system

Abstract

The system according to the embodiment aims to quickly answer questions from customers and provide the answers at the desired speed. [Solution] A system according to an embodiment includes a reception unit, a generation unit, and a reading unit. The reception unit receives questions from customers. The generation unit analyzes the questions received by the reception unit and generates answers. The reading unit reads the answers generated by the generation unit at a speed specified by the customer.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of not providing prompt answers to customer questions and taking a long time to process requests.

[0005] The system according to the embodiment aims to quickly answer questions from customers and provide the answers at the desired speed. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, and a reading unit. The reception unit receives questions from customers. The generation unit analyzes the questions received by the reception unit and generates answers. The reading unit reads the answers generated by the generation unit at a speed specified by the customer. [Effects of the Invention]

[0007] The system according to the embodiment can quickly answer questions from customers and provide the answers at the desired speed. [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 system according to an embodiment of the present invention is designed to reduce the time required for mobile phone and internet contract procedures and improve customer convenience. This system uses AI to quickly respond to customer questions and read the answers aloud at the customer's desired speed. For example, when a customer inputs a question, the AI ​​analyzes the question using natural language processing technology and extracts keywords. Next, based on the extracted keywords, it searches a pre-trained database for an appropriate answer. This database contains detailed information about the contract procedure and explanations of pricing plans. Furthermore, when generating an answer, the AI ​​uses an algorithm that selects the most appropriate answer based on past question and answer data. This results in a fast and accurate answer. The generated answer is converted into speech using speech synthesis technology. The playback speed of the speech is adjusted according to the customer's desired speed setting. For example, if a customer requests a speech read at double speed, speech synthesis technology is used to generate speech at double speed. The speech synthesis technology also includes adjustments to maintain a natural voice quality. This allows the customer to hear the answer in a natural voice. This significantly reduces the time required for contract procedures and improves customer convenience. In addition, because the answers are generated by AI, we are available 24 hours a day and can quickly respond to customer questions.

[0029] A contract procedure support system according to an embodiment includes a reception unit, a generation unit, and a reading unit. The reception unit receives questions from customers. Questions entered by customers may be in text format or voice format, but are not limited to these examples. The reception unit may receive questions via keyboard input or voice input, for example. The generation unit analyzes the questions received by the reception unit and extracts keywords using natural language processing technology. Natural language processing technology may include, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis, for example. The generation unit may segment the questions using morphological analysis, analyze the sentence structure using grammatical analysis, and understand the meaning of the questions using semantic analysis, for example. The generation unit also searches for an appropriate answer from a database previously trained. The database may include, but is not limited to, an FAQ database and past inquiry data. The generation unit uses an algorithm to search for relevant answers from the FAQ database and select the optimal answer based on the past inquiry data, for example. The reading unit converts the generated answers into speech using speech synthesis technology. Examples of speech synthesis technologies include, but are not limited to, text-to-speech synthesis (TTS) and voice sample-based synthesis. The reading unit converts text into speech using, for example, text-to-speech synthesis, and generates natural-sounding speech using voice sample-based synthesis. The reading unit also adjusts the playback speed of the speech according to the speed setting desired by the customer. Speed ​​settings include, for example, 1x speed, 1.5x speed, and 2x speed, but are not limited to these examples. For example, if a customer requests reading at 1.5x speed, the reading unit generates speech at 1.5x speed using speech synthesis technology. As a result, the contract procedure support system according to the embodiment can quickly answer customer questions and read at the double speed setting, thereby shortening the time required for contract procedures and improving convenience.

[0030] The reception unit can accept questions entered by the customer. The reception unit accepts questions entered by the customer using, for example, keyboard input. For example, the reception unit can accept questions entered by the customer through a web form. The reception unit can also accept questions dictated by the customer using voice input. For example, the reception unit can convert questions dictated by the customer through a microphone into text using voice recognition technology and accept the text. This ensures that questions entered by the customer are accepted reliably. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the customer's voice data into a generation AI using voice recognition technology, and have the generation AI convert the voice data into text data.

[0031] The generation unit can analyze the question and extract keywords using natural language processing technology. The generation unit, for example, uses morphological analysis to divide the words in the question, grammatical analysis to analyze the sentence structure, and semantic analysis to understand the meaning of the question. For example, the generation unit can use morphological analysis to divide the words in the question and identify the part of speech of each word. The generation unit can also use grammatical analysis to analyze the sentence structure and identify sentence elements such as the subject, predicate, and object. The generation unit can also use semantic analysis to understand the meaning of the question and identify the intent of the question. For example, the generation unit can use semantic analysis to understand the context of the question and identify the intent of the question. This allows for accurate question analysis and keyword extraction. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can cause a generation AI to analyze the question using natural language processing technology.

[0032] The generation unit can search for an appropriate answer from a pre-trained database. The generation unit can search for a related answer from, for example, an FAQ database. For example, the generation unit can quickly search for an answer related to a question from a pre-trained FAQ database. The generation unit can also use an algorithm that selects the optimal answer based on past inquiry data. For example, the generation unit can analyze past inquiry data and use an algorithm that selects the most appropriate answer. This makes it possible to quickly search for an appropriate answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to search for an answer from a pre-trained database.

[0033] The generation unit can use an algorithm that selects the most appropriate answer based on data of past questions and answers. For example, the generation unit can use an algorithm that analyzes data of past questions and answers and selects the most appropriate answer. For example, the generation unit can use an algorithm that selects an answer that best suits the intent of the question based on data of past questions and answers. The generation unit can also select the optimal answer based on the accuracy and customer satisfaction of past answers. For example, the generation unit uses an algorithm that evaluates the accuracy and customer satisfaction of past answers and selects the most appropriate answer. This makes it possible to provide the optimal answer by utilizing past data. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to select an answer based on data of past questions and answers.

[0034] The reading unit can convert the generated answer into speech using speech synthesis technology. The reading unit can convert the generated answer into speech using, for example, text-to-speech synthesis (TTS). For example, the reading unit can convert a text-format answer into a natural-sounding voice using text-to-speech synthesis technology. The reading unit can also generate a more natural-sounding voice using speech sample-based synthesis. For example, the reading unit can generate a natural-sounding voice based on a speech sample using speech sample-based synthesis technology. This allows the generated answer to be provided by speech. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can cause a generation AI to perform a process of converting the generated answer into speech.

