms in the analysis results according to the user's level of expertise. This makes it possible to provide analysis results that are easier to understand by adjusting the use of technical terms in the analysis results according to the user's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the user's level of expertise using a generation AI and adjust the use of technical terms in the analysis results.

[0047] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the question when making a suggestion. The suggestion unit adjusts the level of detail of the suggestion based on, for example, the importance of the question. For example, the suggestion unit makes a detailed suggestion for an important question. The suggestion unit can also make a standard suggestion for a general question. The suggestion unit can also make a concise suggestion for a question with a low importance. In this way, by adjusting the level of detail of the suggestion according to the importance of the question, it is possible to make a more appropriate suggestion. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the importance of the question using a generation AI and adjust the level of detail of the suggestion.

[0048] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the question. For example, the suggestion unit applies a specialized suggestion algorithm to a technical question. For example, the suggestion unit applies a general suggestion algorithm to a casual question. The suggestion unit can also apply a formal suggestion algorithm to a business-related question. In this way, by applying a suggestion algorithm depending on the category of the question, more appropriate suggestions can be made. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can analyze the category of the question using a generation AI and apply different suggestion algorithms.

[0049] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. The suggestion unit, for example, improves the accuracy of the suggestion by referring to the user's past suggestion results. For example, the suggestion unit improves the accuracy of suggestions for a specific topic based on the user's past suggestion results. The suggestion unit can also learn frequently used expressions from the user's past suggestion results and improve the accuracy of the suggestion. The suggestion unit can also analyze the user's past suggestion results and improve the accuracy of understanding context. In this way, the accuracy of the suggestion can be improved by referring to the user's past suggestion results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the user's past suggestion results using a generation AI to improve the accuracy of the suggestion.

[0050] The suggestion unit can determine the priority of the proposals based on the time when the questions were submitted when making the proposals. The suggestion unit determines the priority of the proposals based on, for example, the time when the questions were submitted. For example, the suggestion unit prioritizes the most recent questions. The suggestion unit can also postpone questions that were submitted earlier. The suggestion unit can also automatically adjust the order of the proposals based on the time when the questions were submitted. In this way, by determining the priority of the proposals based on the time when the questions were submitted, the most recent questions can be prioritized. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the time when the questions were submitted using a generation AI and determine the priority of the proposals.

[0051] The suggestion unit can adjust the order of suggestions based on the relevance of questions when suggesting questions. For example, the suggestion unit preferentially suggests highly relevant questions. For example, the suggestion unit postpones questions with low relevance. The suggestion unit can also automatically adjust the order of suggestions based on the relevance of questions. In this way, by adjusting the order of suggestions based on the relevance of questions, highly relevant questions can be suggested with priority. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the relevance of questions using a generation AI and adjust the order of suggestions.

[0052] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal according to the user's level of expertise. For example, if the user has technical expertise, the suggestion unit makes a proposal that uses a lot of technical terminology. For example, if the user has general knowledge, the suggestion unit makes a proposal that uses less technical terminology. The suggestion unit can also automatically adjust the use of technical terminology in the proposal according to the user's level of expertise. This allows for a proposal that is easier to understand to be made by adjusting the use of technical terminology in the proposal according to the user's level of expertise. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the user's level of expertise using a generation AI and adjust the use of technical terminology in the proposal.

[0053] The history storage unit can determine the priority of storage based on the importance of the conversation when saving the history. The history storage unit determines the priority of storage based on, for example, the importance of the conversation. For example, the history storage unit prioritizes saving important conversation content. The history storage unit can also save general conversation content as a standard. The history storage unit can also postpone saving conversation content with low importance. In this way, by determining the priority of storage based on the importance of the conversation, important conversations can be saved preferentially. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the importance of the conversation using a generation AI and determine the priority of storage.

[0054] The history storage unit can apply different storage formats depending on the category of the conversation when saving the history. For example, the history storage unit saves technical conversations in a detailed text format. For example, the history storage unit saves casual conversations in a concise text format. The history storage unit can also save business conversations in a formal text format. This allows for more appropriate history storage by applying a storage format depending on the category of the conversation. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the category of the conversation using a generation AI and apply a different storage format.

[0055] The history storage unit can optimize the storage method by referring to the user's past history storage settings when saving history. The history storage unit, for example, optimizes the storage method by referring to the user's past history storage settings. For example, the history storage unit suggests an optimal storage method based on the user's past history storage settings. The history storage unit can also adjust the storage format based on the user's past history storage settings. The history storage unit can also analyze the user's past history storage settings and optimize the storage priority. In this way, the storage method can be optimized by referring to the user's past history storage settings. Some or all of the above-described processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the user's past history storage settings using a generation AI and optimize the storage method.

[0056] The history storage unit can determine the priority of storage based on the submission time of the conversation when saving the history. The history storage unit determines the priority of storage based on, for example, the submission time of the conversation. For example, the history storage unit prioritizes saving the most recent conversation. The history storage unit can also postpone conversations that were submitted earlier. The history storage unit can also automatically adjust the order of storage based on the submission time. In this way, by determining the priority of storage based on the submission time of the conversation, the most recent conversation can be prioritized for saving. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the submission time of the conversation using a generation AI and determine the priority of storage.

[0057] The history storage unit can adjust the order of saving based on the relevance of the conversations when saving the history. For example, the history storage unit prioritizes saving highly relevant conversations. For example, the history storage unit postpones less relevant conversations. The history storage unit can also automatically adjust the order of saving based on the relevance of the conversations. In this way, by adjusting the order of saving based on the relevance of the conversations, highly relevant conversations can be saved preferentially. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the relevance of the conversations using a generation AI and adjust the order of saving.

[0058] The history storage unit can adjust the storage format according to the user's level of expertise when saving history. For example, if the user has specialized knowledge, the history storage unit uses a detailed storage format. For example, if the user has general knowledge, the history storage unit uses a simple storage format. The history storage unit can also automatically adjust the storage format according to the user's level of expertise. This allows for more appropriate history storage by adjusting the storage format according to the user's level of expertise. Some or all of the above-described processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the user's level of expertise using a generating AI and adjust the storage format.

[0059] During history analysis, the history analysis unit can optimize the current analysis by referring to past history data. The history analysis unit, for example, optimizes the current analysis by referring to past history data. For example, the history analysis unit improves the accuracy of analysis for a specific topic based on past history data. The history analysis unit can also learn frequently used expressions from past history data to improve the accuracy of analysis. The history analysis unit can also analyze past history data to improve the accuracy of understanding context. In this way, the current analysis can be optimized by referring to past history data. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can optimize the current analysis by referring to past history data using generation AI.

[0060] The history analysis unit can apply different analysis methods to different conversation categories during history analysis. For example, in the case of technical conversation, the history analysis unit applies a specialized analysis method. For example, in the case of casual conversation, the history analysis unit can apply a general analysis method. Furthermore, in the case of business conversation, the history analysis unit can also apply a formal analysis method. In this way, by applying different analysis methods to different conversation categories, more appropriate analysis results can be obtained. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the conversation category using a generation AI and apply different analysis methods.

