system

Abstract

The system according to the embodiment aims to quickly search for appropriate materials and understand the content in response to a question in colloquial language that includes ambiguous expressions. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a search unit, and a summarization unit. The reception unit receives a user's spoken question. The analysis unit analyzes the question received by the reception unit. The search unit searches for materials based on the results of the analysis by the analysis unit. The summarization unit summarizes the contents of the materials searched for by the search unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to quickly search for appropriate materials and understand the content of questions posed in colloquial language that contains ambiguous expressions.

[0005] The system according to the embodiment aims to quickly search for appropriate materials and understand the content in response to a question in colloquial language that includes ambiguous expressions. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a search unit, and a summarization unit. The reception unit receives a user's spoken question. The analysis unit analyzes the question received by the reception unit. The search unit searches for materials based on the results of the analysis by the analysis unit. The summarization unit summarizes the contents of the materials searched for by the search unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly search for appropriate materials and understand the content in response to a question in colloquial language that includes ambiguous expressions. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A generative AI system according to an embodiment of the present invention searches for and summarizes documents based on a user's spoken query. The system allows users to utter a query, and the generative AI analyzes the query and searches for relevant documents. The system accurately summarizes not only the location of the retrieved documents but also their contents and presents them to the user. This system collects and organizes internal company information generated daily in real time, quickly providing the desired information. For example, if a user utters a query such as, "Show me the sales report used in last week's meeting," the generative AI analyzes the query and searches for last week's meeting minutes and sales reports. The system extracts key points and important data from the retrieved documents and provides them to the user in a concise summary. This allows the user to quickly grasp the information they need. The generative AI also automatically collects and organizes new meeting minutes and reports as they are created. This ensures that the system always stores the latest information. Furthermore, the system prioritizes the presentation of highly relevant documents based on the user's past search history and usage. When summarizing the contents of documents, key points are emphasized to help users understand them quickly. This allows the generative AI system to not only easily access the materials users want to see in response to questions in colloquial language that contain ambiguous expressions, but also accurately summarize the contents of the materials, making information gathering more efficient for users.

[0029] A generative AI system according to an embodiment includes a reception unit, an analysis unit, a search unit, and a summarization unit. The reception unit receives a user's spoken query. For example, when the user requests, "Can you show me the sales report used in last week's meeting?", the reception unit receives the query. The analysis unit analyzes the query received by the reception unit. For example, the analysis unit uses natural language processing technology to understand the intent of the query and extract information for searching for related materials. The search unit searches for materials based on the results of the analysis by the analysis unit. For example, the search unit searches for minutes of last week's meeting or sales report. The summarization unit summarizes the contents of the materials searched by the search unit. For example, the summarization unit extracts key points and important data from the sales report and provides a concise summary to the user. This allows the generative AI system according to an embodiment to search for and summarize materials based on the user's spoken query.

[0030] The search unit includes a priority presentation unit that prioritizes presenting highly relevant materials based on the user's past search history. The priority presentation unit prioritizes presenting highly relevant materials, for example, based on the history of materials the user has searched for in the past. For example, materials related to keywords or themes that the user has frequently searched for in the past are displayed preferentially. The priority presentation unit can also predict and present materials to be used during a specific time period based on the user's past search history. For example, if a user searches for a specific report every Monday, the priority presentation unit will prioritize presenting that report. This makes it possible to prioritize presenting highly relevant materials based on the user's past search history.

[0031] The analysis unit is equipped with a collection and organization unit that collects and organizes continuously generated internal company information in real time. The collection and organization unit collects and organizes information such as internal emails, chat logs, and documents in real time. For example, the collection and organization unit automatically collects and organizes information every time new meeting minutes or reports are created. The collection and organization unit can also organize the collected information by category and save it in an easy-to-search format. For example, the collection and organization unit organizes and saves meeting minutes by meeting date and time and participants. This allows internal company information to be collected and organized in real time.