[0035] The reading unit can adjust the audio playback speed according to the speed setting desired by the customer. The reading unit can adjust the audio playback speed according to a speed setting such as 1x speed, 1.5x speed, or 2x speed. For example, if a user desires to have the audio read at 1.5x speed, the reading unit can generate audio at 1.5x speed using speech synthesis technology. The reading unit can also make adjustments to maintain the naturalness of the audio. For example, the reading unit can adjust the pitch and intonation of the audio to generate a natural voice. This allows the audio to be provided at a speed desired by the user. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can have a generation AI adjust the audio playback speed.

[0036] The reception unit can analyze the customer's past question history and select the optimal reception method. For example, the reception unit can prioritize reception of question formats that the customer has frequently used in the past. For example, the reception unit can analyze the customer's past question history, identify the most frequently used question format, and prioritize reception of that format. The reception unit can also select the most efficient reception method from the customer's past question history. For example, the reception unit can select the fastest and most efficient reception method based on the past question history. Furthermore, the reception unit can analyze the patterns of questions the customer has used in the past and suggest the optimal reception method. For example, the reception unit can analyze the past question patterns and suggest the most appropriate reception method. This makes it possible to provide the optimal reception method by utilizing the customer's past question history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can have a generation AI perform analysis of the past question history.

[0037] When receiving a question, the reception unit can filter the questions based on the customer's current contract status and areas of interest. For example, the reception unit can check the customer's current contract status and receive only related questions. For example, the reception unit can retrieve the customer's contract status from a database and prioritize receiving related questions. The reception unit can also prioritize receiving related questions based on the customer's areas of interest. For example, the reception unit can identify areas of interest based on the customer's past inquiries and survey results and prioritize receiving questions related to those areas. Furthermore, the reception unit can combine the customer's contract status and areas of interest to filter the most appropriate questions. For example, the reception unit can filter the most relevant questions based on the customer's contract status and areas of interest. This allows related questions to be prioritized based on the customer's contract status and areas of interest. Some or all of the above-mentioned processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input data on the contract status and areas of interest into a generation AI and have the generation AI perform question filtering.

[0038] When receiving a question, the reception unit can prioritize relevant questions based on the customer's geographical location information. For example, the reception unit can confirm the customer's current location and prioritize questions related to the area. For example, the reception unit can identify the customer's current location using GPS data and prioritize questions related to that area. The reception unit can also filter the most appropriate questions based on the customer's geographical location information. For example, the reception unit can identify the customer's geographical location using an IP address and filter questions related to that location. Furthermore, if the customer is in a specific area, the reception unit can prioritize questions related to that area. For example, if the customer is in a specific city or area, the reception unit can prioritize questions related to that area. This allows relevant questions to be prioritized based on the customer's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input geographical location information data to a generation AI and have the generation AI perform question filtering.

[0039] When receiving a question, the reception unit can analyze the customer's social media activity and receive related questions. The reception unit, for example, analyzes the customer's social media activity and prioritizes receiving related questions. For example, the reception unit can analyze the content of the customer's social media posts, identify related questions, and prioritize receiving them. The reception unit can also filter the most appropriate questions based on the content the customer has mentioned on social media. For example, the reception unit can filter highly relevant questions based on the content of the customer's social media mentions. Furthermore, the reception unit can also receive highly relevant questions based on the customer's social media activity. For example, the reception unit can analyze the customer's social media activity history, identify highly relevant questions, and receive them. This allows related questions to be prioritized based on the customer's social media activity. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input social media activity data to a generation AI and have the generation AI perform question filtering.

[0040] When generating an answer, the generation unit can adjust the level of detail of the answer based on the importance of the question. For example, the generation unit generates a detailed answer for an important question. For example, the generation unit can evaluate the importance of a question and generate an answer including a detailed explanation for an important question. The generation unit can also generate a concise answer for a general question. For example, the generation unit can evaluate the importance of a question and generate a concise and to-the-point answer for a general question. Furthermore, the generation unit can generate a quick and to-the-point answer for an urgent question. For example, the generation unit can evaluate the urgency of a question and generate a quick and to-the-point answer for an urgent question. This makes it possible to provide an answer with an appropriate level of detail depending on the importance of the question. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may have a generation AI perform the evaluation of the importance of the question and the adjustment of the level of detail of the answer.

[0041] When generating an answer, the generation unit can apply different answer algorithms depending on the category of the question. For example, the generation unit applies a specialized answer algorithm to a technical question. For example, the generation unit can apply a specialized answer algorithm based on technical knowledge to a technical question. The generation unit can also apply a contract-specific answer algorithm to a question about a contract. For example, the generation unit can apply a specialized answer algorithm based on detailed knowledge of contracts to a question about a contract. Furthermore, the generation unit can also apply a general-purpose answer algorithm to a general question. For example, the generation unit can apply a general-purpose answer algorithm based on broad knowledge to a general question. This makes it possible to apply an optimal answer algorithm depending on the category of the question. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to apply an answer algorithm depending on the category of the question.

[0042] When generating answers, the generation unit can determine the priority of answers based on the time the question was submitted. For example, the generation unit can generate answers with priority for recently submitted questions. For example, the generation unit can generate answers with priority for recently submitted questions based on the submission date and time of the question. The generation unit can also generate answers with normal priority for previously submitted questions. For example, the generation unit can generate answers with normal priority for previously submitted questions based on the submission date and time of the question. Furthermore, the generation unit can generate answers with highest priority for urgent questions. For example, the generation unit can evaluate the urgency of the question and generate answers with highest priority for urgent questions. This allows answers to be provided with appropriate priority depending on the time the question was submitted. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to evaluate the time the question was submitted and determine the priority of the answers.

[0043] When generating answers, the generation unit can adjust the order of answers based on the relevance of the question. For example, when the relevance of a question is high, the generation unit can generate answers preferentially. For example, the generation unit can generate answers preferentially for questions with high relevance based on the similarity of the question content or related topics. Furthermore, when the relevance of a question is low, the generation unit can generate answers in a normal order. For example, the generation unit can generate answers in a normal order for questions with low relevance based on the similarity of the question content or related topics. Furthermore, the generation unit can dynamically adjust the order of answers depending on the relevance of the question. For example, the generation unit can evaluate the relevance of the question and dynamically adjust the order of answers depending on the relevance. This makes it possible to provide answers in an appropriate order depending on the relevance of the question. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to evaluate the relevance of a question and adjust the order of answers.