[0061] The history analysis unit can perform the analysis taking into account the user's attribute information when analyzing the history. The history analysis unit performs the analysis taking into account, for example, the user's age and gender. For example, the history analysis unit performs the analysis taking into account the user's occupation and hobbies. The history analysis unit can also perform the analysis taking into account the user's past behavioral patterns. In this way, by taking into account the user's attribute information, more appropriate analysis results can be obtained. Some or all of the above-mentioned processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the user's attribute information using a generation AI and perform the analysis.

[0062] During history analysis, the history analysis unit can determine the priority of analysis based on the time when the conversation was submitted. The history analysis unit determines the priority of analysis based on, for example, the time when the conversation was submitted. For example, the history analysis unit prioritizes analysis of the most recent conversation. The history analysis unit can also postpone conversations that were submitted earlier. The history analysis unit can also automatically adjust the order of analysis based on the time of submission. In this way, by determining the priority of analysis based on the time when the conversation was submitted, it is possible to prioritize analysis of the most recent conversation. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the time when the conversation was submitted using a generation AI and determine the priority of analysis.

[0063] During history analysis, the history analysis unit can perform analysis by referring to market data related to the conversation. The history analysis unit, for example, performs analysis by referring to the related market data. For example, the history analysis unit improves the accuracy of analysis on a specific topic based on the related market data. The history analysis unit can also learn frequently used expressions from the related market data to improve the accuracy of analysis. The history analysis unit can also analyze the related market data to improve the accuracy of understanding the context. As a result, more appropriate analysis results can be obtained by referring to the market data related to the conversation. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can perform analysis by referring to the related market data using a generation AI.

[0064] The history analysis unit can perform the analysis taking into account the technical maturity of the conversation when analyzing the history. The history analysis unit performs the analysis taking into account, for example, the technical maturity of the conversation. For example, the history analysis unit performs a detailed analysis in the case of a technically mature conversation. The history analysis unit can also perform a brief analysis in the case of a technically immature conversation. The history analysis unit can also automatically adjust the accuracy of the analysis based on the technical maturity. In this way, more appropriate analysis results can be obtained by taking the technical maturity of the conversation into account. Some or all of the above-mentioned processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the technical maturity of the conversation using a generation AI and perform the analysis.

[0065] When displaying the screen, the staff screen display unit can select the optimal display method by referring to the user's past operation history. The staff screen display unit, for example, selects the optimal display method by referring to the user's past operation history. For example, the staff screen display unit suggests the optimal display method based on the user's past operation history. The staff screen display unit can also adjust the display format based on the user's past operation history. The staff screen display unit can also analyze the user's past operation history and optimize display priorities. This makes it possible to select the optimal display method by referring to the user's past operation history. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's past operation history using a generation AI and select the optimal display method.

[0066] The staff screen display unit can customize the display content according to the user's current task when displaying the screen. The staff screen display unit customizes the display content according to, for example, the user's current task. For example, the staff screen display unit prioritizes displaying information related to the user's current task. The staff screen display unit can also simplify the display content according to the user's current task. The staff screen display unit can also automatically display necessary information based on the user's current task. This allows for more appropriate display by customizing the display content according to the user's current task. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's current task using a generation AI and customize the display content.

[0067] The staff screen display unit can select the optimal display method when displaying the screen, taking into account the user's device information. For example, the staff screen display unit selects the optimal display method by taking into account the user's device information. For example, if the user is using a smartphone, the staff screen display unit can provide a display method tailored to the screen size. Furthermore, if the user is using a tablet, the staff screen display unit can also provide a display method optimized for a large screen. Furthermore, if the user is using a smartwatch, the staff screen display unit can also provide a simple, highly visible display method. This enables more appropriate display by selecting the optimal display method based on the user's device information. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's device information using a generation AI and select the optimal display method.

[0068] The staff screen display unit can make the display content multilingual when displaying the screen according to the user's language setting. The staff screen display unit automatically sets the display content based on, for example, the language setting of the user's device. For example, the staff screen display unit provides a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the staff screen display unit can also provide the display content in that language. This enables more appropriate display by making the display content multilingual based on the user's language setting. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's language setting using a generation AI and make the display content multilingual.

[0069] The staff screen display unit can be customized based on the user's occupation and lifestyle when displaying the screen. The staff screen display unit, for example, prioritizes displaying information related to the user's occupation. For example, the staff screen display unit customizes the display content based on the user's lifestyle. The staff screen display unit can also adjust the display format according to the user's occupation and lifestyle. This enables more appropriate display by customizing the display content based on the user's occupation and lifestyle. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's occupation and lifestyle using a generation AI and customize the display content.

[0070] The staff screen display unit can improve the display method by reflecting user feedback when displaying the screen. The staff screen display unit improves the display method, for example, based on user feedback. For example, the staff screen display unit adjusts the display format based on user feedback. The staff screen display unit can also analyze user feedback and optimize display priorities. This allows the display method to be improved by reflecting user feedback. Some or all of the above-mentioned processing in the staff screen display unit may be performed using AI, for example, or may be performed without using AI. For example, the staff screen display unit can analyze user feedback using generation AI and improve the display method.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The real-time conversation assistance tool can also be equipped with a resource provider that automatically searches for relevant materials and documents based on the content of the conversation and provides them to staff. For example, if a customer asks about a specific product, the resource provider can automatically search for and provide the product's manual or FAQ. If a customer asks about the contents of a contract, the resource provider can provide the relevant contract or terms and conditions. Furthermore, if a customer asks about a technical issue, the resource provider can provide technical support documents. This allows staff to answer customers' questions quickly and accurately.

[0073] The real-time conversation assistance tool may further include a video providing unit that automatically searches for relevant videos and tutorials based on the content of the conversation and provides them to staff. For example, if a customer asks about how to use a product, the video providing unit may automatically search for and provide a video that explains how to use that product. Also, if a customer asks about settings, the video providing unit may provide a tutorial video that explains how to set up the product. Furthermore, if a customer asks about troubleshooting, the video providing unit may provide a troubleshooting video. This allows staff to answer customers' questions in a visually easy-to-understand manner.

[0074] The real-time conversation assistance tool may further include a data providing unit that automatically generates relevant statistical data and graphs based on the content of the conversation and provides them to the staff. For example, if a customer asks about product sales data, the data providing unit automatically generates and provides sales data for that product. Also, if a customer asks about market trends, the data providing unit may provide a graph showing market trends. Furthermore, if a customer asks about customer satisfaction, the data providing unit may provide statistical data on customer satisfaction. This allows the staff to provide accurate information based on data.

[0075] The real-time conversation assistance tool can also be equipped with a news section that automatically searches for relevant news articles and blogs based on the content of the conversation and provides them to staff. For example, if a customer asks about trends in a particular industry, the news section can automatically search for and provide the latest news articles related to that industry. If a customer asks about a new product, the news section can also provide blog articles about that new product. Furthermore, if a customer asks about market trends, the news section can provide articles about market trends. This allows staff to answer customer questions based on the most up-to-date information.