[0032] When receiving a request, the reception unit selects an appropriate reception method by referring to the user's past inquiry history. For example, the reception unit preferentially suggests a query method (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest a method to be used during a specific time period based on the user's past inquiry history. The reception unit can also automatically complete similar queries by referring to content previously input by the user. For example, if the user has previously made a query by voice, the reception unit preferentially suggests voice input. This makes it possible to select the optimal reception method based on the user's past inquiry history.

[0033] The reception unit filters questions based on the user's current situation and areas of interest when receiving the questions. For example, the reception unit preferentially receives questions related to a project in which the user is currently participating. The reception unit can also filter related questions based on the user's areas of interest. The reception unit can also suggest appropriate questions depending on the user's current situation (in a meeting, on the move, etc.). For example, if the user is in a meeting, the reception unit preferentially receives questions related to the meeting. This makes it possible to filter questions based on the user's current situation and areas of interest.

[0034] The reception unit selects an appropriate reception means depending on the user's input method when receiving the request. For example, when the user makes a voice inquiry, the reception unit uses voice recognition technology to receive the request. Furthermore, when the user makes a text inquiry, the reception unit can also use text analysis technology to receive the request. Furthermore, when the user makes a text inquiry, the reception unit can also use image recognition technology to receive the request. For example, when the user makes a voice inquiry, the reception unit converts the voice into text using voice recognition technology and receives the request. This makes it possible to select the optimal reception means depending on the user's input method.

[0035] At the time of reception, the reception unit takes into consideration the user's geographical location information and prioritizes reception of highly relevant questions. For example, when the user is in a specific office, the reception unit prioritizes reception of questions related to the office. Furthermore, when the user is on a business trip, the reception unit can also prioritize reception of questions related to the business trip destination. Furthermore, when the user is at home, the reception unit can also prioritize reception of questions related to the home. For example, the reception unit acquires the user's geographical location information and prioritizes reception of highly relevant questions based on that information. This makes it possible to prioritize reception of highly relevant questions in consideration of the user's geographical location information.

[0036] At the time of reception, the reception unit analyzes the user's social media activity and receives related questions. For example, the reception unit preferentially receives questions related to content mentioned by the user on social media. The reception unit can also analyze the user's social media activity and suggest related questions. The reception unit can also receive related questions by referring to the activity of the user's friends on social media. For example, the reception unit analyzes the content of the user's social media posts and preferentially receives related questions. In this way, the user's social media activity can be analyzed and related questions can be received.

[0037] The reception unit customizes the reception method by reflecting the user's past feedback when receiving a call. The reception unit, for example, suggests the optimal reception method based on feedback provided by the user in the past. The reception unit can also preferentially select a specific reception method based on the user's past feedback. The reception unit can also customize the reception interface by reflecting the user's feedback. For example, the reception unit analyzes feedback provided by the user in the past and suggests the optimal reception method based on the results. In this way, the reception method can be customized by reflecting the user's past feedback.

[0038] During analysis, the analysis unit adjusts the level of detail of the analysis based on the importance of the question. For example, the analysis unit performs a detailed analysis on a question with a high level of importance. The analysis unit can also perform a simplified analysis on a question with a low level of importance. The analysis unit can also appropriately allocate analysis resources according to the importance of the question. For example, the analysis unit analyzes the content of the user's question and evaluates its importance. This makes it possible to adjust the level of detail of the analysis based on the importance of the question.

[0039] During analysis, the analysis unit applies different analysis algorithms depending on the category of the question. For example, the analysis unit applies a business-specific analysis algorithm to a business-related question. The analysis unit can also apply a technology-specific analysis algorithm to a technology-related question. The analysis unit can also apply a general-purpose analysis algorithm to a general question. For example, the analysis unit analyzes the category of the question and selects the optimal analysis algorithm accordingly. This makes it possible to apply different analysis algorithms depending on the category of the question.

[0040] During analysis, the analysis unit improves the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, optimizes the current analysis based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. The analysis unit can also adjust the analysis algorithm by referring to the user's past analysis results. For example, the analysis unit stores the user's past analysis results in a database and performs the current analysis based on them. This makes it possible to improve the accuracy of the analysis by referring to the user's past analysis results.