[0044] The reading unit can adjust the tone and intonation of the voice when reading out based on the content of the answer. For example, if the answer contains important information, the reading unit can read it in an emphasized tone. For example, the reading unit can analyze the content of the answer and read it in an emphasized tone if it contains important information. The reading unit can also read it in a normal tone if the answer contains general information. For example, the reading unit can analyze the content of the answer and read it in a normal tone if it contains general information. Furthermore, the reading unit can also read it in a quick and clear tone if the answer contains urgent information. For example, the reading unit can analyze the content of the answer and read it in a quick and clear tone if it contains urgent information. This allows the answer to be read out in an appropriate tone and intonation according to the content of the answer. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can have a generation AI analyze the content of the answer and adjust the tone and intonation of the voice.

[0045] When reading aloud, the reading unit can select the optimal reading method by referring to the customer's past voice setting history. The reading unit, for example, selects the optimal reading speed based on the voice speed previously set by the customer. For example, the reading unit can select the optimal reading speed by referring to the customer's past voice setting history. The reading unit can also select the optimal tone and intonation from the customer's past voice setting history. For example, the reading unit can select the optimal tone and intonation by referring to the customer's past voice setting history. Furthermore, the reading unit can suggest the optimal reading method based on the voice settings previously used by the customer. For example, the reading unit can suggest the optimal reading method based on the customer's past voice setting history. This makes it possible to provide the optimal reading method based on the customer's past voice setting history. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input data of the past voice setting history into a generation AI and have the generation AI select the optimal reading method.

[0046] When reading out, the reading unit can select the optimal audio format based on the customer's device information. For example, if the customer is using a smartphone, the reading unit can select the optimal audio format. For example, the reading unit can select the optimal audio format for the smartphone based on the customer's device information. Furthermore, if the customer is using a tablet, the reading unit can select the optimal audio format. For example, the reading unit can select the optimal audio format for the tablet based on the customer's device information. Furthermore, if the customer is using a PC, the reading unit can select the optimal audio format. For example, the reading unit can select the optimal audio format for the PC based on the customer's device information. This makes it possible to provide an answer in the optimal audio format based on the customer's device information. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input device information data to a generation AI and have the generation AI select the optimal audio format.

[0047] When reading aloud, the reading unit can complement the content of the audio by referring to literature related to the answer. For example, the reading unit can refer to literature related to the answer and read out supplementary information. For example, the reading unit can refer to academic papers or technical documents related to the answer and read out supplementary information. The reading unit can also refer to data related to the answer and provide detailed information. For example, the reading unit can refer to a database related to the answer and provide detailed information. Furthermore, the reading unit can also refer to past questions and answers related to the answer and provide supplementary information. For example, the reading unit can refer to a database of past questions and answers and provide supplementary information. In this way, supplementary information can be provided by referring to literature related to the answer. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input data from related literature into the generation AI and have the generation AI complete the content of the audio.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The reception unit can predict questions based on the customer's past behavioral history. For example, the reception unit can analyze operations and questions that the customer has frequently performed in the past, and predict the question that the customer is likely to ask next. The reception unit can also suggest the most appropriate question based on the customer's past behavioral patterns. For example, the reception unit can suggest the most appropriate question that the customer is likely to ask next, based on the operations and questions that the customer has performed in the past. Furthermore, the reception unit can determine the priority of questions based on the customer's past behavioral history. For example, the reception unit can prioritize the most important questions based on the operations and questions that the customer has performed in the past. In this way, the customer's past behavioral history can be used to predict and suggest the most appropriate questions.

[0050] The generation unit can provide related videos and images based on the content of the question. For example, the generation unit can analyze the content of the question and search for and provide related videos and images. The generation unit can also generate related videos and images based on the content of the question. For example, the generation unit can generate and provide related videos and images based on the content of the question. Furthermore, the generation unit can edit related videos and images based on the content of the question. For example, the generation unit can edit and provide related videos and images based on the content of the question. This makes it possible to provide related videos and images according to the content of the question.

[0051] The generation unit can refer to related external resources based on the content of the question. For example, the generation unit can analyze the content of the question and search for and refer to related external websites or databases. The generation unit can also query related external experts based on the content of the question. For example, the generation unit can query related external experts based on the content of the question to obtain an answer. The generation unit can also refer to related external literature based on the content of the question. For example, the generation unit can generate an answer by referencing related external academic papers or technical documents based on the content of the question. This makes it possible to refer to related external resources according to the content of the question.

[0052] The generation unit can execute a related simulation based on the content of the question. For example, the generation unit can analyze the content of the question, execute a related simulation, and provide a result. The generation unit can also generate a related simulation model based on the content of the question. For example, the generation unit can generate a related simulation model based on the content of the question and provide a result. The generation unit can also analyze the results of the related simulation based on the content of the question. For example, the generation unit can analyze the results of the related simulation based on the content of the question and generate an answer. This makes it possible to execute a related simulation according to the content of the question.

[0053] The generation unit can visualize related data based on the content of the question. For example, the generation unit can analyze the content of the question and visualize and provide related data in the form of a graph, chart, or the like. The generation unit can also interactively visualize related data based on the content of the question. For example, the generation unit can visualize and provide related data in the form of an interactive graph, chart, or the like based on the content of the question. Furthermore, the generation unit can analyze the visualization results of the related data based on the content of the question. For example, the generation unit can analyze the visualization results of the related data based on the content of the question and generate an answer. This makes it possible to visualize related data according to the content of the question.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The reception unit receives a question from a customer. The question entered by the customer may be in text format or voice format, but is not limited to these examples. The reception unit can receive the question using, for example, keyboard input or voice input. Step 2: The generation unit uses natural language processing technology to analyze the question received by the reception unit and extract keywords. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the generation unit uses morphological analysis to divide the words in the question, grammatical analysis to analyze the sentence structure, and semantic analysis to understand the meaning of the question. The generation unit also searches for an appropriate answer from a database that has been trained in advance. For example, the database includes, but is not limited to, an FAQ database and past inquiry data. For example, the generation unit uses an algorithm that searches for relevant answers from the FAQ database and selects the optimal answer based on past inquiry data. Step 3: The reading unit converts the generated response into speech using speech synthesis technology. Examples of speech synthesis technology include, but are not limited to, text-to-speech synthesis (TTS) and voice sample-based synthesis. For example, the reading unit converts text into speech using text-to-speech synthesis and generates natural-sounding speech using voice sample-based synthesis. The reading unit also adjusts the playback speed of the speech according to the speed setting desired by the customer. Examples of speed settings include, but are not limited to, 1x speed, 1.5x speed, and 2x speed. For example, if the reading unit requests a 1.5x speed, the reading unit generates speech at 1.5x speed using speech synthesis technology.

