system

Abstract

The system according to this embodiment aims to analyze the content of PDFs and slides and automatically generate appropriate answers to questions. [Solution] The system according to the embodiment comprises an analysis unit, an answer generation unit, and a reception unit. The analysis unit analyzes the contents of PDFs and slides. The answer generation unit generates answers to questions based on the information analyzed by the analysis unit. The reception unit receives questions from users.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to automatically generate an appropriate answer to a question based on the content of a PDF or a slide.

[0005] The system according to the embodiment aims to analyze the content of a PDF or a slide and automatically generate an appropriate answer to a question. [[ID=)40]]

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, an answer generation unit, and a reception unit. The analysis unit analyzes the content of a PDF or a slide. The answer generation unit generates an answer to a question based on the information analyzed by the analysis unit. The reception unit receives a question from a user.

Advantages of the Invention

[0007] The system according to this embodiment can analyze the content of PDFs and slides and automatically generate appropriate answers to questions. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An information analysis system according to an embodiment of the present invention is a system that analyzes the contents of PDFs and slides and provides appropriate answers to user questions. This information analysis system takes PDF and slide files as input to a generating AI, which analyzes these files and extracts process and employee information. Based on the extracted information, the generating AI generates appropriate answers to user questions. This mechanism provides quick and accurate answers that take process and employee information into account. For example, a PDF or slide explaining a company's business processes and employee roles is loaded into the generating AI. The generating AI analyzes the file contents and extracts important information. Next, the generating AI analyzes the file and extracts process and employee information. The generating AI analyzes the text and diagrams within the file to identify the flow of business processes and employee roles. For example, it extracts each step of the business process and the assigned tasks of employees. Based on the extracted information, the generating AI generates appropriate answers to user questions. For example, if a user asks, "What is the next step in this business process?", the generating AI answers with the next step based on the extracted information. Furthermore, if a user asks, "Who is in charge of this task?", the generating AI will answer based on employee information. This mechanism provides quick and accurate answers that take processes and employee information into consideration. For example, when a new employee is trying to understand a work process, the generating AI can provide an appropriate answer, making it easier for them to understand the work. Also, when an employee is checking the progress of a task, the generating AI can provide a quick response, improving work efficiency. In this way, the information analysis system can provide quick and accurate answers that take processes and employee information into consideration.

[0029] The information analysis system according to this embodiment comprises an analysis unit, an answer generation unit, and a reception unit. The analysis unit analyzes the contents of PDFs and slides. The analysis unit analyzes the contents of PDFs and slides using, for example, natural language processing technology or image recognition technology. The analysis unit analyzes the text and charts in the files to identify the flow of business processes and the roles of employees. For example, the analysis unit uses text analysis technology to analyze the text in PDFs and slides and extract each step of the business process. The analysis unit can also use image recognition technology to analyze charts in slides and identify the roles of employees. For example, the analysis unit uses OCR technology to extract text in PDFs and identify the flow of business processes. The answer generation unit generates answers to questions based on the information analyzed by the analysis unit. The answer generation unit generates appropriate answers based on the analyzed information using, for example, an inference engine or natural language processing technology. For example, the answer generation unit answers the next step in response to a user's question based on the analyzed information. The answer generation unit can also answer with the person in charge based on employee information. For example, the answer generation unit uses natural language processing technology to analyze the user's question and generate an appropriate answer. The reception unit receives questions from the user. The reception unit uses natural language processing technology to understand the user's question and passes it to the answer generation unit. For example, the reception unit receives the user's question in text format and uses natural language processing technology to analyze the intent of the question. As a result, the information analysis system according to this embodiment can analyze the contents of PDFs and slides and provide appropriate answers to the user's questions.

[0030] The analysis unit can analyze the content of PDFs and slides using natural language processing and image recognition technologies. Natural language processing technologies include, for example, morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis is a technology that divides a sentence into individual words and identifies the part of speech of each word. Grammatical analysis is a technology that analyzes the structure of a sentence and identifies relationships such as subject, predicate, and object. Semantic analysis is a technology that analyzes the meaning of a sentence and identifies the appropriate meaning based on the context. For example, the analysis unit can use morphological analysis to divide the text in a PDF into individual words and identify the part of speech of each word. The analysis unit can also use grammatical analysis to analyze the structure of a sentence and identify relationships such as subject, predicate, and object. Furthermore, the analysis unit can use semantic analysis to analyze the meaning of a sentence and identify the appropriate meaning based on the context. Image recognition technologies include, for example, object detection, face recognition, and character recognition. Object detection is a technology that detects specific objects in an image. Face recognition is a technology that detects faces in an image and identifies specific individuals. Character recognition is a technology that detects characters in an image and converts them into text data. For example, the analysis unit can use object detection technology to analyze diagrams and charts within a slide and detect specific objects. The analysis unit can also use facial recognition technology to detect faces within a slide and identify specific individuals. Furthermore, the analysis unit can use character recognition technology to detect characters within a slide and convert them into text data. This allows for more accurate analysis of PDF and slide content by utilizing natural language processing and image recognition technologies.

[0031] The answer generation unit can generate appropriate answers based on the analyzed information using an inference engine and natural language processing techniques. Inference engines include, for example, rule-based inference and Bayesian inference. Rule-based inference is a technique that performs inference based on predefined rules. Bayesian inference is a technique that performs inference based on probability theory. For example, the answer generation unit uses rule-based inference to generate appropriate answers based on predefined rules. Alternatively, the answer generation unit can use Bayesian inference to generate appropriate answers based on probability theory. Natural language processing techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis is a technique that divides a sentence into words and identifies the part of speech of each word. Grammatical analysis is a technique that analyzes the structure of a sentence and identifies relationships such as subject, predicate, and object. Semantic analysis is a technique that analyzes the meaning of a sentence and identifies the appropriate meaning based on the context. For example, the answer generation unit uses morphological analysis to divide the user's question into words and identify the part of speech of each word. Furthermore, the answer generation unit can analyze the structure of a question using grammatical analysis and identify relationships between subjects, predicates, and objects. In addition, the answer generation unit can analyze the meaning of a question using semantic analysis and generate an appropriate answer based on the context. This allows for the generation of more appropriate answers by utilizing inference engines and natural language processing techniques.