[0041] During analysis, the analysis unit determines the priority of analysis based on the time of submission of the question. For example, the analysis unit prioritizes analysis of the most recently submitted question. The analysis unit can also postpone analysis of questions submitted earlier. The analysis unit can also appropriately allocate analysis resources based on the time of submission. For example, the analysis unit analyzes the submission date and time of the question and determines the priority based on that. This makes it possible to determine the priority of analysis based on the time of submission of the question.

[0042] During analysis, the analysis unit adjusts the order of analysis based on the relevance of the questions. For example, the analysis unit prioritizes analysis of highly relevant questions. The analysis unit can also postpone analysis of less relevant questions. The analysis unit can also appropriately allocate analysis resources based on the relevance of the questions. For example, the analysis unit analyzes the content of the questions and evaluates their relevance. This makes it possible to adjust the order of analysis based on the relevance of the questions.

[0043] During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides analysis results that make extensive use of technical terms. Furthermore, if the user does not have technical expertise, the analysis unit can also provide concise and easy-to-understand analysis results. Furthermore, the analysis unit can adjust the way in which the analysis results are presented according to the user's level of expertise. For example, the analysis unit analyzes the user's work history and past question content to evaluate the user's level of expertise. This makes it possible to adjust the use of technical terms in the analysis according to the user's level of expertise.

[0044] The search unit improves search accuracy by taking into account the interrelationships between materials during a search. For example, the search unit analyzes the interrelationships between materials and prioritizes searching for related materials. The search unit can also filter search results based on the interrelationships between materials. The search unit can also optimize the search algorithm by taking into account the interrelationships between materials. For example, the search unit analyzes the citation relationships and co-author relationships between materials and displays search results based on the analysis. This makes it possible to improve search accuracy by taking into account the interrelationships between materials.

[0045] When searching, the search unit takes into consideration the attribute information of the document submitter. For example, the search unit searches for related documents based on the specialty of the document submitter. The search unit can also prioritize searching for important documents based on the document submitter's job title. The search unit can also search for related documents by referring to the document submitter's past submission history. For example, the search unit analyzes the document submitter's job title and department and displays search results based on that. This makes it possible to perform a search taking into consideration the attribute information of the document submitter.

[0046] During a search, the search unit weights the search based on the frequency of submission of the documents. For example, the search unit prioritizes searches for documents that are submitted frequently. The search unit can also postpone searching for documents that are submitted less frequently. The search unit can also adjust the weighting of search results based on the submission frequency. For example, the search unit analyzes the number of times a document is submitted and the submission interval, and displays search results based on this. This allows the search to be weighted based on the frequency of submission of the document.

[0047] The search unit performs a search while taking into account the geographical distribution of materials. For example, the search unit searches for related materials based on the location of creation of the materials. The search unit can also filter search results by taking into account the geographical distribution of materials. The search unit can also optimize the search algorithm based on the geographical distribution of materials. For example, the search unit analyzes data on the location of creation of materials or by region, and displays search results based on that. This allows searches to be performed while taking into account the geographical distribution of materials.

[0048] The search unit improves the accuracy of the search by referring to the related literature of the material during the search. For example, the search unit refers to the related literature of the material and searches for related materials preferentially. The search unit can also filter search results based on the related literature of the material. The search unit can also optimize the search algorithm by taking the related literature of the material into consideration. For example, the search unit analyzes the cited literature and references of the material and displays search results based on the results. This makes it possible to improve the accuracy of the search by referring to the related literature of the material.

[0049] The search unit takes into consideration the market value of the materials when searching. For example, the search unit may search preferentially for materials with high market value. The search unit may also search for materials with low market value later. The search unit may also adjust the weighting of search results based on market value. For example, the search unit may analyze the sales data or market share of the materials and display search results based on that. This allows searches to be performed taking into consideration the market value of the materials.

[0050] During summarization, the summarization unit adjusts the level of detail of the summarization based on the importance of the material. For example, the summarization unit performs detailed summarization for highly important materials. The summarization unit can also perform simplified summarization for less important materials. The summarization unit can also appropriately allocate summarization resources according to the importance of the material. For example, the summarization unit evaluates the business impact and technical value of the material and adjusts the level of detail of the summarization based on that. This makes it possible to adjust the level of detail of the summarization based on the importance of the material.