[0056] (Example 2) A system according to an embodiment of the present invention is designed to reduce the time required for mobile phone and internet contract procedures and improve customer convenience. This system uses AI to quickly respond to customer questions and read the answers aloud at the customer's desired speed. For example, when a customer inputs a question, the AI ​​analyzes the question using natural language processing technology and extracts keywords. Next, based on the extracted keywords, it searches a pre-trained database for an appropriate answer. This database contains detailed information about the contract procedure and explanations of pricing plans. Furthermore, when generating an answer, the AI ​​uses an algorithm that selects the most appropriate answer based on past question and answer data. This results in a fast and accurate answer. The generated answer is converted into speech using speech synthesis technology. The playback speed of the speech is adjusted according to the customer's desired speed setting. For example, if a customer requests a speech read at double speed, speech synthesis technology is used to generate speech at double speed. The speech synthesis technology also includes adjustments to maintain a natural voice quality. This allows the customer to hear the answer in a natural voice. This significantly reduces the time required for contract procedures and improves customer convenience. In addition, because the answers are generated by AI, we are available 24 hours a day and can quickly respond to customer questions.

[0057] A contract procedure support system according to an embodiment includes a reception unit, a generation unit, and a reading unit. The reception unit receives questions from customers. Questions entered by customers may be in text format or voice format, but are not limited to these examples. The reception unit may receive questions via keyboard input or voice input, for example. The generation unit analyzes the questions received by the reception unit and extracts keywords using natural language processing technology. Natural language processing technology may include, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis, for example. The generation unit may segment the questions using morphological analysis, analyze the sentence structure using grammatical analysis, and understand the meaning of the questions using semantic analysis, for example. The generation unit also searches for an appropriate answer from a database previously trained. The database may include, but is not limited to, an FAQ database and past inquiry data. The generation unit uses an algorithm to search for relevant answers from the FAQ database and select the optimal answer based on the past inquiry data, for example. The reading unit converts the generated answers into speech using speech synthesis technology. Examples of speech synthesis technologies include, but are not limited to, text-to-speech synthesis (TTS) and voice sample-based synthesis. The reading unit converts text into speech using, for example, text-to-speech synthesis, and generates natural-sounding speech using voice sample-based synthesis. The reading unit also adjusts the playback speed of the speech according to the speed setting desired by the customer. Speed ​​settings include, for example, 1x speed, 1.5x speed, and 2x speed, but are not limited to these examples. For example, if a customer requests reading at 1.5x speed, the reading unit generates speech at 1.5x speed using speech synthesis technology. As a result, the contract procedure support system according to the embodiment can quickly answer customer questions and read at the double speed setting, thereby shortening the time required for contract procedures and improving convenience.

[0058] The reception unit can accept questions entered by the customer. The reception unit accepts questions entered by the customer using, for example, keyboard input. For example, the reception unit can accept questions entered by the customer through a web form. The reception unit can also accept questions dictated by the customer using voice input. For example, the reception unit can convert questions dictated by the customer through a microphone into text using voice recognition technology and accept the text. This ensures that questions entered by the customer are accepted reliably. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the customer's voice data into a generation AI using voice recognition technology, and have the generation AI convert the voice data into text data.

[0059] The generation unit can analyze the question and extract keywords using natural language processing technology. The generation unit, for example, uses morphological analysis to divide the words in the question, grammatical analysis to analyze the sentence structure, and semantic analysis to understand the meaning of the question. For example, the generation unit can use morphological analysis to divide the words in the question and identify the part of speech of each word. The generation unit can also use grammatical analysis to analyze the sentence structure and identify sentence elements such as the subject, predicate, and object. The generation unit can also use semantic analysis to understand the meaning of the question and identify the intent of the question. For example, the generation unit can use semantic analysis to understand the context of the question and identify the intent of the question. This allows for accurate question analysis and keyword extraction. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can cause a generation AI to analyze the question using natural language processing technology.

[0060] The generation unit can search for an appropriate answer from a pre-trained database. The generation unit can search for a related answer from, for example, an FAQ database. For example, the generation unit can quickly search for an answer related to a question from a pre-trained FAQ database. The generation unit can also use an algorithm that selects the optimal answer based on past inquiry data. For example, the generation unit can analyze past inquiry data and use an algorithm that selects the most appropriate answer. This makes it possible to quickly search for an appropriate answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to search for an answer from a pre-trained database.

[0061] The generation unit can use an algorithm that selects the most appropriate answer based on data of past questions and answers. For example, the generation unit can use an algorithm that analyzes data of past questions and answers and selects the most appropriate answer. For example, the generation unit can use an algorithm that selects an answer that best suits the intent of the question based on data of past questions and answers. The generation unit can also select the optimal answer based on the accuracy and customer satisfaction of past answers. For example, the generation unit uses an algorithm that evaluates the accuracy and customer satisfaction of past answers and selects the most appropriate answer. This makes it possible to provide the optimal answer by utilizing past data. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to select an answer based on data of past questions and answers.

[0062] The reading unit can convert the generated answer into speech using speech synthesis technology. The reading unit can convert the generated answer into speech using, for example, text-to-speech synthesis (TTS). For example, the reading unit can convert a text-format answer into a natural-sounding voice using text-to-speech synthesis technology. The reading unit can also generate a more natural-sounding voice using speech sample-based synthesis. For example, the reading unit can generate a natural-sounding voice based on a speech sample using speech sample-based synthesis technology. This allows the generated answer to be provided by speech. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can cause a generation AI to perform a process of converting the generated answer into speech.

