system

Abstract

The system according to the embodiment aims to shorten the lead time for customer support at the service desk and improve customer satisfaction. [Solution] The system according to the embodiment includes a linking unit, an acquisition unit, and a display unit. The linking unit links voice data from the customer to the generation AI. The acquisition unit converts the voice data linked by the linking unit into text and acquires an answer from a knowledge base. The display unit displays the answer acquired by the acquisition unit on a prompter.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the lead time for customer support at the service desk is long, and there is room for improvement in improving customer satisfaction.

[0005] The system according to the embodiment aims to shorten the lead time for customer support at the service desk and improve customer satisfaction. [Means for solving the problem]

[0006] The system according to the embodiment includes a linking unit, an acquisition unit, and a display unit. The linking unit links voice data from the customer to the generation AI. The acquisition unit converts the voice data linked by the linking unit into text and acquires an answer from a knowledge base. The display unit displays the answer acquired by the acquisition unit on a prompter. [Effects of the Invention]

[0007] The system according to the embodiment can shorten the lead time for customer support at the service desk and improve customer satisfaction. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A real-time customer support system according to an embodiment of the present invention connects voice data from customers to a generation AI in real time, retrieves answers from a knowledge base, and displays them on a prompter. The real-time customer support system connects voice data from customers to a generation AI, which retrieves answers from the knowledge base and displays them on a prompter, allowing operators to respond quickly. For example, the real-time customer support system sends the voice data of a customer's telephone inquiry directly to the generation AI. The generation AI converts the voice data into text and searches the knowledge base based on the text to retrieve an answer. The retrieved answer is displayed on the prompter in real time. The operator responds to the customer while referring to the answer displayed on the prompter. This allows the operator to solve the problem on the spot without keeping the customer waiting. Furthermore, the generation AI can learn the content of the inquiry and update the knowledge base. This allows the generation AI to always provide answers based on the latest information. This allows the real-time customer support system to shorten the lead time of the service desk and improve customer satisfaction. For example, if a customer calls saying, "I can't connect to the Internet," the operator can respond quickly by referring to the answer displayed on the prompter. This allows the operator to solve the problem on the spot without making the customer wait.

[0029] A real-time customer service support system according to an embodiment includes a linking unit, an acquisition unit, and a display unit. The linking unit links voice data from customers to a generation AI. For example, the linking unit transmits voice data of telephone inquiries to the generation AI in real time. The acquisition unit converts the voice data into text using the generation AI and searches a knowledge base based on the text to acquire an answer. For example, the generation AI converts the voice data into text and searches a knowledge base based on the text to acquire an answer. For example, the generation AI converts the voice data into text using voice recognition technology and searches a knowledge base based on the text. The display unit displays the answer acquired by the acquisition unit on a prompter. For example, the display unit displays the acquired answer on the prompter in real time. This enables the real-time customer service support system according to an embodiment to respond quickly to customer inquiries and improve customer satisfaction.

[0030] The acquisition unit can convert voice data into text and search a knowledge base based on the text to obtain an answer. The acquisition unit, for example, uses a generation AI to convert voice data into text. For example, the generation AI converts voice data into text using voice recognition technology. The acquisition unit can also use the generation AI to search a knowledge base based on the text to obtain an answer. For example, the generation AI searches a knowledge base based on the text to obtain an appropriate answer. In this way, the use of the generation AI improves the accuracy of voice data text conversion and answer acquisition. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input voice data to the generation AI and have the generation AI perform text conversion and answer acquisition.

[0031] The display unit can display the acquired answer on a prompter. The display unit, for example, displays the acquired answer on the prompter in real time. For example, the display unit displays the acquired answer on the prompter, allowing the operator to respond while referring to the answer. This allows the operator to respond quickly by displaying the answer in real time. Some or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input the acquired answer to a generation AI and cause the generation AI to execute processing to display the answer on the prompter.

[0032] The linking unit can transmit voice data to the generation AI. For example, the linking unit transmits voice data of a telephone inquiry to the generation AI in real time. For example, the linking unit transmits voice data to the generation AI in real time, and the generation AI analyzes the voice data. This enables a quick response by transmitting the voice data in real time. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input voice data to the generation AI and have the generation AI execute processing to transmit it in real time.

[0033] The generation AI includes an update unit that analyzes the query content and updates the knowledge base. The update unit allows the generation AI to learn the query content and update the knowledge base. For example, the generation AI analyzes the query content and updates the knowledge base. The generation AI analyzes the query content using, for example, natural language processing technology and updates the knowledge base based on the results. As a result, the generation AI continues to learn, improving the accuracy of the knowledge base. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit may input the query content to the generation AI and cause the generation AI to update the knowledge base.

[0034] When a new troubleshooting technique is added, the update unit can add the information to the knowledge base. For example, when a new troubleshooting technique is added, the update unit adds the information to the knowledge base. For example, the update unit adds the new troubleshooting technique to the knowledge base and provides an appropriate answer to the next inquiry. This allows the knowledge base to always hold the latest information. Some or all of the above-mentioned processing in the update unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the update unit may input the new troubleshooting technique to a generation AI and cause the generation AI to add it to the knowledge base.

[0035] The linking unit can determine the linking priority based on the priority of the inquiry when linking voice data. For example, when linking voice data, the linking unit determines the linking priority based on the priority of the inquiry. For example, in the case of an inquiry with a high level of urgency, the linking unit links the voice data to the generation AI with the highest priority. In addition, in the case of an inquiry with a low level of urgency, the linking unit can link the voice data in parallel with other inquiries. In addition, in the case of an inquiry with a medium level of urgency, the linking unit can link the voice data with an appropriate priority. In this way, by determining the priority according to the urgency of the inquiry, it is possible to respond quickly to important inquiries. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input the urgency data of the inquiry to the generation AI and have the generation AI determine the priority.

[0036] The collaboration unit can select an appropriate collaboration method based on past inquiry history when collaborating voice data. For example, when collaborating voice data, the collaboration unit refers to past inquiry history to select the optimal collaboration method. For example, if a similar inquiry has been made in the past, the collaboration unit selects the optimal collaboration method based on that history. The collaboration unit can also extract a specific pattern from the past inquiry history and select a collaboration method based on that pattern. The collaboration unit can also analyze the past inquiry history and select the most efficient collaboration method. In this way, the optimal collaboration method can be selected by referring to the past inquiry history. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input past inquiry history data into a generation AI and cause the generation AI to select the optimal collaboration method.

[0037] When linking voice data, the linking unit can analyze the quality of the voice and, if the quality is low, perform noise removal before linking. For example, when linking voice data, the linking unit evaluates the quality of the voice and, if the quality is low, perform noise removal before linking to the generation AI. For example, if the quality of the voice data is low, the linking unit performs noise removal before linking to the generation AI. Furthermore, if the quality of the voice data is high, the linking unit can also link to the generation AI directly. Furthermore, the linking unit can evaluate the quality of the voice data in real time and perform noise removal as necessary. In this way, by evaluating the quality of the voice and performing noise removal, the analysis accuracy of the generation AI is improved. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can cause the generation AI to perform quality evaluation and noise removal of the voice data.

