System

Abstract

An object of a system according to an embodiment is to quickly and accurately answer a question about in-house information from an employee.SOLUTION: A system includes a question analysis unit, an answer generation unit, and a database cooperation unit. The question analysis unit analyzes a question about in-house information from an employee. The answer generation unit generates an answer based on the question analyzed by the question analysis unit. The database cooperation unit cooperates with an in-house database to provide the answer generated by the answer 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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] Conventional technology has had the problem of making it difficult to quickly and accurately respond to questions from employees about internal company information.

[0005] The system according to the embodiment aims to quickly and accurately answer questions from employees about internal company information. [Means for solving the problem]

[0006] The system according to the embodiment includes a question analysis unit, an answer generation unit, and a database linkage unit. The question analysis unit analyzes questions about internal company information from employees. The answer generation unit generates answers based on the questions analyzed by the question analysis unit. The database linkage unit links with an internal company database to provide the answers generated by the answer generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly and accurately answer questions from employees about company information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) In the internal information response system according to the embodiment of the present invention, when an employee asks a question about internal information, a generation AI analyzes the question and generates an appropriate answer. This allows employees to quickly and accurately obtain the information they need.

[0029] An internal information response system according to an embodiment includes a question analysis unit, an answer generation unit, and a database linkage unit. The question analysis unit analyzes questions about internal information from employees. For example, the question analysis unit analyzes the content of the question using natural language processing technology. The question analysis unit can also identify important parts of the question using keyword extraction technology. The question analysis unit can also refer to related background information to understand the context of the question. The answer generation unit generates an answer based on the question analyzed by the question analysis unit. For example, the answer generation unit generates an appropriate answer to the question using a generation AI (e.g., a text generation AI or a multimodal generation AI). The answer generation unit can also generate an answer using a template-based generation method. The answer generation unit can also generate an optimal answer to the question using a machine learning model. The database linkage unit links with an internal database to provide the answer generated by the answer generation unit. For example, the database linkage unit accesses the internal database using an API to obtain necessary information. The database linkage unit can also select an appropriate access method depending on the type of database. The database linkage unit provides the information obtained from the database to the answer generation unit. As a result, the in-house information response system according to the embodiment allows employees to quickly and accurately obtain the information they need. For example, if an employee asks, "What is this month's sales data?", the question analysis unit analyzes the question, the response generation unit searches for sales data and generates an answer, and the database linkage unit obtains the sales data and provides the answer. This allows employees to quickly and accurately obtain sales data.

[0030] The question analysis unit can generate a personalized answer by referring to the questioner's past question history. The question analysis unit, for example, references the questioner's past question history to generate a personalized answer. For example, if the same question has been asked in the past, new information is added based on the answer and provided. The question analysis unit also analyzes the questioner's past question history and provides related information preferentially. For example, if the questioner has frequently asked about the progress of a project in the past, the latest progress information is automatically provided. The question analysis unit also builds a system that generates personalized answers based on the questioner's past question history. For example, it learns the content of past questions and provides information that matches the questioner's interests. This makes it possible to provide a personalized answer to the questioner.

[0031] The question analysis unit can provide highly relevant information preferentially based on the questioner's job title or department. The question analysis unit provides highly relevant information preferentially based on the questioner's job title or department, for example. For example, management-related information is provided to managers, and technology-related information is provided to engineers. The question analysis unit also builds a system that provides appropriate information taking into account the questioner's job title or department. For example, the latest sales data is provided for questions from the sales department, and technical specifications are provided for questions from the development department. The question analysis unit also develops an algorithm that provides highly relevant information preferentially based on the questioner's job title or department. For example, different information is displayed preferentially depending on the job title or department. This makes it possible to provide appropriate information according to the questioner's job title or department.

[0032] The question analysis unit can respond to voice input, analyze the question using voice recognition technology, and provide the answer generated by the answer generation unit by voice. The question analysis unit, for example, responds to voice input, analyzes the question using voice recognition technology, and provides the answer generated by the answer generation unit by voice. For example, a question is input using a microphone and the answer is heard through a speaker. The question analysis unit also uses voice recognition technology to analyze the voice-input question and build a system that provides the answer by voice. For example, a question is asked using a voice command and the answer is received by voice. The question analysis unit also responds to voice input, analyzes the question using voice recognition technology, and develops an algorithm that provides the answer by voice. For example, the voice-input question is converted into text and the answer is generated by voice. This makes it possible to provide a question and answer system that supports voice input and voice output.

