system

Abstract

The system according to the embodiment aims to accurately summarize the content of inquiries from customers and store them as a history. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a storage unit. The reception unit inputs the content of an inquiry from a customer. The analysis unit analyzes the content of the inquiry input by the reception unit and extracts important keywords and phrases. The generation unit generates a summary based on the keywords and phrases extracted by the analysis unit. The storage unit saves the summary generated by the generation unit as a history.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately summarize customer inquiries accurately and store them as a history, so there is room for improvement.

[0005] The system according to the embodiment aims to accurately summarize the content of inquiries from customers and store them as a history. [Means for solving the problem]

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a storage unit. The reception unit receives the content of customer inquiries. The analysis unit analyzes the inquiry content received by the reception unit and extracts important keywords and phrases. The generation unit generates a summary based on the keywords and phrases extracted by the analysis unit. The storage unit saves the summaries generated by the generation unit as history. [Effects of the Invention]

[0007] The system according to this embodiment can accurately summarize customer inquiries and save them as a history. [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) The inquiry history management system according to an embodiment of the present invention uses AI to automatically summarize customer inquiries and save the history as text. This system allows different crew members to review the previous history when the same customer contacts the system again. While crew members currently manually record the history, using AI allows for more accurate summarization and reduces crew work time. For example, the inquiry history management system receives a customer's inquiry. Next, AI analyzes the content using natural language processing technology and extracts important keywords and phrases. Based on the extracted keywords and phrases, the AI ​​generates a summary. The AI ​​then uses a pre-trained model to optimize the length and content of the summary. The generated summary is saved as a history for crew members to review. This system allows crew members to quickly understand past inquiries and respond appropriately. For example, if a customer inquires about "I don't know how to use a product," the AI ​​summarizes the content as "Inquiry about product usage" and saves it as a history. The next time the same customer contacts the system and says, "This is a continuation of my previous inquiry," the crew can review the previous history and respond smoothly. This system improves crew efficiency and the quality of customer service. AI-generated summaries are also consistent, making it easier for crew members to share information. It also contributes to reducing work time by eliminating the need for crew members to manually record history. As a result, the inquiry history management system efficiently summarizes customer inquiries and stores them as history, improving crew efficiency.

[0029] The inquiry history management system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a storage unit. The reception unit inputs the content of customer inquiries. Customer inquiries include, but are not limited to, technical questions, product inquiries, and support requests. The reception unit can receive inquiries by methods such as voice input, text input, and image input. The analysis unit analyzes the inquiry content input by the reception unit using natural language processing technology and extracts important keywords and phrases. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit, for example, divides the inquiry content into word units using morphological analysis, analyzes the sentence structure using grammatical analysis, and understands the meaning of the sentences using semantic analysis. The generation unit generates a summary based on the keywords and phrases extracted by the analysis unit using a pre-trained model. The pre-trained model includes, for example, a machine learning model and a deep learning model. The generation unit optimizes the length and content of the summary using a machine learning model and improves the accuracy of the summary using a deep learning model. The storage unit saves the summaries generated by the generation unit as history, making them available for crew members to review. The storage unit can, for example, save the summaries in a database, allowing crew members to search the history as needed. The storage unit can set the storage period and storage format. For example, the storage unit can save the summaries in text format and set the storage period to one year. As a result, the inquiry history management system according to this embodiment improves the efficiency of crew members' work by efficiently summarizing customer inquiries and saving them as history.

[0030] The analysis unit can analyze the query content using natural language processing (NLP) techniques. These techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. For instance, the analysis unit might use morphological analysis to divide the query content into words, grammatical analysis to analyze the sentence structure, and semantic analysis to understand the meaning of the sentence. For example, morphological analysis is a technique that divides a sentence into words and identifies the part of speech of each word. Grammatical analysis is a technique that analyzes the sentence structure and identifies sentence elements such as subject, predicate, and object. Semantic analysis is a technique that understands the meaning of a sentence and extracts important keywords and phrases from it. This improves the accuracy of query analysis by using natural language processing techniques. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the query content into an AI, which can then perform morphological analysis, grammatical analysis, and semantic analysis to extract important keywords and phrases.

[0031] The generation unit can adjust the length and content of the summary using a pre-trained model. Examples of pre-trained models include machine learning models and deep learning models. For example, the generation unit can optimize the length and content of the summary using a machine learning model and improve the accuracy of the summary using a deep learning model. For instance, a machine learning model has an algorithm that learns from a large amount of data and optimizes the length and content of the summary. A deep learning model can generate more sophisticated summaries using a neural network. For example, the generation unit generates a summary based on the length of the text and the importance of the information to adjust the summary length. For example, the generation unit generates a summary based on important keywords and phrases to adjust the content. This optimizes the length and content of the summary by using a pre-trained model. Some or all of the above processing in the generation unit may be performed using AI, or without AI. For example, the generation unit can input a pre-trained model into an AI, which can then adjust the length and content of the summary.

[0032] The storage unit can store the generated summary as a history so that the crew can check it. The storage unit can, for example, store the summary in a database so that the crew can search the history as needed. The storage unit can set a storage period and a storage format. For example, the storage unit can store the summary in text format for a period of one year. For example, the storage unit can classify the summaries by category so that the crew can easily search the history of a specific category. The storage unit can, for example, store the summaries in chronological order so that the crew can check the content of past inquiries in chronological order. In this way, by storing the generated summary as a history, the crew can check the content of past inquiries. Some or all of the above-described processing in the storage unit can be performed, for example, using AI or without AI. For example, the storage unit can input the generated summary to AI, which can store the summary in a database so that the crew can search the history.

[0033] The analysis unit may use topic modeling or a text rank algorithm to extract important keywords and phrases. Topic modeling includes, for example, LDA (Latent Dirichlet Allocation). Text rank algorithms include, for example, graph-based ranking algorithms. The analysis unit may use, for example, LDA to classify the query content into topics and extract important keywords and phrases. The analysis unit may use, for example, a text rank algorithm to rank and extract important keywords and phrases from the query content. In this way, the use of topic modeling and a text rank algorithm improves the accuracy of extracting important keywords and phrases. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the query content into AI, which may then extract important keywords and phrases using topic modeling or a text rank algorithm.

