System

Abstract

To provide a system that enables interaction with a user by utilizing the knowledge and thought of great figures or the deceased.SOLUTION: A system according to an embodiment comprises a digitization unit, a conversion unit, a response generation unit, a reception unit and a provision unit. The digitization unit digitizes writings or logs of great figures or the deceased. The conversion unit performs vector conversion on the data digitized by the digitization unit. The response generation unit analyzes the data vector-converted by the conversion unit and generates a response to the user's question. The reception unit receives the user's question. The provision unit provides the response generated by the response generation unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem that it is difficult to utilize the knowledge and thoughts of great people or deceased people to communicate with users.

[0005] The system according to the embodiment aims to communicate with the user by utilizing the knowledge and ideas of great people and deceased people. [Means for solving the problem]

[0006] The system according to the embodiment includes a digitization unit, a conversion unit, an answer generation unit, a reception unit, and a provision unit. The digitization unit digitizes books or logs of great people or deceased people. The conversion unit vector-converts the data digitized by the digitization unit. The answer generation unit analyzes the data vector-converted by the conversion unit and generates an answer to a user's question. The reception unit accepts the user's question. The provision unit provides the answer generated by the answer generation unit. Effect of the Invention

[0007] The system according to the embodiment can communicate with the user by utilizing the knowledge and ideas of great people and deceased people. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The conversation system according to the embodiment of the present invention is a system that digitizes books and logs left by great people and deceased people, performs vector conversion, and generates and provides appropriate answers to user questions. This conversation system digitizes books and logs left by great people and deceased people, and a generation AI analyzes the vector-converted data and generates appropriate answers to user questions, allowing the user to have an experience of conversing with the great people and deceased people. For example, the conversation system digitizes books and logs left by great people and deceased people. For example, handwritten manuscripts, diaries, lecture notes, etc. are scanned and converted into text data. This digitized data is input to the generation AI. Next, the conversation system vector-converts the digitized data using the generation AI. Vector conversion is a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the meaning of a word or phrase is expressed as a numerical value, and the generation AI analyzes it. Next, the conversation system analyzes the vector-converted data using the generation AI and generates an appropriate answer to the user's question. For example, if a user asks "Please tell me about the thinking of great person A," the generative AI extracts relevant information from the books and logs of great person A and generates an answer. This answer is provided to the user in natural language. This allows the conversation system to provide an experience that makes it seem as if the user is having a conversation with a great person or a deceased person. For example, if you want to learn about the thinking and philosophy of a historical figure, you can gain a deeper understanding by having the generative AI provide an answer based on that person's books and logs. It is also possible to gain insight into modern issues through the words of great people and deceased people. This allows the conversation system to generate and provide appropriate answers to the user's questions.

[0029] The conversation system according to the embodiment includes a digitizing unit, a converting unit, an answer generating unit, a receiving unit, and a providing unit. The digitizing unit digitizes books and logs of great people and deceased people. The books and logs of great people and deceased people include, for example, handwritten manuscripts, diaries, lecture records, etc., but are not limited to such examples. The digitizing unit, for example, digitizes and reads handwritten manuscripts using scanning technology. The digitizing unit can also directly read books and logs submitted in digital format. Furthermore, the digitizing unit can also read printed books and logs using OCR technology. For example, the digitizing unit scans handwritten manuscripts with a high-resolution scanner and converts them into character information using OCR technology. Digital books and logs submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The converting unit uses generation AI to vector convert the data digitized by the digitizing unit. Vector conversion is, for example, a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the generation AI converts text data into vectors using a text generation AI (for example, LLM). The conversion unit can also convert text data into vectors using a multimodal generation AI. The conversion unit can also use the generation AI to express the meaning of words and phrases as numerical values, which the generation AI can analyze. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, as well as text. The generation AI uses keyword extraction technology to pick up particularly important information from the text data and performs vector conversion based on that. The answer generation unit analyzes the data vector-converted by the conversion unit and generates an appropriate answer to the user's question. The answer generation unit extracts relevant information from books and logs of great people and deceased people in response to the user's question, and generates an answer. For example, if a user asks, "Please tell me about the thinking of great person A," the answer generation unit extracts relevant information from the books and logs of great person A and generates an answer.The answer is provided to the user in natural language. The reception unit receives the user's question as an input. The reception unit can receive the user's question in, for example, a text format or a voice format. For example, the reception unit provides an interface for the user to input the question in a text format. The reception unit can also provide an interface for the user to input the question in a voice format. The provision unit provides the answer generated by the answer generation unit to the user. The provision unit can provide the answer in, for example, a text format or a voice format. For example, the provision unit displays the generated answer to the user in a text format. The provision unit can also provide the generated answer to the user in a voice format. In this way, the conversation system according to the embodiment can digitize books and logs of great people and deceased people, and generate and provide appropriate answers to the user's questions.

[0030] The digitization department digitizes books and logs of great people and deceased people. Books and logs of great people and deceased people include, for example, handwritten manuscripts, diaries, lecture records, etc., but are not limited to such examples. For example, the digitization department digitizes and reads handwritten manuscripts using scanning technology. The digitization department can also directly read books and logs submitted in digital format. Furthermore, the digitization department can read printed books and logs using OCR technology. For example, the digitization department scans handwritten manuscripts with a high-resolution scanner and converts them into character information using OCR technology. Digital books and logs submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The digitization department can centrally manage these data and link with other systems and departments as necessary. For example, the digitized data is stored in a cloud server and made accessible to the conversion department and answer generation department. The digitization department can also adjust the frequency and accuracy of data collection to flexibly respond to specific situations and conditions. This allows the digitization department to collect data efficiently and effectively, improving the performance of the entire system. In addition, the digitization department can also verify and correct data to ensure the quality of the digitized data. For example, it can check the resolution of scanned images and the recognition accuracy of OCR, and make manual corrections if necessary. This allows the digitization department to provide high-quality digital data and improve the accuracy of subsequent processing and analysis.

[0031] The conversion unit uses the generation AI to vector-convert the data digitized by the digitization unit. Vector conversion is, for example, a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the generation AI converts the text data into vectors using a text generation AI (for example, LLM). The conversion unit can also convert the text data into vectors using a multimodal generation AI. The conversion unit can also use the generation AI to express the meaning of words and phrases as numerical values, which the generation AI can analyze. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to pick up particularly important information from the text data and performs vector conversion based on that. The conversion unit can centrally manage these vector data and link with other systems and departments as necessary. For example, the vector data is stored in a cloud server so that the answer generation unit can access it. The conversion unit can also verify and correct the conversion results to ensure the accuracy of the data conversion. This enables the conversion unit to provide highly accurate vector data and improve the accuracy of subsequent processing and analysis. Furthermore, the conversion unit can periodically update the learning data of the generation AI to keep up with the latest information and trends. This enables the conversion unit to always use the latest technology to perform highly accurate data conversion and improve the performance of the entire system.