[0076] The real-time conversation assistance tool may further include an event provider that automatically searches for relevant events and seminars based on the content of the conversation and provides them to staff. For example, if a customer asks about a specific technology, the event provider automatically searches for and provides seminars related to that technology. Also, if a customer asks about industry trends, the event provider can provide events related to that industry. Furthermore, if a customer asks about a new product, the event provider can provide exhibitions related to that new product. This allows staff to provide relevant event information to the customer.

[0077] The processing flow of the first embodiment will be briefly explained below.

[0078] Step 1: The recording unit records conversations with customers. Conversations with customers can include phone calls, chats, and face-to-face conversations. The recording unit automatically starts recording when the conversation begins and can improve the quality of the recording using noise-canceling technology. For example, the recording unit can analyze the surrounding environmental sounds and remove noise. Step 2: The analysis unit uses the generative AI to analyze the audio data recorded by the recording unit. Analysis is carried out using speech recognition technology and natural language processing technology, converting the audio data into text data and understanding the content of the conversation. Contextual and semantic analysis is also performed to understand the context of the conversation. Step 3: The suggestion unit uses the generation AI to propose an appropriate answer based on the analysis results obtained by the analysis unit. The suggestion is made using a suggestion algorithm to propose the best answer to the customer's question. The proposed answer is displayed on the staff's screen so that they can check it. Step 4: The history storage unit saves the responses suggested by the suggestion unit and the conversation history. The history is saved in text or audio format, and the saved history can be referenced later. For example, the history storage unit has a function to search and reference the contents of past conversations.

[0079] (Example 2) A real-time conversation assistance tool according to an embodiment of the present invention is a system that records conversations with customers, analyzes them using a generation AI, and proposes appropriate responses. The real-time conversation assistance tool records conversations with customers, analyzes them using a generation AI, and proposes appropriate responses, thereby achieving smooth communication and high customer satisfaction. Furthermore, the real-time conversation assistance tool can reduce the workload of staff and improve work efficiency. For example, the real-time conversation assistance tool records a conversation when a conversation with a customer begins. The recorded voice data is analyzed in real time by a generation AI. The generation AI understands the content of the conversation and proposes an appropriate response. For example, if a customer asks about how to use a product, the generation AI proposes the optimal response to that question. The response proposed by the generation AI is then displayed on the staff member's screen. The staff member reviews the proposed response, modifies it if necessary, and then responds to the customer. This allows the staff member to quickly and accurately answer customer questions. Furthermore, the real-time conversation assistance tool can save the conversation history and refer to it later. This allows the staff member to review past conversation content and improve the quality of customer service. Furthermore, analyzing the conversation history can help identify customer needs and trends and use this information to improve services. This allows the real-time conversation assistance tool to achieve smooth communication with customers, providing high customer satisfaction, while also reducing the workload of staff and improving work efficiency.

[0080] A real-time conversation assistance tool according to an embodiment includes a recording unit, an analysis unit, a suggestion unit, and a history storage unit. The recording unit records a conversation with a customer. The conversation with a customer may include, but is not limited to, a telephone conversation, a chat conversation, or a face-to-face conversation. The recording unit may automatically start recording when the conversation starts. The recording unit may also use noise canceling technology to improve the quality of the recording. For example, the recording unit may analyze ambient sounds and remove noise. The analysis unit may use a generation AI to analyze the audio data recorded by the recording unit. The analysis may be performed using, for example, speech recognition technology or natural language processing technology, but is not limited to, examples. For example, the analysis unit may convert the audio data into text data and understand the content of the conversation. The analysis unit may also perform contextual analysis and semantic analysis. For example, the analysis unit may understand the context by taking into account the context of the conversation. The suggestion unit uses the generation AI to suggest an appropriate answer based on the analysis results obtained by the analysis unit. The suggestion may be performed using, for example, a suggestion algorithm, but is not limited to, examples. For example, the suggestion unit may suggest an optimal answer to a customer's question. The suggestion unit can also display the content of the suggestion on the staff member's screen. For example, the suggestion unit can display the proposed answer on the staff member's screen so that the staff member can confirm it. The history storage unit stores the answers proposed by the suggestion unit and the conversation history. The history storage can be, for example, in text format or audio format, but is not limited to such examples. For example, the history storage unit stores the conversation history as text data. The history storage unit can also make the stored history available for later reference. For example, the history storage unit has a function for searching and referencing past conversation content. This enables the real-time conversation assistance tool according to the embodiment to achieve smooth communication with customers and provide high customer satisfaction. Some or all of the above-described processes in the recording unit, analysis unit, suggestion unit, and history storage unit may be performed using, or without, AI. For example, the recording unit can input recorded audio data to a generation AI and cause the generation AI to analyze the audio data. The analysis unit can suggest an appropriate answer based on the data analyzed by the generation AI.The suggestion unit can display the answers proposed by the generation AI on the staff member's screen, and the history storage unit can later refer to the history saved by the generation AI.

[0081] The history storage unit can store the conversation history. The history storage unit stores the conversation history in, for example, text format or audio format. For example, the history storage unit stores the content of the conversation as text data. The history storage unit can also store the audio data of the conversation as is. For example, the history storage unit stores recorded audio data so that it can be played back later. By storing the conversation history, it can be referenced later, improving the quality of customer service. Some or all of the above-described processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can later reference the history stored by the generation AI.

[0082] The real-time conversation assistance tool further includes a history analysis unit that analyzes the conversation history stored by the history storage unit. The history analysis unit analyzes the conversation history stored by the history storage unit. The history analysis is performed using, for example, data mining technology or statistical analysis, but is not limited to these examples. For example, the history analysis unit identifies customer needs and trends based on the stored conversation history. The history analysis unit can also use the analysis of the conversation history to improve services. For example, the history analysis unit identifies customer needs and identifies areas for improvement in services. In this way, analyzing the conversation history can identify customer needs and trends and be used to improve services. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can identify customer needs and trends based on the history stored by the generation AI.

[0083] The real-time conversation assistance tool further includes a staff screen display unit that displays the answer proposed by the suggestion unit on the staff screen. The staff screen display unit displays the answer proposed by the suggestion unit on the staff screen. The screen display is performed, for example, based on the type of information to be displayed and the display layout, but is not limited to such examples. For example, the staff screen display unit displays the proposed answer on the staff screen so that the staff can confirm it. The staff screen display unit can also customize the type of information to be displayed. For example, the staff screen display unit displays the answer to the customer's question in detail. The staff screen display unit can also adjust the display layout to improve visibility. For example, the staff screen display unit displays the answer in an easy-to-read format. This allows the staff to confirm the proposed answer and quickly and accurately answer the customer's question. Some or all of the above-described processing in the staff screen display unit may be performed, for example, using AI or without AI. For example, the staff screen display unit can display the answer proposed by the generation AI on the staff screen.

[0084] The analysis unit can understand the content of the conversation and suggest an appropriate response. The analysis unit, for example, uses a generation AI to understand the content of the conversation. For example, the analysis unit converts audio data into text data and understands the content of the conversation. The analysis unit can also perform contextual analysis and semantic analysis. For example, the analysis unit understands the context by taking into account the context of the conversation. This allows the analysis unit to understand the content of the conversation and suggest a more appropriate response. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can suggest an appropriate response based on data analyzed by the generation AI.