[0063] The reading unit can adjust the audio playback speed according to the speed setting desired by the customer. The reading unit can adjust the audio playback speed according to a speed setting such as 1x speed, 1.5x speed, or 2x speed. For example, if a user desires to have the audio read at 1.5x speed, the reading unit can generate audio at 1.5x speed using speech synthesis technology. The reading unit can also make adjustments to maintain the naturalness of the audio. For example, the reading unit can adjust the pitch and intonation of the audio to generate a natural voice. This allows the audio to be provided at a speed desired by the user. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can have a generation AI adjust the audio playback speed.

[0064] The contract procedure support system further includes a reception unit that estimates a customer's emotions and adjusts the timing of receiving questions based on the estimated emotions. For example, if a customer is feeling stressed, the reception unit uses AI to estimate the customer's emotions and promptly accept questions. For example, the reception unit can analyze the customer's facial expressions using facial expression recognition technology to determine whether the customer is feeling stressed. Furthermore, if a customer is relaxed, the reception unit can use AI to estimate the customer's emotions and promptly accept questions. For example, the reception unit can analyze the customer's tone and speed of voice using voice analysis technology to determine whether the customer is relaxed. Furthermore, if a customer is in a hurry, the reception unit can use AI to estimate the customer's emotions and promptly accept questions. For example, the reception unit can measure the customer's heart rate and electrodermal activity using a biosensor to determine whether the customer is in a hurry. This allows questions to be accepted at an appropriate time based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input data for emotion estimation to the generation AI and cause the generation AI to estimate the emotion.

[0065] The reception unit can analyze the customer's past question history and select the optimal reception method. For example, the reception unit can prioritize reception of question formats that the customer has frequently used in the past. For example, the reception unit can analyze the customer's past question history, identify the most frequently used question format, and prioritize reception of that format. The reception unit can also select the most efficient reception method from the customer's past question history. For example, the reception unit can select the fastest and most efficient reception method based on the past question history. Furthermore, the reception unit can analyze the patterns of questions the customer has used in the past and suggest the optimal reception method. For example, the reception unit can analyze the past question patterns and suggest the most appropriate reception method. This makes it possible to provide the optimal reception method by utilizing the customer's past question history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can have a generation AI perform analysis of the past question history.

[0066] When receiving a question, the reception unit can filter the questions based on the customer's current contract status and areas of interest. For example, the reception unit can check the customer's current contract status and receive only related questions. For example, the reception unit can retrieve the customer's contract status from a database and prioritize receiving related questions. The reception unit can also prioritize receiving related questions based on the customer's areas of interest. For example, the reception unit can identify areas of interest based on the customer's past inquiries and survey results and prioritize receiving questions related to those areas. Furthermore, the reception unit can combine the customer's contract status and areas of interest to filter the most appropriate questions. For example, the reception unit can filter the most relevant questions based on the customer's contract status and areas of interest. This allows related questions to be prioritized based on the customer's contract status and areas of interest. Some or all of the above-mentioned processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input data on the contract status and areas of interest into a generation AI and have the generation AI perform question filtering.

[0067] The reception unit can estimate a customer's emotions and prioritize questions based on the estimated emotions. For example, if a customer is feeling stressed, the reception unit can use AI to estimate the customer's emotions and prioritize important questions. For example, the reception unit can use facial expression recognition technology to analyze the customer's facial expressions, determine whether the customer is feeling stressed, and prioritize important questions. Alternatively, if a customer is relaxed, the reception unit can use AI to estimate the customer's emotions and prioritize questions. For example, the reception unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and prioritize questions. Furthermore, if a customer is in a hurry, the reception unit can use AI to estimate the customer's emotions and prioritize urgent questions. For example, the reception unit can use biosensors to measure the customer's heart rate and electrodermal activity, determine whether the customer is in a hurry, and prioritize urgent questions. This allows important questions to be prioritized based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit may input data for emotion estimation to the generation AI and cause the generation AI to estimate the emotion.

[0068] When receiving a question, the reception unit can prioritize relevant questions based on the customer's geographical location information. For example, the reception unit can confirm the customer's current location and prioritize questions related to the area. For example, the reception unit can identify the customer's current location using GPS data and prioritize questions related to that area. The reception unit can also filter the most appropriate questions based on the customer's geographical location information. For example, the reception unit can identify the customer's geographical location using an IP address and filter questions related to that location. Furthermore, if the customer is in a specific area, the reception unit can prioritize questions related to that area. For example, if the customer is in a specific city or area, the reception unit can prioritize questions related to that area. This allows relevant questions to be prioritized based on the customer's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input geographical location information data to a generation AI and have the generation AI perform question filtering.

[0069] When receiving a question, the reception unit can analyze the customer's social media activity and receive related questions. The reception unit, for example, analyzes the customer's social media activity and prioritizes receiving related questions. For example, the reception unit can analyze the content of the customer's social media posts, identify related questions, and prioritize receiving them. The reception unit can also filter the most appropriate questions based on the content the customer has mentioned on social media. For example, the reception unit can filter highly relevant questions based on the content of the customer's social media mentions. Furthermore, the reception unit can also receive highly relevant questions based on the customer's social media activity. For example, the reception unit can analyze the customer's social media activity history, identify highly relevant questions, and receive them. This allows related questions to be prioritized based on the customer's social media activity. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input social media activity data to a generation AI and have the generation AI perform question filtering.

[0070] The generation unit can estimate the customer's emotions and adjust the way the answer is expressed based on the estimated emotions. For example, if the customer is feeling stressed, the generation unit generates a concise and clear answer. For example, the generation unit can use facial expression recognition technology to analyze the customer's facial expressions, determine whether the customer is feeling stressed, and generate a concise and clear answer. The generation unit can also generate an answer with a detailed explanation if the customer is relaxed. For example, the generation unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and generate an answer with a detailed explanation. Furthermore, the generation unit can generate a quick and concise answer if the customer is in a hurry. For example, the generation unit can measure the customer's heart rate and electrodermal activity using a biosensor, determine whether the customer is in a hurry, and generate a quick and concise answer. This allows the system to provide an answer in an appropriate manner based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input data for emotion estimation to the generation AI and cause the generation AI to estimate the emotion.