[0032] The answer generation unit analyzes the data vector-converted by the conversion unit and generates an appropriate answer to the user's question. For example, the answer generation unit extracts relevant information from books and logs of great people and deceased people in response to the user's question, and generates an answer. For example, if the user asks, "Please tell me about the way great person A thinks," the answer generation unit extracts relevant information from books and logs of great person A and generates an answer. This answer is provided to the user in natural language. The answer generation unit uses a generation AI to analyze the intention of the user's question and select the most appropriate information. For example, the generation AI analyzes the context and keywords of the question and identifies related information. In addition, the answer generation unit uses the generation AI to reconstruct the extracted information in natural language and provide it to the user. This allows the answer generation unit to quickly and accurately generate answers to the user's questions. Furthermore, the answer generation unit can learn data on past questions and answers and continuously improve the accuracy and quality of the answers. For example, the generation AI model is updated based on data on past questions and answers, and is given more advanced natural language processing capabilities. The answer generation unit can also collect user feedback and use it to improve the accuracy and quality of the answers, allowing the answer generation unit to always provide highly accurate answers based on the latest information and improve user satisfaction.

[0033] The reception unit receives a user's question as an input. The reception unit can receive the user's question in, for example, a text format or a voice format. For example, the reception unit provides an interface for the user to input a question in text format. The reception unit can also provide an interface for the user to input a question in voice format. The reception unit can centrally manage these input data and cooperate with other systems and departments as necessary. For example, the reception unit stores the text format question in a database so that the conversion unit and the answer generation unit can access it. Furthermore, the voice format question can be converted into text using voice recognition technology and similarly stored in a database. This allows the reception unit to efficiently and effectively receive the user's question and improve the performance of the entire system. Furthermore, the reception unit can perform appropriate processing according to the content and format of the user's question. For example, a specific processing rule is applied to a question that includes a specific keyword or phrase, and the reception unit can respond quickly. Furthermore, the reception unit can manage the history of the user's questions and refer to past questions and answers to perform a more appropriate response. This allows the reception unit to quickly and accurately respond to the user's questions and improve the reliability of the entire system and user satisfaction.

[0034] The providing unit provides the answer generated by the answer generating unit to the user. The providing unit can provide the answer in, for example, a text format or a voice format. For example, the providing unit displays the generated answer to the user in a text format. The providing unit can also provide the generated answer to the user in a voice format. The providing unit can centrally manage these answer data and cooperate with other systems and departments as necessary. For example, the providing unit can store the text format answer in a database so that the user can refer to it later. The voice format answer can also be stored as an audio file so that the user can similarly play it later. This allows the providing unit to provide answers efficiently and effectively and improve the performance of the entire system. Furthermore, the providing unit can collect user feedback and continuously improve the accuracy and quality of the answers. For example, the providing unit provides an interface for the user to input evaluations and comments on the provided answers, and updates the model of the answer generating unit based on these feedbacks. The providing unit can also reliably transmit information using multiple communication means. For example, important information can be reliably delivered by using not only text format answers but also voice calls, SMS, emails, etc. This enables the providing unit to provide answers to users quickly and reliably, thereby improving the reliability of the entire system and user satisfaction.

[0035] The digitizing unit can scan handwritten manuscripts, diaries, and lecture notes and convert them into text data. For example, the digitizing unit reads handwritten manuscripts with a scanner and saves them as image data. The digitizing unit then converts the image data into text data using OCR technology. The digitizing unit can also take a picture of a handwritten manuscript using a smartphone camera and convert the image data into text data using a dedicated app. For example, the app automatically corrects the image and performs character recognition. The digitizing unit can also write handwritten manuscripts with a dedicated digital pen, which then converts the manuscripts into digital data in real time. For example, a sensor detects the movement of the pen and saves it as character data. This makes it possible to digitize handwritten manuscripts, diaries, lecture notes, and the like.

[0036] The conversion unit can perform vector conversion to convert text data into numerical data. The conversion unit, for example, performs vector conversion to convert text data into numerical data. Vector conversion is a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the conversion unit converts text data into vectors using a text generation AI (for example, LLM). The conversion unit can also convert text data into vectors using a multimodal generation AI. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities such as images and audio as well as text. The generation AI uses keyword extraction technology to pick up particularly important information in the text data and performs vector conversion based on that. This allows the text data to be converted into numerical data.

[0037] The answer generation unit can analyze the vector-converted data and generate an appropriate answer to the user's question. The answer generation unit, for example, analyzes the vector-converted data and generates an appropriate answer to the user's question. The answer generation unit, for example, extracts relevant information from books and logs of great people and deceased people in response to the user's question and generates an answer. For example, if the user asks, "Please tell me about the thinking of great person A," the answer generation unit extracts relevant information from books and logs of great person A and generates an answer. This answer is provided to the user in natural language. This makes it possible to generate an appropriate answer to the user's question.

[0038] The reception unit can receive a user's question as an input. The reception unit can receive the user's question in, for example, a text format or a voice format. For example, the reception unit provides an interface for the user to input a question in text format. The reception unit can also provide an interface for the user to input a question in voice format. In this way, the user's question can be received as an input.

[0039] The providing unit can provide the generated answer to the user. The providing unit can provide the answer in, for example, a text format or an audio format. For example, the providing unit displays the generated answer to the user in a text format. The providing unit can also provide the generated answer to the user in an audio format. In this way, the generated answer can be provided to the user.

[0040] The digitization unit can learn the unique characteristics of the handwriting of great people or deceased people in order to improve the accuracy of handwritten character recognition. For example, the digitization unit learns the characteristics of the handwritten characters of great person A and improves the recognition accuracy. The digitization unit can also learn the handwriting habits of great person B and reduce erroneous recognition. Furthermore, the digitization unit can also learn the unique writing style of great person C and convert it into accurate text data. This can improve the accuracy of handwritten character recognition.

[0041] The digitizing unit can select the optimal scanning method in consideration of the deterioration state of the book or log. For example, the digitizing unit selects low pressure scanning when scanning a deteriorated book. The digitizing unit can also use a color correction function when scanning a faded log. Furthermore, the digitizing unit can also select a special scanning method to protect the pages when scanning a book that is easily torn. In this way, the optimal scanning method can be selected in consideration of the deterioration state of the book or log.

[0042] The digitizing unit can select the optimal scanning method in consideration of the physical storage state of the book or log. For example, the digitizing unit selects low pressure scanning when scanning a book that is deteriorating. The digitizing unit can also use a color correction function when scanning a faded log. Furthermore, the digitizing unit can also select a special scanning method to protect the pages when scanning a book that is easily torn. In this way, the optimal scanning method can be selected in consideration of the physical storage state of the book or log.

[0043] The digitization unit can apply different digitization algorithms based on the contents of the book or log. For example, the digitization unit applies a handwriting recognition algorithm to a handwritten manuscript. The digitization unit can also apply an OCR algorithm to a printed book. Furthermore, the digitization unit can apply an image recognition algorithm to a log that contains many photos and figures. In this way, different digitization algorithms can be applied based on the contents of the book or log.

[0044] The conversion unit can combine multiple conversion algorithms to gain a deeper understanding of the context of the text data. For example, the conversion unit can combine Word2Vec and BERT to understand the meaning of words. The conversion unit can also combine LSTM and Transformer to understand the context. Furthermore, the conversion unit can combine GloVe and ELMo to understand the meaning of phrases. This allows for a deeper understanding of the context of the text data.