[0085] The suggestion unit can suggest an optimal answer to a customer's question. The suggestion unit can, for example, use a generation AI to suggest an optimal answer to a customer's question. For example, the suggestion unit can use a suggestion algorithm to suggest an optimal answer to a customer's question. The suggestion unit can also display the content of the suggestion on the staff member's screen. For example, the suggestion unit can display the suggested answer on the staff member's screen so that the staff member can check it. This makes it possible to improve customer satisfaction by suggesting an optimal answer to a customer's question. Some or all of the above-mentioned processing in the suggestion unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the suggestion unit can display an answer suggested by the generation AI on the staff member's screen.

[0086] The recording unit can analyze the user's emotions and adjust the start timing of recording based on the analyzed user's emotions. The recording unit, for example, estimates the user's emotions and adjusts the start timing of recording based on the estimated user's emotions. For example, if the user is excited, the recording unit starts recording from the beginning of the conversation. Also, if the user is relaxed, the recording unit can start recording after the conversation has progressed. Also, if the user is nervous, the recording unit can record only the important parts of the conversation. This allows for more appropriate recording by adjusting the start timing of recording according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the recording unit may be performed using AI, or may be performed without AI. For example, the recording unit can adjust the start timing of recording based on the user's emotions estimated by the generation AI.

[0087] The recording unit can automatically remove background noise during recording. For example, the recording unit analyzes the surrounding environmental sounds when recording starts and removes noise. For example, the recording unit filters sudden noise that occurs during conversation in real time. The recording unit can also remove noise from the recorded data through post-processing after recording ends. This removes background noise, thereby improving the quality of the recording. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can perform noise removal using generation AI.

[0088] The recording unit can adjust the quality of the recording based on the importance of the conversation during recording. The recording unit adjusts the quality of the recording based on, for example, the importance of the conversation. For example, the recording unit records at high quality if the content of the conversation is important. The recording unit can also record at standard quality if the content of the conversation is general. The recording unit can also record at low quality if the content of the conversation is less important. In this way, by adjusting the quality of the recording according to the importance of the conversation, important conversations can be recorded at high quality. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can evaluate the importance of the conversation using a generation AI and adjust the quality of the recording.

[0089] The recording unit can integrate and record audio from multiple audio input sources during recording. For example, the recording unit simultaneously records and integrates audio from multiple microphones. For example, the recording unit integrates audio from different devices in real time during a conversation. The recording unit can also integrate multiple audio data into a single file after recording. This enables more comprehensive recording by integrating audio from multiple audio input sources. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can integrate multiple audio data using generative AI.

[0090] The recording unit can analyze the user's emotions and determine the recording priority based on the analyzed user's emotions. The recording unit, for example, estimates the user's emotions and determines the recording priority based on the estimated user's emotions. For example, the recording unit can set the recording priority to high if the user is excited. The recording unit can also set the recording priority to medium if the user is relaxed. The recording unit can also set the recording priority to low if the user is nervous. This allows important conversations to be recorded preferentially by determining the recording priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the recording unit can be performed using, for example, AI, or without AI. For example, the recording unit can determine the recording priority based on the user's emotions estimated by the generation AI.

[0091] The recording unit can customize recording settings taking into account the user's geographical location information when recording. The recording unit customizes the recording settings taking into account the user's geographical location information, for example. For example, the recording unit records with standard settings when the user is in a quiet place. The recording unit can also enhance noise cancellation when the user is in a noisy place. The recording unit can also adjust recording sensitivity when the user is moving. This allows for more appropriate recording by customizing the recording settings based on the user's geographical location information. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can analyze the user's geographical location information using generation AI and customize the recording settings.

[0092] The recording unit can optimize recording settings by referring to the user's past conversation history when recording. The recording unit, for example, optimizes recording settings by referring to the user's past conversation history. For example, the recording unit suggests optimal recording settings based on the settings of conversations previously recorded by the user. The recording unit can also adjust the intensity of noise canceling based on the user's past conversation history. The recording unit can also analyze the user's past conversation history and optimize recording sensitivity. In this way, the recording settings can be optimized by referring to the user's past conversation history. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can analyze the user's past conversation history using a generation AI and optimize the recording settings.

[0093] When recording, the recording unit can analyze the user's social media activity and prioritize recording relevant conversations. For example, the recording unit can analyze the user's social media activity and prioritize recording relevant conversations. For example, the recording unit can prioritize recording conversations related to topics the user frequently mentions on social media. The recording unit can also predict important conversations from the user's social media activity and prioritize recording them. The recording unit can also prioritize recording conversations with the user's social media friends. In this way, by prioritizing recording relevant conversations based on the user's social media activity, important conversations can be recorded without missing them. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can analyze the user's social media activity using generation AI and prioritize recording relevant conversations.

[0094] The analysis unit can analyze the user's emotions and adjust the accuracy of the analysis based on the analyzed user's emotions. The analysis unit, for example, estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user's emotions. For example, the analysis unit sets the analysis accuracy high when the user is excited. The analysis unit can also set the analysis accuracy to medium when the user is relaxed. The analysis unit can also set the analysis accuracy to low when the user is nervous. This allows for adjusting the analysis accuracy according to the user's emotions to obtain more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the analysis unit can adjust the analysis accuracy based on the user's emotions estimated by the generation AI.

[0095] During analysis, the analysis unit can enhance the natural language processing algorithm for understanding the context of the conversation. For example, the analysis unit can enhance the algorithm for understanding the context by taking into account the context of the conversation. For example, the analysis unit can enhance the algorithm for understanding the technical terms and slang used in the conversation. The analysis unit can also track changes in the topic of the conversation and enhance the algorithm for understanding the context. This can improve the accuracy of the analysis by enhancing the algorithm for understanding the context of the conversation. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using a generation AI or without using a generation AI. For example, the analysis unit can enhance the algorithm for understanding the context of the conversation by a generation AI.

[0096] During analysis, the analysis unit can apply different analysis methods depending on the category of the conversation. For example, in the case of technical conversation, the analysis unit applies an analysis method that emphasizes technical terminology. For example, in the case of casual conversation, the analysis unit applies an analysis method that emphasizes slang and colloquial expressions. In addition, in the case of business conversation, the analysis unit can also apply an analysis method that emphasizes formal expressions. In this way, by applying an analysis method depending on the category of the conversation, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can apply different analysis methods depending on the category of the conversation using a generation AI.

[0097] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past conversation history. The analysis unit can improve the accuracy of the analysis by, for example, referring to the user's past conversation history. For example, the analysis unit can improve the analysis accuracy for a specific topic based on the user's past conversation history. The analysis unit can also learn frequently used expressions from the user's past conversation history to improve the analysis accuracy. The analysis unit can also analyze the user's past conversation history to improve the accuracy of understanding context. In this way, the analysis accuracy can be improved by referring to the user's past conversation history. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can improve the analysis accuracy by referring to the user's past conversation history using a generation AI.