[0071] When generating an answer, the generation unit can adjust the level of detail of the answer based on the importance of the question. For example, the generation unit generates a detailed answer for an important question. For example, the generation unit can evaluate the importance of a question and generate an answer including a detailed explanation for an important question. The generation unit can also generate a concise answer for a general question. For example, the generation unit can evaluate the importance of a question and generate a concise and to-the-point answer for a general question. Furthermore, the generation unit can generate a quick and to-the-point answer for an urgent question. For example, the generation unit can evaluate the urgency of a question and generate a quick and to-the-point answer for an urgent question. This makes it possible to provide an answer with an appropriate level of detail depending on the importance of the question. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may have a generation AI perform the evaluation of the importance of the question and the adjustment of the level of detail of the answer.

[0072] When generating an answer, the generation unit can apply different answer algorithms depending on the category of the question. For example, the generation unit applies a specialized answer algorithm to a technical question. For example, the generation unit can apply a specialized answer algorithm based on technical knowledge to a technical question. The generation unit can also apply a contract-specific answer algorithm to a question about a contract. For example, the generation unit can apply a specialized answer algorithm based on detailed knowledge of contracts to a question about a contract. Furthermore, the generation unit can also apply a general-purpose answer algorithm to a general question. For example, the generation unit can apply a general-purpose answer algorithm based on broad knowledge to a general question. This makes it possible to apply an optimal answer algorithm depending on the category of the question. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to apply an answer algorithm depending on the category of the question.

[0073] The generation unit can estimate the customer's emotions and adjust the length of the response based on the estimated emotions. For example, if the customer is feeling stressed, the generation unit generates a short, concise response. For example, the generation unit can use facial expression recognition technology to analyze the customer's facial expressions, determine whether the customer is feeling stressed, and generate a short, concise response. The generation unit can also generate a longer response with detailed explanations if the customer is relaxed. For example, the generation unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and generate a longer response with detailed explanations. The generation unit can also generate a quick, concise response if the customer is in a hurry. For example, the generation unit can use a biosensor to measure the customer's heart rate and electrodermal activity, determine whether the customer is in a hurry, and generate a quick, concise response. This allows the response to be provided at an appropriate length 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 generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input data for emotion estimation to the generation AI and cause the generation AI to estimate the emotion.

[0074] When generating answers, the generation unit can determine the priority of answers based on the time the question was submitted. For example, the generation unit can generate answers with priority for recently submitted questions. For example, the generation unit can generate answers with priority for recently submitted questions based on the submission date and time of the question. The generation unit can also generate answers with normal priority for previously submitted questions. For example, the generation unit can generate answers with normal priority for previously submitted questions based on the submission date and time of the question. Furthermore, the generation unit can generate answers with highest priority for urgent questions. For example, the generation unit can evaluate the urgency of the question and generate answers with highest priority for urgent questions. This allows answers to be provided with appropriate priority depending on the time the question was submitted. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to evaluate the time the question was submitted and determine the priority of the answers.

[0075] When generating answers, the generation unit can adjust the order of answers based on the relevance of the question. For example, when the relevance of a question is high, the generation unit can generate answers preferentially. For example, the generation unit can generate answers preferentially for questions with high relevance based on the similarity of the question content or related topics. Furthermore, when the relevance of a question is low, the generation unit can generate answers in a normal order. For example, the generation unit can generate answers in a normal order for questions with low relevance based on the similarity of the question content or related topics. Furthermore, the generation unit can dynamically adjust the order of answers depending on the relevance of the question. For example, the generation unit can evaluate the relevance of the question and dynamically adjust the order of answers depending on the relevance. This makes it possible to provide answers in an appropriate order depending on the relevance of the question. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can cause a generation AI to evaluate the relevance of a question and adjust the order of answers.

[0076] The reading unit can estimate the customer's emotions and adjust the reading speed based on the estimated emotions. For example, if the customer is feeling stressed, the reading unit can read at a slower speed. For example, the reading unit can use facial expression recognition technology to analyze the customer's facial expression, determine whether the customer is feeling stressed, and then read at a slower speed. Furthermore, if the customer is relaxed, the reading unit can read at a normal speed. For example, the reading unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and then read at a normal speed. Furthermore, if the customer is in a hurry, the reading unit can read at a faster speed. For example, the reading unit can use a biosensor to measure the customer's heart rate and electrodermal activity, determine whether the customer is in a hurry, and then read at a faster speed. This allows the answer to be read at an appropriate speed depending on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit may input data for emotion estimation to the generation AI and cause the generation AI to estimate the emotion.

[0077] The reading unit can adjust the tone and intonation of the voice when reading out based on the content of the answer. For example, if the answer contains important information, the reading unit can read it in an emphasized tone. For example, the reading unit can analyze the content of the answer and read it in an emphasized tone if it contains important information. The reading unit can also read it in a normal tone if the answer contains general information. For example, the reading unit can analyze the content of the answer and read it in a normal tone if it contains general information. Furthermore, the reading unit can also read it in a quick and clear tone if the answer contains urgent information. For example, the reading unit can analyze the content of the answer and read it in a quick and clear tone if it contains urgent information. This allows the answer to be read out in an appropriate tone and intonation according to the content of the answer. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can have a generation AI analyze the content of the answer and adjust the tone and intonation of the voice.

[0078] When reading aloud, the reading unit can select the optimal reading method by referring to the customer's past voice setting history. The reading unit, for example, selects the optimal reading speed based on the voice speed previously set by the customer. For example, the reading unit can select the optimal reading speed by referring to the customer's past voice setting history. The reading unit can also select the optimal tone and intonation from the customer's past voice setting history. For example, the reading unit can select the optimal tone and intonation by referring to the customer's past voice setting history. Furthermore, the reading unit can suggest the optimal reading method based on the voice settings previously used by the customer. For example, the reading unit can suggest the optimal reading method based on the customer's past voice setting history. This makes it possible to provide the optimal reading method based on the customer's past voice setting history. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input data of the past voice setting history into a generation AI and have the generation AI select the optimal reading method.

[0079] The reading unit can estimate the customer's emotions and adjust the reading order based on the estimated emotions. For example, if the customer is feeling stressed, the reading unit can read important information first. For example, the reading unit can use facial expression recognition technology to analyze the customer's facial expressions, determine whether the customer is feeling stressed, and read important information first. Furthermore, if the customer is relaxed, the reading unit can read in the normal order. For example, the reading unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and read in the normal order. Furthermore, if the customer is in a hurry, the reading unit can prioritize reading urgent information. For example, the reading unit can use a biosensor to measure the customer's heart rate and electrodermal activity, determine whether the customer is in a hurry, and prioritize reading urgent information. This allows answers to be read in an appropriate order based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit may input data for emotion estimation to the generation AI and cause the generation AI to estimate the emotion.