[0034] The generation unit can learn using past inquiry history to improve the accuracy of the summary. For example, the generation unit uses the past inquiry history as a dataset to learn to improve the accuracy of the summary. For example, the generation unit learns an algorithm that optimizes the length and content of the summary based on the past inquiry history. For example, the generation unit uses the past inquiry history to evaluate the accuracy of the summary and improves the algorithm based on the feedback. In this way, the accuracy of the summary is improved by using the past inquiry history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the past inquiry history into AI and have the AI ​​learn to improve the accuracy of the summary.

[0035] The reception unit can refer to past inquiry history and select an appropriate reception method. The reception unit, for example, retrieves past inquiry history from a database and selects the optimal reception method. For example, the reception unit automatically displays inquiries that the user has frequently made in the past as candidates. The reception unit can also preferentially suggest reception methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest the reception method to be used during a specific time period based on the user's past inquiry history. In this way, the optimal reception method can be selected by referring to the past inquiry history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past inquiry history into AI, which then selects the optimal reception method.

[0036] The reception unit can filter inquiries based on the user's current situation and areas of interest when receiving the inquiries. For example, when a user inputs their current situation, the reception unit prioritizes receiving inquiries related to that situation. For example, if a user inputs "I'm in a hurry," the reception unit prioritizes receiving inquiries requiring a quick response. The reception unit can also filter related inquiries based on the user's areas of interest and prioritize receiving them. For example, if a user inputs that they are interested in "technical questions," the reception unit prioritizes receiving technical inquiries. Furthermore, when a user is in a specific situation, the reception unit can filter according to the situation and receive the most appropriate inquiries. For example, if a user inputs "I'm traveling," the reception unit prioritizes receiving travel-related inquiries. This allows for filtering based on the user's current situation and areas of interest, thereby allowing for more appropriate inquiries to be received. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's current situation and areas of interest into AI, which then performs filtering.

[0037] When receiving an inquiry, the reception unit can prioritize receiving highly relevant inquiries by taking into account the user's geographical location information. The reception unit, for example, acquires the user's geographical location information from GPS data or an IP address and prioritizes receiving highly relevant inquiries. For example, if the user is in a specific area, the reception unit prioritizes receiving inquiries related to that area. The reception unit can also filter highly relevant inquiries based on the geographical location information and prioritize receiving them. For example, if the user is traveling, the reception unit prioritizes receiving inquiries related to the travel destination. Furthermore, if the user is traveling, the reception unit can prioritize receiving optimal inquiries based on the user's current location. For example, if the user searches for "nearby restaurants" while traveling, the reception unit provides optimal restaurant information based on the user's current location. In this way, highly relevant inquiries can be prioritized by taking the user's geographical location information into consideration. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information into AI, which can then prioritize receiving highly relevant inquiries.

[0038] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. The reception unit, for example, analyzes the user's social media activity and prioritizes receiving related inquiries. For example, the reception unit filters and receives related inquiries based on the user's social media mentions. The reception unit can also prioritize receiving inquiries of high interest from the user's social media activity. For example, if the user expresses interest in a "new gadget" on social media, the reception unit prioritizes receiving inquiries related to that gadget. The reception unit can also determine the priority of inquiries based on the user's social media activity. For example, if the user mentions "urgent" on social media, the reception unit prioritizes receiving inquiries related to that gadget. In this way, by analyzing the user's social media activity, related inquiries can be prioritized. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data into AI, and the AI ​​can prioritize receiving related inquiries.

[0039] The analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry content during analysis. For example, the analysis unit evaluates the importance of the inquiry content and performs a detailed analysis on inquiry content with high importance. For example, the analysis unit evaluates the importance of the inquiry content based on urgency and impact and performs a detailed analysis on inquiry content with high importance. The analysis unit can also perform a simplified analysis on inquiry content with low importance. For example, the analysis unit performs only a basic analysis on inquiry content with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance. For example, the analysis unit adjusts the level of detail of the analysis in real time according to changes in the importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the inquiry content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the importance of the inquiry content to AI, and the AI ​​can adjust the level of detail of the analysis based on the importance.

[0040] The analysis unit can apply different analysis algorithms depending on the category of the inquiry during analysis. For example, the analysis unit can classify the category of the inquiry and apply the most suitable analysis algorithm according to the category. For example, the analysis unit can apply a specialized analysis algorithm to technical inquiries. It can also apply a general-purpose analysis algorithm to general inquiries. Furthermore, the analysis unit can select and apply the most suitable analysis algorithm according to the category of the inquiry. For example, the analysis unit can classify the inquiry into categories such as technical questions, product inquiries, and support requests, and apply an analysis algorithm appropriate for each. This improves the accuracy of the analysis by applying the most suitable analysis algorithm according to the category of the inquiry. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the inquiry into the AI, and the AI ​​can apply the most suitable analysis algorithm according to the category.

[0041] The analysis unit can determine the priority of analysis based on the submission date of the inquiry during the analysis process. For example, the analysis unit can evaluate the submission date of the inquiry and set a lower priority for older inquiries. For example, the analysis unit can evaluate the submission date based on the submission date and time elapsed since submission and set a lower priority for older inquiries. The analysis unit can also set a higher priority for newer inquiries. For example, the analysis unit sets a higher priority for newer inquiries to ensure a quick response. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the submission date. For example, the analysis unit adjusts the analysis priority in real time in response to changes in the submission date. This enables efficient analysis by determining the analysis priority based on the submission date of the inquiry. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the submission date of the inquiry into the AI, and the AI ​​can determine the analysis priority based on the submission date.

[0042] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the query content. For example, the analysis unit evaluates the relevance of the query content and prioritizes analysis of highly relevant query content. For example, the analysis unit evaluates the relevance based on content similarity or related topics and prioritizes analysis of highly relevant content. The analysis unit can also postpone analysis of less relevant query content. For example, the analysis unit performs only basic analysis on less relevant content. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the query content. For example, the analysis unit adjusts the order of analysis in real time in response to changes in relevance. This enables efficient analysis by adjusting the order of analysis based on the relevance of the query content. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the relevance of the query content to AI, and the AI ​​can adjust the order of analysis based on the relevance.