[0051] The summarization unit applies different summarization algorithms depending on the category of the material during summarization. For example, the summarization unit applies a business-specific summarization algorithm to business-related materials. The summarization unit can also apply a technology-specific summarization algorithm to technology-related materials. The summarization unit can also apply a general-purpose summarization algorithm to general materials. For example, the summarization unit analyzes the category of the material and selects the optimal summarization algorithm accordingly. This makes it possible to apply different summarization algorithms depending on the category of the material.

[0052] The summarization unit improves the accuracy of summarization by referring to the user's past summarization results during summarization. For example, the summarization unit optimizes the current summarization based on the user's past summarization results. The summarization unit can also extract specific patterns from the user's past summarization results and reflect them in the summarization. The summarization unit can also adjust the summarization algorithm by referring to the user's past summarization results. For example, the summarization unit stores the user's past summarization results in a database and performs the current summarization based on them. This makes it possible to improve the accuracy of summarization by referring to the user's past summarization results.

[0053] During summarization, the summarization section determines the priority of summarization based on the submission date of the materials. For example, the summarization section prioritizes summarization of recently submitted materials. The summarization section can also postpone summarization of older submitted materials. The summarization section can also appropriately allocate summarization resources based on the submission date. For example, the summarization section analyzes the submission date and time of the materials and determines the priority based on that. This makes it possible to determine the priority of summarization based on the submission date of the materials.

[0054] The summarization unit adjusts the order of summarization based on the relevance of the materials during summarization. For example, the summarization unit prioritizes summarization of highly relevant materials. The summarization unit can also postpone summarization of less relevant materials. The summarization unit can also appropriately allocate summarization resources based on the relevance of the materials. For example, the summarization unit analyzes the content of the materials and evaluates their relevance. This makes it possible to adjust the order of summarization based on the relevance of the materials.

[0055] The summarization unit adjusts the use of technical terms in the summary according to the user's level of expertise during summarization. For example, if the user has technical expertise, the summarization unit provides a summary that uses a lot of technical terms. Also, if the user does not have technical expertise, the summarization unit can provide a concise and easy-to-understand summary. The summarization unit can also adjust the way the summary results are presented according to the user's level of expertise. For example, the summarization unit analyzes the user's work history and past questions to evaluate the user's level of expertise. This allows the use of technical terms in the summary to be adjusted according to the user's level of expertise.

[0056] The collection and organization unit optimizes the collection algorithm by referring to past collected data when collecting and organizing data. For example, the collection and organization unit analyzes past collected data and applies an optimal collection algorithm. The collection and organization unit can also extract specific patterns from past collected data and reflect them in the collection algorithm. The collection and organization unit can also adjust the collection algorithm based on past collected data. For example, the collection and organization unit stores past collected data in a database and performs current collection based on that data. This makes it possible to optimize the collection algorithm by referring to past collected data.

[0057] The collection and organization unit updates the collected data by reflecting user feedback during collection and organization. The collection and organization unit updates the collected data based on, for example, user feedback. The collection and organization unit can also prioritize collection of specific data based on user feedback. The collection and organization unit can also adjust the collection algorithm by reflecting user feedback. For example, the collection and organization unit analyzes feedback provided by the user and updates the collected data based on the results. In this way, the collected data can be updated by reflecting user feedback.

[0058] During collection and organization, the collection and organization unit weights the collected data based on the time of submission of the information. For example, the collection and organization unit prioritizes collection of recently submitted information. The collection and organization unit can also postpone collection of information that was submitted earlier. The collection and organization unit can also adjust the weighting of the collected data based on the time of submission. For example, the collection and organization unit analyzes the submission date and time of the information and weights the collected data based on that. This makes it possible to weight the collected data based on the time of submission of the information.