[0033] The question analysis unit generates answers that include visual data, making them easier to understand visually. For example, the question analysis unit generates answers that include visual data, making them easier to understand visually. For example, sales data may be displayed in a graph. The question analysis unit also builds a system that generates answers that include visual data, providing information that is easy to understand visually. For example, the progress of a project may be shown in a diagram. The question analysis unit also develops an algorithm that generates answers that include visual data. For example, meeting schedules may be displayed in calendar format. This makes it possible to provide answers that are easy to understand visually.

[0034] When learning from databases and documents, generative AI can evaluate the reliability and recency of data and prioritize learning from highly reliable information. For example, when learning from databases and documents, generative AI evaluates the reliability and recency of data and prioritizes learning from highly reliable information. For example, it selects information based on the most recent update date or a highly reliable source. Generative AI can also develop algorithms to evaluate the reliability and recency of data and build systems that prioritize learning from highly reliable information. For example, it can calculate a reliability score and prioritize learning from information with a high score. When learning from databases and documents, generative AI can set criteria for evaluating the reliability and recency of data and prioritize learning from highly reliable information. For example, it can prioritize learning from official documents and the latest reports. This allows it to provide accurate answers by prioritizing learning from highly reliable information.

[0035] Generative AI can learn from a wider range of information sources by including unstructured data in its data. For example, generative AI can include unstructured data in its data to learn from a wider range of information sources. For example, it can analyze email content and chat conversations to extract relevant information. Generative AI can also build systems that analyze and learn from unstructured data. For example, it can use natural language processing technology to extract important information from emails and chat logs. Generative AI can also develop algorithms that learn from a wider range of information sources by including unstructured data in its data. For example, it can convert unstructured data into text data and use it for learning. This allows it to learn from a wider range of information sources and provide comprehensive answers.

[0036] Generative AI can generate answers by including industry and market data in its data and integrating internal and external information. For example, generative AI can include industry and market data in its data and integrate internal and external information to generate answers. For example, it can use industry reports and market research data for learning. Generative AI can also integrate external data to build systems that allow it to learn. For example, it can use external APIs to obtain industry and market data and use it for learning. Generative AI can also develop algorithms that integrate internal and external information to generate answers by including industry and market data in its data. For example, it can integrate external data with internal data and reflect it in the answers. This makes it possible to provide comprehensive answers by integrating internal and external information.

[0037] Generative AI can update data regularly, ensuring that the latest information is always provided. For example, generative AI builds a system that updates data regularly, ensuring that the latest information is always provided. For example, updating the database every week and adding new information to the learning. Generative AI also automates regular data updates and develops algorithms that allow generative AI to learn the latest information. For example, automatically updating data based on a schedule. Generative AI also builds a system that updates data regularly, ensuring that the latest information is always provided. For example, automatically learning is performed every time new documents or data are added. This ensures that the latest information is always provided.

[0038] When linking with a database, generative AI can take data access permissions into consideration and provide information only to users with appropriate permissions. For example, when linking with a database, generative AI can take data access permissions into consideration and provide information only to users with appropriate permissions. For example, confidential information can be provided only to managers. Generative AI can also build a system to manage data access permissions and provide information only to users with appropriate permissions. For example, access permissions can be set based on the user's job title or department. Generative AI can also develop an algorithm that takes data access permissions into consideration when linking with a database. For example, it can check access permissions and provide appropriate information. This ensures information security by providing information only to users with appropriate permissions.

[0039] When linking with a database, the generative AI can check the consistency of the data and provide information that is free of contradictions. For example, when linking with a database, the generative AI checks the consistency of the data and provides information that is free of contradictions. For example, it compares information obtained from multiple databases and provides matching information. The generative AI can also build a system that checks the consistency of the data and provides information that is free of contradictions. For example, it can compare data between databases and confirm consistency. The generative AI can also develop an algorithm that checks the consistency of the data when linking with a database. For example, it can check the consistency of the data and provide information that is free of contradictions. This makes it possible to provide highly reliable answers by providing information that is free of contradictions.