[0045] The conversion unit can apply different conversion methods depending on the category of the text data. For example, the conversion unit applies a conversion method that takes into account historical context to historical text. The conversion unit can also apply a conversion method that takes into account scientific terms to scientific text. The conversion unit can also apply a conversion method that takes into account philosophical concepts to philosophical text. This makes it possible to apply different conversion methods depending on the category of the text data.

[0046] The conversion unit can select an optimal conversion method in consideration of the language characteristics of the text data. For example, the conversion unit applies an English-specific conversion method to English text. The conversion unit can also apply a Japanese-specific conversion method to Japanese text. Furthermore, the conversion unit can also apply conversion methods corresponding to each language to multilingual text. This makes it possible to select an optimal conversion method in consideration of the language characteristics of the text data.

[0047] The conversion unit can adjust the conversion algorithm according to the length of the text data. For example, the conversion unit applies a lightweight conversion algorithm to short text. The conversion unit can also apply a detailed conversion algorithm to long text. Furthermore, the conversion unit can also apply a balanced conversion algorithm to medium-length text. This makes it possible to adjust the conversion algorithm according to the length of the text data.

[0048] The answer generation unit can refer to multiple data sources to more deeply reflect the thoughts and philosophies of great people and deceased people. For example, the answer generation unit generates an answer by referring to the books and lecture records of great person A. The answer generation unit can also generate an answer by referring to the diary and letters of great person B. Furthermore, the answer generation unit can also generate an answer by referring to the writings and interviews of great person C. This allows the thoughts and philosophies of great people and deceased people to be more deeply reflected.

[0049] The answer generation unit can apply different generation algorithms depending on the category of the user's question. For example, the answer generation unit applies a generation algorithm that takes historical context into consideration to a question about history. The answer generation unit can also apply a generation algorithm that takes scientific knowledge into consideration to a question about science. Furthermore, the answer generation unit can also apply a generation algorithm that takes philosophical concepts into consideration to a question about philosophy. This makes it possible to generate an optimal answer depending on the category of the user's question.

[0050] The answer generation unit can provide an optimal answer by referring to the user's past question history. The answer generation unit can provide a relevant answer based on, for example, the content of a question asked by the user in the past. The answer generation unit can also provide an answer that is likely to be of interest to the user from the user's past question history. Furthermore, the answer generation unit can analyze the user's past question history and provide the most appropriate answer. This makes it possible to provide an optimal answer based on the user's past question history.

[0051] The answer generation unit can adjust the level of detail of the answer depending on the user's level of expertise. For example, the answer generation unit can provide a beginner with an answer that includes a basic explanation. The answer generation unit can also provide an intermediate user with an answer that includes a detailed explanation. Furthermore, the answer generation unit can also provide an advanced user with an answer that includes specialized knowledge. This makes it possible to provide an optimal answer depending on the user's level of expertise.

[0052] The reception unit can select the optimal reception method by referring to the user's past question history. For example, the reception unit preferentially suggests an input method (voice, text, etc.) that the user has used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past question history. Furthermore, the reception unit can analyze the user's past question history and suggest the most efficient reception method. This makes it possible to select the optimal reception method based on the user's past question history.

[0053] The reception unit can select the optimal reception method in consideration of the device information of the user. For example, when the user is using a smartphone, the reception unit preferentially suggests voice input. Furthermore, when the user is using a tablet, the reception unit can also preferentially suggest touch input. Furthermore, when the user is using a desktop, the reception unit can also preferentially suggest keyboard input. In this way, the optimal reception method can be selected based on the device information of the user.

[0054] The providing unit can select the optimal providing method by referring to the user's past answer history. The providing unit selects the optimal providing method based on, for example, the format of answers the user has received in the past. The providing unit can also provide answers in a format that is likely to interest the user based on the user's past answer history. Furthermore, the providing unit can analyze the user's past answer history and select the most appropriate providing method. In this way, the optimal providing method can be selected based on the user's past answer history.

[0055] The providing unit can select the optimal providing method in consideration of the device information of the user. For example, when the user is using a smartphone, the providing unit provides a display method that matches the screen size. In addition, when the user is using a tablet, the providing unit can also provide a display method optimized for a large screen. Furthermore, when the user is using a desktop, the providing unit can also provide a display method that includes detailed information. This makes it possible to select the optimal providing method based on the device information of the user.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The conversation system may further include a history analysis unit that analyzes the user's past question history. The history analysis unit analyzes the pattern of questions the user has asked in the past to identify the user's interests and concerns. For example, if the user frequently asks questions about a particular historical figure, new information related to that historical figure may be provided preferentially. The history analysis unit may also predict future questions based on the user's question trends and prepare related information in advance. Furthermore, the history analysis unit may provide more detailed information based on the user's question history, taking into account the content of answers the user has obtained in the past. This allows the user's past question history to be utilized to provide more personalized answers.

[0058] The transformation part can combine multiple transformation algorithms to further understand the context of the text data. For example, it can combine Word2Vec and BERT to understand the meaning of words. It can also combine LSTM and Transformer to understand the context. It can also combine GloVe and ELMo to understand the meaning of phrases. This allows for a deeper understanding of the context of the text data.

[0059] The conversation system may further include an expertise estimation unit that estimates the expertise level of the user. The expertise estimation unit estimates the expertise level of the user based on the content of the user's question and past question history. For example, an answer including a basic explanation may be provided to a beginner. Also, an answer including a detailed explanation may be provided to an intermediate user. Furthermore, an answer including specialized knowledge may be provided to an advanced user. In this way, the most suitable answer may be provided according to the user's expertise level.

[0060] The conversation system may further include a device adaptation unit that selects the optimal presentation method in consideration of the user's device information. The device adaptation unit detects the type and characteristics of the device used by the user and selects the optimal presentation method accordingly. For example, if the user is using a smartphone, a display method that matches the screen size can be provided. Also, if the user is using a tablet, a display method optimized for a large screen can be provided. Furthermore, if the user is using a desktop, a display method including detailed information can be provided. This makes it possible to select the optimal presentation method based on the user's device information.

[0061] The conversation system may further include a category adaptation unit that applies different generation algorithms depending on the category of the user's question. The category adaptation unit analyzes the content of the user's question and selects the optimal generation algorithm depending on the category. For example, a generation algorithm that takes historical context into consideration may be applied to a question about history. Also, a generation algorithm that takes scientific knowledge into consideration may be applied to a question about science. Furthermore, a generation algorithm that takes philosophical concepts into consideration may be applied to a question about philosophy. This makes it possible to generate an optimal answer depending on the category of the user's question.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The Digitization Department digitizes the books and logs of great and deceased people. For example, handwritten manuscripts can be digitized and read using scanning technology. It can also directly read books and logs submitted in digital format. It can also read printed books and logs using OCR technology. Step 2: The conversion unit converts the data digitized by the digitization unit into vectors using a generation AI. For example, the conversion unit converts the text data into vectors using a text generation AI (e.g., LLM). The conversion unit can also convert the text data into vectors using a multimodal generation AI. Step 3: The answer generation unit analyzes the vector-converted data by the conversion unit and generates an appropriate answer to the user's question. For example, in response to the user's question, the answer generation unit extracts relevant information from books and logs of great people and deceased people and generates an answer. Step 4: The reception unit receives a user's question as an input. For example, the user's question can be received in text format or voice format. Step 5: The providing unit provides the answer generated by the answer generating unit to the user. For example, the answer can be provided in a text format or a voice format.