[0080] When reading out, the reading unit can select the optimal audio format based on the customer's device information. For example, if the customer is using a smartphone, the reading unit can select the optimal audio format. For example, the reading unit can select the optimal audio format for the smartphone based on the customer's device information. Furthermore, if the customer is using a tablet, the reading unit can select the optimal audio format. For example, the reading unit can select the optimal audio format for the tablet based on the customer's device information. Furthermore, if the customer is using a PC, the reading unit can select the optimal audio format. For example, the reading unit can select the optimal audio format for the PC based on the customer's device information. This makes it possible to provide an answer in the optimal audio format based on the customer's device information. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input device information data to a generation AI and have the generation AI select the optimal audio format.

[0081] When reading aloud, the reading unit can complement the content of the audio by referring to literature related to the answer. For example, the reading unit can refer to literature related to the answer and read out supplementary information. For example, the reading unit can refer to academic papers or technical documents related to the answer and read out supplementary information. The reading unit can also refer to data related to the answer and provide detailed information. For example, the reading unit can refer to a database related to the answer and provide detailed information. Furthermore, the reading unit can also refer to past questions and answers related to the answer and provide supplementary information. For example, the reading unit can refer to a database of past questions and answers and provide supplementary information. In this way, supplementary information can be provided by referring to literature related to the answer. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input data from related literature into the generation AI and have the generation AI complete the content of the audio. === Hard Collateral 1-1 === Each of the multiple elements, including the above-described reception unit, generation unit, reading unit, and emotion estimation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives a customer's question. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the question using natural language processing technology and generates an appropriate answer. The reading unit is realized, for example, by the control unit 46A of the smart device 14 and converts the generated answer into speech and reads it at a desired speed setting. The emotion estimation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and estimates the customer's emotion and adjusts the timing of receiving the question. === Hard Collateral 1-2 === Each of the multiple elements, including the above-described reception unit, generation unit, reading unit, and emotion estimation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives a customer's question. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the question using natural language processing technology and generates an appropriate answer. The reading unit is realized, for example, by the control unit 46A of the smart glasses 214 and converts the generated answer into speech and reads it out at a desired speed setting. The emotion estimation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and estimates the customer's emotion and adjusts the timing of receiving the question. === Hard Collateral 1-3 === Each of the multiple elements including the above-described reception unit, generation unit, reading unit, and emotion estimation unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and receives a customer's question. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the question using natural language processing technology and generates an appropriate answer. The reading unit is realized by the control unit 46A of the headset-type terminal 314 and converts the generated answer into speech and reads it out at a desired speed. The emotion estimation unit is realized by the specific processing unit 290 of the data processing device 12 and estimates the customer's emotion and adjusts the timing of receiving the question. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, generation unit, reading unit, and emotion estimation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives a customer's question. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the question using natural language processing technology and generates an appropriate answer. The reading unit is realized, for example, by the control unit 46A of the robot 414 and converts the generated answer into speech and reads it out at a desired speed. The emotion estimation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and estimates the customer's emotion and adjusts the timing of receiving the question.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The reception unit can predict questions based on the customer's past behavioral history. For example, the reception unit can analyze operations and questions that the customer has frequently performed in the past, and predict the question that the customer is likely to ask next. The reception unit can also suggest the most appropriate question based on the customer's past behavioral patterns. For example, the reception unit can suggest the most appropriate question that the customer is likely to ask next, based on the operations and questions that the customer has performed in the past. Furthermore, the reception unit can determine the priority of questions based on the customer's past behavioral history. For example, the reception unit can prioritize the most important questions based on the operations and questions that the customer has performed in the past. In this way, the customer's past behavioral history can be used to predict and suggest the most appropriate questions.

[0084] The generation unit can provide related videos and images based on the content of the question. For example, the generation unit can analyze the content of the question and search for and provide related videos and images. The generation unit can also generate related videos and images based on the content of the question. For example, the generation unit can generate and provide related videos and images based on the content of the question. Furthermore, the generation unit can edit related videos and images based on the content of the question. For example, the generation unit can edit and provide related videos and images based on the content of the question. This makes it possible to provide related videos and images according to the content of the question.

[0085] The generation unit can refer to related external resources based on the content of the question. For example, the generation unit can analyze the content of the question and search for and refer to related external websites or databases. The generation unit can also query related external experts based on the content of the question. For example, the generation unit can query related external experts based on the content of the question to obtain an answer. The generation unit can also refer to related external literature based on the content of the question. For example, the generation unit can generate an answer by referencing related external academic papers or technical documents based on the content of the question. This makes it possible to refer to related external resources according to the content of the question.

[0086] The generation unit can execute a related simulation based on the content of the question. For example, the generation unit can analyze the content of the question, execute a related simulation, and provide a result. The generation unit can also generate a related simulation model based on the content of the question. For example, the generation unit can generate a related simulation model based on the content of the question and provide a result. The generation unit can also analyze the results of the related simulation based on the content of the question. For example, the generation unit can analyze the results of the related simulation based on the content of the question and generate an answer. This makes it possible to execute a related simulation according to the content of the question.

[0087] The generation unit can visualize related data based on the content of the question. For example, the generation unit can analyze the content of the question and visualize and provide related data in the form of a graph, chart, or the like. The generation unit can also interactively visualize related data based on the content of the question. For example, the generation unit can visualize and provide related data in the form of an interactive graph, chart, or the like based on the content of the question. Furthermore, the generation unit can analyze the visualization results of the related data based on the content of the question. For example, the generation unit can analyze the visualization results of the related data based on the content of the question and generate an answer. This makes it possible to visualize related data according to the content of the question.

[0088] The generation unit can estimate the customer's emotions and adjust the tone of the response based on the estimated emotions. For example, if the customer is feeling stressed, the generation unit can generate a response in a gentle tone. For example, the generation unit can analyze the customer's facial expressions using facial expression recognition technology to determine whether the customer is feeling stressed and generate a response in a gentle tone. The generation unit can also generate a response in a normal tone if the customer is relaxed. For example, the generation unit can analyze the tone and speed of the customer's voice using voice analysis technology to determine whether the customer is relaxed and generate a response in a normal tone. Furthermore, the generation unit can generate a response in a quick tone if the customer is in a hurry. For example, the generation unit can measure the customer's heart rate and electrodermal activity using a biosensor to determine whether the customer is in a hurry and generate a response in a quick tone. This makes it possible to provide a response in an appropriate tone according to the customer's emotions.