[0040] When linking with databases, generative AI can integrate data between different databases and provide comprehensive answers. For example, when linking with databases, generative AI can integrate data between different databases and provide comprehensive answers. For example, it can integrate sales data and inventory data and provide them. Generative AI can also build systems that integrate data between different databases and provide comprehensive answers. For example, it can integrate data from a project management system and a human resources system. When linking with databases, generative AI can also develop algorithms that integrate data between different databases. For example, it can map and integrate data between databases. This allows it to provide comprehensive answers by integrating data between different databases.

[0041] When linking with a database, generative AI can acquire data in real time and provide the latest information. For example, when linking with a database, generative AI can acquire data in real time and provide the latest information. For example, it can provide the latest sales data or project progress in real time. Generative AI can also build systems that acquire data in real time and provide the latest information. For example, it can reflect database updates in real time. Generative AI can also develop algorithms that acquire data in real time when linking with a database. For example, it can detect changes in the database in real time and provide information. This allows it to provide the latest information in real time.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The question analysis unit can refer to the questioner's past question history and generate a personalized answer. For example, if the questioner has asked the same question in the past, new information can be added and provided based on the answer. The question analysis unit can also analyze the questioner's past question history and provide related information preferentially. For example, if the questioner has frequently asked about the progress of a project in the past, the latest progress information can be automatically provided. The question analysis unit can also build a system that generates personalized answers based on the questioner's past question history. For example, it can learn the content of past questions and provide information that matches the questioner's interests. This makes it possible to provide a personalized answer to the questioner.

[0044] The question analysis unit can prioritize providing highly relevant information based on the questioner's position or department. For example, it can provide management-related information to managers and technology-related information to engineers. The question analysis unit can also build a system that provides appropriate information taking into account the questioner's position or department. For example, it can provide the latest sales data for questions from the sales department and technical specifications for questions from the development department. The question analysis unit can also develop an algorithm that prioritizes providing highly relevant information based on the questioner's position or department. For example, it can prioritize displaying different information depending on the position or department. This makes it possible to provide appropriate information according to the questioner's position or department.

[0045] The question analysis unit can respond to voice input, analyze the question using voice recognition technology, and provide the answer generated by the answer generation unit by voice. For example, a question is input using a microphone and the answer is heard through a speaker. The question analysis unit can also use voice recognition technology to build a system that analyzes a voice-input question and provides an answer by voice. For example, a question is asked using a voice command and an answer is received by voice. The question analysis unit can also respond to voice input, analyze the question using voice recognition technology, and develop an algorithm that provides an answer by voice. For example, the voice-input question can be converted into text and an answer can be generated by voice. This makes it possible to provide a question and answer system that supports voice input and voice output.

[0046] The question analysis unit can generate answers that include visual data, making them easier to understand visually. For example, sales data can be displayed in a graph. The question analysis unit can also build a system that generates answers that include visual data, providing information that is easier to understand visually. For example, the progress of a project can be shown in a diagram. The question analysis unit can also develop an algorithm that generates answers that include visual data. For example, meeting schedules can be displayed in calendar format. This makes it possible to provide answers that are easier to understand visually.

[0047] When learning from databases and documents, generative AI can evaluate the reliability and recency of data and prioritize learning from highly reliable information. For example, it can select information based on the most recent update date or a highly reliable source. Generative AI can also develop algorithms to evaluate the reliability and recency of data and build systems that prioritize learning from highly reliable information. For example, it can calculate a reliability score and prioritize learning from information with a high score. When learning from databases and documents, generative AI can also set criteria for evaluating the reliability and recency of data and prioritize learning from highly reliable information. For example, it can prioritize learning from official documents and the latest reports. This allows it to prioritize learning from highly reliable information and provide accurate answers.

[0048] Generative AI can learn from a wider range of information sources by including unstructured data in its data. For example, it can analyze email content and chat conversations to extract relevant information. Generative AI can also build systems that analyze and learn from unstructured data. For example, natural language processing techniques can be used to extract important information from emails and chat logs. Generative AI can also develop algorithms that learn from a wider range of information sources by including unstructured data in its data. For example, unstructured data can be converted into text data and used for learning. This allows it to learn from a wider range of information sources and provide comprehensive answers.