[0038] The linking unit can prioritize linking highly relevant data by taking geographical location information into consideration when linking voice data. For example, the linking unit prioritizes linking highly relevant data by taking geographical location information into consideration when linking voice data. For example, the linking unit prioritizes linking highly relevant data based on customer location information. The linking unit can also prioritize linking inquiries from geographically close locations. The linking unit can also select an optimal linking method by taking geographical location information into consideration. In this way, highly relevant data can be prioritized by taking geographical location information into consideration. Some or all of the above-described processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input geographical location information data to the generation AI and cause the generation AI to select highly relevant data.

[0039] The linking unit can analyze social media activity and link related data when linking voice data. For example, the linking unit analyzes social media activity and link related data when linking voice data. For example, the linking unit analyzes the customer's social media activity and link related data. The linking unit can also link related data based on the content of posts on social media. The linking unit can also link related data with reference to the activities of friends on social media. In this way, related data can be linked by analyzing social media activity. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input social media activity data to the generation AI and cause the generation AI to link related data.

[0040] The collaboration unit can customize the collaboration method by reflecting past feedback when linking voice data. For example, the collaboration unit customizes the collaboration method by reflecting past feedback when linking voice data. For example, the collaboration unit customizes the optimal collaboration method based on past feedback. The collaboration unit can also analyze the feedback content and improve the collaboration method. The collaboration unit can also optimize the collaboration method by reflecting past feedback. In this way, the collaboration method can be optimized by reflecting past feedback. Some or all of the above-mentioned processing in the collaboration unit may be performed using AI, for example, or may be performed without using AI. For example, the collaboration unit can input past feedback data into the generation AI and cause the generation AI to customize the collaboration method.

[0041] The acquisition unit can adjust the level of detail of the conversion based on the importance of the query when converting voice data into text. For example, the acquisition unit adjusts the level of detail of the conversion based on the importance of the query when converting voice data into text. For example, the acquisition unit performs detailed text conversion for queries with high importance. The acquisition unit can also perform simple text conversion for queries with low importance. The acquisition unit can also perform text conversion with an appropriate level of detail for queries with medium importance. In this way, appropriate text conversion can be performed by adjusting the level of detail of the conversion depending on the importance of the query. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input query importance data to a generation AI and cause the generation AI to adjust the level of detail of the conversion.

[0042] The acquisition unit can apply different conversion algorithms depending on the category of the inquiry when converting voice data to text. For example, the acquisition unit applies different conversion algorithms depending on the category of the inquiry when converting voice data to text. For example, in the case of a technical inquiry, the acquisition unit applies a conversion algorithm including technical terms. In addition, the acquisition unit can apply a concise conversion algorithm in the case of a general inquiry. In addition, the acquisition unit can apply a conversion algorithm including polite expressions in the case of an inquiry regarding customer service. In this way, by applying an appropriate conversion algorithm depending on the category of the inquiry, conversion accuracy is improved. Some or all of the above-mentioned processing in the acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the acquisition unit can input inquiry category data to a generation AI and cause the generation AI to apply the conversion algorithm.

[0043] The acquisition unit can improve the accuracy of conversion by referring to past conversion results when converting voice data into text. For example, the acquisition unit improves the accuracy of conversion by referring to past conversion results when converting voice data into text. For example, the acquisition unit adjusts the conversion algorithm based on past conversion results. The acquisition unit can also analyze past conversion results and improve accuracy. The acquisition unit can also select an optimal conversion method by referring to past conversion results. In this way, the conversion accuracy is improved by referring to past conversion results. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input past conversion result data into a generation AI and cause the generation AI to improve the conversion accuracy.

[0044] The acquisition unit can determine the conversion priority based on the time of inquiry submission when converting voice data into text. The acquisition unit, for example, determines the conversion priority based on the time of inquiry submission when converting voice data into text. For example, the acquisition unit prioritizes text conversion of inquiries submitted earlier. The acquisition unit can also postpone text conversion of inquiries submitted later. The acquisition unit can also perform text conversion with appropriate priority based on the time of submission. In this way, efficient text conversion can be achieved by determining the priority based on the time of inquiry submission. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input inquiry submission time data to a generation AI and have the generation AI determine the priority.

[0045] The acquisition unit can adjust the order of conversion based on relevance when converting voice data into text. The acquisition unit adjusts the order of conversion based on relevance when converting voice data into text, for example. For example, the acquisition unit prioritizes text conversion of highly relevant inquiries. The acquisition unit can also postpone text conversion of less relevant inquiries. The acquisition unit can also perform text conversion in an appropriate order based on relevance. In this way, adjusting the order of conversion based on relevance enables efficient text conversion. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input query relevance data to a generation AI and cause the generation AI to adjust the conversion order.

[0046] The acquisition unit can adjust the use of technical terminology in the conversion according to the level of expertise when converting voice data into text. For example, the acquisition unit adjusts the use of technical terminology in the conversion according to the level of expertise when converting voice data into text. For example, when the level of expertise is high, the acquisition unit performs text conversion that makes heavy use of technical terminology. Furthermore, when the level of expertise is low, the acquisition unit can perform concise and easy-to-understand text conversion. Furthermore, the acquisition unit can adjust the use of appropriate technical terminology according to the level of expertise. In this way, appropriate text conversion can be performed by adjusting the use of technical terminology according to the level of expertise. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input expertise level data to a generation AI and cause the generation AI to use technical terminology.

[0047] The display unit can adjust the level of detail of the display based on the importance of the inquiry when displaying the answer. For example, the display unit adjusts the level of detail of the display based on the importance of the inquiry when displaying the answer. For example, the display unit provides a detailed display for an inquiry of high importance. The display unit can also provide a concise display for an inquiry of low importance. The display unit can also provide a display with an appropriate level of detail for an inquiry of medium importance. This allows appropriate information to be provided by adjusting the level of detail of the display according to the importance of the inquiry. Some or all of the above-described processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input inquiry importance data to the generation AI and cause the generation AI to adjust the level of detail of the display.

[0048] The display unit can apply different display algorithms depending on the category of the inquiry when displaying the answer. For example, the display unit can apply different display algorithms depending on the category of the inquiry when displaying the answer. For example, in the case of a technical inquiry, the display unit can apply a display algorithm including technical terms. In addition, the display unit can apply a concise display algorithm in the case of a general inquiry. In addition, the display unit can apply a display algorithm including polite language in the case of an inquiry regarding customer service. In this way, by applying an appropriate display algorithm depending on the category of the inquiry, display accuracy is improved. Some or all of the above-mentioned processing in the display unit can be performed using AI, for example, or can be performed without using AI. For example, the display unit can input inquiry category data to the generation AI and cause the generation AI to apply the display algorithm.