[0059] During collection and organization, the collection and organization unit integrates information from different data sources to expand the collected data. For example, the collection and organization unit integrates information from different data sources to expand the collected data. The collection and organization unit can also analyze information from different data sources and apply the optimal collection method. The collection and organization unit can also adjust the collection algorithm based on information from different data sources. For example, the collection and organization unit integrates information from an in-house database or an external API and expands the collected data based on that information. In this way, the collected data can be expanded by integrating information from different data sources.

[0060] During collection and organization, the collection and organization unit refers to the user's calendar information to collect information based on the schedule. For example, the collection and organization unit refers to the schedules registered in the user's calendar and collects related information. The collection and organization unit can also preferentially collect information related to specific events from the user's calendar information. The collection and organization unit can also adjust the collection algorithm based on the user's calendar information. For example, the collection and organization unit analyzes the user's calendar information and updates the collected data based on that analysis. This makes it possible to collect information based on the schedule by referring to the user's calendar information.

[0061] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0062] The analysis unit may include a priority presentation unit that prioritizes the presentation of highly relevant materials based on the user's past search history. For example, materials related to keywords or themes that the user has frequently searched for in the past may be displayed preferentially. The analysis unit may also predict and present materials to be used during a specific time period based on the user's past search history. Furthermore, if the user searches for a specific report every Monday, the priority presentation unit may prioritize the presentation of that report. This allows highly relevant materials to be displayed preferentially based on the user's past search history.

[0063] The Collection and Organizing Department can collect and organize information such as internal emails, chat logs, and documents in real time. For example, whenever new meeting minutes or reports are created, the information is automatically collected and organized. It can also organize collected information by category and save it in an easy-to-search format. Furthermore, it can organize and save meeting minutes by meeting date and time and participants. This allows internal information to be collected and organized in real time.

[0064] When receiving a call, the reception unit can select an appropriate reception method by referring to the user's past inquiry history. For example, it can prioritize and suggest inquiry methods (voice, text, etc.) that the user has frequently used in the past. It can also predict and suggest a method to use during a specific time period based on the user's past inquiry history. Furthermore, it can automatically complete similar inquiries by referring to content entered by the user in the past. This makes it possible to select the optimal reception method based on the user's past inquiry history.

[0065] The reception unit can filter questions based on the user's current situation and areas of interest when receiving the questions. For example, questions related to a project in which the user is currently participating are preferentially received. Related questions can also be filtered based on the user's areas of interest. Furthermore, appropriate questions can be suggested depending on the user's current situation (e.g., in a meeting, traveling, etc.). This makes it possible to filter questions based on the user's current situation and areas of interest.

[0066] The reception unit can select an appropriate reception means depending on the user's input method when receiving the request. For example, if the user makes a voice inquiry, the reception can be performed using voice recognition technology. If the user makes a text inquiry, the reception can also be performed using text analysis technology. Furthermore, if the user makes a text inquiry using an image, the reception can also be performed using image recognition technology. This makes it possible to select the optimal reception means depending on the user's input method.

[0067] When receiving a question, the reception unit can prioritize receiving highly relevant questions by taking into consideration the user's geographical location information. For example, if the user is in a specific office, it can prioritize receiving questions related to the office. Also, if the user is on a business trip, it can prioritize receiving questions related to the business trip destination. Furthermore, if the user is at home, it can prioritize receiving questions related to the home. In this way, it is possible to prioritize receiving highly relevant questions by taking into consideration the user's geographical location information.

[0068] The reception unit can analyze the user's social media activity and receive related questions at the time of reception. For example, it can preferentially receive questions related to content mentioned by the user on social media. It can also analyze the user's social media activity and suggest related questions. Furthermore, it can also receive related questions by referring to the activity of the user's friends on social media. In this way, it is possible to analyze the user's social media activity and receive related questions.

[0069] The processing flow of the first embodiment will be briefly explained below.