[0049] Generative AI can generate answers by including industry and market data in its data and integrating internal and external information. For example, it can use industry reports and market research data for learning. Generative AI can also integrate external data to build systems that learn from it. For example, it can use external APIs to obtain industry and market data and use it for learning. Generative AI can also develop algorithms that integrate internal and external information to generate answers by including industry and market data in its data. For example, it can integrate external data with internal data and reflect it in the answers. This makes it possible to provide comprehensive answers by integrating internal and external information.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The question analysis unit analyzes questions about internal company information from employees. For example, it uses natural language processing technology to analyze the content of the question and keyword extraction technology to identify the important parts of the question. It can also refer to relevant background information to understand the context of the question. Step 2: The answer generation unit generates an answer based on the question analyzed by the question analysis unit. For example, an appropriate answer can be generated using a generative AI (text generation AI or multimodal generation AI), or an optimal answer can be generated using a template-based generation method or a machine learning model. Step 3: The database linking unit links with the company's internal database to provide the answer generated by the answer generation unit. For example, it uses an API to access the company's internal database and obtain the necessary information. It selects the appropriate access method depending on the type of database and provides the information obtained from the database to the answer generation unit.

[0052] (Example 2) In the internal information response system according to the embodiment of the present invention, when an employee asks a question about internal information, a generation AI analyzes the question and generates an appropriate answer. This allows employees to quickly and accurately obtain the information they need.

[0053] An internal information response system according to an embodiment includes a question analysis unit, an answer generation unit, and a database linkage unit. The question analysis unit analyzes questions about internal information from employees. For example, the question analysis unit analyzes the content of the question using natural language processing technology. The question analysis unit can also identify important parts of the question using keyword extraction technology. The question analysis unit can also refer to related background information to understand the context of the question. The answer generation unit generates an answer based on the question analyzed by the question analysis unit. For example, the answer generation unit generates an appropriate answer to the question using a generation AI (e.g., a text generation AI or a multimodal generation AI). The answer generation unit can also generate an answer using a template-based generation method. The answer generation unit can also generate an optimal answer to the question using a machine learning model. The database linkage unit links with an internal database to provide the answer generated by the answer generation unit. For example, the database linkage unit accesses the internal database using an API to obtain necessary information. The database linkage unit can also select an appropriate access method depending on the type of database. The database linkage unit provides the information obtained from the database to the answer generation unit. As a result, the in-house information response system according to the embodiment allows employees to quickly and accurately obtain the information they need. For example, if an employee asks, "What is this month's sales data?", the question analysis unit analyzes the question, the response generation unit searches for sales data and generates an answer, and the database linkage unit obtains the sales data and provides the answer. This allows employees to quickly and accurately obtain sales data.

[0054] The question analysis unit can generate a personalized answer by referring to the questioner's past question history. The question analysis unit, for example, references the questioner's past question history to generate a personalized answer. For example, if the same question has been asked in the past, new information is added based on the answer and provided. The question analysis unit also analyzes the questioner's past question history and provides related information preferentially. For example, if the questioner has frequently asked about the progress of a project in the past, the latest progress information is automatically provided. The question analysis unit also builds a system that generates personalized answers based on the questioner's past question history. For example, it learns the content of past questions and provides information that matches the questioner's interests. This makes it possible to provide a personalized answer to the questioner.

[0055] The question analysis unit can provide highly relevant information preferentially based on the questioner's job title or department. The question analysis unit provides highly relevant information preferentially based on the questioner's job title or department, for example. For example, management-related information is provided to managers, and technology-related information is provided to engineers. The question analysis unit also builds a system that provides appropriate information taking into account the questioner's job title or department. For example, the latest sales data is provided for questions from the sales department, and technical specifications are provided for questions from the development department. The question analysis unit also develops an algorithm that provides highly relevant information preferentially based on the questioner's job title or department. For example, different information is displayed preferentially depending on the job title or department. This makes it possible to provide appropriate information according to the questioner's job title or department.

[0056] The question analysis unit can use the emotion estimation function to analyze the emotional state of the questioner and generate an answer that reduces stress and anxiety. The question analysis unit, for example, uses the emotion estimation function to analyze the emotional state of the questioner and generate an answer that reduces stress and anxiety. For example, if the questioner is feeling anxious, an answer that gives a sense of security is provided. The question analysis unit also analyzes the emotional state of the questioner in real time and generates an answer that elicits positive emotions. For example, an answer that includes encouraging words or positive information is provided. The question analysis unit also uses the emotion estimation function to build a system that analyzes the emotional state of the questioner and generates an answer that reduces stress and anxiety. For example, words or information that have a relaxing effect are provided. This makes it possible to provide an answer that reduces the stress and anxiety of the questioner.