[0049] The display unit can improve the accuracy of the display when displaying an answer by referring to past display results. For example, when displaying an answer, the display unit improves the accuracy of the display by referring to past display results. For example, the display unit adjusts the display algorithm based on past display results. The display unit can also analyze past display results and improve the accuracy. The display unit can also select an optimal display method by referring to past display results. In this way, the display accuracy is improved by referring to past display results. Some or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input past display result data into the generation AI and cause the generation AI to improve the display accuracy.

[0050] The display unit can determine the display priority based on the time of submission of the inquiry when displaying the answer. The display unit, for example, determines the display priority based on the time of submission of the inquiry when displaying the answer. For example, the display unit prioritizes display of inquiries submitted earlier. The display unit can also display inquiries submitted later later at a later date. The display unit can also display with appropriate priority based on the time of submission. In this way, by determining the priority based on the time of submission of the inquiry, efficient information provision can be achieved. Some or all of the above-described processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input inquiry submission time data to the generation AI and cause the generation AI to determine the priority.

[0051] The display unit can adjust the display order based on relevance when displaying answers. The display unit, for example, adjusts the display order based on relevance when displaying answers. For example, the display unit prioritizes displaying highly relevant inquiries. The display unit can also display less relevant inquiries later. The display unit can also display in an appropriate order based on relevance. As a result, adjusting the display order based on relevance enables efficient information provision. Some or all of the above-described processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input query relevance data to a generation AI and cause the generation AI to adjust the display order.

[0052] The display unit can adjust the use of technical terminology when displaying an answer according to the level of expertise. For example, the display unit can adjust the use of technical terminology when displaying an answer according to the level of expertise. For example, when the level of expertise is high, the display unit displays an answer using a lot of technical terminology. Furthermore, when the level of expertise is low, the display unit can display an answer in a concise and easy-to-understand manner. The display unit can also adjust the use of appropriate technical terminology according to the level of expertise. This allows appropriate information to be provided by adjusting the use of technical terminology according to the level of expertise. Some or all of the above-mentioned processing in the display unit can be performed using AI, for example, or without AI. For example, the display unit can input expertise level data to the generation AI and cause the generation AI to use technical terminology.

[0053] The update unit can optimize the update algorithm by referring to past inquiry data when updating the knowledge base. For example, the update unit optimizes the update algorithm by referring to past inquiry data when updating the knowledge base. For example, the update unit adjusts the update algorithm based on the past inquiry data. The update unit can also analyze the past inquiry data and select an optimal update method. The update unit can also optimize the update algorithm by referring to the past inquiry data. In this way, the update algorithm can be optimized by referring to the past inquiry data. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the past inquiry data into the generation AI and cause the generation AI to optimize the update algorithm.

[0054] The update unit can select update data by reflecting user feedback when updating the knowledge base. For example, the update unit selects update data by reflecting user feedback when updating the knowledge base. For example, the update unit selects update data based on user feedback. The update unit can also analyze the feedback content and improve the update data. The update unit can also optimize the update data by reflecting user feedback. In this way, the update data can be optimized by reflecting user feedback. Some or all of the above-mentioned processing in the update unit may be performed using AI, for example, or may be performed without using AI. For example, the update unit can input user feedback data to a generation AI and cause the generation AI to select update data.

[0055] The update unit can set criteria for adding a new troubleshooting method when updating the knowledge base. For example, the update unit sets criteria for adding a new troubleshooting method when updating the knowledge base. For example, the update unit sets criteria for adding a new troubleshooting method. The update unit can also select an appropriate troubleshooting method based on the criteria. The update unit can also periodically review the criteria and add an optimal troubleshooting method. In this way, setting criteria for adding a new troubleshooting method improves the accuracy of the knowledge base. Some or all of the above-described processing in the update unit may be performed using AI, for example, or may be performed without using AI. For example, the update unit can input criteria for a new troubleshooting method to a generation AI and cause the generation AI to set the criteria.

[0056] The update unit can weight the update data based on the time of inquiry submission when updating the knowledge base. The update unit, for example, weights the update data based on the time of inquiry submission when updating the knowledge base. For example, the update unit prioritizes updating data related to inquiries submitted earlier. The update unit can also postpone updating data related to inquiries submitted later. The update unit can also select update data with appropriate weighting based on the time of submission. In this way, weighting the update data based on the time of inquiry submission enables efficient updating of the knowledge base. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input inquiry submission time data to the generation AI and cause the generation AI to adjust the weighting.

[0057] The update unit can integrate information from different data sources to enrich the updated data when updating the knowledge base. For example, the update unit integrates information from different data sources to enrich the updated data when updating the knowledge base. For example, the update unit integrates information from different data sources to update the knowledge base. The update unit can also evaluate the reliability of the data sources and prioritize integration of highly reliable information. The update unit can also analyze information from different data sources and select optimal update data. In this way, the accuracy of the knowledge base is improved by integrating information from different data sources. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input data from different data sources to a generation AI and cause the generation AI to integrate the information.

[0058] The update unit can adjust the update algorithm by reflecting user feedback when updating the knowledge base. For example, the update unit adjusts the update algorithm by reflecting user feedback when updating the knowledge base. For example, the update unit adjusts the update algorithm based on user feedback. The update unit can also analyze the feedback content and improve the update algorithm. The update unit can also optimize the update algorithm by reflecting user feedback. In this way, the update algorithm can be optimized by reflecting user feedback. Some or all of the above-mentioned processing in the update unit may be performed using AI, for example, or may be performed without using AI. For example, the update unit can input user feedback data to the generation AI and cause the generation AI to adjust the update algorithm.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] When linking voice data, the linking unit can refer to the user's past inquiry history and, if a similar inquiry is received, select the optimal linking method based on that history. For example, if a similar inquiry has been received in the past, the linking unit selects the optimal linking method based on that history. The linking unit can also extract specific patterns from the past inquiry history and select a linking method based on those patterns. The linking unit can also analyze the past inquiry history and select the most efficient linking method. In this way, the optimal linking method can be selected by referring to the past inquiry history.

[0061] When converting speech data into text, the acquisition unit can adjust the use of technical terms in the conversion depending on the user's level of expertise. For example, if the user has a high level of expertise, the acquisition unit can perform text conversion that uses a lot of technical terms. Alternatively, if the user has a low level of expertise, the acquisition unit can perform text conversion that is concise and easy to understand. The acquisition unit can also adjust the use of appropriate technical terms depending on the user's level of expertise. This allows for appropriate text conversion by adjusting the use of technical terms depending on the user's level of expertise.

[0062] When displaying a response, the display unit can apply different display algorithms depending on the category of the inquiry. For example, the display unit can apply a display algorithm including technical terms to a technical inquiry. The display unit can also apply a concise display algorithm to a general inquiry. The display unit can also apply a display algorithm including polite language to an inquiry related to customer service. This improves display accuracy by applying an appropriate display algorithm depending on the category of the inquiry.