[0043] The generation unit can adjust the level of detail of the summary based on the importance of the inquiry content when generating a summary. For example, the generation unit evaluates the importance of the inquiry content and generates a detailed summary for the inquiry content with high importance. For example, the generation unit evaluates the importance of the inquiry content based on urgency and impact and generates a detailed summary for the inquiry content with high importance. The generation unit can also generate a simplified summary for the inquiry content with low importance. For example, the generation unit generates only a basic summary for the inquiry content with low importance. Furthermore, the generation unit can dynamically adjust the level of detail of the summary based on the importance. For example, the generation unit adjusts the level of detail of the summary in real time in response to changes in the importance. This enables efficient summarization by adjusting the level of detail of the summary based on the importance of the inquiry content. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the importance of the inquiry content to AI, and the AI ​​can adjust the level of detail of the summary based on the importance.

[0044] When generating a summary, the generation unit can apply different summarization algorithms depending on the category of the inquiry content. For example, the generation unit classifies the category of the inquiry content and applies the optimal summarization algorithm depending on the category. For example, the generation unit applies a specialized summarization algorithm to technical inquiry content. The generation unit can also apply a general-purpose summarization algorithm to general inquiry content. Furthermore, the generation unit can select and apply the optimal summarization algorithm depending on the category of the inquiry content. For example, the generation unit can classify the inquiry content into categories such as technical questions, product inquiries, and support requests, and apply the appropriate summarization algorithm for each category. This improves the accuracy of the summary by applying the optimal summarization algorithm depending on the category of the inquiry content. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of the inquiry content into AI, which can then apply the optimal summarization algorithm depending on the category.

[0045] The generation unit can determine the priority of summaries based on the submission date of the inquiry when generating summaries. For example, the generation unit can evaluate the submission date of the inquiry and set a lower priority for older inquiries. For example, the generation unit can evaluate the submission date based on the submission date and time elapsed since submission and set a lower priority for older inquiries. The generation unit can also set a higher priority for newer inquiries. For example, the generation unit sets a higher priority for newer inquiries to ensure a quick response. Furthermore, the generation unit can dynamically adjust the priority of summaries according to the submission date. For example, the generation unit adjusts the priority of summaries in real time in response to changes in the submission date. This enables efficient summarization by determining the priority of summaries based on the submission date of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input the submission date of the inquiry into the AI, and the AI ​​can determine the priority of summaries based on the submission date.

[0046] The generation unit can adjust the order of summaries based on the relevance of the inquiry content during summary generation. For example, the generation unit can evaluate the relevance of the inquiry content and prioritize generating summaries for highly relevant inquiries. For example, the generation unit can evaluate relevance based on similarity of content or related topics and prioritize generating summaries for highly relevant content. The generation unit can also postpone generating summaries for less relevant inquiries. For example, the generation unit can generate only a basic summary for less relevant content. Furthermore, the generation unit can dynamically adjust the order of summaries according to the relevance of the inquiry content. For example, the generation unit can adjust the order of summaries in real time in response to changes in relevance. This enables efficient summarization by adjusting the order of summaries based on the relevance of the inquiry content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the relevance of the inquiry content into the AI, and the AI ​​can adjust the order of summaries based on the relevance.

[0047] The storage unit can select an appropriate storage method by referring to past inquiry history when saving data. For example, the storage unit can retrieve past inquiry history from a database and select the optimal storage method. For example, the storage unit can analyze a user's past inquiry history and select the optimal storage format. The storage unit can also group and save relevant summaries based on past inquiry history. For example, the storage unit can classify relevant inquiry content by category, group them, and save them. Furthermore, the storage unit can determine the priority of summaries to save by referring to a user's past inquiry history. For example, the storage unit prioritizes saving summaries of high importance based on past inquiry history. This allows the storage unit to select the optimal storage method by referring to past inquiry history. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input past inquiry history into AI, which can then select the optimal storage method.

[0048] The storage unit can apply different storage algorithms depending on the category of the inquiry content when storing the data. The storage unit, for example, classifies the category of the inquiry content and applies an optimal storage algorithm depending on the category. For example, the storage unit applies a specialized storage algorithm to technical inquiry content. The storage unit can also apply a general-purpose storage algorithm to general inquiry content. Furthermore, the storage unit can select and apply an optimal storage algorithm depending on the category of the inquiry content. For example, the storage unit can classify the inquiry content into categories such as technical questions, product inquiries, and support requests, and apply an appropriate storage algorithm for each category. This improves storage accuracy by applying the optimal storage algorithm depending on the category of the inquiry content. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the category of the inquiry content into AI, which can then apply the optimal storage algorithm depending on the category.

[0049] The storage unit can save inquiry content while considering its geographical distribution. For example, the storage unit can obtain the user's geographical location information from GPS data or IP address and save relevant inquiry content by region. For example, the storage unit can save relevant inquiry content by region based on the user's geographical location information. The storage unit can also classify inquiry content based on geographical distribution and select the optimal storage method. For example, the storage unit can classify inquiry content based on the number of inquiries by region and geographical trends and select the optimal storage method. Furthermore, if the user is in a specific region, the storage unit can prioritize saving inquiry content related to that region. For example, if the user is in a specific region, the storage unit will prioritize saving inquiry content related to that region. This allows for the priority saving of highly relevant content by considering the geographical distribution of inquiry content. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the user's geographical location information into AI, and the AI ​​can save highly relevant inquiry content by region.

[0050] The storage unit can improve the accuracy of saving by referring to related literature for the query content during the saving process. For example, the storage unit can optimize the saving format of the query content by referring to related literature. For example, the storage unit can improve the accuracy of saving by supplementing the summary of the query content based on related literature. The storage unit can also classify the query content by referring to related literature and select the optimal saving method. For example, the storage unit can classify the query content by category based on related literature and select a suitable saving method for each. This improves the accuracy of saving by referring to related literature. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input related literature into AI, and the AI ​​can improve the accuracy of saving based on the related literature.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The reception unit can predict the content of an inquiry based on the user's past inquiry history and adjust the reception method based on the predicted content. For example, the reception unit can analyze the content of inquiries frequently made by the user in the past and predict the content of the next inquiry. The reception unit can also extract specific patterns from the user's past inquiry history and adjust the reception method based on the predicted content. Furthermore, the reception unit can predict and suggest the reception method to be used during a specific time period based on the user's past inquiry history. This makes it possible to select a more appropriate reception method by referring to the past inquiry history.