[0057] The question analysis unit can respond to voice input, analyze the question using voice recognition technology, and provide the answer generated by the answer generation unit by voice. The question analysis unit, for example, responds to voice input, analyzes the question using voice recognition technology, and provides the answer generated by the answer generation unit by voice. For example, a question is input using a microphone and the answer is heard through a speaker. The question analysis unit also uses voice recognition technology to analyze the voice-input question and build a system that provides the answer by voice. For example, a question is asked using a voice command and the answer is received by voice. The question analysis unit also responds to voice input, analyzes the question using voice recognition technology, and develops an algorithm that provides the answer by voice. For example, the voice-input question is converted into text and the answer is generated by voice. This makes it possible to provide a question and answer system that supports voice input and voice output.

[0058] The question analysis unit generates answers that include visual data, making them easier to understand visually. For example, the question analysis unit generates answers that include visual data, making them easier to understand visually. For example, sales data may be displayed in a graph. The question analysis unit also builds a system that generates answers that include visual data, providing information that is easy to understand visually. For example, the progress of a project may be shown in a diagram. The question analysis unit also develops an algorithm that generates answers that include visual data. For example, meeting schedules may be displayed in calendar format. This makes it possible to provide answers that are easy to understand visually.

[0059] The question analysis unit uses the emotion estimation function to generate answers that evoke positive emotions in the asker, thereby improving motivation. The question analysis unit, for example, uses the emotion estimation function to generate answers that evoke positive emotions in the asker. For example, it provides answers that include encouraging words and success stories. The question analysis unit also analyzes the emotional state of the asker and builds a system that generates answers that elicit positive emotions. For example, it provides answers that include positive feedback and words of praise. The question analysis unit also uses the emotion estimation function to develop an algorithm that generates answers that evoke positive emotions in the asker. For example, it provides positive information preferentially based on the emotion score. This makes it possible to provide answers that improve the asker's motivation.

[0060] When learning from databases and documents, generative AI can evaluate the reliability and recency of data and prioritize learning from highly reliable information. For example, when learning from databases and documents, generative AI evaluates the reliability and recency of data and prioritizes learning from highly reliable information. For example, it selects information based on the most recent update date or a highly reliable source. Generative AI can also develop algorithms to evaluate the reliability and recency of data and build systems that prioritize learning from highly reliable information. For example, it can calculate a reliability score and prioritize learning from information with a high score. When learning from databases and documents, generative AI can set criteria for evaluating the reliability and recency of data and prioritize learning from highly reliable information. For example, it can prioritize learning from official documents and the latest reports. This allows it to provide accurate answers by prioritizing learning from highly reliable information.

[0061] Generative AI can learn from a wider range of information sources by including unstructured data in its data. For example, generative AI can include unstructured data in its data to learn from a wider range of information sources. For example, it can analyze email content and chat conversations to extract relevant information. Generative AI can also build systems that analyze and learn from unstructured data. For example, it can use natural language processing technology to extract important information from emails and chat logs. Generative AI can also develop algorithms that learn from a wider range of information sources by including unstructured data in its data. For example, it can convert unstructured data into text data and use it for learning. This allows it to learn from a wider range of information sources and provide comprehensive answers.

[0062] The generative AI can use the emotion estimation function to extract emotionally positive information from the training data and reflect it in the answer. For example, the generative AI can use the emotion estimation function to extract emotionally positive information from the training data and reflect it in the answer. For example, it can prioritize providing information with a high positive emotion score. The generative AI can also perform emotion analysis of the training data and build a system to extract positive information. For example, it can select positive information based on the emotion score and reflect it in the answer. The generative AI can also develop an algorithm that uses the emotion estimation function to extract emotionally positive information from the training data and reflect it in the answer. For example, it can prioritize positive information based on the emotion score. This can improve the satisfaction of the questioner by providing emotionally positive information.

[0063] Generative AI can generate answers by including industry and market data in its data and integrating internal and external information. For example, generative AI can include industry and market data in its data and integrate internal and external information to generate answers. For example, it can use industry reports and market research data for learning. Generative AI can also integrate external data to build systems that allow it to learn. For example, it can use external APIs to obtain industry and market data and use it for learning. Generative AI can also develop algorithms that integrate internal and external information to generate answers by including industry and market data in its data. For example, it can integrate external data with internal data and reflect it in the answers. This makes it possible to provide comprehensive answers by integrating internal and external information.