[0063] When linking voice data, the linking unit can prioritize linking highly relevant data by taking geographical location information into consideration. For example, the linking unit can prioritize linking highly relevant data based on the customer's location information. The linking unit can also prioritize linking inquiries from geographically close locations. The linking unit can also select the optimal linking method by taking geographical location information into consideration. This allows highly relevant data to be linked preferentially by taking geographical location information into consideration.

[0064] When updating the knowledge base, the update unit can integrate information from different data sources to enrich the updated data. For example, the update unit integrates information from different data sources and updates the knowledge base. The update unit can also evaluate the reliability of the data sources and prioritize integration of highly reliable information. The update unit can also analyze information from different data sources and select the most appropriate update data. In this way, the accuracy of the knowledge base is improved by integrating information from different data sources.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The linking unit links the voice data from the customer to the generation AI. For example, the voice data from a phone inquiry is sent to the generation AI in real time. Step 2: The acquisition unit uses the generation AI to convert the voice data into text, and then searches the knowledge base based on that text to obtain an answer. For example, the generation AI uses voice recognition technology to convert the voice data into text, and then searches the knowledge base based on that text. Step 3: The display unit displays the answers acquired by the acquisition unit on the prompter, for example, by displaying the acquired answers on the prompter in real time.

[0067] (Example 2) A real-time customer support system according to an embodiment of the present invention connects voice data from customers to a generation AI in real time, retrieves answers from a knowledge base, and displays them on a prompter. The real-time customer support system connects voice data from customers to a generation AI, which retrieves answers from the knowledge base and displays them on a prompter, allowing operators to respond quickly. For example, the real-time customer support system sends the voice data of a customer's telephone inquiry directly to the generation AI. The generation AI converts the voice data into text and searches the knowledge base based on the text to retrieve an answer. The retrieved answer is displayed on the prompter in real time. The operator responds to the customer while referring to the answer displayed on the prompter. This allows the operator to solve the problem on the spot without keeping the customer waiting. Furthermore, the generation AI can learn the content of the inquiry and update the knowledge base. This allows the generation AI to always provide answers based on the latest information. This allows the real-time customer support system to shorten the lead time of the service desk and improve customer satisfaction. For example, if a customer calls saying, "I can't connect to the Internet," the operator can respond quickly by referring to the answer displayed on the prompter. This allows the operator to solve the problem on the spot without making the customer wait.

[0068] A real-time customer service support system according to an embodiment includes a linking unit, an acquisition unit, and a display unit. The linking unit links voice data from customers to a generation AI. For example, the linking unit transmits voice data of telephone inquiries to the generation AI in real time. The acquisition unit converts the voice data into text using the generation AI and searches a knowledge base based on the text to acquire an answer. For example, the generation AI converts the voice data into text and searches a knowledge base based on the text to acquire an answer. For example, the generation AI converts the voice data into text using voice recognition technology and searches a knowledge base based on the text. The display unit displays the answer acquired by the acquisition unit on a prompter. For example, the display unit displays the acquired answer on the prompter in real time. This enables the real-time customer service support system according to an embodiment to respond quickly to customer inquiries and improve customer satisfaction.

[0069] The acquisition unit can convert voice data into text and search a knowledge base based on the text to obtain an answer. The acquisition unit, for example, uses a generation AI to convert voice data into text. For example, the generation AI converts voice data into text using voice recognition technology. The acquisition unit can also use the generation AI to search a knowledge base based on the text to obtain an answer. For example, the generation AI searches a knowledge base based on the text to obtain an appropriate answer. In this way, the use of the generation AI improves the accuracy of voice data text conversion and answer acquisition. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input voice data to the generation AI and have the generation AI perform text conversion and answer acquisition.

[0070] The display unit can display the acquired answer on a prompter. The display unit, for example, displays the acquired answer on the prompter in real time. For example, the display unit displays the acquired answer on the prompter, allowing the operator to respond while referring to the answer. This allows the operator to respond quickly by displaying the answer in real time. Some or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input the acquired answer to a generation AI and cause the generation AI to execute processing to display the answer on the prompter.

[0071] The linking unit can transmit voice data to the generation AI. For example, the linking unit transmits voice data of a telephone inquiry to the generation AI in real time. For example, the linking unit transmits voice data to the generation AI in real time, and the generation AI analyzes the voice data. This enables a quick response by transmitting the voice data in real time. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input voice data to the generation AI and have the generation AI execute processing to transmit it in real time.

[0072] The generation AI includes an update unit that analyzes the query content and updates the knowledge base. The update unit allows the generation AI to learn the query content and update the knowledge base. For example, the generation AI analyzes the query content and updates the knowledge base. The generation AI analyzes the query content using, for example, natural language processing technology and updates the knowledge base based on the results. As a result, the generation AI continues to learn, improving the accuracy of the knowledge base. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit may input the query content to the generation AI and cause the generation AI to update the knowledge base.

[0073] When a new troubleshooting technique is added, the update unit can add the information to the knowledge base. For example, when a new troubleshooting technique is added, the update unit adds the information to the knowledge base. For example, the update unit adds the new troubleshooting technique to the knowledge base and provides an appropriate answer to the next inquiry. This allows the knowledge base to always hold the latest information. Some or all of the above-mentioned processing in the update unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the update unit may input the new troubleshooting technique to a generation AI and cause the generation AI to add it to the knowledge base.

[0074] The linking unit can analyze the customer's emotions and adjust the timing of voice data linking based on the analyzed customer's emotions. The linking unit, for example, analyzes the customer's emotions and adjusts the timing of voice data linking based on the analyzed customer's emotions. For example, if the customer is impatient, the linking unit immediately links the voice data to the generation AI. Furthermore, if the customer is relaxed, the linking unit can slightly delay the linking of the voice data to allow the operator time to understand the situation. Furthermore, if the customer is angry, the linking unit can quickly link the voice data and prepare for a prompt response. This allows for a more appropriate response by adjusting the linking timing based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, 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 linking unit may be performed using, for example, an AI. For example, the linking unit can input customer emotion data into the generation AI and cause the generation AI to adjust the linking timing based on the emotion.

[0075] The linking unit can determine the linking priority based on the priority of the inquiry when linking voice data. For example, when linking voice data, the linking unit determines the linking priority based on the priority of the inquiry. For example, in the case of an inquiry with a high level of urgency, the linking unit links the voice data to the generation AI with the highest priority. In addition, in the case of an inquiry with a low level of urgency, the linking unit can link the voice data in parallel with other inquiries. In addition, in the case of an inquiry with a medium level of urgency, the linking unit can link the voice data with an appropriate priority. In this way, by determining the priority according to the urgency of the inquiry, it is possible to respond quickly to important inquiries. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input the urgency data of the inquiry to the generation AI and have the generation AI determine the priority.