[0053] When analyzing the content of an inquiry, the analysis unit can determine the priority of the analysis based on the user's current situation and areas of interest. For example, when the user inputs their current situation, the analysis unit prioritizes the analysis of inquiry content related to that situation. The analysis unit can also prioritize the analysis of related inquiry content based on the user's areas of interest. Furthermore, when the user is in a specific situation, the analysis unit can perform analysis according to that situation and provide optimal analysis results. This enables more appropriate analysis by determining the priority of the analysis based on the user's current situation and areas of interest.

[0054] When generating a summary, the generator can refer to the user's past inquiry history to improve the accuracy of the summary. For example, the generator can use the past inquiry history as a dataset to perform learning to improve the accuracy of the summary. The generator can also learn an algorithm to optimize the length and content of the summary based on the past inquiry history. Furthermore, the generator can use the past inquiry history to evaluate the accuracy of the summary and improve the algorithm based on feedback. In this way, the accuracy of the summary can be improved by referring to the past inquiry history.

[0055] The storage unit can determine the priority of storage based on the importance of the inquiry content when saving. For example, the storage unit evaluates the urgency and impact of the inquiry content and prioritizes saving of the inquiry content with high importance. The storage unit can also apply a simpler storage method to inquiry content with low importance. Furthermore, the storage unit can dynamically adjust the priority of storage according to the importance. This allows for efficient storage by determining the priority of storage based on the importance of the inquiry content.

[0056] The storage unit can adjust the order of storage based on the relevance of the inquiry content when storing. For example, the storage unit evaluates the relevance based on the similarity of the inquiry content or related topics, and stores highly relevant content preferentially. The storage unit can also postpone storing less relevant inquiry content. Furthermore, the storage unit can dynamically adjust the order of storage according to the relevance of the inquiry content. This allows for efficient storage by adjusting the order of storage based on the relevance of the inquiry content.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The reception unit inputs the customer's inquiry. Inquiries include technical questions, product inquiries, and support requests. The reception unit can accept inquiries by voice input, text input, image input, and other methods. Step 2: The analysis unit uses natural language processing technology to analyze the inquiry entered by the reception unit and extract important keywords and phrases. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. The analysis unit uses morphological analysis to divide the inquiry into words, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of the sentence. Step 3: The generator uses a pre-trained model to generate a summary based on the keywords and phrases extracted by the analyzer. Pre-trained models include machine learning models and deep learning models. The generator uses the machine learning model to optimize the length and content of the summary, and the deep learning model to improve the accuracy of the summary. Step 4: The storage unit stores the summary generated by the generation unit as a history so that the crew can check it. The storage unit stores the summary in a database so that the crew can search the history as needed. The storage unit can set the storage period and storage format. For example, the summary can be stored in text format for one year.

[0059] (Example 2) The inquiry history management system according to an embodiment of the present invention uses AI to automatically summarize customer inquiries and save the history as text. This system allows different crew members to review the previous history when the same customer contacts the system again. While crew members currently manually record the history, using AI allows for more accurate summarization and reduces crew work time. For example, the inquiry history management system receives a customer's inquiry. Next, AI analyzes the content using natural language processing technology and extracts important keywords and phrases. Based on the extracted keywords and phrases, the AI ​​generates a summary. The AI ​​then uses a pre-trained model to optimize the length and content of the summary. The generated summary is saved as a history for crew members to review. This system allows crew members to quickly understand past inquiries and respond appropriately. For example, if a customer inquires about "I don't know how to use a product," the AI ​​summarizes the content as "Inquiry about product usage" and saves it as a history. The next time the same customer contacts the system and says, "This is a continuation of my previous inquiry," the crew can review the previous history and respond smoothly. This system improves crew efficiency and the quality of customer service. AI-generated summaries are also consistent, making it easier for crew members to share information. It also contributes to reducing work time by eliminating the need for crew members to manually record history. As a result, the inquiry history management system efficiently summarizes customer inquiries and stores them as history, improving crew efficiency.

[0060] The inquiry history management system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a storage unit. The reception unit inputs the content of customer inquiries. Customer inquiries include, but are not limited to, technical questions, product inquiries, and support requests. The reception unit can receive inquiries by methods such as voice input, text input, and image input. The analysis unit analyzes the inquiry content input by the reception unit using natural language processing technology and extracts important keywords and phrases. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit, for example, divides the inquiry content into word units using morphological analysis, analyzes the sentence structure using grammatical analysis, and understands the meaning of the sentences using semantic analysis. The generation unit generates a summary based on the keywords and phrases extracted by the analysis unit using a pre-trained model. The pre-trained model includes, for example, a machine learning model and a deep learning model. The generation unit optimizes the length and content of the summary using a machine learning model and improves the accuracy of the summary using a deep learning model. The storage unit saves the summaries generated by the generation unit as history, making them available for crew members to review. The storage unit can, for example, save the summaries in a database, allowing crew members to search the history as needed. The storage unit can set the storage period and storage format. For example, the storage unit can save the summaries in text format and set the storage period to one year. As a result, the inquiry history management system according to this embodiment improves the efficiency of crew members' work by efficiently summarizing customer inquiries and saving them as history.

[0061] The analysis unit can analyze the query content using natural language processing (NLP) techniques. These techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. For instance, the analysis unit might use morphological analysis to divide the query content into words, grammatical analysis to analyze the sentence structure, and semantic analysis to understand the meaning of the sentence. For example, morphological analysis is a technique that divides a sentence into words and identifies the part of speech of each word. Grammatical analysis is a technique that analyzes the sentence structure and identifies sentence elements such as subject, predicate, and object. Semantic analysis is a technique that understands the meaning of a sentence and extracts important keywords and phrases from it. This improves the accuracy of query analysis by using natural language processing techniques. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the query content into an AI, which can then perform morphological analysis, grammatical analysis, and semantic analysis to extract important keywords and phrases.

[0062] The generation unit can adjust the length and content of the summary using a pre-trained model. Examples of pre-trained models include machine learning models and deep learning models. For example, the generation unit can optimize the length and content of the summary using a machine learning model and improve the accuracy of the summary using a deep learning model. For instance, a machine learning model has an algorithm that learns from a large amount of data and optimizes the length and content of the summary. A deep learning model can generate more sophisticated summaries using a neural network. For example, the generation unit generates a summary based on the length of the text and the importance of the information to adjust the summary length. For example, the generation unit generates a summary based on important keywords and phrases to adjust the content. This optimizes the length and content of the summary by using a pre-trained model. Some or all of the above processing in the generation unit may be performed using AI, or without AI. For example, the generation unit can input a pre-trained model into an AI, which can then adjust the length and content of the summary.