[0064] Generative AI can update data regularly, ensuring that the latest information is always provided. For example, generative AI builds a system that updates data regularly, ensuring that the latest information is always provided. For example, updating the database every week and adding new information to the learning. Generative AI also automates regular data updates and develops algorithms that allow generative AI to learn the latest information. For example, automatically updating data based on a schedule. Generative AI also builds a system that updates data regularly, ensuring that the latest information is always provided. For example, automatically learning is performed every time new documents or data are added. This ensures that the latest information is always provided.

[0065] The generation AI can use the emotion estimation function to extract information that users can easily empathize with from the training data and reflect it in the answer. For example, the generation AI can use the emotion estimation function to extract information that users can easily empathize with from the training data and reflect it in the answer. For example, it can prioritize providing information that is highly empathetic. The generation AI can also perform emotion analysis of the training data and build a system that extracts information that users can easily empathize with. For example, it can select information that is highly empathetic based on the emotion score and reflect it in the answer. The generation AI can also develop an algorithm that uses the emotion estimation function to extract information that users can easily empathize with from the training data and reflect it in the answer. For example, it can prioritize learning information that is highly empathetic based on the emotion score. This can improve satisfaction by providing information that users can easily empathize with.

[0066] When linking with a database, generative AI can take data access permissions into consideration and provide information only to users with appropriate permissions. For example, when linking with a database, generative AI can take data access permissions into consideration and provide information only to users with appropriate permissions. For example, confidential information can be provided only to managers. Generative AI can also build a system to manage data access permissions and provide information only to users with appropriate permissions. For example, access permissions can be set based on the user's job title or department. Generative AI can also develop an algorithm that takes data access permissions into consideration when linking with a database. For example, it can check access permissions and provide appropriate information. This ensures information security by providing information only to users with appropriate permissions.

[0067] When linking with a database, the generative AI can check the consistency of the data and provide information that is free of contradictions. For example, when linking with a database, the generative AI checks the consistency of the data and provides information that is free of contradictions. For example, it compares information obtained from multiple databases and provides matching information. The generative AI can also build a system that checks the consistency of the data and provides information that is free of contradictions. For example, it can compare data between databases and confirm consistency. The generative AI can also develop an algorithm that checks the consistency of the data when linking with a database. For example, it can check the consistency of the data and provide information that is free of contradictions. This makes it possible to provide highly reliable answers by providing information that is free of contradictions.

[0068] The generative AI can use the emotion estimation function to analyze a user's emotional response to information retrieved from a database, and prioritize providing information that elicits a positive response. For example, the generative AI can use the emotion estimation function to analyze a user's emotional response to information retrieved from a database, and prioritize providing information that elicits a positive response. For example, it can prioritize providing information with a high emotion score. The generative AI can also analyze a user's emotional response to information retrieved from a database, and build a system that provides information that elicits a positive response. For example, it can select and provide information based on the emotion score. The generative AI can also use the emotion estimation function to analyze a user's emotional response to information retrieved from a database, and develop an algorithm that prioritizes providing information that elicits a positive response. For example, it can select and provide information based on the emotion score. This can improve user satisfaction by providing information that elicits a positive response.

[0069] When linking with databases, generative AI can integrate data between different databases and provide comprehensive answers. For example, when linking with databases, generative AI can integrate data between different databases and provide comprehensive answers. For example, it can integrate sales data and inventory data and provide them. Generative AI can also build systems that integrate data between different databases and provide comprehensive answers. For example, it can integrate data from a project management system and a human resources system. When linking with databases, generative AI can also develop algorithms that integrate data between different databases. For example, it can map and integrate data between databases. This allows it to provide comprehensive answers by integrating data between different databases.

[0070] When linking with a database, generative AI can acquire data in real time and provide the latest information. For example, when linking with a database, generative AI can acquire data in real time and provide the latest information. For example, it can provide the latest sales data or project progress in real time. Generative AI can also build systems that acquire data in real time and provide the latest information. For example, it can reflect database updates in real time. Generative AI can also develop algorithms that acquire data in real time when linking with a database. For example, it can detect changes in the database in real time and provide information. This allows it to provide the latest information in real time.