[0032] The reception unit can understand user questions using natural language processing (NLP) techniques and pass them on to the answer generation unit. NLP techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis is a technique that divides a sentence into individual words and identifies the part of speech of each word. Grammatical analysis is a technique that analyzes the structure of a sentence and identifies relationships such as subject, predicate, and object. Semantic analysis is a technique that analyzes the meaning of a sentence and identifies the appropriate meaning based on the context. For example, the reception unit can use morphological analysis to divide the user's question into individual words and identify the part of speech of each word. It can also use grammatical analysis to analyze the structure of the question and identify relationships such as subject, predicate, and object. Furthermore, it can use semantic analysis to analyze the meaning of the question and identify the appropriate meaning based on the context. This allows the system to accurately understand user questions and provide information necessary to generate appropriate answers by utilizing natural language processing techniques.

[0033] The analysis unit can analyze text and diagrams within files to identify the flow of business processes and the roles of employees. Text and diagrams include, for example, sentences, bullet points, graphs, and charts. For instance, the analysis unit can use text analysis technology to analyze text in PDFs and slides and extract each step of a business process. For example, it can use morphological analysis to divide sentences into individual words and identify the part of speech of each word. It can also use grammatical analysis to analyze the structure of sentences and identify relationships such as subject, predicate, and object. Furthermore, it can use semantic analysis to analyze the meaning of sentences and identify the appropriate meaning based on context. Diagrams include, for example, graphs, charts, and flowcharts. The analysis unit can use, for example, image recognition technology to analyze diagrams within slides and detect specific objects. For example, it can use object detection technology to analyze diagrams within slides and detect specific objects. It can also use character recognition technology to detect characters within slides and convert them into text data. This allows for the accurate identification of business process flows and employee roles by analyzing text and diagrams within files.

[0034] The answer generation unit can generate appropriate answers to user questions based on extracted information. Extracted information includes, for example, text data, numerical data, and image data. Text data includes, for example, each step of a business process, employee roles, and the progress of work. Numerical data includes, for example, work progress, employee performance evaluations, and data related to work efficiency. Image data includes, for example, business process flowcharts, employee portraits, and work deliverables. The answer generation unit generates appropriate answers to user questions based on text data. For example, it answers user questions with the next step based on information about each step of a business process. It can also answer user questions with the person responsible based on information about employee roles. When using numerical data, the answer generation unit generates appropriate answers to user questions based on data related to work progress and employee performance evaluations. For example, it answers user questions with the current progress based on data related to work progress. When using image data as a basis, the answer generation unit generates appropriate answers to user questions based on business process flowcharts and employee photos. For example, the answer generation unit analyzes a business process flowchart and answers the user's question with the next step. The answer generation unit can also answer user questions with the assigned person based on employee photos. This allows for more appropriate answers to user questions based on the extracted information.

[0035] The analysis unit can improve the accuracy of its analysis by considering the file's metadata when analyzing the content of PDFs and slides. Metadata includes, for example, creation date and time, creator, and file size. The analysis unit can, for example, consider the file's creation date and time and prioritize the analysis of the latest information. For example, the analysis unit can prioritize the analysis of the latest information based on the file's creation date and time. The analysis unit can also consider the file's creator information and prioritize the analysis of highly reliable information. For example, the analysis unit can prioritize the analysis of highly reliable information based on the file's creator information. Furthermore, the analysis unit can also consider the file's version information and prioritize the analysis of the latest version. For example, the analysis unit can prioritize the analysis of the latest version based on the file's version information. This improves the accuracy of the analysis by considering the file's metadata. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input the file's metadata into a generating AI, and the generating AI can analyze the metadata to improve the accuracy of the analysis.

[0036] The analysis unit can prioritize analyzing the latest information by referring to the file's update history during analysis. The update history includes, for example, the modification date and time, the content of the changes, and the person who made the changes. The analysis unit can prioritize analyzing the latest information based on the file's modification date and time. For example, the analysis unit can prioritize analyzing the latest information based on the file's update content. For example, the analysis unit can prioritize analyzing important changes based on the file's update content. Furthermore, the analysis unit can prioritize analyzing information that is frequently updated based on the file's update history. For example, the analysis unit can prioritize analyzing information that is frequently updated based on the file's update history. This allows the analysis unit to prioritize analyzing the latest information by referring to the file's update history. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can input the file's update history into a generation AI, which can analyze the update history and prioritize analyzing the latest information.

[0037] The analysis unit can evaluate the reliability of the analysis by considering the file creator information during the analysis. Creator information includes, for example, name, affiliation, and position. For example, the analysis unit will rate the reliability of the analysis results highly if the file creator is an expert. The analysis unit may also rate the reliability of the analysis results lower if the file creator is a newcomer. Furthermore, if there are multiple file creators, the analysis unit can comprehensively evaluate the reliability of each creator. In this way, considering the file creator information improves the reliability of the analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can input the file creator information into a generation AI, and the generation AI can analyze the creator information to evaluate the reliability of the analysis.

[0038] The analysis unit can improve the accuracy of its analysis by referring to relevant documents related to the file during the analysis. These relevant documents include, for example, academic papers, technical reports, and patent documents. The analysis unit can, for example, refer to documents related to the file content to improve the accuracy of the analysis results. Furthermore, the analysis unit can also improve the accuracy of its analysis results by referring to patent documents related to the file content. In addition, the analysis unit can improve the accuracy of its analysis results by referring to academic papers related to the file content. Thus, by referring to relevant documents, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input relevant documents into a generating AI, which can then analyze the documents to improve the accuracy of the analysis.

[0039] The answer generation unit can adjust the level of detail in the answer by considering the context of the question when generating an answer. For example, if the question is specific, the answer generation unit can generate a detailed answer. For example, the answer generation unit analyzes the user's question and generates a detailed answer to a specific question. The answer generation unit can also generate a concise answer if the question is abstract. For example, the answer generation unit analyzes the user's question and generates a concise answer to an abstract question. Furthermore, if the question is complex, the answer generation unit can generate a progressively more detailed answer. For example, the answer generation unit analyzes the user's question and generates a progressively more detailed answer to a complex question. This allows for the provision of an answer with a more appropriate level of detail by considering the context of the question. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the answer generation unit can input the context of the question into the generation AI, which can analyze the context and adjust the level of detail in the answer.

[0040] The answer generation unit can generate the optimal answer by referring to past question history when generating an answer. Past question history includes, for example, the question content, the answer content, and the date and time of the question. For example, the answer generation unit can generate the optimal answer to a question similar to one previously asked by the user, by referring to past answers. For example, the answer generation unit generates the optimal answer to a similar question based on past question history. The answer generation unit can also analyze patterns of questions previously asked by the user and generate the optimal answer. For example, the answer generation unit analyzes past question patterns and generates the optimal answer. Furthermore, the answer generation unit can generate an answer that includes relevant information based on the history of questions previously asked by the user. For example, the answer generation unit generates an answer that includes relevant information based on past question history. This allows for the provision of more optimal answers by referring to past question history. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the answer generation unit can input past question history into a generation AI, which can then analyze the question history and generate the optimal answer.