[0064] (Example 2) The conversation system according to the embodiment of the present invention is a system that digitizes books and logs left by great people and deceased people, performs vector conversion, and generates and provides appropriate answers to user questions. This conversation system digitizes books and logs left by great people and deceased people, and a generation AI analyzes the vector-converted data and generates appropriate answers to user questions, allowing the user to have an experience of conversing with the great people and deceased people. For example, the conversation system digitizes books and logs left by great people and deceased people. For example, handwritten manuscripts, diaries, lecture notes, etc. are scanned and converted into text data. This digitized data is input to the generation AI. Next, the conversation system vector-converts the digitized data using the generation AI. Vector conversion is a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the meaning of a word or phrase is expressed as a numerical value, and the generation AI analyzes it. Next, the conversation system analyzes the vector-converted data using the generation AI and generates an appropriate answer to the user's question. For example, if a user asks "Please tell me about the thinking of great person A," the generative AI extracts relevant information from the books and logs of great person A and generates an answer. This answer is provided to the user in natural language. This allows the conversation system to provide an experience that makes it seem as if the user is having a conversation with a great person or a deceased person. For example, if you want to learn about the thinking and philosophy of a historical figure, you can gain a deeper understanding by having the generative AI provide an answer based on that person's books and logs. It is also possible to gain insight into modern issues through the words of great people and deceased people. This allows the conversation system to generate and provide appropriate answers to the user's questions.

[0065] The conversation system according to the embodiment includes a digitizing unit, a converting unit, an answer generating unit, a receiving unit, and a providing unit. The digitizing unit digitizes books and logs of great people and deceased people. The books and logs of great people and deceased people include, for example, handwritten manuscripts, diaries, lecture records, etc., but are not limited to such examples. The digitizing unit, for example, digitizes and reads handwritten manuscripts using scanning technology. The digitizing unit can also directly read books and logs submitted in digital format. Furthermore, the digitizing unit can also read printed books and logs using OCR technology. For example, the digitizing unit scans handwritten manuscripts with a high-resolution scanner and converts them into character information using OCR technology. Digital books and logs submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The converting unit uses generation AI to vector convert the data digitized by the digitizing unit. Vector conversion is, for example, a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the generation AI converts text data into vectors using a text generation AI (for example, LLM). The conversion unit can also convert text data into vectors using a multimodal generation AI. The conversion unit can also use the generation AI to express the meaning of words and phrases as numerical values, which the generation AI can analyze. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, as well as text. The generation AI uses keyword extraction technology to pick up particularly important information from the text data and performs vector conversion based on that. The answer generation unit analyzes the data vector-converted by the conversion unit and generates an appropriate answer to the user's question. The answer generation unit extracts relevant information from books and logs of great people and deceased people in response to the user's question, and generates an answer. For example, if a user asks, "Please tell me about the thinking of great person A," the answer generation unit extracts relevant information from the books and logs of great person A and generates an answer.The answer is provided to the user in natural language. The reception unit receives the user's question as an input. The reception unit can receive the user's question in, for example, a text format or a voice format. For example, the reception unit provides an interface for the user to input the question in a text format. The reception unit can also provide an interface for the user to input the question in a voice format. The provision unit provides the answer generated by the answer generation unit to the user. The provision unit can provide the answer in, for example, a text format or a voice format. For example, the provision unit displays the generated answer to the user in a text format. The provision unit can also provide the generated answer to the user in a voice format. In this way, the conversation system according to the embodiment can digitize books and logs of great people and deceased people, and generate and provide appropriate answers to the user's questions.

[0066] The digitization department digitizes books and logs of great people and deceased people. Books and logs of great people and deceased people include, for example, handwritten manuscripts, diaries, lecture records, etc., but are not limited to such examples. For example, the digitization department digitizes and reads handwritten manuscripts using scanning technology. The digitization department can also directly read books and logs submitted in digital format. Furthermore, the digitization department can read printed books and logs using OCR technology. For example, the digitization department scans handwritten manuscripts with a high-resolution scanner and converts them into character information using OCR technology. Digital books and logs submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The digitization department can centrally manage these data and link with other systems and departments as necessary. For example, the digitized data is stored in a cloud server and made accessible to the conversion department and answer generation department. The digitization department can also adjust the frequency and accuracy of data collection to flexibly respond to specific situations and conditions. This allows the digitization department to collect data efficiently and effectively, improving the performance of the entire system. In addition, the digitization department can also verify and correct data to ensure the quality of the digitized data. For example, it can check the resolution of scanned images and the recognition accuracy of OCR, and make manual corrections if necessary. This allows the digitization department to provide high-quality digital data and improve the accuracy of subsequent processing and analysis.

[0067] The conversion unit uses the generation AI to vector-convert the data digitized by the digitization unit. Vector conversion is, for example, a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the generation AI converts the text data into vectors using a text generation AI (for example, LLM). The conversion unit can also convert the text data into vectors using a multimodal generation AI. The conversion unit can also use the generation AI to express the meaning of words and phrases as numerical values, which the generation AI can analyze. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to pick up particularly important information from the text data and performs vector conversion based on that. The conversion unit can centrally manage these vector data and link with other systems and departments as necessary. For example, the vector data is stored in a cloud server so that the answer generation unit can access it. The conversion unit can also verify and correct the conversion results to ensure the accuracy of the data conversion. This enables the conversion unit to provide highly accurate vector data and improve the accuracy of subsequent processing and analysis. Furthermore, the conversion unit can periodically update the learning data of the generation AI to keep up with the latest information and trends. This enables the conversion unit to always use the latest technology to perform highly accurate data conversion and improve the performance of the entire system.

[0068] The answer generation unit analyzes the data vector-converted by the conversion unit and generates an appropriate answer to the user's question. For example, the answer generation unit extracts relevant information from books and logs of great people and deceased people in response to the user's question, and generates an answer. For example, if the user asks, "Please tell me about the way great person A thinks," the answer generation unit extracts relevant information from books and logs of great person A and generates an answer. This answer is provided to the user in natural language. The answer generation unit uses a generation AI to analyze the intention of the user's question and select the most appropriate information. For example, the generation AI analyzes the context and keywords of the question and identifies related information. In addition, the answer generation unit uses the generation AI to reconstruct the extracted information in natural language and provide it to the user. This allows the answer generation unit to quickly and accurately generate answers to the user's questions. Furthermore, the answer generation unit can learn data on past questions and answers and continuously improve the accuracy and quality of the answers. For example, the generation AI model is updated based on data on past questions and answers, and is given more advanced natural language processing capabilities. The answer generation unit can also collect user feedback and use it to improve the accuracy and quality of the answers, allowing the answer generation unit to always provide highly accurate answers based on the latest information and improve user satisfaction.