[0076] The collaboration unit can select an appropriate collaboration method based on past inquiry history when collaborating voice data. For example, when collaborating voice data, the collaboration unit refers to past inquiry history to select the optimal collaboration method. For example, if a similar inquiry has been made in the past, the collaboration unit selects the optimal collaboration method based on that history. The collaboration unit can also extract a specific pattern from the past inquiry history and select a collaboration method based on that pattern. The collaboration unit can also analyze the past inquiry history and select the most efficient collaboration method. In this way, the optimal collaboration method can be selected by referring to the past inquiry history. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input past inquiry history data into a generation AI and cause the generation AI to select the optimal collaboration method.

[0077] When linking voice data, the linking unit can analyze the quality of the voice and, if the quality is low, perform noise removal before linking. For example, when linking voice data, the linking unit evaluates the quality of the voice and, if the quality is low, perform noise removal before linking to the generation AI. For example, if the quality of the voice data is low, the linking unit performs noise removal before linking to the generation AI. Furthermore, if the quality of the voice data is high, the linking unit can also link to the generation AI directly. Furthermore, the linking unit can evaluate the quality of the voice data in real time and perform noise removal as necessary. In this way, by evaluating the quality of the voice and performing noise removal, the analysis accuracy of the generation AI is improved. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can cause the generation AI to perform quality evaluation and noise removal of the voice data.

[0078] The linking unit can estimate the customer's emotions and prioritize the voice data to be linked based on the estimated customer emotions. The linking unit, for example, estimates the customer's emotions and prioritizes the voice data based on the estimated customer emotions. For example, if the customer is impatient, the linking unit links the voice data with the highest priority. Furthermore, if the customer is relaxed, the linking unit can link the voice data in parallel with other voice data. Furthermore, if the customer is angry, the linking unit can quickly link the voice data and respond quickly. This enables more appropriate responses by prioritizing the voice data according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation 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 linking unit may be performed using AI, for example, or without AI. For example, the linking unit can input customer emotion data into the generation AI and cause the generation AI to determine priorities based on emotions.

[0079] The linking unit can prioritize linking highly relevant data by taking geographical location information into consideration when linking voice data. For example, the linking unit prioritizes linking highly relevant data by taking geographical location information into consideration when linking voice data. For example, the linking unit prioritizes linking highly relevant data based on customer location information. The linking unit can also prioritize linking inquiries from geographically close locations. The linking unit can also select an optimal linking method by taking geographical location information into consideration. In this way, highly relevant data can be prioritized by taking geographical location information into consideration. Some or all of the above-described processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input geographical location information data to the generation AI and cause the generation AI to select highly relevant data.

[0080] The linking unit can analyze social media activity and link related data when linking voice data. For example, the linking unit analyzes social media activity and link related data when linking voice data. For example, the linking unit analyzes the customer's social media activity and link related data. The linking unit can also link related data based on the content of posts on social media. The linking unit can also link related data with reference to the activities of friends on social media. In this way, related data can be linked by analyzing social media activity. Some or all of the above-mentioned processing in the linking unit may be performed using AI, for example, or may be performed without using AI. For example, the linking unit can input social media activity data to the generation AI and cause the generation AI to link related data.

[0081] The collaboration unit can customize the collaboration method by reflecting past feedback when linking voice data. For example, the collaboration unit customizes the collaboration method by reflecting past feedback when linking voice data. For example, the collaboration unit customizes the optimal collaboration method based on past feedback. The collaboration unit can also analyze the feedback content and improve the collaboration method. The collaboration unit can also optimize the collaboration method by reflecting past feedback. In this way, the collaboration method can be optimized by reflecting past feedback. Some or all of the above-mentioned processing in the collaboration unit may be performed using AI, for example, or may be performed without using AI. For example, the collaboration unit can input past feedback data into the generation AI and cause the generation AI to customize the collaboration method.

[0082] The acquisition unit can estimate the customer's emotions and adjust the expression method for text conversion based on the estimated customer emotions. The acquisition unit, for example, estimates the customer's emotions and adjusts the expression method for text conversion based on the estimated customer emotions. For example, if the customer is anxious, the acquisition unit uses a concise and easy-to-understand expression method. If the customer is relaxed, the acquisition unit can use an expression method that includes detailed explanations. If the customer is angry, the acquisition unit can use a polite and calm expression method. This allows for adjusting the expression method for text conversion according to the customer's emotions to obtain a more appropriate answer. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the acquisition unit may be performed using AI, or may be performed without AI. For example, the acquisition unit can input customer emotion data into the generation AI and have the generation AI adjust the expression method.

[0083] The acquisition unit can adjust the level of detail of the conversion based on the importance of the query when converting voice data into text. For example, the acquisition unit adjusts the level of detail of the conversion based on the importance of the query when converting voice data into text. For example, the acquisition unit performs detailed text conversion for queries with high importance. The acquisition unit can also perform simple text conversion for queries with low importance. The acquisition unit can also perform text conversion with an appropriate level of detail for queries with medium importance. In this way, appropriate text conversion can be performed by adjusting the level of detail of the conversion depending on the importance of the query. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input query importance data to a generation AI and cause the generation AI to adjust the level of detail of the conversion.

[0084] The acquisition unit can apply different conversion algorithms depending on the category of the inquiry when converting voice data to text. For example, the acquisition unit applies different conversion algorithms depending on the category of the inquiry when converting voice data to text. For example, in the case of a technical inquiry, the acquisition unit applies a conversion algorithm including technical terms. In addition, the acquisition unit can apply a concise conversion algorithm in the case of a general inquiry. In addition, the acquisition unit can apply a conversion algorithm including polite expressions in the case of an inquiry regarding customer service. In this way, by applying an appropriate conversion algorithm depending on the category of the inquiry, conversion accuracy is improved. Some or all of the above-mentioned processing in the acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the acquisition unit can input inquiry category data to a generation AI and cause the generation AI to apply the conversion algorithm.

[0085] The acquisition unit can improve the accuracy of conversion by referring to past conversion results when converting voice data into text. For example, the acquisition unit improves the accuracy of conversion by referring to past conversion results when converting voice data into text. For example, the acquisition unit adjusts the conversion algorithm based on past conversion results. The acquisition unit can also analyze past conversion results and improve accuracy. The acquisition unit can also select an optimal conversion method by referring to past conversion results. In this way, the conversion accuracy is improved by referring to past conversion results. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input past conversion result data into a generation AI and cause the generation AI to improve the conversion accuracy.

[0086] The acquisition unit can estimate the customer's emotions and adjust the length of the text conversion based on the estimated customer emotions. For example, the acquisition unit estimates the customer's emotions and adjusts the length of the text conversion based on the estimated customer emotions. For example, if the customer is anxious, the acquisition unit can perform short, to-the-point text conversion. Alternatively, if the customer is relaxed, the acquisition unit can perform longer text conversion with detailed explanations. Alternatively, if the customer is angry, the acquisition unit can perform polite, concise text conversion. This allows for adjusting the length of the text conversion according to the customer's emotions to obtain a more appropriate answer. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the acquisition unit may be performed using AI, or may be performed without AI. For example, the acquisition unit can input customer emotion data into the generation AI and cause the generation AI to adjust the length of the text conversion.