[0071] The generative AI can use the emotion estimation function to collect the user's emotional reactions to information retrieved from the database as feedback and reflect it in the next answer. For example, the generative AI can use the emotion estimation function to collect the user's emotional reactions to information retrieved from the database as feedback and reflect it in the next answer. For example, it can prioritize providing information with a high number of positive reactions. The generative AI can also build a system that collects the user's emotional reactions to information retrieved from the database as feedback and reflects it in the next answer. For example, it can select and provide information based on an emotion score. The generative AI can also develop an algorithm that uses the emotion estimation function to collect the user's emotional reactions to information retrieved from the database as feedback and reflect it in the next answer. For example, it can select and provide information based on an emotion score. In this way, the user's emotional reactions can be collected as feedback and reflected in the next answer, thereby providing a more appropriate answer.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The question analysis unit can refer to the questioner's past question history and generate a personalized answer. For example, if the questioner has asked the same question in the past, new information can be added and provided based on the answer. The question analysis unit can also analyze the questioner's past question history and provide related information preferentially. For example, if the questioner has frequently asked about the progress of a project in the past, the latest progress information can be automatically provided. The question analysis unit can also build a system that generates personalized answers based on the questioner's past question history. For example, it can learn the content of past questions and provide information that matches the questioner's interests. This makes it possible to provide a personalized answer to the questioner.

[0074] The question analysis unit can prioritize providing highly relevant information based on the questioner's position or department. For example, it can provide management-related information to managers and technology-related information to engineers. The question analysis unit can also build a system that provides appropriate information taking into account the questioner's position or department. For example, it can provide the latest sales data for questions from the sales department and technical specifications for questions from the development department. The question analysis unit can also develop an algorithm that prioritizes providing highly relevant information based on the questioner's position or department. For example, it can prioritize displaying different information depending on the position or department. This makes it possible to provide appropriate information according to the questioner's position or department.

[0075] The question analysis unit can use the emotion estimation function to analyze the emotional state of the questioner and generate an answer that reduces stress and anxiety. For example, if the questioner is feeling anxious, an answer that gives a sense of security is provided. The question analysis unit can also analyze the emotional state of the questioner in real time and generate an answer that elicits positive emotions. For example, an answer that includes encouraging words or positive information is provided. The question analysis unit can also use the emotion estimation function to build a system that analyzes the emotional state of the questioner and generates an answer that reduces stress and anxiety. For example, words or information that have a relaxing effect are provided. This makes it possible to provide an answer that reduces the questioner's stress and anxiety.

[0076] The question analysis unit can respond to voice input, analyze the question using voice recognition technology, and provide the answer generated by the answer generation unit by voice. For example, a question is input using a microphone and the answer is heard through a speaker. The question analysis unit can also use voice recognition technology to build a system that analyzes a voice-input question and provides an answer by voice. For example, a question is asked using a voice command and an answer is received by voice. The question analysis unit can also respond to voice input, analyze the question using voice recognition technology, and develop an algorithm that provides an answer by voice. For example, the voice-input question can be converted into text and an answer can be generated by voice. This makes it possible to provide a question and answer system that supports voice input and voice output.

[0077] The question analysis unit can generate answers that include visual data, making them easier to understand visually. For example, sales data can be displayed in a graph. The question analysis unit can also build a system that generates answers that include visual data, providing information that is easier to understand visually. For example, the progress of a project can be shown in a diagram. The question analysis unit can also develop an algorithm that generates answers that include visual data. For example, meeting schedules can be displayed in calendar format. This makes it possible to provide answers that are easier to understand visually.

[0078] The question analysis unit can use the emotion estimation function to generate answers that evoke positive emotions in the asker, thereby improving motivation. For example, it can provide answers that include encouraging words or success stories. The question analysis unit can also build a system that analyzes the emotional state of the asker and generates answers that elicit positive emotions. For example, it can provide answers that include positive feedback or words of praise. The question analysis unit can also use the emotion estimation function to develop an algorithm that generates answers that evoke positive emotions in the asker. For example, it can provide positive information preferentially based on the emotion score. This makes it possible to provide answers that improve the asker's motivation.

[0079] When learning from databases and documents, generative AI can evaluate the reliability and recency of data and prioritize learning from highly reliable information. For example, it can select information based on the most recent update date or a highly reliable source. Generative AI can also develop algorithms to evaluate the reliability and recency of data and build systems that prioritize learning from highly reliable information. For example, it can calculate a reliability score and prioritize learning from information with a high score. When learning from databases and documents, generative AI can also set criteria for evaluating the reliability and recency of data and prioritize learning from highly reliable information. For example, it can prioritize learning from official documents and the latest reports. This allows it to prioritize learning from highly reliable information and provide accurate answers.