[0070] Step 1: The reception unit receives a user's spoken inquiry. For example, if the user makes a request such as "Show me the sales report used in last week's meeting," the reception unit receives the request. Step 2: The analysis unit analyzes the query received by the reception unit. For example, the analysis unit uses natural language processing technology to understand the intent of the query and extract information to search for related materials. Step 3: The search unit searches for materials based on the results of the analysis by the analysis unit. For example, the search unit searches for last week's meeting minutes or sales reports. Step 4: The summarization section summarizes the contents of the documents retrieved by the search section. For example, the summarization section extracts the main points and important data from a sales report, summarizes them concisely, and provides them to the user.

[0071] (Example 2) A generative AI system according to an embodiment of the present invention searches for and summarizes documents based on a user's spoken query. The system allows users to utter a query, and the generative AI analyzes the query and searches for relevant documents. The system accurately summarizes not only the location of the retrieved documents but also their contents and presents them to the user. This system collects and organizes internal company information generated daily in real time, quickly providing the desired information. For example, if a user utters a query such as, "Show me the sales report used in last week's meeting," the generative AI analyzes the query and searches for last week's meeting minutes and sales reports. The system extracts key points and important data from the retrieved documents and provides them to the user in a concise summary. This allows the user to quickly grasp the information they need. The generative AI also automatically collects and organizes new meeting minutes and reports as they are created. This ensures that the system always stores the latest information. Furthermore, the system prioritizes the presentation of highly relevant documents based on the user's past search history and usage. When summarizing the contents of documents, key points are emphasized to help users understand them quickly. This allows the generative AI system to not only easily access the materials users want to see in response to questions in colloquial language that contain ambiguous expressions, but also accurately summarize the contents of the materials, making information gathering more efficient for users.

[0072] A generative AI system according to an embodiment includes a reception unit, an analysis unit, a search unit, and a summarization unit. The reception unit receives a user's spoken query. For example, when the user requests, "Can you show me the sales report used in last week's meeting?", the reception unit receives the query. The analysis unit analyzes the query received by the reception unit. For example, the analysis unit uses natural language processing technology to understand the intent of the query and extract information for searching for related materials. The search unit searches for materials based on the results of the analysis by the analysis unit. For example, the search unit searches for minutes of last week's meeting or sales report. The summarization unit summarizes the contents of the materials searched by the search unit. For example, the summarization unit extracts key points and important data from the sales report and provides a concise summary to the user. This allows the generative AI system according to an embodiment to search for and summarize materials based on the user's spoken query.

[0073] The search unit includes a priority presentation unit that prioritizes presenting highly relevant materials based on the user's past search history. The priority presentation unit prioritizes presenting highly relevant materials, for example, based on the history of materials the user has searched for in the past. For example, materials related to keywords or themes that the user has frequently searched for in the past are displayed preferentially. The priority presentation unit can also predict and present materials to be used during a specific time period based on the user's past search history. For example, if a user searches for a specific report every Monday, the priority presentation unit will prioritize presenting that report. This makes it possible to prioritize presenting highly relevant materials based on the user's past search history.

[0074] The analysis unit is equipped with a collection and organization unit that collects and organizes continuously generated internal company information in real time. The collection and organization unit collects and organizes information such as internal emails, chat logs, and documents in real time. For example, the collection and organization unit automatically collects and organizes information every time new meeting minutes or reports are created. The collection and organization unit can also organize the collected information by category and save it in an easy-to-search format. For example, the collection and organization unit organizes and saves meeting minutes by meeting date and time and participants. This allows internal company information to be collected and organized in real time.

[0075] The reception unit estimates the user's emotions and adjusts the method of receiving questions based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit provides a simple interface and minimizes input steps. Furthermore, if the user is relaxed, the reception unit can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and quickly receive questions. For example, the reception unit analyzes the user's tone of voice and facial expressions to estimate the user's emotions. This allows the method of receiving questions to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0076] When receiving a request, the reception unit selects an appropriate reception method by referring to the user's past inquiry history. For example, the reception unit preferentially suggests a query method (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest a method to be used during a specific time period based on the user's past inquiry history. The reception unit can also automatically complete similar queries by referring to content previously input by the user. For example, if the user has previously made a query by voice, the reception unit preferentially suggests voice input. This makes it possible to select the optimal reception method based on the user's past inquiry history.