[0041] The answer generation unit can determine the priority of answers based on when the question was submitted. The question submission period includes, for example, the submission date and time, and the frequency of submission. The answer generation unit can, for example, prioritize answers if the question is urgent. For example, the answer generation unit can prioritize answers to urgent questions based on the submission date and time. The answer generation unit can also generate answers with normal priority if the question is not urgent. For example, the answer generation unit can generate answers with normal priority to normal questions based on the submission date and time. Furthermore, the answer generation unit can generate answers with a lower priority if the question is from the past. For example, the answer generation unit can generate answers with a lower priority to past questions based on the submission date and time. By determining the priority of answers based on when the question was submitted, answers can be provided at a more appropriate time. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the answer generation unit can input the question submission period into a generation AI, and the generation AI can analyze the submission period to determine the priority of answers.

[0042] The answer generation unit can adjust the order of answers based on the relevance of the questions when generating answers. Question relevance includes, for example, the degree of topic matching and relevance to past questions. The answer generation unit, for example, prioritizes generating answers for questions that are highly relevant. For example, the answer generation unit prioritizes generating answers for highly relevant questions based on the degree of topic matching. The answer generation unit can also generate answers with a lower priority if the questions are less relevant. For example, the answer generation unit generates answers with a lower priority for less relevant questions based on the degree of topic matching. Furthermore, if there are multiple questions, the answer generation unit can generate answers in order of relevance. For example, the answer generation unit generates answers for multiple questions in order of relevance based on the degree of topic matching. By adjusting the order of answers based on the relevance of the questions, answers can be provided in a more appropriate order. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the answer generation unit can input the relationships between questions into the generation AI, which can then analyze the relationships and adjust the order of the answers.

[0043] The reception desk can select the most appropriate reception method when receiving a question by referring to the user's past question history. Past question history includes, for example, the question content, the answer content, and the date and time of the question. The reception desk can, for example, prioritize suggesting question formats that the user has frequently used in the past. For example, the reception desk can prioritize suggesting frequently used question formats based on past question history. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. For example, the reception desk can prioritize suggesting input methods that the user has frequently used based on past question history. Furthermore, the reception desk can predict and suggest question formats to be used during specific time periods based on the user's past question history. For example, the reception desk can predict and suggest question formats to be used during specific time periods based on past question history. This allows for the selection of a more appropriate reception method by referring to past question history. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or without a generative AI. For example, the reception desk can input past question history into a generative AI, which can analyze the question history and select the most appropriate reception method.

[0044] The reception desk can adjust the priority of questions based on the user's current situation when receiving a question. The user's current situation includes, for example, current activities, current location, and current state. The reception desk will, for example, prioritize urgent questions if the user is asking one. For example, the reception desk will prioritize urgent questions based on the user's current activities. The reception desk can also prioritize regular questions if the user is asking one. For example, the reception desk will prioritize regular questions based on the user's current activities. Furthermore, the reception desk can give lower priority to questions that the user has asked in the past. For example, the reception desk will give lower priority to questions that have been asked in the past based on the user's current activities. By adjusting the priority of questions based on the user's current situation, questions can be received in a more appropriate order. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's current situation into a generative AI, which can analyze the situation and adjust the priority of questions.

[0045] The reception desk can prioritize receiving questions that are highly relevant to the user, taking into account the user's geographical location information. Geographical location information includes, for example, GPS data and address information. For example, if the user is in a specific region, the reception desk will prioritize receiving questions related to that region. For example, the reception desk will prioritize receiving questions related to the region based on the user's geographical location information. The reception desk can also prioritize receiving questions related to the user's current location if the user is on the move. For example, the reception desk will prioritize receiving questions related to the current location of a user on the move based on the user's geographical location information. Furthermore, if the user is in a specific facility, the reception desk can also prioritize receiving questions related to that facility. For example, the reception desk will prioritize receiving questions related to a specific facility for a user in that facility based on the user's geographical location information. In this way, by taking the user's geographical location information into consideration, highly relevant questions can be prioritized. Some or all of the above processing in the reception desk may be performed using, for example, generative AI, or without using generative AI. For example, the reception desk can input the user's geographical location information into a generating AI, which then analyzes the location information to prioritize receiving highly relevant questions.

[0046] The reception desk can analyze a user's social media activity when receiving a question and accept relevant questions. Social media activity includes, for example, posts, comments, and the number of likes. For example, if a user mentions a specific topic on social media, the reception desk will prioritize accepting questions related to that topic. For example, the reception desk will prioritize accepting questions related to a specific topic based on the user's social media activity. The reception desk can also prioritize accepting questions related to an event if a user participates in a specific event on social media. For example, the reception desk will prioritize accepting questions related to an event based on the user's social media activity. Furthermore, if a user uses a specific hashtag on social media, the reception desk will prioritize accepting questions related to that hashtag. For example, the reception desk will prioritize accepting questions related to a specific hashtag based on the user's social media activity. In this way, by analyzing a user's social media activity, relevant questions can be prioritized. Some or all of the above processing in the reception desk may be performed using, for example, generative AI, or not using generative AI. For example, the reception desk can input a user's social media activity into a generating AI, which can then analyze the activity and prioritize receiving relevant questions.

[0047] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0048] The analysis unit can improve the accuracy of the analysis by considering the file creator's area of ​​expertise during the analysis process. For example, if the creator is an expert in a specific field, the analysis will prioritize information related to that field. Furthermore, if the creator is an expert in multiple fields, the analysis can comprehensively analyze information related to each field. In addition, the analysis can improve the accuracy of the results by referencing relevant literature and data based on the creator's area of ​​expertise. Thus, considering the creator's area of ​​expertise improves the accuracy of the analysis.

[0049] The analysis unit can adjust the analysis priority during analysis, taking into account the update frequency of files. For example, it can prioritize the analysis of frequently updated files to provide the latest information. Furthermore, it can perform detailed analysis on files with low update frequency as needed. It can also improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on the update frequency. This allows for the adjustment of analysis priority by considering file update frequency, thereby providing more appropriate analysis results.

[0050] The analysis unit can adjust the analysis priority by considering the relationships between files during the analysis process. For example, it can prioritize the analysis of highly relevant files to quickly provide important information. Furthermore, it can perform detailed analysis on less relevant files as needed. It can also improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on relationships. In this way, by considering the relationships between files, the analysis priority can be adjusted, providing more appropriate analysis results.