[0063] The storage unit can store the generated summary as a history so that the crew can check it. The storage unit can, for example, store the summary in a database so that the crew can search the history as needed. The storage unit can set a storage period and a storage format. For example, the storage unit can store the summary in text format for a period of one year. For example, the storage unit can classify the summaries by category so that the crew can easily search the history of a specific category. The storage unit can, for example, store the summaries in chronological order so that the crew can check the content of past inquiries in chronological order. In this way, by storing the generated summary as a history, the crew can check the content of past inquiries. Some or all of the above-described processing in the storage unit can be performed, for example, using AI or without AI. For example, the storage unit can input the generated summary to AI, which can store the summary in a database so that the crew can search the history.

[0064] The analysis unit may use topic modeling or a text rank algorithm to extract important keywords and phrases. Topic modeling includes, for example, LDA (Latent Dirichlet Allocation). Text rank algorithms include, for example, graph-based ranking algorithms. The analysis unit may use, for example, LDA to classify the query content into topics and extract important keywords and phrases. The analysis unit may use, for example, a text rank algorithm to rank and extract important keywords and phrases from the query content. In this way, the use of topic modeling and a text rank algorithm improves the accuracy of extracting important keywords and phrases. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the query content into AI, which may then extract important keywords and phrases using topic modeling or a text rank algorithm.

[0065] The generation unit can learn using past inquiry history to improve the accuracy of the summary. For example, the generation unit uses the past inquiry history as a dataset to learn to improve the accuracy of the summary. For example, the generation unit learns an algorithm that optimizes the length and content of the summary based on the past inquiry history. For example, the generation unit uses the past inquiry history to evaluate the accuracy of the summary and improves the algorithm based on the feedback. In this way, the accuracy of the summary is improved by using the past inquiry history. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the past inquiry history into AI and have the AI ​​learn to improve the accuracy of the summary.

[0066] The reception desk can estimate the user's emotions and adjust the way inquiries are handled based on those estimated emotions. For example, the reception desk can capture the user's facial expressions with a camera and estimate their emotions using an emotion analysis algorithm. For example, the reception desk can calculate an emotion score based on changes in facial expressions and adjust the handling method. The reception desk can also record the user's voice and estimate their emotions using voice analysis technology. For example, the reception desk can analyze the tone and speed of the voice, calculate an emotion score, and adjust the handling method. Furthermore, the reception desk can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion analysis algorithm. For example, the reception desk can calculate an emotion score based on fluctuations in heart rate and adjust the handling method. This allows for more appropriate responses by adjusting the handling method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes at the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input user emotion data into the AI, which can then estimate the emotion and adjust the reception method accordingly.

[0067] The reception unit can refer to past inquiry history and select an appropriate reception method. The reception unit, for example, retrieves past inquiry history from a database and selects the optimal reception method. For example, the reception unit automatically displays inquiries that the user has frequently made in the past as candidates. The reception unit can also preferentially suggest reception methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest the reception method to be used during a specific time period based on the user's past inquiry history. In this way, the optimal reception method can be selected by referring to the past inquiry history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input past inquiry history into AI, which then selects the optimal reception method.

[0068] The reception unit can filter inquiries based on the user's current situation and areas of interest when receiving the inquiries. For example, when a user inputs their current situation, the reception unit prioritizes receiving inquiries related to that situation. For example, if a user inputs "I'm in a hurry," the reception unit prioritizes receiving inquiries requiring a quick response. The reception unit can also filter related inquiries based on the user's areas of interest and prioritize receiving them. For example, if a user inputs that they are interested in "technical questions," the reception unit prioritizes receiving technical inquiries. Furthermore, when a user is in a specific situation, the reception unit can filter according to the situation and receive the most appropriate inquiries. For example, if a user inputs "I'm traveling," the reception unit prioritizes receiving travel-related inquiries. This allows for filtering based on the user's current situation and areas of interest, thereby allowing for more appropriate inquiries to be received. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's current situation and areas of interest into AI, which then performs filtering.

[0069] The reception unit can estimate the user's emotions and prioritize inquiries based on the estimated user emotions. For example, the reception unit captures the user's facial expressions with a camera and estimates the emotions using an emotion analysis algorithm. For example, the reception unit calculates an emotion score based on changes in facial expressions and prioritizes the inquiries. The reception unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice, calculates an emotion score, and prioritizes the inquiries. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion analysis algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations and prioritizes the inquiries. This enables more appropriate responses by prioritizing the inquiries based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative 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 reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input user emotion data into AI, which infers the emotion and determines the priority of the inquiry content.

[0070] When receiving an inquiry, the reception unit can prioritize receiving highly relevant inquiries by taking into account the user's geographical location information. The reception unit, for example, acquires the user's geographical location information from GPS data or an IP address and prioritizes receiving highly relevant inquiries. For example, if the user is in a specific area, the reception unit prioritizes receiving inquiries related to that area. The reception unit can also filter highly relevant inquiries based on the geographical location information and prioritize receiving them. For example, if the user is traveling, the reception unit prioritizes receiving inquiries related to the travel destination. Furthermore, if the user is traveling, the reception unit can prioritize receiving optimal inquiries based on the user's current location. For example, if the user searches for "nearby restaurants" while traveling, the reception unit provides optimal restaurant information based on the user's current location. In this way, highly relevant inquiries can be prioritized by taking the user's geographical location information into consideration. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information into AI, which can then prioritize receiving highly relevant inquiries.

[0071] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. The reception unit, for example, analyzes the user's social media activity and prioritizes receiving related inquiries. For example, the reception unit filters and receives related inquiries based on the user's social media mentions. The reception unit can also prioritize receiving inquiries of high interest from the user's social media activity. For example, if the user expresses interest in a "new gadget" on social media, the reception unit prioritizes receiving inquiries related to that gadget. The reception unit can also determine the priority of inquiries based on the user's social media activity. For example, if the user mentions "urgent" on social media, the reception unit prioritizes receiving inquiries related to that gadget. In this way, by analyzing the user's social media activity, related inquiries can be prioritized. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's social media activity data into AI, and the AI ​​can prioritize receiving related inquiries.