[0098] The analysis unit can analyze the user's emotions and adjust the display method of the analysis results based on the analyzed user's emotions. The analysis unit, for example, estimates the user's emotions and adjusts the display method of the analysis results based on the estimated user's emotions. For example, the analysis unit can display detailed analysis results when the user is excited. The analysis unit can also display concise analysis results when the user is relaxed. The analysis unit can also display visually easy-to-understand analysis results when the user is nervous. This allows for more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can adjust the display method of the analysis results based on the user's emotions estimated by the generation AI.

[0099] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the conversation. The analysis unit determines the priority of analysis based on, for example, the time of submission of the conversation. For example, the analysis unit prioritizes analysis of the most recent conversation. The analysis unit can also postpone conversations that were submitted earlier. The analysis unit can also automatically adjust the order of analysis based on the time of submission. In this way, by determining the priority of analysis based on the time of submission of the conversation, it is possible to prioritize analysis of the most recent conversation. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the time of submission of the conversation using a generation AI and determine the priority of analysis.

[0100] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversations. For example, the analysis unit prioritizes analysis of highly relevant conversations. For example, the analysis unit postpones analysis of less relevant conversations. The analysis unit can also automatically adjust the order of analysis based on the relevance of the conversations. In this way, by adjusting the order of analysis based on the relevance of the conversations, highly relevant conversations can be analyzed with priority. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the relevance of the conversations using a generation AI and adjust the order of analysis.

[0101] During analysis, the analysis unit can adjust the use of technical terms in the analysis results according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit displays analysis results that use a lot of technical terms. For example, if the user has general knowledge, the analysis unit displays analysis results that use less technical terms. The analysis unit can also automatically adjust the use of technical terms in the analysis results according to the user's level of expertise. This makes it possible to provide analysis results that are easier to understand by adjusting the use of technical terms in the analysis results according to the user's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the user's level of expertise using a generation AI and adjust the use of technical terms in the analysis results.

[0102] The suggestion unit can analyze the user's emotions and adjust the way the suggestions are expressed based on the analyzed user's emotions. The suggestion unit, for example, estimates the user's emotions and adjusts the way the suggestions are expressed based on the estimated user's emotions. For example, the suggestion unit can make detailed suggestions when the user is excited. The suggestion unit can also make concise suggestions when the user is relaxed. The suggestion unit can also make visually easy-to-understand suggestions when the user is nervous. This allows for more appropriate suggestions to be made by adjusting the way the suggestions are expressed based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the suggestion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the suggestion unit can adjust the way the suggestions are expressed based on the user's emotions estimated by the generation AI.

[0103] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the question when making a suggestion. The suggestion unit adjusts the level of detail of the suggestion based on, for example, the importance of the question. For example, the suggestion unit makes a detailed suggestion for an important question. The suggestion unit can also make a standard suggestion for a general question. The suggestion unit can also make a concise suggestion for a question with a low importance. In this way, by adjusting the level of detail of the suggestion according to the importance of the question, it is possible to make a more appropriate suggestion. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the importance of the question using a generation AI and adjust the level of detail of the suggestion.

[0104] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the question. For example, the suggestion unit applies a specialized suggestion algorithm to a technical question. For example, the suggestion unit applies a general suggestion algorithm to a casual question. The suggestion unit can also apply a formal suggestion algorithm to a business-related question. In this way, by applying a suggestion algorithm depending on the category of the question, more appropriate suggestions can be made. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can analyze the category of the question using a generation AI and apply different suggestion algorithms.

[0105] When making a suggestion, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. The suggestion unit, for example, improves the accuracy of the suggestion by referring to the user's past suggestion results. For example, the suggestion unit improves the accuracy of suggestions for a specific topic based on the user's past suggestion results. The suggestion unit can also learn frequently used expressions from the user's past suggestion results and improve the accuracy of the suggestion. The suggestion unit can also analyze the user's past suggestion results and improve the accuracy of understanding context. In this way, the accuracy of the suggestion can be improved by referring to the user's past suggestion results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the user's past suggestion results using a generation AI to improve the accuracy of the suggestion.

[0106] The suggestion unit can analyze the user's emotions and adjust the length of the suggestions based on the analyzed user's emotions. The suggestion unit, for example, estimates the user's emotions and adjusts the length of the suggestions based on the estimated user's emotions. For example, the suggestion unit can provide detailed suggestions when the user is excited. The suggestion unit can also provide concise suggestions when the user is relaxed. The suggestion unit can also provide visually easy-to-understand suggestions when the user is nervous. This allows for more appropriate suggestions to be made by adjusting the length of the suggestions according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the suggestion unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the suggestion unit can adjust the length of the suggestions based on the user's emotions estimated by the generation AI.

[0107] The suggestion unit can determine the priority of the proposals based on the time when the questions were submitted when making the proposals. The suggestion unit determines the priority of the proposals based on, for example, the time when the questions were submitted. For example, the suggestion unit prioritizes the most recent questions. The suggestion unit can also postpone questions that were submitted earlier. The suggestion unit can also automatically adjust the order of the proposals based on the time when the questions were submitted. In this way, by determining the priority of the proposals based on the time when the questions were submitted, the most recent questions can be prioritized. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the time when the questions were submitted using a generation AI and determine the priority of the proposals.

[0108] The suggestion unit can adjust the order of suggestions based on the relevance of questions when suggesting questions. For example, the suggestion unit preferentially suggests highly relevant questions. For example, the suggestion unit postpones questions with low relevance. The suggestion unit can also automatically adjust the order of suggestions based on the relevance of questions. In this way, by adjusting the order of suggestions based on the relevance of questions, highly relevant questions can be suggested with priority. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the relevance of questions using a generation AI and adjust the order of suggestions.

[0109] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal according to the user's level of expertise. For example, if the user has technical expertise, the suggestion unit makes a proposal that uses a lot of technical terminology. For example, if the user has general knowledge, the suggestion unit makes a proposal that uses less technical terminology. The suggestion unit can also automatically adjust the use of technical terminology in the proposal according to the user's level of expertise. This allows for a proposal that is easier to understand to be made by adjusting the use of technical terminology in the proposal according to the user's level of expertise. Some or all of the above-described processing in the suggestion unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the suggestion unit can analyze the user's level of expertise using a generation AI and adjust the use of technical terminology in the proposal.

[0110] The history storage unit can analyze the user's emotions and adjust the history storage method based on the analyzed user's emotions. The history storage unit, for example, estimates the user's emotions and adjusts the history storage method based on the estimated user's emotions. For example, the history storage unit can store detailed history when the user is excited. The history storage unit can also store concise history when the user is relaxed. The history storage unit can also store visually easy-to-understand history when the user is nervous. This enables more appropriate history storage by adjusting the history storage method according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the history storage unit may be performed using AI, or may be performed without AI. For example, the history storage unit can adjust the history storage method based on the user's emotions estimated by the generation AI.