[0051] The analysis unit can adjust the analysis priority during analysis, taking into account the reliability of the file creator. For example, it can prioritize the analysis of files from highly reliable creators to provide reliable information. Furthermore, it can perform detailed analysis on files from less reliable creators as needed. In addition, it can improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on the creator's reliability. This allows for adjustment of analysis priorities and the provision of more appropriate analysis results by considering the creator's reliability.

[0052] The analysis unit can adjust the analysis priority during analysis, taking into account the file creation date and time. For example, it can prioritize the analysis of the most recent files to provide the latest information. For older files, it can perform detailed analysis as needed. Furthermore, it can improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on the creation date and time. This allows for adjustment of analysis priority and the provision of more appropriate analysis results by considering the file creation date and time.

[0053] The following briefly describes the processing flow for example form 1.

[0054] Step 1: The analysis unit analyzes the content of PDFs and slides. The analysis unit uses natural language processing and image recognition technologies to analyze the content of PDFs and slides, analyzing text and diagrams within the files to identify the flow of business processes and the roles of employees. For example, it can use text analysis technology to analyze text and extract each step of the business process. It can also use image recognition technology to analyze diagrams within slides and identify the roles of employees. It is also possible to use OCR technology to extract text from PDFs and identify the flow of business processes. Step 2: The answer generation unit generates an answer to the question based on the information analyzed by the analysis unit. The answer generation unit generates an appropriate answer based on the information analyzed using an inference engine and natural language processing technology. For example, it can answer the next step based on the analyzed information in response to a user's question, or answer the person in charge based on employee information. It analyzes the user's question using natural language processing technology and generates an appropriate answer. Step 3: The reception unit receives questions from users. The reception unit uses natural language processing technology to understand the user's questions and passes them on to the answer generation unit. For example, the user's question is received in text format, and the intent of the question is analyzed using natural language processing technology.

[0055] (Example of form 2) An information analysis system according to an embodiment of the present invention is a system that analyzes the contents of PDFs and slides and provides appropriate answers to user questions. This information analysis system takes PDF and slide files as input to a generating AI, which analyzes these files and extracts process and employee information. Based on the extracted information, the generating AI generates appropriate answers to user questions. This mechanism provides quick and accurate answers that take process and employee information into account. For example, a PDF or slide explaining a company's business processes and employee roles is loaded into the generating AI. The generating AI analyzes the file contents and extracts important information. Next, the generating AI analyzes the file and extracts process and employee information. The generating AI analyzes the text and diagrams within the file to identify the flow of business processes and employee roles. For example, it extracts each step of the business process and the assigned tasks of employees. Based on the extracted information, the generating AI generates appropriate answers to user questions. For example, if a user asks, "What is the next step in this business process?", the generating AI answers with the next step based on the extracted information. Furthermore, if a user asks, "Who is in charge of this task?", the generating AI will answer based on employee information. This mechanism provides quick and accurate answers that take processes and employee information into consideration. For example, when a new employee is trying to understand a work process, the generating AI can provide an appropriate answer, making it easier for them to understand the work. Also, when an employee is checking the progress of a task, the generating AI can provide a quick response, improving work efficiency. In this way, the information analysis system can provide quick and accurate answers that take processes and employee information into consideration.

[0056] The information analysis system according to this embodiment comprises an analysis unit, an answer generation unit, and a reception unit. The analysis unit analyzes the contents of PDFs and slides. The analysis unit analyzes the contents of PDFs and slides using, for example, natural language processing technology or image recognition technology. The analysis unit analyzes the text and charts in the files to identify the flow of business processes and the roles of employees. For example, the analysis unit uses text analysis technology to analyze the text in PDFs and slides and extract each step of the business process. The analysis unit can also use image recognition technology to analyze charts in slides and identify the roles of employees. For example, the analysis unit uses OCR technology to extract text in PDFs and identify the flow of business processes. The answer generation unit generates answers to questions based on the information analyzed by the analysis unit. The answer generation unit generates appropriate answers based on the analyzed information using, for example, an inference engine or natural language processing technology. For example, the answer generation unit answers the next step in response to a user's question based on the analyzed information. The answer generation unit can also answer with the person in charge based on employee information. For example, the answer generation unit uses natural language processing technology to analyze the user's question and generate an appropriate answer. The reception unit receives questions from the user. The reception unit uses natural language processing technology to understand the user's question and passes it to the answer generation unit. For example, the reception unit receives the user's question in text format and uses natural language processing technology to analyze the intent of the question. As a result, the information analysis system according to this embodiment can analyze the contents of PDFs and slides and provide appropriate answers to the user's questions.

[0057] The analysis unit can analyze the content of PDFs and slides using natural language processing and image recognition technologies. Natural language processing technologies include, for example, morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis is a technology that divides a sentence into individual words and identifies the part of speech of each word. Grammatical analysis is a technology that analyzes the structure of a sentence and identifies relationships such as subject, predicate, and object. Semantic analysis is a technology that analyzes the meaning of a sentence and identifies the appropriate meaning based on the context. For example, the analysis unit can use morphological analysis to divide the text in a PDF into individual words and identify the part of speech of each word. The analysis unit can also use grammatical analysis to analyze the structure of a sentence and identify relationships such as subject, predicate, and object. Furthermore, the analysis unit can use semantic analysis to analyze the meaning of a sentence and identify the appropriate meaning based on the context. Image recognition technologies include, for example, object detection, face recognition, and character recognition. Object detection is a technology that detects specific objects in an image. Face recognition is a technology that detects faces in an image and identifies specific individuals. Character recognition is a technology that detects characters in an image and converts them into text data. For example, the analysis unit can use object detection technology to analyze diagrams and charts within a slide and detect specific objects. The analysis unit can also use facial recognition technology to detect faces within a slide and identify specific individuals. Furthermore, the analysis unit can use character recognition technology to detect characters within a slide and convert them into text data. This allows for more accurate analysis of PDF and slide content by utilizing natural language processing and image recognition technologies.