[0087] The acquisition unit can determine the conversion priority based on the time of inquiry submission when converting voice data into text. The acquisition unit, for example, determines the conversion priority based on the time of inquiry submission when converting voice data into text. For example, the acquisition unit prioritizes text conversion of inquiries submitted earlier. The acquisition unit can also postpone text conversion of inquiries submitted later. The acquisition unit can also perform text conversion with appropriate priority based on the time of submission. In this way, efficient text conversion can be achieved by determining the priority based on the time of inquiry submission. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input inquiry submission time data to a generation AI and have the generation AI determine the priority.

[0088] The acquisition unit can adjust the order of conversion based on relevance when converting voice data into text. The acquisition unit adjusts the order of conversion based on relevance when converting voice data into text, for example. For example, the acquisition unit prioritizes text conversion of highly relevant inquiries. The acquisition unit can also postpone text conversion of less relevant inquiries. The acquisition unit can also perform text conversion in an appropriate order based on relevance. In this way, adjusting the order of conversion based on relevance enables efficient text conversion. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input query relevance data to a generation AI and cause the generation AI to adjust the conversion order.

[0089] The acquisition unit can adjust the use of technical terminology in the conversion according to the level of expertise when converting voice data into text. For example, the acquisition unit adjusts the use of technical terminology in the conversion according to the level of expertise when converting voice data into text. For example, when the level of expertise is high, the acquisition unit performs text conversion that makes heavy use of technical terminology. Furthermore, when the level of expertise is low, the acquisition unit can perform concise and easy-to-understand text conversion. Furthermore, the acquisition unit can adjust the use of appropriate technical terminology according to the level of expertise. In this way, appropriate text conversion can be performed by adjusting the use of technical terminology according to the level of expertise. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input expertise level data to a generation AI and cause the generation AI to use technical terminology.

[0090] The display unit can estimate the customer's emotions and adjust the display method based on the estimated customer emotions. For example, the display unit can estimate the customer's emotions and adjust the display method based on the estimated customer emotions. For example, if the customer is impatient, the display unit can provide a simple, highly visible display method. Furthermore, if the customer is relaxed, the display unit can provide a display method including detailed information. Furthermore, if the customer is angry, the display unit can provide a polite, calm display method. This allows for more appropriate responses by adjusting the display method according to the customer's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the display unit can be performed using, for example, AI, or without AI. For example, the display unit can input customer emotion data into the generation AI and have the generation AI adjust the display method.

[0091] The display unit can adjust the level of detail of the display based on the importance of the inquiry when displaying the answer. For example, the display unit adjusts the level of detail of the display based on the importance of the inquiry when displaying the answer. For example, the display unit provides a detailed display for an inquiry of high importance. The display unit can also provide a concise display for an inquiry of low importance. The display unit can also provide a display with an appropriate level of detail for an inquiry of medium importance. This allows appropriate information to be provided by adjusting the level of detail of the display according to the importance of the inquiry. Some or all of the above-described processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input inquiry importance data to the generation AI and cause the generation AI to adjust the level of detail of the display.

[0092] The display unit can apply different display algorithms depending on the category of the inquiry when displaying the answer. For example, the display unit can apply different display algorithms depending on the category of the inquiry when displaying the answer. For example, in the case of a technical inquiry, the display unit can apply a display algorithm including technical terms. In addition, the display unit can apply a concise display algorithm in the case of a general inquiry. In addition, the display unit can apply a display algorithm including polite language in the case of an inquiry regarding customer service. In this way, by applying an appropriate display algorithm depending on the category of the inquiry, display accuracy is improved. Some or all of the above-mentioned processing in the display unit can be performed using AI, for example, or can be performed without using AI. For example, the display unit can input inquiry category data to the generation AI and cause the generation AI to apply the display algorithm.

[0093] The display unit can improve the accuracy of the display when displaying an answer by referring to past display results. For example, when displaying an answer, the display unit improves the accuracy of the display by referring to past display results. For example, the display unit adjusts the display algorithm based on past display results. The display unit can also analyze past display results and improve the accuracy. The display unit can also select an optimal display method by referring to past display results. In this way, the display accuracy is improved by referring to past display results. Some or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input past display result data into the generation AI and cause the generation AI to improve the display accuracy.

[0094] The display unit can estimate the customer's emotions and adjust the display length based on the estimated customer emotions. For example, the display unit can estimate the customer's emotions and adjust the display length based on the estimated customer emotions. For example, if the customer is anxious, the display unit can display a short, to-the-point message. Alternatively, if the customer is relaxed, the display unit can display a longer message with detailed explanations. Alternatively, if the customer is angry, the display unit can display a polite, concise message. This allows for more appropriate information provision by adjusting the display length based on the customer's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the display unit can be performed using, for example, an AI. For example, the display unit can input customer emotion data into the generation AI and have the generation AI adjust the display length.

[0095] The display unit can determine the display priority based on the time of submission of the inquiry when displaying the answer. The display unit, for example, determines the display priority based on the time of submission of the inquiry when displaying the answer. For example, the display unit prioritizes display of inquiries submitted earlier. The display unit can also display inquiries submitted later later at a later date. The display unit can also display with appropriate priority based on the time of submission. In this way, by determining the priority based on the time of submission of the inquiry, efficient information provision can be achieved. Some or all of the above-described processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input inquiry submission time data to the generation AI and cause the generation AI to determine the priority.

[0096] The display unit can adjust the display order based on relevance when displaying answers. The display unit, for example, adjusts the display order based on relevance when displaying answers. For example, the display unit prioritizes displaying highly relevant inquiries. The display unit can also display less relevant inquiries later. The display unit can also display in an appropriate order based on relevance. As a result, adjusting the display order based on relevance enables efficient information provision. Some or all of the above-described processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input query relevance data to a generation AI and cause the generation AI to adjust the display order.

[0097] The display unit can adjust the use of technical terminology when displaying an answer according to the level of expertise. For example, the display unit can adjust the use of technical terminology when displaying an answer according to the level of expertise. For example, when the level of expertise is high, the display unit displays an answer using a lot of technical terminology. Furthermore, when the level of expertise is low, the display unit can display an answer in a concise and easy-to-understand manner. The display unit can also adjust the use of appropriate technical terminology according to the level of expertise. This allows appropriate information to be provided by adjusting the use of technical terminology according to the level of expertise. Some or all of the above-mentioned processing in the display unit can be performed using AI, for example, or without AI. For example, the display unit can input expertise level data to the generation AI and cause the generation AI to use technical terminology.