[0111] The history storage unit can determine the priority of storage based on the importance of the conversation when saving the history. The history storage unit determines the priority of storage based on, for example, the importance of the conversation. For example, the history storage unit prioritizes saving important conversation content. The history storage unit can also save general conversation content as a standard. The history storage unit can also postpone saving conversation content with low importance. In this way, by determining the priority of storage based on the importance of the conversation, important conversations can be saved preferentially. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the importance of the conversation using a generation AI and determine the priority of storage.

[0112] The history storage unit can apply different storage formats depending on the category of the conversation when saving the history. For example, the history storage unit saves technical conversations in a detailed text format. For example, the history storage unit saves casual conversations in a concise text format. The history storage unit can also save business conversations in a formal text format. This allows for more appropriate history storage by applying a storage format depending on the category of the conversation. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the category of the conversation using a generation AI and apply a different storage format.

[0113] The history storage unit can optimize the storage method by referring to the user's past history storage settings when saving history. The history storage unit, for example, optimizes the storage method by referring to the user's past history storage settings. For example, the history storage unit suggests an optimal storage method based on the user's past history storage settings. The history storage unit can also adjust the storage format based on the user's past history storage settings. The history storage unit can also analyze the user's past history storage settings and optimize the storage priority. In this way, the storage method can be optimized by referring to the user's past history storage settings. Some or all of the above-described processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the user's past history storage settings using a generation AI and optimize the storage method.

[0114] The history storage unit can analyze the user's emotions and adjust the display method of the history based on the analyzed user's emotions. The history storage unit, for example, estimates the user's emotions and adjusts the display method of the history based on the estimated user's emotions. For example, the history storage unit can display a detailed history when the user is excited. The history storage unit can also display a concise history when the user is relaxed. The history storage unit can also display a visually easy-to-understand history when the user is nervous. This enables more appropriate history display by adjusting the display method of the history according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the history storage unit may be performed using AI, or may be performed without AI. For example, the history storage unit can adjust the display method of the history based on the user's emotions estimated by the generation AI.

[0115] The history storage unit can determine the priority of storage based on the submission time of the conversation when saving the history. The history storage unit determines the priority of storage based on, for example, the submission time of the conversation. For example, the history storage unit prioritizes saving the most recent conversation. The history storage unit can also postpone conversations that were submitted earlier. The history storage unit can also automatically adjust the order of storage based on the submission time. In this way, by determining the priority of storage based on the submission time of the conversation, the most recent conversation can be prioritized for saving. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the submission time of the conversation using a generation AI and determine the priority of storage.

[0116] The history storage unit can adjust the order of saving based on the relevance of the conversations when saving the history. For example, the history storage unit prioritizes saving highly relevant conversations. For example, the history storage unit postpones less relevant conversations. The history storage unit can also automatically adjust the order of saving based on the relevance of the conversations. In this way, by adjusting the order of saving based on the relevance of the conversations, highly relevant conversations can be saved preferentially. Some or all of the above-mentioned processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the relevance of the conversations using a generation AI and adjust the order of saving.

[0117] The history storage unit can adjust the storage format according to the user's level of expertise when saving history. For example, if the user has specialized knowledge, the history storage unit uses a detailed storage format. For example, if the user has general knowledge, the history storage unit uses a simple storage format. The history storage unit can also automatically adjust the storage format according to the user's level of expertise. This allows for more appropriate history storage by adjusting the storage format according to the user's level of expertise. Some or all of the above-described processing in the history storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the history storage unit can analyze the user's level of expertise using a generating AI and adjust the storage format.

[0118] The history analysis unit can analyze the user's emotions and adjust the accuracy of the analysis based on the analyzed user's emotions. The history analysis unit, for example, estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user's emotions. For example, the history analysis unit sets the analysis accuracy high when the user is excited. The history analysis unit can also set the analysis accuracy to medium when the user is relaxed. The history analysis unit can also set the analysis accuracy to low when the user is nervous. This allows for adjusting the analysis accuracy according to the user's emotions to obtain more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the history analysis unit can be performed using AI, for example, or without AI. For example, the history analysis unit can adjust the analysis accuracy based on the user's emotions estimated by the generation AI.

[0119] During history analysis, the history analysis unit can optimize the current analysis by referring to past history data. The history analysis unit, for example, optimizes the current analysis by referring to past history data. For example, the history analysis unit improves the accuracy of analysis for a specific topic based on past history data. The history analysis unit can also learn frequently used expressions from past history data to improve the accuracy of analysis. The history analysis unit can also analyze past history data to improve the accuracy of understanding context. In this way, the current analysis can be optimized by referring to past history data. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can optimize the current analysis by referring to past history data using generation AI.

[0120] The history analysis unit can apply different analysis methods to different conversation categories during history analysis. For example, in the case of technical conversation, the history analysis unit applies a specialized analysis method. For example, in the case of casual conversation, the history analysis unit can apply a general analysis method. Furthermore, in the case of business conversation, the history analysis unit can also apply a formal analysis method. In this way, by applying different analysis methods to different conversation categories, more appropriate analysis results can be obtained. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the conversation category using a generation AI and apply different analysis methods.

[0121] The history analysis unit can perform the analysis taking into account the user's attribute information when analyzing the history. The history analysis unit performs the analysis taking into account, for example, the user's age and gender. For example, the history analysis unit performs the analysis taking into account the user's occupation and hobbies. The history analysis unit can also perform the analysis taking into account the user's past behavioral patterns. In this way, by taking into account the user's attribute information, more appropriate analysis results can be obtained. Some or all of the above-mentioned processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the user's attribute information using a generation AI and perform the analysis.

[0122] The history analysis unit can analyze the user's emotions and adjust the display method of the analysis results based on the analyzed user's emotions. The history analysis unit, for example, estimates the user's emotions and adjusts the display method of the analysis results based on the estimated user's emotions. For example, the history analysis unit can display detailed analysis results when the user is excited. The history analysis unit can also display concise analysis results when the user is relaxed. The history analysis unit can also display visually easy-to-understand analysis results when the user is nervous. This enables more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the history analysis unit may be performed using AI, or may be performed without AI. For example, the history analysis unit can adjust the display method of the analysis results based on the user's emotions estimated by the generation AI.

[0123] During history analysis, the history analysis unit can determine the priority of analysis based on the time when the conversation was submitted. The history analysis unit determines the priority of analysis based on, for example, the time when the conversation was submitted. For example, the history analysis unit prioritizes analysis of the most recent conversation. The history analysis unit can also postpone conversations that were submitted earlier. The history analysis unit can also automatically adjust the order of analysis based on the time of submission. In this way, by determining the priority of analysis based on the time when the conversation was submitted, it is possible to prioritize analysis of the most recent conversation. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the time when the conversation was submitted using a generation AI and determine the priority of analysis.

[0124] During history analysis, the history analysis unit can perform analysis by referring to market data related to the conversation. The history analysis unit, for example, performs analysis by referring to the related market data. For example, the history analysis unit improves the accuracy of analysis on a specific topic based on the related market data. The history analysis unit can also learn frequently used expressions from the related market data to improve the accuracy of analysis. The history analysis unit can also analyze the related market data to improve the accuracy of understanding the context. As a result, more appropriate analysis results can be obtained by referring to the market data related to the conversation. Some or all of the above-described processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can perform analysis by referring to the related market data using a generation AI.