[0058] The answer generation unit can generate appropriate answers based on the analyzed information using an inference engine and natural language processing techniques. Inference engines include, for example, rule-based inference and Bayesian inference. Rule-based inference is a technique that performs inference based on predefined rules. Bayesian inference is a technique that performs inference based on probability theory. For example, the answer generation unit uses rule-based inference to generate appropriate answers based on predefined rules. Alternatively, the answer generation unit can use Bayesian inference to generate appropriate answers based on probability theory. Natural language processing techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis is a technique that divides a sentence into words and identifies the part of speech of each word. Grammatical analysis is a technique that analyzes the structure of a sentence and identifies relationships such as subject, predicate, and object. Semantic analysis is a technique that analyzes the meaning of a sentence and identifies the appropriate meaning based on the context. For example, the answer generation unit uses morphological analysis to divide the user's question into words and identify the part of speech of each word. Furthermore, the answer generation unit can analyze the structure of a question using grammatical analysis and identify relationships between subjects, predicates, and objects. In addition, the answer generation unit can analyze the meaning of a question using semantic analysis and generate an appropriate answer based on the context. This allows for the generation of more appropriate answers by utilizing inference engines and natural language processing techniques.

[0059] The reception unit can understand user questions using natural language processing (NLP) techniques and pass them on to the answer generation unit. NLP techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis is a technique that divides a sentence into individual words and identifies the part of speech of each word. Grammatical analysis is a technique that analyzes the structure of a sentence and identifies relationships such as subject, predicate, and object. Semantic analysis is a technique that analyzes the meaning of a sentence and identifies the appropriate meaning based on the context. For example, the reception unit can use morphological analysis to divide the user's question into individual words and identify the part of speech of each word. It can also use grammatical analysis to analyze the structure of the question and identify relationships such as subject, predicate, and object. Furthermore, it can use semantic analysis to analyze the meaning of the question and identify the appropriate meaning based on the context. This allows the system to accurately understand user questions and provide information necessary to generate appropriate answers by utilizing natural language processing techniques.

[0060] The analysis unit can analyze text and diagrams within files to identify the flow of business processes and the roles of employees. Text and diagrams include, for example, sentences, bullet points, graphs, and charts. For instance, the analysis unit can use text analysis technology to analyze text in PDFs and slides and extract each step of a business process. For example, it can use morphological analysis to divide sentences into individual words and identify the part of speech of each word. It can also use grammatical analysis to analyze the structure of sentences and identify relationships such as subject, predicate, and object. Furthermore, it can use semantic analysis to analyze the meaning of sentences and identify the appropriate meaning based on context. Diagrams include, for example, graphs, charts, and flowcharts. The analysis unit can use, for example, image recognition technology to analyze diagrams within slides and detect specific objects. For example, it can use object detection technology to analyze diagrams within slides and detect specific objects. It can also use character recognition technology to detect characters within slides and convert them into text data. This allows for the accurate identification of business process flows and employee roles by analyzing text and diagrams within files.

[0061] The answer generation unit can generate appropriate answers to user questions based on extracted information. Extracted information includes, for example, text data, numerical data, and image data. Text data includes, for example, each step of a business process, employee roles, and the progress of work. Numerical data includes, for example, work progress, employee performance evaluations, and data related to work efficiency. Image data includes, for example, business process flowcharts, employee portraits, and work deliverables. The answer generation unit generates appropriate answers to user questions based on text data. For example, it answers user questions with the next step based on information about each step of a business process. It can also answer user questions with the person responsible based on information about employee roles. When using numerical data, the answer generation unit generates appropriate answers to user questions based on data related to work progress and employee performance evaluations. For example, it answers user questions with the current progress based on data related to work progress. When using image data as a basis, the answer generation unit generates appropriate answers to user questions based on business process flowcharts and employee photos. For example, the answer generation unit analyzes a business process flowchart and answers the user's question with the next step. The answer generation unit can also answer user questions with the assigned person based on employee photos. This allows for more appropriate answers to user questions based on the extracted information.

[0062] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated emotions. For example, if the user is stressed, the analysis unit prioritizes analyzing important information and provides results quickly. For instance, the analysis unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. The analysis unit calculates an emotion score based on changes in facial expressions and prioritizes analyzing important information for stressed users. Furthermore, if the user is relaxed, the analysis unit performs an analysis that includes detailed information and provides comprehensive results. For example, the analysis unit records the user's voice and estimates their emotions using voice analysis technology. The analysis unit analyzes the tone and speed of the voice and performs an analysis that includes detailed information for relaxed users. In addition, if the user is in a hurry, the analysis unit prioritizes analyzing the most important information and provides results quickly. For example, the analysis unit collects the user's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. The analysis unit calculates an emotion score based on heart rate fluctuations and prioritizes analyzing the most important information for users in a hurry. This allows for more appropriate analysis results by adjusting the analysis priority based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0063] The analysis unit can improve the accuracy of its analysis by considering the file's metadata when analyzing the content of PDFs and slides. Metadata includes, for example, creation date and time, creator, and file size. The analysis unit can, for example, consider the file's creation date and time and prioritize the analysis of the latest information. For example, the analysis unit can prioritize the analysis of the latest information based on the file's creation date and time. The analysis unit can also consider the file's creator information and prioritize the analysis of highly reliable information. For example, the analysis unit can prioritize the analysis of highly reliable information based on the file's creator information. Furthermore, the analysis unit can also consider the file's version information and prioritize the analysis of the latest version. For example, the analysis unit can prioritize the analysis of the latest version based on the file's version information. This improves the accuracy of the analysis by considering the file's metadata. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input the file's metadata into a generating AI, and the generating AI can analyze the metadata to improve the accuracy of the analysis.

[0064] The analysis unit can prioritize analyzing the latest information by referring to the file's update history during analysis. The update history includes, for example, the modification date and time, the content of the changes, and the person who made the changes. The analysis unit can prioritize analyzing the latest information based on the file's modification date and time. For example, the analysis unit can prioritize analyzing the latest information based on the file's update content. For example, the analysis unit can prioritize analyzing important changes based on the file's update content. Furthermore, the analysis unit can prioritize analyzing information that is frequently updated based on the file's update history. For example, the analysis unit can prioritize analyzing information that is frequently updated based on the file's update history. This allows the analysis unit to prioritize analyzing the latest information by referring to the file's update history. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can input the file's update history into a generation AI, which can analyze the update history and prioritize analyzing the latest information.