[0098] The update unit can estimate a customer's emotions and adjust the update frequency of the knowledge base based on the estimated customer emotions. The update unit, for example, estimates a customer's emotions and adjusts the update frequency of the knowledge base based on the estimated customer emotions. For example, if a customer frequently expresses dissatisfaction, the update unit can increase the update frequency of the knowledge base. Alternatively, if a customer is satisfied, the update unit can maintain the normal update frequency. Alternatively, if a customer expresses dissatisfaction with a specific issue, the update unit can increase the update frequency of information related to that issue. This allows for more appropriate information to be provided by adjusting the update frequency of the knowledge base according to the customer's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the update unit may be performed using, for example, an AI. For example, the update unit can input customer emotion data into the generation AI and have the generation AI adjust the update frequency.

[0099] The update unit can optimize the update algorithm by referring to past inquiry data when updating the knowledge base. For example, the update unit optimizes the update algorithm by referring to past inquiry data when updating the knowledge base. For example, the update unit adjusts the update algorithm based on the past inquiry data. The update unit can also analyze the past inquiry data and select an optimal update method. The update unit can also optimize the update algorithm by referring to the past inquiry data. In this way, the update algorithm can be optimized by referring to the past inquiry data. Some or all of the above-mentioned processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input the past inquiry data into the generation AI and cause the generation AI to optimize the update algorithm.

[0100] The update unit can select update data by reflecting user feedback when updating the knowledge base. For example, the update unit selects update data by reflecting user feedback when updating the knowledge base. For example, the update unit selects update data based on user feedback. The update unit can also analyze the feedback content and improve the update data. The update unit can also optimize the update data by reflecting user feedback. In this way, the update data can be optimized by reflecting user feedback. Some or all of the above-mentioned processing in the update unit may be performed using AI, for example, or may be performed without using AI. For example, the update unit can input user feedback data to a generation AI and cause the generation AI to select update data.

[0101] The update unit can set criteria for adding a new troubleshooting method when updating the knowledge base. For example, the update unit sets criteria for adding a new troubleshooting method when updating the knowledge base. For example, the update unit sets criteria for adding a new troubleshooting method. The update unit can also select an appropriate troubleshooting method based on the criteria. The update unit can also periodically review the criteria and add an optimal troubleshooting method. In this way, setting criteria for adding a new troubleshooting method improves the accuracy of the knowledge base. Some or all of the above-described processing in the update unit may be performed using AI, for example, or may be performed without using AI. For example, the update unit can input criteria for a new troubleshooting method to a generation AI and cause the generation AI to set the criteria.

[0102] The update unit can estimate a customer's emotions and adjust the updates to the knowledge base based on the estimated customer emotions. For example, the update unit estimates a customer's emotions and adjusts the updates to the knowledge base based on the estimated customer emotions. For example, if a customer frequently expresses dissatisfaction, the update unit prioritizes updating information related to that dissatisfaction. Furthermore, if a customer is satisfied, the update unit can maintain the normal updates. Furthermore, if a customer expresses dissatisfaction with a specific issue, the update unit can prioritize updating information related to that issue. This allows for more appropriate information to be provided by adjusting the updates to the knowledge base based on the customer's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the update unit may be performed using, for example, an AI, or without an AI. For example, the update unit can input customer emotion data into the generation AI and have the generation AI adjust the updates.

[0103] The update unit can weight the update data based on the time of inquiry submission when updating the knowledge base. The update unit, for example, weights the update data based on the time of inquiry submission when updating the knowledge base. For example, the update unit prioritizes updating data related to inquiries submitted earlier. The update unit can also postpone updating data related to inquiries submitted later. The update unit can also select update data with appropriate weighting based on the time of submission. In this way, weighting the update data based on the time of inquiry submission enables efficient updating of the knowledge base. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input inquiry submission time data to the generation AI and cause the generation AI to adjust the weighting.

[0104] The update unit can integrate information from different data sources to enrich the updated data when updating the knowledge base. For example, the update unit integrates information from different data sources to enrich the updated data when updating the knowledge base. For example, the update unit integrates information from different data sources to update the knowledge base. The update unit can also evaluate the reliability of the data sources and prioritize integration of highly reliable information. The update unit can also analyze information from different data sources and select optimal update data. In this way, the accuracy of the knowledge base is improved by integrating information from different data sources. Some or all of the above-described processing in the update unit may be performed using, for example, AI, or may be performed without using AI. For example, the update unit can input data from different data sources to a generation AI and cause the generation AI to integrate the information.

[0105] The update unit can adjust the update algorithm by reflecting user feedback when updating the knowledge base. For example, the update unit adjusts the update algorithm by reflecting user feedback when updating the knowledge base. For example, the update unit adjusts the update algorithm based on user feedback. The update unit can also analyze the feedback content and improve the update algorithm. The update unit can also optimize the update algorithm by reflecting user feedback. In this way, the update algorithm can be optimized by reflecting user feedback. Some or all of the above-mentioned processing in the update unit may be performed using AI, for example, or may be performed without using AI. For example, the update unit can input user feedback data to the generation AI and cause the generation AI to adjust the update algorithm. === Hard Collateral 1-1 === Each of the multiple elements, including the linking unit, acquisition unit, display unit, update unit, and emotion analysis unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the linking unit is realized by the control unit 46A of the smart device 14 and links voice data from the customer to the generation AI. The acquisition unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI converts the voice data to text and searches a knowledge base to obtain an answer. The display unit is realized by the output device 40 of the smart device 14 and displays the obtained answer on a prompter. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI learns the inquiry content and updates the knowledge base. The emotion analysis unit analyzes the customer's emotion using the camera 42 and microphone 38B of the smart device 14, and the linking unit adjusts the timing of linking the voice data based on the analysis results. === Hard Collateral 1-2 === Each of the multiple elements, including the linking unit, acquisition unit, display unit, update unit, and emotion analysis unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the linking unit is realized by the control unit 46A of the smart glasses 214 and links voice data from the customer to the generation AI. The acquisition unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI converts the voice data into text and searches a knowledge base to obtain an answer. The display unit is realized by the speaker 240 of the smart glasses 214 and displays the obtained answer on a prompter. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI learns the content of the inquiry and updates the knowledge base. The emotion analysis unit analyzes the customer's emotion using the camera 42 and microphone 238 of the smart glasses 214, and the linking unit adjusts the timing of linking the voice data based on the analysis results. === Hard Collateral 1-3 === Each of the multiple elements, including the linking unit, acquisition unit, display unit, update unit, and emotion analysis unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the linking unit is realized by the control unit 46A of the headset-type terminal 314 and links voice data from the customer to the generation AI. The acquisition unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI converts the voice data to text and searches a knowledge base to obtain an answer. The display unit is realized by the display 343 of the headset-type terminal 314 and displays the obtained answer on a prompter. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI learns the inquiry content and updates the knowledge base. The emotion analysis unit analyzes the customer's emotions using the camera 42 and microphone 238 of the headset-type terminal 314, and the linking unit adjusts the timing of linking the voice data based on the analysis results. === Hard Collateral 1-4 === Each of the multiple elements, including the linking unit, acquisition unit, display unit, update unit, and emotion analysis unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the linking unit is realized by the control unit 46A of the robot 414 and links voice data from the customer to the generation AI. The acquisition unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI converts the voice data into text and searches a knowledge base to obtain an answer. The display unit is realized by the speaker 240 of the robot 414 and displays the obtained answer on a prompter. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI learns the content of the inquiry and updates the knowledge base. The emotion analysis unit analyzes the customer's emotions using the camera 42 and microphone 238 of the robot 414, and the linking unit adjusts the timing of linking the voice data based on the analysis results.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] When linking voice data, the linking unit can refer to the user's past inquiry history and, if a similar inquiry is received, select the optimal linking method based on that history. For example, if a similar inquiry has been received in the past, the linking unit selects the optimal linking method based on that history. The linking unit can also extract specific patterns from the past inquiry history and select a linking method based on those patterns. The linking unit can also analyze the past inquiry history and select the most efficient linking method. In this way, the optimal linking method can be selected by referring to the past inquiry history.