[0069] The reception unit receives a user's question as an input. The reception unit can receive the user's question in, for example, a text format or a voice format. For example, the reception unit provides an interface for the user to input a question in text format. The reception unit can also provide an interface for the user to input a question in voice format. The reception unit can centrally manage these input data and cooperate with other systems and departments as necessary. For example, the reception unit stores the text format question in a database so that the conversion unit and the answer generation unit can access it. Furthermore, the voice format question can be converted into text using voice recognition technology and similarly stored in a database. This allows the reception unit to efficiently and effectively receive the user's question and improve the performance of the entire system. Furthermore, the reception unit can perform appropriate processing according to the content and format of the user's question. For example, a specific processing rule is applied to a question that includes a specific keyword or phrase, and the reception unit can respond quickly. Furthermore, the reception unit can manage the history of the user's questions and refer to past questions and answers to perform a more appropriate response. This allows the reception unit to quickly and accurately respond to the user's questions and improve the reliability of the entire system and user satisfaction.

[0070] The providing unit provides the answer generated by the answer generating unit to the user. The providing unit can provide the answer in, for example, a text format or a voice format. For example, the providing unit displays the generated answer to the user in a text format. The providing unit can also provide the generated answer to the user in a voice format. The providing unit can centrally manage these answer data and cooperate with other systems and departments as necessary. For example, the providing unit can store the text format answer in a database so that the user can refer to it later. The voice format answer can also be stored as an audio file so that the user can similarly play it later. This allows the providing unit to provide answers efficiently and effectively and improve the performance of the entire system. Furthermore, the providing unit can collect user feedback and continuously improve the accuracy and quality of the answers. For example, the providing unit provides an interface for the user to input evaluations and comments on the provided answers, and updates the model of the answer generating unit based on these feedbacks. The providing unit can also reliably transmit information using multiple communication means. For example, important information can be reliably delivered by using not only text format answers but also voice calls, SMS, emails, etc. This enables the providing unit to provide answers to users quickly and reliably, thereby improving the reliability of the entire system and user satisfaction.

[0071] The digitizing unit can scan handwritten manuscripts, diaries, and lecture notes and convert them into text data. For example, the digitizing unit reads handwritten manuscripts with a scanner and saves them as image data. The digitizing unit then converts the image data into text data using OCR technology. The digitizing unit can also take a picture of a handwritten manuscript using a smartphone camera and convert the image data into text data using a dedicated app. For example, the app automatically corrects the image and performs character recognition. The digitizing unit can also write handwritten manuscripts with a dedicated digital pen, which then converts the manuscripts into digital data in real time. For example, a sensor detects the movement of the pen and saves it as character data. This makes it possible to digitize handwritten manuscripts, diaries, lecture notes, and the like.

[0072] The conversion unit can perform vector conversion to convert text data into numerical data. The conversion unit, for example, performs vector conversion to convert text data into numerical data. Vector conversion is a process of converting text data into numerical data, and is a necessary step for the generation AI to understand the meaning and context of the text. For example, the conversion unit converts text data into vectors using a text generation AI (for example, LLM). The conversion unit can also convert text data into vectors using a multimodal generation AI. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities such as images and audio as well as text. The generation AI uses keyword extraction technology to pick up particularly important information in the text data and performs vector conversion based on that. This allows the text data to be converted into numerical data.

[0073] The answer generation unit can analyze the vector-converted data and generate an appropriate answer to the user's question. The answer generation unit, for example, analyzes the vector-converted data and generates an appropriate answer to the user's question. The answer generation unit, for example, extracts relevant information from books and logs of great people and deceased people in response to the user's question and generates an answer. For example, if the user asks, "Please tell me about the thinking of great person A," the answer generation unit extracts relevant information from books and logs of great person A and generates an answer. This answer is provided to the user in natural language. This makes it possible to generate an appropriate answer to the user's question.

[0074] The reception unit can receive a user's question as an input. The reception unit can receive the user's question in, for example, a text format or a voice format. For example, the reception unit provides an interface for the user to input a question in text format. The reception unit can also provide an interface for the user to input a question in voice format. In this way, the user's question can be received as an input.

[0075] The providing unit can provide the generated answer to the user. The providing unit can provide the answer in, for example, a text format or an audio format. For example, the providing unit displays the generated answer to the user in a text format. The providing unit can also provide the generated answer to the user in an audio format. In this way, the generated answer can be provided to the user.

[0076] The digitization unit can estimate the user's emotion and determine the priority of digitization based on the estimated user's emotion. For example, when the user is excited, the digitization unit can digitize books and logs with interesting content with priority. In addition, when the user is relaxed, the digitization unit can also digitize books and logs with relaxing content with priority. Furthermore, when the user is in a hurry, the digitization unit can also digitize books and logs that can be digitized in a short time with priority. This makes it possible to determine the priority of digitization based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0077] The digitization unit can learn the unique characteristics of the handwriting of great people or deceased people in order to improve the accuracy of handwritten character recognition. For example, the digitization unit learns the characteristics of the handwritten characters of great person A and improves the recognition accuracy. The digitization unit can also learn the handwriting habits of great person B and reduce erroneous recognition. Furthermore, the digitization unit can also learn the unique writing style of great person C and convert it into accurate text data. This can improve the accuracy of handwritten character recognition.

[0078] The digitizing unit can select the optimal scanning method in consideration of the deterioration state of the book or log. For example, the digitizing unit selects low pressure scanning when scanning a deteriorated book. The digitizing unit can also use a color correction function when scanning a faded log. Furthermore, the digitizing unit can also select a special scanning method to protect the pages when scanning a book that is easily torn. In this way, the optimal scanning method can be selected in consideration of the deterioration state of the book or log.

[0079] The digitization unit can estimate the user's emotions and select books and logs to be digitized based on the estimated user's emotions. For example, when the user is excited, the digitization unit selects books and logs with interesting content. In addition, when the user is relaxed, the digitization unit can also select books and logs with relaxing content. Furthermore, when the user is in a hurry, the digitization unit can also select books and logs that can be digitized in a short time. This makes it possible to select books and logs to be digitized based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0080] The digitizing unit can select the optimal scanning method in consideration of the physical storage state of the book or log. For example, the digitizing unit selects low pressure scanning when scanning a book that is deteriorating. The digitizing unit can also use a color correction function when scanning a faded log. Furthermore, the digitizing unit can also select a special scanning method to protect the pages when scanning a book that is easily torn. In this way, the optimal scanning method can be selected in consideration of the physical storage state of the book or log.

[0081] The digitization unit can apply different digitization algorithms based on the contents of the book or log. For example, the digitization unit applies a handwriting recognition algorithm to a handwritten manuscript. The digitization unit can also apply an OCR algorithm to a printed book. Furthermore, the digitization unit can apply an image recognition algorithm to a log that contains many photos and figures. In this way, different digitization algorithms can be applied based on the contents of the book or log.