[0065] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit provides a simple and easy-to-understand display method. For instance, the analysis unit captures the user's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. The analysis unit calculates an emotion score based on changes in facial expression and provides a simple and easy-to-understand display method for nervous users. Furthermore, if the user is relaxed, the analysis unit provides a display method that includes detailed information. For example, the analysis unit records the user's voice and estimates their emotions using voice analysis technology. The analysis unit analyzes the tone and speed of the voice and provides a display method that includes detailed information for relaxed users. In addition, if the user is in a hurry, the analysis unit provides a concise display method. For example, the analysis unit collects the user's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. The analysis unit calculates an emotion score based on fluctuations in heart rate and provides a concise display method for users in a hurry. This allows for more appropriate display by adjusting how analysis results are shown based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0066] The analysis unit can evaluate the reliability of the analysis by considering the file creator information during the analysis. Creator information includes, for example, name, affiliation, and position. For example, the analysis unit will rate the reliability of the analysis results highly if the file creator is an expert. The analysis unit may also rate the reliability of the analysis results lower if the file creator is a newcomer. Furthermore, if there are multiple file creators, the analysis unit can comprehensively evaluate the reliability of each creator. In this way, considering the file creator information improves the reliability of the analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can input the file creator information into a generation AI, and the generation AI can analyze the creator information to evaluate the reliability of the analysis.

[0067] The analysis unit can improve the accuracy of its analysis by referring to relevant documents related to the file during the analysis. These relevant documents include, for example, academic papers, technical reports, and patent documents. The analysis unit can, for example, refer to documents related to the file content to improve the accuracy of the analysis results. Furthermore, the analysis unit can also improve the accuracy of its analysis results by referring to patent documents related to the file content. In addition, the analysis unit can improve the accuracy of its analysis results by referring to academic papers related to the file content. Thus, by referring to relevant documents, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input relevant documents into a generating AI, which can then analyze the documents to improve the accuracy of the analysis.

[0068] The response generation unit can estimate the user's emotions and adjust the way the response is expressed based on the estimated emotions. For example, if the user is relaxed, the response generation unit will generate a detailed and polite response. For example, the response generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The response generation unit will calculate an emotion score based on the changes in facial expressions and generate a detailed and polite response for a relaxed user. Also, if the user is in a hurry, the response generation unit will generate a concise and to-the-point response. For example, the response generation unit can record the user's voice and estimate their emotions using voice analysis technology. The response generation unit will analyze the tone and speed of the voice and generate a concise and to-the-point response for a user in a hurry. Furthermore, if the user is excited, the response generation unit will generate a response with visually stimulating effects. For example, the response generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. The response generation unit calculates an emotion score based on heart rate fluctuations and generates responses with visually stimulating effects for excited users. This allows for the provision of more appropriate responses by adjusting the expression of responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0069] The answer generation unit can adjust the level of detail in the answer by considering the context of the question when generating an answer. For example, if the question is specific, the answer generation unit can generate a detailed answer. For example, the answer generation unit analyzes the user's question and generates a detailed answer to a specific question. The answer generation unit can also generate a concise answer if the question is abstract. For example, the answer generation unit analyzes the user's question and generates a concise answer to an abstract question. Furthermore, if the question is complex, the answer generation unit can generate a progressively more detailed answer. For example, the answer generation unit analyzes the user's question and generates a progressively more detailed answer to a complex question. This allows for the provision of an answer with a more appropriate level of detail by considering the context of the question. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the answer generation unit can input the context of the question into the generation AI, which can analyze the context and adjust the level of detail in the answer.

[0070] The answer generation unit can generate the optimal answer by referring to past question history when generating an answer. Past question history includes, for example, the question content, the answer content, and the date and time of the question. For example, the answer generation unit can generate the optimal answer to a question similar to one previously asked by the user, by referring to past answers. For example, the answer generation unit generates the optimal answer to a similar question based on past question history. The answer generation unit can also analyze patterns of questions previously asked by the user and generate the optimal answer. For example, the answer generation unit analyzes past question patterns and generates the optimal answer. Furthermore, the answer generation unit can generate an answer that includes relevant information based on the history of questions previously asked by the user. For example, the answer generation unit generates an answer that includes relevant information based on past question history. This allows for the provision of more optimal answers by referring to past question history. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the answer generation unit can input past question history into a generation AI, which can then analyze the question history and generate the optimal answer.

[0071] The response generation unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is in a hurry, the response generation unit will generate a short, concise response. For example, the response generation unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The response generation unit will calculate an emotion score based on the changes in facial expressions and generate a short, concise response for the user in a hurry. Furthermore, if the user is relaxed, the response generation unit will generate a longer response that includes detailed explanations. For example, the response generation unit can record the user's voice and estimate their emotions using voice analysis technology. The response generation unit will analyze the tone and speed of the voice and generate a longer response that includes detailed explanations for the relaxed user. In addition, if the user is excited, the response generation unit will generate a response with visually stimulating effects. For example, the response generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. The response generation unit calculates an emotion score based on heart rate fluctuations and generates responses with visually stimulating effects for excited users. This allows for the provision of more appropriate responses by adjusting the length of the response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0072] The answer generation unit can determine the priority of answers based on when the question was submitted. The question submission period includes, for example, the submission date and time, and the frequency of submission. The answer generation unit can, for example, prioritize answers if the question is urgent. For example, the answer generation unit can prioritize answers to urgent questions based on the submission date and time. The answer generation unit can also generate answers with normal priority if the question is not urgent. For example, the answer generation unit can generate answers with normal priority to normal questions based on the submission date and time. Furthermore, the answer generation unit can generate answers with a lower priority if the question is from the past. For example, the answer generation unit can generate answers with a lower priority to past questions based on the submission date and time. By determining the priority of answers based on when the question was submitted, answers can be provided at a more appropriate time. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the answer generation unit can input the question submission period into a generation AI, and the generation AI can analyze the submission period to determine the priority of answers.

[0073] The answer generation unit can adjust the order of answers based on the relevance of the questions when generating answers. Question relevance includes, for example, the degree of topic matching and relevance to past questions. The answer generation unit, for example, prioritizes generating answers for questions that are highly relevant. For example, the answer generation unit prioritizes generating answers for highly relevant questions based on the degree of topic matching. The answer generation unit can also generate answers with a lower priority if the questions are less relevant. For example, the answer generation unit generates answers with a lower priority for less relevant questions based on the degree of topic matching. Furthermore, if there are multiple questions, the answer generation unit can generate answers in order of relevance. For example, the answer generation unit generates answers for multiple questions in order of relevance based on the degree of topic matching. By adjusting the order of answers based on the relevance of the questions, answers can be provided in a more appropriate order. Some or all of the above processing in the answer generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the answer generation unit can input the relationships between questions into the generation AI, which can then analyze the relationships and adjust the order of the answers.