[0108] When converting speech data into text, the acquisition unit can adjust the use of technical terms in the conversion depending on the user's level of expertise. For example, if the user has a high level of expertise, the acquisition unit can perform text conversion that uses a lot of technical terms. Alternatively, if the user has a low level of expertise, the acquisition unit can perform text conversion that is concise and easy to understand. The acquisition unit can also adjust the use of appropriate technical terms depending on the user's level of expertise. This allows for appropriate text conversion by adjusting the use of technical terms depending on the user's level of expertise.

[0109] When displaying a response, the display unit can apply different display algorithms depending on the category of the inquiry. For example, the display unit can apply a display algorithm including technical terms to a technical inquiry. The display unit can also apply a concise display algorithm to a general inquiry. The display unit can also apply a display algorithm including polite language to an inquiry related to customer service. This improves display accuracy by applying an appropriate display algorithm depending on the category of the inquiry.

[0110] When linking voice data, the linking unit can prioritize linking highly relevant data by taking geographical location information into consideration. For example, the linking unit can prioritize linking highly relevant data based on the customer's location information. The linking unit can also prioritize linking inquiries from geographically close locations. The linking unit can also select the optimal linking method by taking geographical location information into consideration. This allows highly relevant data to be linked preferentially by taking geographical location information into consideration.

[0111] When updating the knowledge base, the update unit can integrate information from different data sources to enrich the updated data. For example, the update unit integrates information from different data sources and updates the knowledge base. The update unit can also evaluate the reliability of the data sources and prioritize integration of highly reliable information. The update unit can also analyze information from different data sources and select the most appropriate update data. In this way, the accuracy of the knowledge base is improved by integrating information from different data sources.

[0112] The linking unit can analyze the customer's emotions and adjust the timing of voice data linking based on the analyzed customer emotions. For example, if the customer is impatient, the linking unit will immediately link the voice data to the generating AI. If the customer is relaxed, the linking unit can also delay the linking of the voice data slightly to allow the operator time to understand the situation. If the customer is angry, the linking unit can quickly link the voice data and prepare for an immediate response. This allows for more appropriate responses by adjusting the linking timing according to the customer's emotions.

[0113] The acquisition unit can estimate the customer's emotions and adjust the expression method of the text conversion based on the estimated customer's emotions. For example, if the customer is impatient, the acquisition unit can use a concise and easy-to-understand expression method. If the customer is relaxed, the acquisition unit can also use an expression method that includes detailed explanations. If the customer is angry, the acquisition unit can also use a polite and calm expression method. In this way, by adjusting the expression method of the text conversion according to the customer's emotions, a more appropriate response can be obtained.

[0114] The display unit can estimate the customer's emotions and adjust the display method based on the estimated customer emotions. For example, if the customer is impatient, the display unit can provide a simple, highly visible display method. If the customer is relaxed, the display unit can also provide a display method that includes detailed information. If the customer is angry, the display unit can also provide a polite, calm display method. This makes it possible to respond more appropriately by adjusting the display method according to the customer's emotions.

[0115] The update unit can estimate the customer's emotions and adjust the update frequency of the knowledge base based on the estimated customer's emotions. For example, if a customer frequently expresses dissatisfaction, the update unit can increase the update frequency of the knowledge base. Alternatively, if a customer is satisfied, the update unit can maintain the update frequency at normal levels. Alternatively, if a customer expresses dissatisfaction with a particular issue, the update unit can increase the update frequency of information related to that issue. In this way, by adjusting the update frequency of the knowledge base according to the customer's emotions, more appropriate information can be provided.

[0116] The acquisition unit can estimate the customer's emotions and adjust the length of the text conversion based on the estimated customer's emotions. For example, if the customer is impatient, the acquisition unit can perform short, to-the-point text conversion. If the customer is relaxed, the acquisition unit can also perform longer text conversion with detailed explanations. If the customer is angry, the acquisition unit can also perform polite, concise text conversion. In this way, by adjusting the length of the text conversion according to the customer's emotions, a more appropriate response can be obtained.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The linking unit links the voice data from the customer to the generation AI. For example, the voice data from a phone inquiry is sent to the generation AI in real time. Step 2: The acquisition unit uses the generation AI to convert the voice data into text, and then searches the knowledge base based on that text to obtain an answer. For example, the generation AI uses voice recognition technology to convert the voice data into text, and then searches the knowledge base based on that text. Step 3: The display unit displays the answers acquired by the acquisition unit on the prompter, for example, by displaying the acquired answers on the prompter in real time.

[0119] 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.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] 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.

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

[0124] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[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 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.

[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. 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.

[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 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.

[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 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.

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

[0137] 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.

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

[0140] 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.

[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 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.

[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 (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).

[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] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 7, a 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] [Explanation of symbols]

[0191] 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 linking unit that links voice data from customers to the AI ​​generator, an acquisition unit that converts the voice data linked by the linking unit into text and acquires an answer from a knowledge base; a display unit that displays the answer acquired by the acquisition unit on a prompter; Equipped with A system characterized by:

2. The acquisition unit Converts speech data to text and uses that text to search a knowledge base for answers 2. The system of claim 1.

3. The display unit Display the obtained answers in the prompter 2. The system of claim 1.

4. The linking unit is Send the voice data to the generating AI 2. The system of claim 1.

5. The generated AI is Equipped with an update unit that analyzes the content of inquiries and updates the knowledge base 2. The system of claim 1.

6. The update unit When new troubleshooting techniques are added, they are added to the knowledge base.

6. The system of claim 5.

7. The linking unit is Analyze customer emotions and adjust the timing of voice data sharing based on the analyzed customer emotions 2. The system of claim 1.

8. The linking unit is When linking voice data, determine the priority of linking based on the priority of the inquiry.

2. The system of claim 1.

Images