[0125] The history analysis unit can perform the analysis taking into account the technical maturity of the conversation when analyzing the history. The history analysis unit performs the analysis taking into account, for example, the technical maturity of the conversation. For example, the history analysis unit performs a detailed analysis in the case of a technically mature conversation. The history analysis unit can also perform a brief analysis in the case of a technically immature conversation. The history analysis unit can also automatically adjust the accuracy of the analysis based on the technical maturity. In this way, more appropriate analysis results can be obtained by taking the technical maturity of the conversation into account. Some or all of the above-mentioned processing in the history analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the history analysis unit can analyze the technical maturity of the conversation using a generation AI and perform the analysis.

[0126] The staff screen display unit can analyze the user's emotions and adjust the screen display method based on the analyzed user's emotions. The staff screen display unit, for example, estimates the user's emotions and adjusts the screen display method based on the estimated user's emotions. For example, the staff screen display unit can display detailed information when the user is excited. The staff screen display unit can also display concise information when the user is relaxed. The staff screen display unit can also display visually easy-to-understand information when the user is nervous. This allows for more appropriate display by adjusting the screen display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the staff screen display unit can be performed using, for example, AI, or without AI. For example, the staff screen display unit can adjust the screen display method based on the user's emotions estimated by the generation AI.

[0127] When displaying the screen, the staff screen display unit can select the optimal display method by referring to the user's past operation history. The staff screen display unit, for example, selects the optimal display method by referring to the user's past operation history. For example, the staff screen display unit suggests the optimal display method based on the user's past operation history. The staff screen display unit can also adjust the display format based on the user's past operation history. The staff screen display unit can also analyze the user's past operation history and optimize display priorities. This makes it possible to select the optimal display method by referring to the user's past operation history. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's past operation history using a generation AI and select the optimal display method.

[0128] The staff screen display unit can customize the display content according to the user's current task when displaying the screen. The staff screen display unit customizes the display content according to, for example, the user's current task. For example, the staff screen display unit prioritizes displaying information related to the user's current task. The staff screen display unit can also simplify the display content according to the user's current task. The staff screen display unit can also automatically display necessary information based on the user's current task. This allows for more appropriate display by customizing the display content according to the user's current task. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's current task using a generation AI and customize the display content.

[0129] The staff screen display unit can select the optimal display method when displaying the screen, taking into account the user's device information. For example, the staff screen display unit selects the optimal display method by taking into account the user's device information. For example, if the user is using a smartphone, the staff screen display unit can provide a display method tailored to the screen size. Furthermore, if the user is using a tablet, the staff screen display unit can also provide a display method optimized for a large screen. Furthermore, if the user is using a smartwatch, the staff screen display unit can also provide a simple, highly visible display method. This enables more appropriate display by selecting the optimal display method based on the user's device information. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's device information using a generation AI and select the optimal display method.

[0130] The staff screen display unit can analyze the user's emotions and adjust the screen display operation procedures based on the analyzed user's emotions. The staff screen display unit, for example, estimates the user's emotions and adjusts the screen display operation procedures based on the estimated user's emotions. For example, the staff screen display unit can display detailed operation procedures when the user is excited. The staff screen display unit can also display concise operation procedures when the user is relaxed. The staff screen display unit can also display visually easy-to-understand operation procedures when the user is nervous. This enables more appropriate operation by adjusting the screen display operation procedures according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the staff screen display unit can be performed using, for example, AI, or without AI. For example, the staff screen display unit can adjust the screen display operation procedures based on the user's emotions estimated by the generation AI.

[0131] The staff screen display unit can make the display content multilingual when displaying the screen according to the user's language setting. The staff screen display unit automatically sets the display content based on, for example, the language setting of the user's device. For example, the staff screen display unit provides a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the staff screen display unit can also provide the display content in that language. This enables more appropriate display by making the display content multilingual based on the user's language setting. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's language setting using a generation AI and make the display content multilingual.

[0132] The staff screen display unit can be customized based on the user's occupation and lifestyle when displaying the screen. The staff screen display unit, for example, prioritizes displaying information related to the user's occupation. For example, the staff screen display unit customizes the display content based on the user's lifestyle. The staff screen display unit can also adjust the display format according to the user's occupation and lifestyle. This enables more appropriate display by customizing the display content based on the user's occupation and lifestyle. Some or all of the above-described processing in the staff screen display unit may be performed using, for example, AI, or may be performed without using AI. For example, the staff screen display unit can analyze the user's occupation and lifestyle using a generation AI and customize the display content.

[0133] The staff screen display unit can improve the display method by reflecting user feedback when displaying the screen. The staff screen display unit improves the display method, for example, based on user feedback. For example, the staff screen display unit adjusts the display format based on user feedback. The staff screen display unit can also analyze user feedback and optimize display priorities. This allows the display method to be improved by reflecting user feedback. Some or all of the above-mentioned processing in the staff screen display unit may be performed using AI, for example, or may be performed without using AI. For example, the staff screen display unit can analyze user feedback using generation AI and improve the display method. === Hard Collateral 1-1 === Each of the multiple elements, including the recording unit, analysis unit, suggestion unit, history storage unit, history analysis unit, and staff screen display unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the recording unit records a conversation with a customer using the microphone 38B of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the recorded voice data. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and suggests an appropriate answer based on the analysis results. The history storage unit stores the conversation history in the database 24 of the data processing device 12. The history analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the stored history. The staff screen display unit displays the suggested answer on the display 40A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the recording unit, analysis unit, suggestion unit, history storage unit, history analysis unit, and staff screen display unit described above, is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the recording unit records a conversation with a customer using the microphone 238 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the recorded voice data. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and suggests an appropriate answer based on the analysis result. The history storage unit stores the conversation history in the database 24 of the data processing device 12. The history analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the stored history. The staff screen display unit displays the suggested answer on the display of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements, including the recording unit, analysis unit, suggestion unit, history storage unit, history analysis unit, and staff screen display unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the recording unit records a conversation with a customer using the microphone 238 of the headset terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the recorded voice data. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and suggests an appropriate answer based on the analysis results. The history storage unit stores the conversation history in the database 24 of the data processing device 12. The history analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the stored history. The staff screen display unit displays the suggested answer on the display 343 of the headset terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the recording unit, analysis unit, suggestion unit, history storage unit, history analysis unit, and staff screen display unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the recording unit records a conversation with a customer using the microphone 238 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the recorded voice data. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and suggests an appropriate answer based on the analysis result. The history storage unit saves the conversation history in the database 24 of the data processing device 12. The history analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the saved history. The staff screen display unit displays the suggested answer on the display of the robot 414.