[0080] Generative AI can learn from a wider range of information sources by including unstructured data in its data. For example, it can analyze email content and chat conversations to extract relevant information. Generative AI can also build systems that analyze and learn from unstructured data. For example, natural language processing techniques can be used to extract important information from emails and chat logs. Generative AI can also develop algorithms that learn from a wider range of information sources by including unstructured data in its data. For example, unstructured data can be converted into text data and used for learning. This allows it to learn from a wider range of information sources and provide comprehensive answers.

[0081] Generative AI can use its emotion estimation function to extract emotionally positive information from training data and reflect it in answers. For example, it can prioritize providing information with a high positive emotion score. Generative AI can also build a system that performs emotion analysis of training data and extracts positive information. For example, it can select positive information based on the emotion score and reflect it in answers. Generative AI can also use its emotion estimation function to develop an algorithm that extracts emotionally positive information from training data and reflects it in answers. For example, it can prioritize learning positive information based on the emotion score. This can improve the satisfaction of the questioner by providing emotionally positive information.

[0082] Generative AI can generate answers by including industry and market data in its data and integrating internal and external information. For example, it can use industry reports and market research data for learning. Generative AI can also integrate external data to build systems that learn from it. For example, it can use external APIs to obtain industry and market data and use it for learning. Generative AI can also develop algorithms that integrate internal and external information to generate answers by including industry and market data in its data. For example, it can integrate external data with internal data and reflect it in the answers. This makes it possible to provide comprehensive answers by integrating internal and external information.

[0083] The processing flow of the second embodiment will be briefly explained below.

[0084] Step 1: The question analysis unit analyzes questions about internal company information from employees. For example, it uses natural language processing technology to analyze the content of the question and keyword extraction technology to identify the important parts of the question. It can also refer to relevant background information to understand the context of the question. Step 2: The answer generation unit generates an answer based on the question analyzed by the question analysis unit. For example, an appropriate answer can be generated using a generative AI (text generation AI or multimodal generation AI), or an optimal answer can be generated using a template-based generation method or a machine learning model. Step 3: The database linking unit links with the company's internal database to provide the answer generated by the answer generation unit. For example, it uses an API to access the company's internal database and obtain the necessary information. It selects the appropriate access method depending on the type of database and provides the information obtained from the database to the answer generation unit.

[0085] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0086] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0087] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0088] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0089] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0090] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0091] 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.

[0092] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0093] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0094] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0095] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0096] 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.

[0097] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0098] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0099] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0103] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0104] 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.

[0105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0106] 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.

[0107] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0110] 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.

[0111] 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.

[0112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0113] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. 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 specific processing unit 290 using these models.

[0114] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0115] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0118] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0119] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] 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.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0126] 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.

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

[0129] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0131] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0133] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0134] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0135] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0136] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0137] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0138] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0139] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0140] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0141] 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.

[0142] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0143] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0144] 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.

[0145] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0146] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0147] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0148] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0149] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0150] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0151] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0152] 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 question analysis department that analyzes questions about internal company information from employees; an answer generation unit that generates an answer based on the question analyzed by the question analysis unit; a database linking unit that links with an in-house database to provide the answer generated by the answer generating unit; A system characterized by:

2. The question analysis unit Refer to the questioner's past question history and generate a personalized answer 2. The system of claim 1.

3. The question analysis unit Prioritize relevant information based on the questioner's job title or department 2. The system of claim 1.

4. The question analysis unit Analyze the questioner's emotional state and generate answers that reduce stress and anxiety 2. The system of claim 1.

5. The question analysis unit Responding to voice input, analyzing the question using voice recognition technology, and providing the answer generated by the answer generation unit by voice.

2. The system of claim 1.

6. The question analysis unit Generate answers that include visual data for easy visual understanding 2. The system of claim 1.

7. The question analysis unit To generate answers that give the questioner positive feelings and improve motivation 2. The system of claim 1.

8. The generated AI is When learning from the database or document, the reliability and recency of the data are evaluated, and highly reliable information is given priority in learning.

2. The system of claim 1.

Images