[0082] The conversion unit can estimate the user's emotion and adjust the parameters of the vector conversion based on the estimated user's emotion. For example, the conversion unit performs detailed vector conversion when the user is relaxed. Also, the conversion unit can perform simplified vector conversion when the user is in a hurry. Furthermore, the conversion unit can emphasize parameters related to emotions when the user is excited. This makes it possible to adjust the parameters of the vector conversion based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0083] The conversion unit can combine multiple conversion algorithms to gain a deeper understanding of the context of the text data. For example, the conversion unit can combine Word2Vec and BERT to understand the meaning of words. The conversion unit can also combine LSTM and Transformer to understand the context. Furthermore, the conversion unit can combine GloVe and ELMo to understand the meaning of phrases. This allows for a deeper understanding of the context of the text data.

[0084] The conversion unit can apply different conversion methods depending on the category of the text data. For example, the conversion unit applies a conversion method that takes into account historical context to historical text. The conversion unit can also apply a conversion method that takes into account scientific terms to scientific text. The conversion unit can also apply a conversion method that takes into account philosophical concepts to philosophical text. This makes it possible to apply different conversion methods depending on the category of the text data.

[0085] The conversion unit can estimate the user's emotion and determine the priority of vector conversion based on the estimated user's emotion. For example, when the user is excited, the conversion unit preferentially vector converts text with interesting content. Also, when the user is relaxed, the conversion unit can preferentially vector convert text with relaxing content. Furthermore, when the user is in a hurry, the conversion unit can preferentially vector convert text that can be vector converted in a short time. This makes it possible to determine the priority of vector conversion based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0086] The conversion unit can select an optimal conversion method in consideration of the language characteristics of the text data. For example, the conversion unit applies an English-specific conversion method to English text. The conversion unit can also apply a Japanese-specific conversion method to Japanese text. Furthermore, the conversion unit can also apply conversion methods corresponding to each language to multilingual text. This makes it possible to select an optimal conversion method in consideration of the language characteristics of the text data.

[0087] The conversion unit can adjust the conversion algorithm according to the length of the text data. For example, the conversion unit applies a lightweight conversion algorithm to short text. The conversion unit can also apply a detailed conversion algorithm to long text. Furthermore, the conversion unit can also apply a balanced conversion algorithm to medium-length text. This makes it possible to adjust the conversion algorithm according to the length of the text data.

[0088] The answer generation unit can estimate the user's emotion and adjust the way of expressing the answer based on the estimated emotion of the user. For example, when the user is nervous, the answer generation unit uses a simple and easy-to-understand expression method. Also, when the user is relaxed, the answer generation unit can use an expression method including a detailed explanation. Furthermore, when the user is in a hurry, the answer generation unit can use a concise expression method that focuses on the main points. This makes it possible to adjust the way of expressing the answer based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0089] The answer generation unit can refer to multiple data sources to more deeply reflect the thoughts and philosophies of great people and deceased people. For example, the answer generation unit generates an answer by referring to the books and lecture records of great person A. The answer generation unit can also generate an answer by referring to the diary and letters of great person B. Furthermore, the answer generation unit can also generate an answer by referring to the writings and interviews of great person C. This allows the thoughts and philosophies of great people and deceased people to be more deeply reflected.

[0090] The answer generation unit can apply different generation algorithms depending on the category of the user's question. For example, the answer generation unit applies a generation algorithm that takes historical context into consideration to a question about history. The answer generation unit can also apply a generation algorithm that takes scientific knowledge into consideration to a question about science. Furthermore, the answer generation unit can also apply a generation algorithm that takes philosophical concepts into consideration to a question about philosophy. This makes it possible to generate an optimal answer depending on the category of the user's question.

[0091] The answer generation unit can estimate the user's emotion and adjust the length of the answer based on the estimated user's emotion. For example, when the user is in a hurry, the answer generation unit generates a short answer that is to the point. Also, when the user is relaxed, the answer generation unit can generate a longer answer that includes a detailed explanation. Furthermore, when the user is excited, the answer generation unit can generate an answer that includes a visually stimulating effect. This allows the length of the answer to be adjusted based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0092] The answer generation unit can provide an optimal answer by referring to the user's past question history. The answer generation unit can provide a relevant answer based on, for example, the content of a question asked by the user in the past. The answer generation unit can also provide an answer that is likely to be of interest to the user from the user's past question history. Furthermore, the answer generation unit can analyze the user's past question history and provide the most appropriate answer. This makes it possible to provide an optimal answer based on the user's past question history.

[0093] The answer generation unit can adjust the level of detail of the answer depending on the user's level of expertise. For example, the answer generation unit can provide a beginner with an answer that includes a basic explanation. The answer generation unit can also provide an intermediate user with an answer that includes a detailed explanation. Furthermore, the answer generation unit can also provide an advanced user with an answer that includes specialized knowledge. This makes it possible to provide an optimal answer depending on the user's level of expertise.

[0094] The reception unit can estimate the user's emotion and adjust the method of receiving the question based on the estimated user's emotion. For example, when the user is nervous, the reception unit provides a simple interface and minimizes the input procedure. Also, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit can prioritize voice input and quickly accept questions. This makes it possible to adjust the method of receiving the question based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0095] The reception unit can select the optimal reception method by referring to the user's past question history. For example, the reception unit preferentially suggests an input method (voice, text, etc.) that the user has used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past question history. Furthermore, the reception unit can analyze the user's past question history and suggest the most efficient reception method. This makes it possible to select the optimal reception method based on the user's past question history.

[0096] The reception unit can estimate the user's emotion and determine the priority of questions based on the estimated user's emotion. For example, when the user is excited, the reception unit preferentially receives questions with high urgency. Also, when the user is relaxed, the reception unit can preferentially receive normal questions. Furthermore, when the user is in a hurry, the reception unit can preferentially receive questions that require a quick answer. This makes it possible to determine the priority of questions based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0097] The reception unit can select the optimal reception method in consideration of the device information of the user. For example, when the user is using a smartphone, the reception unit preferentially suggests voice input. Furthermore, when the user is using a tablet, the reception unit can also preferentially suggest touch input. Furthermore, when the user is using a desktop, the reception unit can also preferentially suggest keyboard input. In this way, the optimal reception method can be selected based on the device information of the user.

[0098] The providing unit can estimate the user's emotion and adjust the method of providing an answer based on the estimated user's emotion. For example, when the user is nervous, the providing unit provides a simple and easy-to-understand answer. Also, when the user is relaxed, the providing unit can provide an answer including a detailed explanation. Furthermore, when the user is in a hurry, the providing unit can provide a concise answer that focuses on the main points. This makes it possible to adjust the method of providing an answer based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0099] The providing unit can select the optimal providing method by referring to the user's past answer history. The providing unit selects the optimal providing method based on, for example, the format of answers the user has received in the past. The providing unit can also provide answers in a format that is likely to interest the user based on the user's past answer history. Furthermore, the providing unit can analyze the user's past answer history and select the most appropriate providing method. In this way, the optimal providing method can be selected based on the user's past answer history.