[0074] The reception system can estimate the user's emotions and adjust how questions are answered based on those emotions. For example, if the user is stressed, the reception system can provide a simple interface and minimize the input steps. For instance, the reception system can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Based on changes in facial expressions, the reception system can calculate an emotion score and provide a simple interface and minimize the input steps for stressed users. Furthermore, if the user is relaxed, the reception system can provide detailed input options and suggest customizable input methods. For example, the reception system can record the user's voice and estimate their emotions using voice analysis technology. The reception system can analyze the tone and speed of the voice and provide detailed input options and suggest customizable input methods for relaxed users. In addition, if the user is in a hurry, the reception system can prioritize voice input to quickly answer questions. For example, the reception system can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. The reception desk calculates an emotion score based on heart rate fluctuations, prioritizing voice input for users in a hurry to quickly process their questions. This allows for more appropriate question processing by adjusting the question processing method based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0075] The reception desk can select the most appropriate reception method when receiving a question by referring to the user's past question history. Past question history includes, for example, the question content, the answer content, and the date and time of the question. The reception desk can, for example, prioritize suggesting question formats that the user has frequently used in the past. For example, the reception desk can prioritize suggesting frequently used question formats based on past question history. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. For example, the reception desk can prioritize suggesting input methods that the user has frequently used based on past question history. Furthermore, the reception desk can predict and suggest question formats to be used during specific time periods based on the user's past question history. For example, the reception desk can predict and suggest question formats to be used during specific time periods based on past question history. This allows for the selection of a more appropriate reception method by referring to past question history. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or without a generative AI. For example, the reception desk can input past question history into a generative AI, which can analyze the question history and select the most appropriate reception method.

[0076] The reception desk can adjust the priority of questions based on the user's current situation when receiving a question. The user's current situation includes, for example, current activities, current location, and current state. The reception desk will, for example, prioritize urgent questions if the user is asking one. For example, the reception desk will prioritize urgent questions based on the user's current activities. The reception desk can also prioritize regular questions if the user is asking one. For example, the reception desk will prioritize regular questions based on the user's current activities. Furthermore, the reception desk can give lower priority to questions that the user has asked in the past. For example, the reception desk will give lower priority to questions that have been asked in the past based on the user's current activities. By adjusting the priority of questions based on the user's current situation, questions can be received in a more appropriate order. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's current situation into a generative AI, which can analyze the situation and adjust the priority of questions.

[0077] The reception desk can estimate the user's emotions and adjust the order in which questions are answered based on the estimated emotions. For example, if the user is nervous, the reception desk will answer questions quickly. For example, the reception desk may capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The reception desk will calculate an emotion score based on changes in facial expression and answer questions quickly for nervous users. The reception desk can also answer questions in the normal order if the user is relaxed. For example, the reception desk may record the user's voice and estimate their emotions using voice analysis technology. The reception desk will analyze the tone and speed of the voice and answer questions in the normal order for relaxed users. Furthermore, the reception desk can also prioritize answering questions if the user is in a hurry. For example, the reception desk may collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. The reception desk will calculate an emotion score based on fluctuations in heart rate and prioritize answering questions for users in a hurry. This allows for a more appropriate order in which questions are received by adjusting the order based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0078] The reception desk can prioritize receiving questions that are highly relevant to the user, taking into account the user's geographical location information. Geographical location information includes, for example, GPS data and address information. For example, if the user is in a specific region, the reception desk will prioritize receiving questions related to that region. For example, the reception desk will prioritize receiving questions related to the region based on the user's geographical location information. The reception desk can also prioritize receiving questions related to the user's current location if the user is on the move. For example, the reception desk will prioritize receiving questions related to the current location of a user on the move based on the user's geographical location information. Furthermore, if the user is in a specific facility, the reception desk can also prioritize receiving questions related to that facility. For example, the reception desk will prioritize receiving questions related to a specific facility for a user in that facility based on the user's geographical location information. In this way, by taking the user's geographical location information into consideration, highly relevant questions can be prioritized. Some or all of the above processing in the reception desk may be performed using, for example, generative AI, or without using generative AI. For example, the reception desk can input the user's geographical location information into a generating AI, which then analyzes the location information to prioritize receiving highly relevant questions.

[0079] The reception desk can analyze a user's social media activity when receiving a question and accept relevant questions. Social media activity includes, for example, posts, comments, and the number of likes. For example, if a user mentions a specific topic on social media, the reception desk will prioritize accepting questions related to that topic. For example, the reception desk will prioritize accepting questions related to a specific topic based on the user's social media activity. The reception desk can also prioritize accepting questions related to an event if a user participates in a specific event on social media. For example, the reception desk will prioritize accepting questions related to an event based on the user's social media activity. Furthermore, if a user uses a specific hashtag on social media, the reception desk will prioritize accepting questions related to that hashtag. For example, the reception desk will prioritize accepting questions related to a specific hashtag based on the user's social media activity. In this way, by analyzing a user's social media activity, relevant questions can be prioritized. Some or all of the above processing in the reception desk may be performed using, for example, generative AI, or not using generative AI. For example, the reception desk can input a user's social media activity into a generating AI, which can then analyze the activity and prioritize receiving relevant questions. === Hard Collateral 1-1 === Each of the multiple elements described above, including the analysis unit, answer generation unit, and reception unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes the contents of PDFs and slides. The answer generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates answers to questions based on the analyzed information. The reception unit is implemented by the control unit 46A of the smart device 14 and receives questions from the user. The analysis unit can, for example, estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. Emotion estimation is implemented using, for example, the camera 42 and microphone 38B of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements described above, including the analysis unit, answer generation unit, and reception unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes the contents of PDFs and slides. The answer generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates answers to questions based on the analyzed information. The reception unit is implemented by the control unit 46A of the smart glasses 214 and receives questions from the user. The analysis unit can, for example, estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. Emotion estimation is implemented using, for example, the camera 42 and microphone 238 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements described above, including the analysis unit, answer generation unit, and reception unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes the contents of PDFs and slides. The answer generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates answers to questions based on the analyzed information. The reception unit is implemented by the control unit 46A of the headset terminal 314 and receives questions from the user. The analysis unit can, for example, estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. Emotion estimation is implemented using, for example, the camera 42 and microphone 238 of the headset terminal 314. === Hard Collateral 1-4 === Each of the multiple elements described above, including the analysis unit, answer generation unit, and reception unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes the contents of PDFs and slides. The answer generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates answers to questions based on the analyzed information. The reception unit is implemented by the control unit 46A of the robot 414 and receives questions from the user. The analysis unit can, for example, estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. Emotion estimation is implemented using, for example, the camera 42 and microphone 238 of the robot 414.

[0080] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0081] The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on those emotions. For example, if the user is stressed, the analysis unit prioritizes analyzing important information and provides results quickly. If the user is relaxed, the analysis unit performs a detailed analysis and provides comprehensive results. Furthermore, if the user is in a hurry, the analysis unit prioritizes analyzing the most important information and provides results quickly. By adjusting the depth of the analysis based on the user's emotions, more appropriate analysis results can be provided.