[0072] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using an emotion analysis algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expressions and adjusts the analysis method. The analysis unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the analysis method. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion analysis algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations and adjusts the analysis method. This enables more appropriate analysis by adjusting the analysis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative 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 analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data into AI, which may infer the emotion and adjust the analysis method.

[0073] The analysis unit can adjust the level of detail of the analysis based on the importance of the inquiry content during analysis. For example, the analysis unit evaluates the importance of the inquiry content and performs a detailed analysis on inquiry content with high importance. For example, the analysis unit evaluates the importance of the inquiry content based on urgency and impact and performs a detailed analysis on inquiry content with high importance. The analysis unit can also perform a simplified analysis on inquiry content with low importance. For example, the analysis unit performs only a basic analysis on inquiry content with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance. For example, the analysis unit adjusts the level of detail of the analysis in real time according to changes in the importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the inquiry content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the importance of the inquiry content to AI, and the AI ​​can adjust the level of detail of the analysis based on the importance.

[0074] The analysis unit can apply different analysis algorithms depending on the category of the inquiry during analysis. For example, the analysis unit can classify the category of the inquiry and apply the most suitable analysis algorithm according to the category. For example, the analysis unit can apply a specialized analysis algorithm to technical inquiries. It can also apply a general-purpose analysis algorithm to general inquiries. Furthermore, the analysis unit can select and apply the most suitable analysis algorithm according to the category of the inquiry. For example, the analysis unit can classify the inquiry into categories such as technical questions, product inquiries, and support requests, and apply an analysis algorithm appropriate for each. This improves the accuracy of the analysis by applying the most suitable analysis algorithm according to the category of the inquiry. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the inquiry into the AI, and the AI ​​can apply the most suitable analysis algorithm according to the category.

[0075] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate emotions using an emotion analysis algorithm. For example, the analysis unit can calculate an emotion score based on changes in facial expressions and determine the priority of analysis. The analysis unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the analysis unit can analyze the tone and speed of the voice, calculate an emotion score, and determine the priority of analysis. The analysis unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion analysis algorithm. For example, the analysis unit can calculate an emotion score based on fluctuations in heart rate and determine the priority of analysis. This allows for more appropriate responses by determining the priority of analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into AI, which can then estimate the emotion and determine the priority of the analysis.

[0076] The analysis unit can determine the priority of analysis based on the submission date of the inquiry during the analysis process. For example, the analysis unit can evaluate the submission date of the inquiry and set a lower priority for older inquiries. For example, the analysis unit can evaluate the submission date based on the submission date and time elapsed since submission and set a lower priority for older inquiries. The analysis unit can also set a higher priority for newer inquiries. For example, the analysis unit sets a higher priority for newer inquiries to ensure a quick response. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the submission date. For example, the analysis unit adjusts the analysis priority in real time in response to changes in the submission date. This enables efficient analysis by determining the analysis priority based on the submission date of the inquiry. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the submission date of the inquiry into the AI, and the AI ​​can determine the analysis priority based on the submission date.

[0077] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the query content. For example, the analysis unit evaluates the relevance of the query content and prioritizes analysis of highly relevant query content. For example, the analysis unit evaluates the relevance based on content similarity or related topics and prioritizes analysis of highly relevant content. The analysis unit can also postpone analysis of less relevant query content. For example, the analysis unit performs only basic analysis on less relevant content. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the query content. For example, the analysis unit adjusts the order of analysis in real time in response to changes in relevance. This enables efficient analysis by adjusting the order of analysis based on the relevance of the query content. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the relevance of the query content to AI, and the AI ​​can adjust the order of analysis based on the relevance.

[0078] The generation unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, the generation unit can capture the user's facial expressions with a camera and estimate emotions using an emotion analysis algorithm. For example, the generation unit can calculate an emotion score based on changes in facial expressions and adjust the way the summary is presented. The generation unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the generation unit can analyze the tone and speed of the voice, calculate an emotion score, and adjust the way the summary is presented. The generation unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion analysis algorithm. For example, the generation unit can calculate an emotion score based on fluctuations in heart rate and adjust the way the summary is presented. By adjusting the way the summary is presented based on the user's emotions, a more appropriate summary is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input user emotion data into AI, which may infer the emotion and adjust the way the summary is expressed.

[0079] The generation unit can adjust the level of detail of the summary based on the importance of the inquiry content when generating a summary. For example, the generation unit evaluates the importance of the inquiry content and generates a detailed summary for the inquiry content with high importance. For example, the generation unit evaluates the importance of the inquiry content based on urgency and impact and generates a detailed summary for the inquiry content with high importance. The generation unit can also generate a simplified summary for the inquiry content with low importance. For example, the generation unit generates only a basic summary for the inquiry content with low importance. Furthermore, the generation unit can dynamically adjust the level of detail of the summary based on the importance. For example, the generation unit adjusts the level of detail of the summary in real time in response to changes in the importance. This enables efficient summarization by adjusting the level of detail of the summary based on the importance of the inquiry content. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input the importance of the inquiry content to AI, and the AI ​​can adjust the level of detail of the summary based on the importance.

[0080] When generating a summary, the generation unit can apply different summarization algorithms depending on the category of the inquiry content. For example, the generation unit classifies the category of the inquiry content and applies the optimal summarization algorithm depending on the category. For example, the generation unit applies a specialized summarization algorithm to technical inquiry content. The generation unit can also apply a general-purpose summarization algorithm to general inquiry content. Furthermore, the generation unit can select and apply the optimal summarization algorithm depending on the category of the inquiry content. For example, the generation unit can classify the inquiry content into categories such as technical questions, product inquiries, and support requests, and apply the appropriate summarization algorithm for each category. This improves the accuracy of the summary by applying the optimal summarization algorithm depending on the category of the inquiry content. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of the inquiry content into AI, which can then apply the optimal summarization algorithm depending on the category.