[0100] The providing unit can estimate the user's emotion and adjust the display order of the answers based on the estimated user's emotion. For example, when the user is excited, the providing unit displays important information first. Also, when the user is relaxed, the providing unit can sequentially display detailed information. Furthermore, when the user is in a hurry, the providing unit can display information with the main points first. This makes it possible to adjust the display order of the answers based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0101] The providing unit can select the optimal providing method in consideration of the device information of the user. For example, when the user is using a smartphone, the providing unit provides a display method that matches the screen size. In addition, when the user is using a tablet, the providing unit can also provide a display method optimized for a large screen. Furthermore, when the user is using a desktop, the providing unit can also provide a display method that includes detailed information. This makes it possible to select the optimal providing method based on the device information of the user.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] The conversation system may further include a history analysis unit that analyzes the user's past question history. The history analysis unit analyzes the pattern of questions the user has asked in the past to identify the user's interests and concerns. For example, if the user frequently asks questions about a particular historical figure, new information related to that historical figure may be provided preferentially. The history analysis unit may also predict future questions based on the user's question trends and prepare related information in advance. Furthermore, the history analysis unit may provide more detailed information based on the user's question history, taking into account the content of answers the user has obtained in the past. This allows the user's past question history to be utilized to provide more personalized answers.

[0104] The digitization unit can further estimate the user's emotions and determine the priority of digitization based on the estimated user's emotions. For example, if the user is excited, books and logs with interesting content can be digitized with priority. Also, if the user is relaxed, books and logs with relaxing content can be digitized with priority. Furthermore, if the user is in a hurry, books and logs that can be digitized in a short time can be digitized with priority. In this way, the priority of digitization can be determined based on the user's emotions.

[0105] The transformation part can combine multiple transformation algorithms to further understand the context of the text data. For example, it can combine Word2Vec and BERT to understand the meaning of words. It can also combine LSTM and Transformer to understand the context. It can also combine GloVe and ELMo to understand the meaning of phrases. This allows for a deeper understanding of the context of the text data.

[0106] The answer generation unit can further estimate the user's emotions and adjust the way the answer is expressed based on the estimated user's emotions. For example, if the user is nervous, a simple and easy-to-understand expression can be used. If the user is relaxed, an expression that includes a detailed explanation can be used. If the user is in a hurry, a concise expression that gets straight to the point can be used. This makes it possible to adjust the way the answer is expressed based on the user's emotions.

[0107] The reception unit can further estimate the user's emotion and adjust the method of receiving a question based on the estimated user's emotion. For example, if the user is nervous, a simple interface can be provided to minimize input steps. Also, if the user is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized to quickly receive questions. In this way, the method of receiving a question can be adjusted based on the user's emotion.

[0108] The providing unit can further estimate the user's emotions and adjust the way in which the answer is provided based on the estimated user's emotions. For example, if the user is nervous, a simple and easy-to-understand answer can be provided. If the user is relaxed, an answer including a detailed explanation can be provided. Furthermore, if the user is in a hurry, a concise answer that hits the main points can be provided. In this way, the way in which the answer is provided can be adjusted based on the user's emotions.

[0109] The conversation system may further include an expertise estimation unit that estimates the expertise level of the user. The expertise estimation unit estimates the expertise level of the user based on the content of the user's question and past question history. For example, an answer including a basic explanation may be provided to a beginner. Also, an answer including a detailed explanation may be provided to an intermediate user. Furthermore, an answer including specialized knowledge may be provided to an advanced user. In this way, the most suitable answer may be provided according to the user's expertise level.

[0110] The conversation system may further include a device adaptation unit that selects the optimal presentation method in consideration of the user's device information. The device adaptation unit detects the type and characteristics of the device used by the user and selects the optimal presentation method accordingly. For example, if the user is using a smartphone, a display method that matches the screen size can be provided. Also, if the user is using a tablet, a display method optimized for a large screen can be provided. Furthermore, if the user is using a desktop, a display method including detailed information can be provided. This makes it possible to select the optimal presentation method based on the user's device information.

[0111] The conversation system may further include a category adaptation unit that applies different generation algorithms depending on the category of the user's question. The category adaptation unit analyzes the content of the user's question and selects the optimal generation algorithm depending on the category. For example, a generation algorithm that takes historical context into consideration may be applied to a question about history. Also, a generation algorithm that takes scientific knowledge into consideration may be applied to a question about science. Furthermore, a generation algorithm that takes philosophical concepts into consideration may be applied to a question about philosophy. This makes it possible to generate an optimal answer depending on the category of the user's question.

[0112] The conversation system can further estimate the user's emotions and adjust the length of the answer based on the estimated user's emotions. For example, if the user is in a hurry, a short and to the point answer can be generated. If the user is relaxed, a longer answer with detailed explanations can be generated. Furthermore, if the user is excited, an answer with visually stimulating effects can be generated. In this way, the length of the answer can be adjusted based on the user's emotions.

[0113] The process flow of the second embodiment will be briefly described below.

[0114] Step 1: The Digitization Department digitizes the books and logs of great and deceased people. For example, handwritten manuscripts can be digitized and read using scanning technology. It can also directly read books and logs submitted in digital format. It can also read printed books and logs using OCR technology. Step 2: The conversion unit converts the data digitized by the digitization unit into vectors using a generation AI. For example, the conversion unit converts the text data into vectors using a text generation AI (e.g., LLM). The conversion unit can also convert the text data into vectors using a multimodal generation AI. Step 3: The answer generation unit analyzes the vector-converted data by the conversion unit and generates an appropriate answer to the user's question. For example, in response to the user's question, the answer generation unit extracts relevant information from books and logs of great people and deceased people and generates an answer. Step 4: The reception unit receives a user's question as an input. For example, the user's question can be received in text format or voice format. Step 5: The providing unit provides the answer generated by the answer generating unit to the user. For example, the answer can be provided in a text format or a voice format.

[0115] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0116] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0117] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements including the above-mentioned digitization unit, conversion unit, answer generation unit, reception unit, and provision unit is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the digitization unit digitizes handwritten manuscripts and diaries using the camera 42 or scanner of the smart device 14. The conversion unit performs vector conversion by the specific processing unit 290 of the data processing device 12. The answer generation unit generates an appropriate answer to a user's question by the specific processing unit 290 of the data processing device 12. The reception unit receives a user's question using the reception device 38 of the smart device 14. The provision unit provides the user with the answer generated using the output device 40 of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0119] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0120] 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.

[0121] 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, the RAM 30, and the 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.

[0122] 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.

[0123] 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 the voice according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0125] 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 performed in a secure state.

[0126] Fig. 4 shows an example of 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.

[0127] 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.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0129] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0130] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0131] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0132] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0133] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements including the above-mentioned digitization unit, conversion unit, answer generation unit, reception unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the digitization unit digitizes handwritten manuscripts and diaries using the camera 42 of the smart glasses 214. The conversion unit performs vector conversion by the specific processing unit 290 of the data processing device 12. The answer generation unit generates an appropriate answer to a user's question by the specific processing unit 290 of the data processing device 12. The reception unit receives a user's question using the microphone 238 of the smart glasses 214. The provision unit provides the user with the generated answer using the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0135] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0136] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0137] 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, the RAM 30, and the 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.