[0082] The analysis unit can improve the accuracy of the analysis by considering the file creator's area of ​​expertise during the analysis process. For example, if the creator is an expert in a specific field, the analysis will prioritize information related to that field. Furthermore, if the creator is an expert in multiple fields, the analysis can comprehensively analyze information related to each field. In addition, the analysis can improve the accuracy of the results by referencing relevant literature and data based on the creator's area of ​​expertise. Thus, considering the creator's area of ​​expertise improves the accuracy of the analysis.

[0083] The response generation unit can estimate the user's emotions and adjust the tone of the response based on those emotions. For example, if the user is stressed, the response generation unit will generate a response in a calm tone. If the user is relaxed, the response generation unit can generate a response in a friendly tone. Furthermore, if the user is in a hurry, the response generation unit can generate a response in a concise and direct tone. By adjusting the tone of the response based on the user's emotions, it is possible to provide more appropriate answers.

[0084] The reception system can estimate the user's emotions and adjust how questions are handled based on that estimation. For example, if the user is stressed, it can provide a simple interface and minimize the input steps. If the user is relaxed, it can offer detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, it can prioritize voice input to allow for quick question processing. This allows for more appropriate question processing by adjusting how questions are handled based on the user's emotions.

[0085] The analysis unit can adjust the analysis priority during analysis, taking into account the update frequency of files. For example, it can prioritize the analysis of frequently updated files to provide the latest information. Furthermore, it can perform detailed analysis on files with low update frequency as needed. It can also improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on the update frequency. This allows for the adjustment of analysis priority by considering file update frequency, thereby providing more appropriate analysis results.

[0086] The response generation unit can estimate the user's emotions and adjust the level of detail in the response based on the estimated emotions. For example, if the user is stressed, it can generate a concise and to-the-point response. If the user is relaxed, it can generate a response that includes detailed explanations. Furthermore, if the user is in a hurry, it can generate a short and to-the-point response. In this way, by adjusting the level of detail in the response based on the user's emotions, it can provide a more appropriate response.

[0087] The analysis unit can adjust the analysis priority by considering the relationships between files during the analysis process. For example, it can prioritize the analysis of highly relevant files to quickly provide important information. Furthermore, it can perform detailed analysis on less relevant files as needed. It can also improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on relationships. In this way, by considering the relationships between files, the analysis priority can be adjusted, providing more appropriate analysis results.

[0088] The analysis unit can adjust the analysis priority during analysis, taking into account the reliability of the file creator. For example, it can prioritize the analysis of files from highly reliable creators to provide reliable information. Furthermore, it can perform detailed analysis on files from less reliable creators as needed. In addition, it can improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on the creator's reliability. This allows for adjustment of analysis priorities and the provision of more appropriate analysis results by considering the creator's reliability.

[0089] The response generation unit can estimate the user's emotions and adjust the format of the response based on those emotions. For example, if the user is stressed, it can provide a simple and easy-to-read response. If the user is relaxed, it can provide a response in a format that includes detailed information. Furthermore, if the user is in a hurry, it can provide a response in a concise format. By adjusting the response format based on the user's emotions, it can provide a more appropriate response.

[0090] The analysis unit can adjust the analysis priority during analysis, taking into account the file creation date and time. For example, it can prioritize the analysis of the most recent files to provide the latest information. For older files, it can perform detailed analysis as needed. Furthermore, it can improve the accuracy of the analysis results by prioritizing the analysis of relevant information based on the creation date and time. This allows for adjustment of analysis priority and the provision of more appropriate analysis results by considering the file creation date and time.

[0091] The following briefly describes the processing flow for example form 2.

[0092] Step 1: The analysis unit analyzes the content of PDFs and slides. The analysis unit uses natural language processing and image recognition technologies to analyze the content of PDFs and slides, analyzing text and diagrams within the files to identify the flow of business processes and the roles of employees. For example, it can use text analysis technology to analyze text and extract each step of the business process. It can also use image recognition technology to analyze diagrams within slides and identify the roles of employees. It is also possible to use OCR technology to extract text from PDFs and identify the flow of business processes. Step 2: The answer generation unit generates an answer to the question based on the information analyzed by the analysis unit. The answer generation unit generates an appropriate answer based on the information analyzed using an inference engine and natural language processing technology. For example, it can answer the next step based on the analyzed information in response to a user's question, or answer the person in charge based on employee information. It analyzes the user's question using natural language processing technology and generates an appropriate answer. Step 3: The reception unit receives questions from users. The reception unit uses natural language processing technology to understand the user's questions and passes them on to the answer generation unit. For example, the user's question is received in text format, and the intent of the question is analyzed using natural language processing technology.

[0093] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0094] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0095] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0096] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0097] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0098] As shown in Figure 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.

[0099] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0100] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0101] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0103] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0104] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0105] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0106] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0107] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0108] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0109] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0111] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0112] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0113] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0114] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0115] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0116] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0117] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0119] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0120] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0121] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0122] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0123] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0124] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0125] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0127] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0129] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0130] As shown in Figure 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.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0137] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0146] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0147] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0148] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0149] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0150] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0151] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0152] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0153] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0154] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0155] 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.

[0156] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0157] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0158] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0159] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0160] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0161] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0162] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0163] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0164] [Explanation of Symbols]

[0165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes the contents of PDFs and slides, An answer generation unit generates an answer to a question based on the information analyzed by the aforementioned analysis unit, It includes a reception desk for receiving questions from users. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze the content of PDFs and slides using natural language processing and image recognition technologies. The system according to feature 1.

3. The aforementioned response generation unit, Using inference engines and natural language processing techniques, appropriate answers are generated based on the analyzed information. The system according to feature 1.

4. The aforementioned reception unit is The system uses natural language processing technology to understand the user's question and passes it to the answer generation unit. The system according to feature 1.

5. The aforementioned analysis unit, Analyze the text and diagrams within the file to identify the workflow and employee roles. The system according to feature 1.

6. The aforementioned response generation unit, Based on the extracted information, generate appropriate answers to the user's questions. The system according to feature 1.

7. The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis priority based on the estimated user emotions. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing the content of PDFs and slides, consider the file metadata to improve analysis accuracy. The system according to feature 1.

9. The aforementioned analysis unit, During analysis, the system prioritizes analyzing the latest information by referring to the file's update history. The system according to feature 1.

10. The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system according to feature 1.

Images