[0081] The generation unit can estimate the user's emotions and adjust the length of the summary based on the estimated user emotions. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using an emotion analysis algorithm. For example, the generation unit calculates an emotion score based on changes in facial expressions and adjusts the length of the summary. The generation unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the summary. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the emotions using an emotion analysis algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations and adjusts the length of the summary. In this way, a more appropriate summary can be generated by adjusting the length of the summary based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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 processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user emotion data into AI, which can then estimate the emotion and adjust the length of the summary.

[0082] The generation unit can determine the priority of summaries based on the submission date of the inquiry when generating summaries. For example, the generation unit can evaluate the submission date of the inquiry and set a lower priority for older inquiries. For example, the generation unit can evaluate the submission date based on the submission date and time elapsed since submission and set a lower priority for older inquiries. The generation unit can also set a higher priority for newer inquiries. For example, the generation unit sets a higher priority for newer inquiries to ensure a quick response. Furthermore, the generation unit can dynamically adjust the priority of summaries according to the submission date. For example, the generation unit adjusts the priority of summaries in real time in response to changes in the submission date. This enables efficient summarization by determining the priority of summaries based on the submission date of the inquiry. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input the submission date of the inquiry into the AI, and the AI ​​can determine the priority of summaries based on the submission date.

[0083] The generation unit can adjust the order of summaries based on the relevance of the inquiry content during summary generation. For example, the generation unit can evaluate the relevance of the inquiry content and prioritize generating summaries for highly relevant inquiries. For example, the generation unit can evaluate relevance based on similarity of content or related topics and prioritize generating summaries for highly relevant content. The generation unit can also postpone generating summaries for less relevant inquiries. For example, the generation unit can generate only a basic summary for less relevant content. Furthermore, the generation unit can dynamically adjust the order of summaries according to the relevance of the inquiry content. For example, the generation unit can adjust the order of summaries in real time in response to changes in relevance. This enables efficient summarization by adjusting the order of summaries based on the relevance of the inquiry content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the relevance of the inquiry content into the AI, and the AI ​​can adjust the order of summaries based on the relevance.

[0084] The storage unit can estimate the user's emotions and determine the priority of summaries to be saved based on the estimated user emotions. For example, the storage unit captures the user's facial expressions with a camera and estimates the emotions using an emotion analysis algorithm. For example, the storage unit calculates an emotion score based on changes in facial expressions and determines the priority of summaries to be saved. The storage unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the storage unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of summaries to be saved. The storage unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion analysis algorithm. For example, the storage unit calculates an emotion score based on heart rate fluctuations and determines the priority of summaries to be saved. This enables more appropriate saving by determining the priority of summaries to be saved based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using AI, or may be performed without using AI. For example, the storage unit may input user emotion data into AI, which may infer the emotion and determine the priority of summaries to be stored.

[0085] The storage unit can select an appropriate storage method by referring to past inquiry history when saving data. For example, the storage unit can retrieve past inquiry history from a database and select the optimal storage method. For example, the storage unit can analyze a user's past inquiry history and select the optimal storage format. The storage unit can also group and save relevant summaries based on past inquiry history. For example, the storage unit can classify relevant inquiry content by category, group them, and save them. Furthermore, the storage unit can determine the priority of summaries to save by referring to a user's past inquiry history. For example, the storage unit prioritizes saving summaries of high importance based on past inquiry history. This allows the storage unit to select the optimal storage method by referring to past inquiry history. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input past inquiry history into AI, which can then select the optimal storage method.

[0086] The storage unit can apply different storage algorithms depending on the category of the inquiry content when storing the data. The storage unit, for example, classifies the category of the inquiry content and applies an optimal storage algorithm depending on the category. For example, the storage unit applies a specialized storage algorithm to technical inquiry content. The storage unit can also apply a general-purpose storage algorithm to general inquiry content. Furthermore, the storage unit can select and apply an optimal storage algorithm depending on the category of the inquiry content. For example, the storage unit can classify the inquiry content into categories such as technical questions, product inquiries, and support requests, and apply an appropriate storage algorithm for each category. This improves storage accuracy by applying the optimal storage algorithm depending on the category of the inquiry content. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the category of the inquiry content into AI, which can then apply the optimal storage algorithm depending on the category.

[0087] The storage unit can estimate the user's emotions and adjust the display method of the saved summary based on the estimated user emotions. For example, the storage unit can capture the user's facial expressions with a camera and estimate emotions using an emotion analysis algorithm. For example, the storage unit can calculate an emotion score based on changes in facial expressions and adjust the display method of the saved summary. The storage unit can also record the user's voice and estimate emotions using voice analysis technology. For example, the storage unit can analyze the tone and speed of the voice, calculate an emotion score, and adjust the display method of the saved summary. The storage unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion analysis algorithm. For example, the storage unit can calculate an emotion score based on fluctuations in heart rate and adjust the display method of the saved summary. By adjusting the display method of the saved summary based on the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generating AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the storage unit may be performed using AI, or not using AI. For example, the storage unit can input user sentiment data into the AI, which can estimate the sentiment and adjust how the saved summary is displayed.

[0088] The storage unit can save inquiry content while considering its geographical distribution. For example, the storage unit can obtain the user's geographical location information from GPS data or IP address and save relevant inquiry content by region. For example, the storage unit can save relevant inquiry content by region based on the user's geographical location information. The storage unit can also classify inquiry content based on geographical distribution and select the optimal storage method. For example, the storage unit can classify inquiry content based on the number of inquiries by region and geographical trends and select the optimal storage method. Furthermore, if the user is in a specific region, the storage unit can prioritize saving inquiry content related to that region. For example, if the user is in a specific region, the storage unit will prioritize saving inquiry content related to that region. This allows for the priority saving of highly relevant content by considering the geographical distribution of inquiry content. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the user's geographical location information into AI, and the AI ​​can save highly relevant inquiry content by region.