[0138] 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.

[0139] 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 the voice according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0141] 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 performed in a secure state.

[0142] 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.

[0143] 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.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0145] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

[0146] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0147] 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 voice indicating a user input for 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.

[0148] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0149] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements including the above-mentioned digitizing unit, converting unit, answer generating unit, receiving unit, and providing unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the digitizing unit digitizes handwritten manuscripts and diaries using the camera 42 of the headset type terminal 314. The converting unit performs vector conversion by the specific processing unit 290 of the data processing device 12. The answer generating unit generates an appropriate answer to a user's question by the specific processing unit 290 of the data processing device 12. The receiving unit receives a user's question using the microphone 238 of the headset type terminal 314. The providing unit provides the generated answer to the user using the speaker 240 of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0151] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0152] 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.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] The 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.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0158] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0159] 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.

[0160] 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.

[0161] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0162] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0163] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0164] 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 a voice indicating a user input for 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.

[0165] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0166] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0167] Each of the multiple elements including the digitizing unit, the converting unit, the answer generating unit, the receiving unit, and the providing unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the digitizing unit digitizes handwritten manuscripts and diaries using the camera 42 of the robot 414. The converting unit performs vector conversion by the specific processing unit 290 of the data processing device 12. The answer generating unit generates an appropriate answer to a user's question by the specific processing unit 290 of the data processing device 12. The receiving unit receives a user's question using the microphone 238 of the robot 414. The providing unit provides the user with the answer generated using the speaker 240 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0168] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0169] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0170] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0171] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0172] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0173] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0174] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0175] 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.

[0176] 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 Universal Serial Bus (USB) 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.

[0177] In addition, 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 upon request from the data processing device 12.

[0178] 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.

[0179] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0180] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0181] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0182] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0183] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0184] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0185] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0186] (Appendix 1) a digitization department for digitizing books or logs of great or deceased persons; A conversion unit that performs vector conversion on the data digitized by the digitization unit; an answer generation unit that analyzes the data that has been vector-converted by the conversion unit and generates an answer to a user's question; a reception unit for receiving a question from a user; a providing unit that provides the answer generated by the answer generating unit; A system characterized by: (Appendix 2) The digitization unit includes: Scan handwritten manuscripts, diaries, or lecture notes and convert them into text data 2. The system of claim 1, (Appendix 3) The conversion unit is Perform vector conversion to convert text data into numerical data 2. The system of claim 1, (Appendix 4) The answer generation unit: Analyze the vectorized data and generate appropriate answers to user questions 2. The system of claim 1, (Appendix 5) The reception unit is Accepts user questions as input 2. The system of claim 1, (Appendix 6) The providing unit is Providing the generated answer to the user 2. The system of claim 1, (Appendix 7) The digitization unit includes: Estimate user sentiment and determine digitization priorities based on the estimated user sentiment 2. The system of claim 1, (Appendix 8) The digitization unit includes: Learning the unique handwriting features of famous and deceased people to improve handwritten character recognition 2. The system of claim 1, (Appendix 9) The digitization unit includes: Select the most appropriate scanning method taking into account the deterioration state of books and logs. 2. The system of claim 1, (Appendix 10) The digitization unit includes: Estimate the user's emotions and select books and logs to digitize based on the estimated user emotions. 2. The system of claim 1, (Appendix 11) The digitization unit includes: Select the most appropriate scanning method taking into consideration the physical storage conditions of books and logs. 2. The system of claim 1, (Appendix 12) The digitization unit includes: Apply different digitization algorithms based on the content of books and logs 2. The system of claim 1, (Appendix 13) The conversion unit is Estimate the user's emotion and adjust the vector transformation parameters based on the estimated user's emotion. 2. The system of claim 1, (Appendix 14) The conversion unit is Combine multiple transformation algorithms to gain a deeper understanding of the context of text data 2. The system of claim 1, (Appendix 15) The conversion unit is Apply different transformation techniques depending on the category of text data 2. The system of claim 1, (Appendix 16) The conversion unit is Estimate the user's emotion and determine the priority of vector transformation based on the estimated user's emotion. 2. The system of claim 1, (Appendix 17) The conversion unit is Select the optimal conversion method taking into account the linguistic characteristics of the text data 2. The system of claim 1, (Appendix 18) The conversion unit is Adjust the conversion algorithm depending on the length of the text data 2. The system of claim 1, (Appendix 19) The answer generation unit: Infer user sentiment and adjust answer expression based on the inferred sentiment 2. The system of claim 1, (Appendix 20) The answer generation unit: Refer to multiple data sources to more deeply reflect the thoughts and philosophies of great and deceased people 2. The system of claim 1, (Appendix 21) The answer generation unit: Apply different generation algorithms depending on the category of the user's question 2. The system of claim 1, (Appendix 22) The answer generation unit: Infer user sentiment and adjust the length of answers based on the estimated user sentiment 2. The system of claim 1, (Appendix 23) The answer generation unit: Provide the best answer by referring to the user's past question history 2. The system of claim 1, (Appendix 24) The answer generation unit: Tailor the level of detail in your answers to suit your level of expertise 2. The system of claim 1, (Appendix 25) The reception unit is Estimate the user's emotions and adjust the way questions are accepted based on the estimated user's emotions 2. The system of claim 1, (Appendix 26) The reception unit is Select the best way to receive a question by looking at the user's past question history 2. The system of claim 1, (Appendix 27) The reception unit is Estimate user sentiment and prioritize questions based on the estimated user sentiment 2. The system of claim 1, (Appendix 28) The reception unit is Select the optimal reception method taking into account the user's device information 2. The system of claim 1, (Appendix 29) The providing unit is Inferring user sentiment and adjusting answer delivery based on the inferred user sentiment 2. The system of claim 1, (Appendix 30) The providing unit is Select the optimal delivery method by referring to the user's past answer history 2. The system of claim 1, (Appendix 31) The providing unit is Infer user sentiment and adjust the display order of answers based on the estimated user sentiment 2. The system of claim 1, (Appendix 32) The providing unit is Select the optimal delivery method taking into account the user's device information 2. The system of claim 1, [Explanation of symbols]

[0187] 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 digitization department for digitizing books or logs of great or deceased persons; A conversion unit that performs vector conversion on the data digitized by the digitization unit; an answer generation unit that analyzes the data that has been vector-converted by the conversion unit and generates an answer to a user's question; a reception unit for receiving a question from a user; a providing unit that provides the answer generated by the answer generating unit; A system characterized by:

2. The digitization unit includes: Scan handwritten manuscripts, diaries, or lecture notes and convert them into text data 2. The system of claim 1 .

3. The answer generation unit: Provide the best answer by referring to the user's past question history 2. The system of claim 1 .

4. The conversion unit is Apply different transformation techniques depending on the category of text data 2. The system of claim 1 .

5. The digitization unit includes: Estimate user sentiment and determine digitization priorities based on the estimated user sentiment 2. The system of claim 1 .

6. The digitization unit includes: Learning the unique handwriting features of famous and deceased people to improve handwritten character recognition 2. The system of claim 1 .

Images