[0089] The generation unit can estimate the customer's emotions and adjust the level of detail of the answer based on the estimated emotions. For example, if the customer is feeling stressed, the generation unit can generate a concise and clear answer. For example, the generation unit can use facial expression recognition technology to analyze the customer's facial expressions, determine whether the customer is feeling stressed, and generate a concise and clear answer. The generation unit can also generate an answer including a detailed explanation if the customer is relaxed. For example, the generation unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and generate an answer including a detailed explanation. Furthermore, the generation unit can generate a quick answer that gets to the point if the customer is in a hurry. For example, the generation unit can use a biosensor to measure the customer's heart rate and electrodermal activity, determine whether the customer is in a hurry, and generate a quick answer that gets to the point. This makes it possible to provide answers with an appropriate level of detail according to the customer's emotions.

[0090] The generation unit can estimate the customer's emotions and adjust the order of answers based on the estimated emotions. For example, if the customer is feeling stressed, the generation unit can provide important information first. For example, the generation unit can analyze the customer's facial expressions using facial expression recognition technology to determine whether the customer is feeling stressed and provide important information first. The generation unit can also provide answers in the normal order if the customer is relaxed. For example, the generation unit can analyze the tone and speed of the customer's voice using voice analysis technology to determine whether the customer is relaxed and provide answers in the normal order. Furthermore, the generation unit can provide urgent information with the highest priority if the customer is in a hurry. For example, the generation unit can measure the customer's heart rate and electrodermal activity using a biosensor to determine whether the customer is in a hurry and provide urgent information with the highest priority. This makes it possible to provide answers in an appropriate order according to the customer's emotions.

[0091] The generation unit can estimate the customer's emotions and adjust the format of the answer based on the estimated emotions. For example, if the customer is feeling stressed, the generation unit can provide a concise answer in text format. For example, the generation unit can use facial expression recognition technology to analyze the customer's facial expressions, determine whether the customer is feeling stressed, and provide a concise answer in text format. The generation unit can also provide a detailed answer in audio format if the customer is relaxed. For example, the generation unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and provide a detailed answer in audio format. Furthermore, if the customer is in a hurry, the generation unit can provide an answer in a video format that is concise to the point. For example, the generation unit can use a biosensor to measure the customer's heart rate and electrodermal activity, determine whether the customer is in a hurry, and provide an answer in a video format that is concise to the point. This makes it possible to provide an answer in an appropriate format according to the customer's emotions.

[0092] The generation unit can estimate the customer's emotions and adjust the content of the answer based on the estimated emotions. For example, if the customer is feeling stressed, the generation unit can generate an answer containing positive content. For example, the generation unit can use facial expression recognition technology to analyze the customer's facial expressions, determine whether the customer is feeling stressed, and generate an answer containing positive content. The generation unit can also generate an answer containing detailed explanations if the customer is relaxed. For example, the generation unit can use voice analysis technology to analyze the tone and speed of the customer's voice, determine whether the customer is relaxed, and generate an answer containing detailed explanations. Furthermore, the generation unit can generate a quick answer that gets to the point if the customer is in a hurry. For example, the generation unit can use a biosensor to measure the customer's heart rate and electrodermal activity, determine whether the customer is in a hurry, and generate a quick answer that gets to the point. This makes it possible to provide an answer with appropriate content according to the customer's emotions.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The reception unit receives a question from a customer. The question entered by the customer may be in text format or voice format, but is not limited to these examples. The reception unit can receive the question using, for example, keyboard input or voice input. Step 2: The generation unit uses natural language processing technology to analyze the question received by the reception unit and extract keywords. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the generation unit uses morphological analysis to divide the words in the question, grammatical analysis to analyze the sentence structure, and semantic analysis to understand the meaning of the question. The generation unit also searches for an appropriate answer from a database that has been trained in advance. For example, the database includes, but is not limited to, an FAQ database and past inquiry data. For example, the generation unit uses an algorithm that searches for relevant answers from the FAQ database and selects the optimal answer based on past inquiry data. Step 3: The reading unit converts the generated response into speech using speech synthesis technology. Examples of speech synthesis technology include, but are not limited to, text-to-speech synthesis (TTS) and voice sample-based synthesis. For example, the reading unit converts text into speech using text-to-speech synthesis and generates natural-sounding speech using voice sample-based synthesis. The reading unit also adjusts the playback speed of the speech according to the speed setting desired by the customer. Examples of speed settings include, but are not limited to, 1x speed, 1.5x speed, and 2x speed. For example, if the reading unit requests a 1.5x speed, the reading unit generates speech at 1.5x speed using speech synthesis technology.

[0095] 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.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0097] 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.

[0098] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0099] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0100] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0113] 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.

[0114] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0115] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0129] 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.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 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.

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

[0134] The 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.

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

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

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

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0146] 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.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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."

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0165] 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.

[0166] [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk to answer questions from customers, a generation unit that analyzes the question received by the reception unit and generates an answer; a reading unit that reads out the answer generated by the generation unit at a speed specified by the customer. A system characterized by:

2. The reception unit Accept questions entered by customers 2. The system of claim 1.

3. The generation unit Analyze questions and extract keywords using natural language processing technology 2. The system of claim 1.

4. The generation unit Searching for the right answer from a pre-trained database 2. The system of claim 1.

5. The generation unit Uses an algorithm that selects the most appropriate answer based on data from past questions and answers 2. The system of claim 1.

6. The reading unit Convert the generated answers into speech using speech synthesis technology 2. The system of claim 1.

7. The reading unit Adjust the audio playback speed according to your desired speed setting 2. The system of claim 1.

8. The reception unit Estimate customer emotions and adjust the timing of questions based on those emotions 2. The system of claim 1.

9. The reception unit Analyze the customer's past question history and select the most appropriate reception method 2. The system of claim 1.

10. The reception unit When you submit a question, we filter it based on your current contract status and areas of interest.

2. The system of claim 1.

Images