[0089] The storage unit can improve the accuracy of saving by referring to related literature for the query content during the saving process. For example, the storage unit can optimize the saving format of the query content by referring to related literature. For example, the storage unit can improve the accuracy of saving by supplementing the summary of the query content based on related literature. The storage unit can also classify the query content by referring to related literature and select the optimal saving method. For example, the storage unit can classify the query content by category based on related literature and select a suitable saving method for each. This improves the accuracy of saving by referring to related literature. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input related literature into AI, and the AI ​​can improve the accuracy of saving based on the related literature. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, and storage unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives voice input and text input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the inquiry content using natural language processing technology. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a summary using a pre-trained model. The storage unit stores the summary in the database 24 of the data processing device 12 so that the crew can review it. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, and storage unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives voice input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the inquiry content using natural language processing technology. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a summary using a pre-trained model. The storage unit stores the summary in the database 24 of the data processing device 12 so that the crew can review it. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and storage unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives voice input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the inquiry content using natural language processing technology. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a summary using a pre-trained model. The storage unit stores the summary in the database 24 of the data processing device 12 so that the crew can review it. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and storage unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives voice input. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the inquiry content using natural language processing technology. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a summary using a pre-trained model. The storage unit stores the summary in the database 24 of the data processing device 12 so that the crew can review it.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The reception unit can predict the content of an inquiry based on the user's past inquiry history and adjust the reception method based on the predicted content. For example, the reception unit can analyze the content of inquiries frequently made by the user in the past and predict the content of the next inquiry. The reception unit can also extract specific patterns from the user's past inquiry history and adjust the reception method based on the predicted content. Furthermore, the reception unit can predict and suggest the reception method to be used during a specific time period based on the user's past inquiry history. This makes it possible to select a more appropriate reception method by referring to the past inquiry history.

[0092] When analyzing the content of an inquiry, the analysis unit can determine the priority of the analysis based on the user's current situation and areas of interest. For example, when the user inputs their current situation, the analysis unit prioritizes the analysis of inquiry content related to that situation. The analysis unit can also prioritize the analysis of related inquiry content based on the user's areas of interest. Furthermore, when the user is in a specific situation, the analysis unit can perform analysis according to that situation and provide optimal analysis results. This enables more appropriate analysis by determining the priority of the analysis based on the user's current situation and areas of interest.

[0093] When generating a summary, the generator can refer to the user's past inquiry history to improve the accuracy of the summary. For example, the generator can use the past inquiry history as a dataset to perform learning to improve the accuracy of the summary. The generator can also learn an algorithm to optimize the length and content of the summary based on the past inquiry history. Furthermore, the generator can use the past inquiry history to evaluate the accuracy of the summary and improve the algorithm based on feedback. In this way, the accuracy of the summary can be improved by referring to the past inquiry history.

[0094] The storage unit can determine the priority of storage based on the importance of the inquiry content when saving. For example, the storage unit evaluates the urgency and impact of the inquiry content and prioritizes saving of the inquiry content with high importance. The storage unit can also apply a simpler storage method to inquiry content with low importance. Furthermore, the storage unit can dynamically adjust the priority of storage according to the importance. This allows for efficient storage by determining the priority of storage based on the importance of the inquiry content.

[0095] The storage unit can adjust the order of storage based on the relevance of the inquiry content when storing. For example, the storage unit evaluates the relevance based on the similarity of the inquiry content or related topics, and stores highly relevant content preferentially. The storage unit can also postpone storing less relevant inquiry content. Furthermore, the storage unit can dynamically adjust the order of storage according to the relevance of the inquiry content. This allows for efficient storage by adjusting the order of storage based on the relevance of the inquiry content.

[0096] The reception desk can estimate the user's emotions and adjust the way inquiries are handled based on those estimated emotions. For example, the reception desk can capture the user's facial expressions with a camera and estimate their emotions using an emotion analysis algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the reception desk can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion analysis algorithm. This allows for more appropriate responses by adjusting the reception method based on the user's emotions.

[0097] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion analysis algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the analysis unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion analysis algorithm. This allows for more appropriate analysis by adjusting the analysis method based on the user's emotions.

[0098] The generation unit can estimate the user's emotions and adjust the way the summary is presented based on those estimated emotions. For example, the generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion analysis algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion analysis algorithm. By adjusting the way the summary is presented based on the user's emotions, a more appropriate summary can be generated.

[0099] The storage unit can estimate the user's emotions and determine the priority of summaries to save based on the estimated emotions. For example, the storage unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion analysis algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the storage unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion analysis algorithm. This allows for more appropriate storage by determining the priority of summaries to save based on the user's emotions.

[0100] The storage unit can estimate the user's emotions and adjust how the stored summary is displayed based on the estimated emotions. For example, the storage unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion analysis algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the storage unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion analysis algorithm. This allows for more appropriate display by adjusting how the stored summary is displayed based on the user's emotions.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The reception unit inputs the customer's inquiry. Inquiries include technical questions, product inquiries, and support requests. The reception unit can accept inquiries by voice input, text input, image input, and other methods. Step 2: The analysis unit uses natural language processing technology to analyze the inquiry entered by the reception unit and extract important keywords and phrases. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. The analysis unit uses morphological analysis to divide the inquiry into words, grammatical analysis to analyze the structure of the sentence, and semantic analysis to understand the meaning of the sentence. Step 3: The generator uses a pre-trained model to generate a summary based on the keywords and phrases extracted by the analyzer. Pre-trained models include machine learning models and deep learning models. The generator uses the machine learning model to optimize the length and content of the summary, and the deep learning model to improve the accuracy of the summary. Step 4: The storage unit stores the summary generated by the generation unit as a history so that the crew can check it. The storage unit stores the summary in a database so that the crew can search the history as needed. The storage unit can set the storage period and storage format. For example, the summary can be stored in text format for one year.

[0103] 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.

[0104] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0105] 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.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 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 reception desk where customers can input their inquiries, an analysis unit that analyzes the inquiry content input by the reception unit and extracts important keywords and phrases; a generation unit that generates a summary based on the keywords and phrases extracted by the analysis unit; a storage unit that stores the summary generated by the generation unit as a history. A system characterized by:

2. The analysis unit Analyzing inquiries using natural language processing technology The system of claim 1 .

3. The generation unit Use pre-trained models to adjust the length and content of summaries The system of claim 1 .

4. The storage unit The generated summary is saved as a history for the crew to review. The system of claim 1 .

5. The analysis unit Use topic modeling or text rank algorithms to extract important keywords and phrases The system of claim 1 .

6. The generation unit Improves the accuracy of summaries by learning from past inquiry history The system of claim 1 .

7. The reception unit Estimate the user's emotions and adjust the way inquiries are received based on the estimated user emotions The system of claim 1 .

8. The reception unit Refer to past inquiry history and select the appropriate reception method The system of claim 1 .

Images