[0134] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0135] The real-time conversation assistance tool may further include a tone adjustment unit that estimates the user's emotions and adjusts the tone of the conversation based on the estimated emotions. For example, if the user is angry, the tone adjustment unit may suggest a calm and subdued tone. If the user is sad, the tone adjustment unit may suggest a gentle tone. Furthermore, if the user is excited, the tone adjustment unit may suggest an energetic tone. This makes it possible to respond with an appropriate tone according to the user's emotions, thereby improving customer satisfaction.

[0136] The real-time conversation assistance tool can also be equipped with a resource provider that automatically searches for relevant materials and documents based on the content of the conversation and provides them to staff. For example, if a customer asks about a specific product, the resource provider can automatically search for and provide the product's manual or FAQ. If a customer asks about the contents of a contract, the resource provider can provide the relevant contract or terms and conditions. Furthermore, if a customer asks about a technical issue, the resource provider can provide technical support documents. This allows staff to answer customers' questions quickly and accurately.

[0137] The real-time conversation assistance tool may further include a progress adjustment unit that estimates the user's emotions and adjusts the progress of the conversation based on the estimated emotions. For example, if the user is impatient, the progress adjustment unit may suggest that the conversation proceed slowly. Also, if the user is relaxed, the progress adjustment unit may suggest that the conversation proceed smoothly. Furthermore, if the user is confused, the progress adjustment unit may suggest that the conversation be organized and proceed in an easy-to-understand manner. This makes it possible to appropriately progress the conversation according to the user's emotions, thereby improving customer satisfaction.

[0138] The real-time conversation assistance tool may further include a video providing unit that automatically searches for relevant videos and tutorials based on the content of the conversation and provides them to staff. For example, if a customer asks about how to use a product, the video providing unit may automatically search for and provide a video that explains how to use that product. Also, if a customer asks about settings, the video providing unit may provide a tutorial video that explains how to set up the product. Furthermore, if a customer asks about troubleshooting, the video providing unit may provide a troubleshooting video. This allows staff to answer customers' questions in a visually easy-to-understand manner.

[0139] The real-time conversation assistance tool may further include a summarization unit that estimates the user's emotions and summarizes the content of the conversation based on the estimated emotions. For example, if the user is tired, the summarization unit may provide a concise summary of the content of the conversation. If the user is concentrating, the summarization unit may also provide a detailed summary. Furthermore, if the user is confused, the summarization unit may also provide a summary that highlights the important points of the conversation. This enables an appropriate summary according to the user's emotions, thereby improving customer satisfaction.

[0140] The real-time conversation assistance tool may further include a data providing unit that automatically generates relevant statistical data and graphs based on the content of the conversation and provides them to the staff. For example, if a customer asks about product sales data, the data providing unit automatically generates and provides sales data for that product. Also, if a customer asks about market trends, the data providing unit may provide a graph showing market trends. Furthermore, if a customer asks about customer satisfaction, the data providing unit may provide statistical data on customer satisfaction. This allows the staff to provide accurate information based on data.

[0141] The real-time conversation assistance tool may further include a follow-up suggestion unit that estimates the user's emotions and suggests follow-up to the conversation based on the estimated emotions. For example, if the user is dissatisfied, the follow-up suggestion unit may suggest additional support. If the user is satisfied, the follow-up suggestion unit may also suggest a thank-you message. Furthermore, if the user has a question, the follow-up suggestion unit may also suggest a detailed explanation. This enables appropriate follow-up according to the user's emotions, thereby improving customer satisfaction.

[0142] The real-time conversation assistance tool can also be equipped with a news section that automatically searches for relevant news articles and blogs based on the content of the conversation and provides them to staff. For example, if a customer asks about trends in a particular industry, the news section can automatically search for and provide the latest news articles related to that industry. If a customer asks about a new product, the news section can also provide blog articles about that new product. Furthermore, if a customer asks about market trends, the news section can provide articles about market trends. This allows staff to answer customer questions based on the most up-to-date information.

[0143] The real-time conversation assistance tool may further include a feedback providing unit that estimates the user's emotions and provides conversation feedback based on the estimated emotions. For example, if the user is satisfied, the feedback providing unit provides positive feedback. If the user is dissatisfied, the feedback providing unit may also suggest improvements. Furthermore, if the user has neutral emotions, the feedback providing unit may also suggest improvements for the next time. This makes it possible to provide appropriate feedback according to the user's emotions, thereby improving customer satisfaction.

[0144] The real-time conversation assistance tool may further include an event provider that automatically searches for relevant events and seminars based on the content of the conversation and provides them to staff. For example, if a customer asks about a specific technology, the event provider automatically searches for and provides seminars related to that technology. Also, if a customer asks about industry trends, the event provider can provide events related to that industry. Furthermore, if a customer asks about a new product, the event provider can provide exhibitions related to that new product. This allows staff to provide relevant event information to the customer.

[0145] The processing flow of the second embodiment will be briefly explained below.

[0146] Step 1: The recording unit records conversations with customers. Conversations with customers can include phone calls, chats, and face-to-face conversations. The recording unit automatically starts recording when the conversation begins and can improve the quality of the recording using noise-canceling technology. For example, the recording unit can analyze the surrounding environmental sounds and remove noise. Step 2: The analysis unit uses the generative AI to analyze the audio data recorded by the recording unit. Analysis is carried out using speech recognition technology and natural language processing technology, converting the audio data into text data and understanding the content of the conversation. Contextual and semantic analysis is also performed to understand the context of the conversation. Step 3: The suggestion unit uses the generation AI to propose an appropriate answer based on the analysis results obtained by the analysis unit. The suggestion is made using a suggestion algorithm to propose the best answer to the customer's question. The proposed answer is displayed on the staff's screen so that they can check it. Step 4: The history storage unit saves the responses suggested by the suggestion unit and the conversation history. The history is saved in text or audio format, and the saved history can be referenced later. For example, the history storage unit has a function to search and reference the contents of past conversations.

[0147] 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.

[0148] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0149] 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.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0177] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0183] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0194] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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).

[0204] 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.

[0205] 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."

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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, to avoid confusion and 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.

[0217] 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.

[0218] [Explanation of symbols]

[0219] 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 voice data recorded by the recording unit; a suggestion unit that proposes an answer based on the analysis result obtained by the analysis unit; a history storage unit that stores the history of the answers and conversations proposed by the suggestion unit. A system characterized by:

2. The history storage unit Save your conversation history 2. The system of claim 1.

3. A history analysis unit that analyzes the conversation history stored by the history storage unit 2. The system of claim 1.

4. a staff screen display unit that displays the answer proposed by the suggestion unit on the staff screen; 2. The system of claim 1.

5. The analysis unit Understand the content of the conversation and suggest appropriate responses 2. The system of claim 1.

6. The proposal unit Suggest answers to customer questions 2. The system of claim 1.

7. The recording unit Analyzes the user's emotions and adjusts the start timing of recording based on the analyzed user's emotions.

2. The system of claim 1.

8. The recording unit Add a filtering function to automatically remove background noise when recording.

2. The system of claim 1.

9. The recording unit When recording, adjust the recording quality based on the importance of the conversation 2. The system of claim 1.

10. The recording unit Add a function to record audio from multiple audio input sources.

2. The system of claim 1.

Images