[0077] The reception unit filters questions based on the user's current situation and areas of interest when receiving the questions. For example, the reception unit preferentially receives questions related to a project in which the user is currently participating. The reception unit can also filter related questions based on the user's areas of interest. The reception unit can also suggest appropriate questions depending on the user's current situation (in a meeting, on the move, etc.). For example, if the user is in a meeting, the reception unit preferentially receives questions related to the meeting. This makes it possible to filter questions based on the user's current situation and areas of interest.

[0078] The reception unit selects an appropriate reception means depending on the user's input method when receiving the request. For example, when the user makes a voice inquiry, the reception unit uses voice recognition technology to receive the request. Furthermore, when the user makes a text inquiry, the reception unit can also use text analysis technology to receive the request. Furthermore, when the user makes a text inquiry, the reception unit can also use image recognition technology to receive the request. For example, when the user makes a voice inquiry, the reception unit converts the voice into text using voice recognition technology and receives the request. This makes it possible to select the optimal reception means depending on the user's input method.

[0079] The reception unit estimates the user's emotions and determines the priority of the queries to be received based on the estimated user emotions. For example, when the user is expressing an urgent emotion, the reception unit receives the query with the highest priority. Furthermore, when the user is relaxed, the reception unit can receive the query with a normal priority. Furthermore, when the user is feeling stressed, the reception unit can receive the query with a higher priority in order to respond quickly. For example, the reception unit analyzes the user's tone of voice and facial expression to estimate the user's emotions. This makes it possible to determine the priority of the queries based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0080] At the time of reception, the reception unit takes into consideration the user's geographical location information and prioritizes reception of highly relevant questions. For example, when the user is in a specific office, the reception unit prioritizes reception of questions related to the office. Furthermore, when the user is on a business trip, the reception unit can also prioritize reception of questions related to the business trip destination. Furthermore, when the user is at home, the reception unit can also prioritize reception of questions related to the home. For example, the reception unit acquires the user's geographical location information and prioritizes reception of highly relevant questions based on that information. This makes it possible to prioritize reception of highly relevant questions in consideration of the user's geographical location information.

[0081] At the time of reception, the reception unit analyzes the user's social media activity and receives related questions. For example, the reception unit preferentially receives questions related to content mentioned by the user on social media. The reception unit can also analyze the user's social media activity and suggest related questions. The reception unit can also receive related questions by referring to the activity of the user's friends on social media. For example, the reception unit analyzes the content of the user's social media posts and preferentially receives related questions. In this way, the user's social media activity can be analyzed and related questions can be received.

[0082] The reception unit customizes the reception method by reflecting the user's past feedback when receiving a call. The reception unit, for example, suggests the optimal reception method based on feedback provided by the user in the past. The reception unit can also preferentially select a specific reception method based on the user's past feedback. The reception unit can also customize the reception interface by reflecting the user's feedback. For example, the reception unit analyzes feedback provided by the user in the past and suggests the optimal reception method based on the results. In this way, the reception method can be customized by reflecting the user's past feedback.

[0083] The analysis unit estimates the user's emotions and adjusts the analysis method based on the estimated user emotions. For example, if the user is nervous, the analysis unit applies a simple and quick analysis method. Furthermore, if the user is relaxed, the analysis unit can also apply a detailed analysis method. Furthermore, if the user is stressed, the analysis unit can also apply a quick and accurate analysis method. For example, the analysis unit analyzes the user's tone of voice and facial expressions to estimate the user's emotions. This allows the analysis method to be adjusted based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0084] During analysis, the analysis unit adjusts the level of detail of the analysis based on the importance of the question. For example, the analysis unit performs a detailed analysis on a question with a high level of importance. The analysis unit can also perform a simplified analysis on a question with a low level of importance. The analysis unit can also appropriately allocate analysis resources according to the importance of the question. For example, the analysis unit analyzes the content of the user's question and evaluates its importance. This makes it possible to adjust the level of detail of the analysis based on the importance of the question.

[0085] During analysis, the analysis unit applies different analysis algorithms depending on the category of the question. For example, the analysis unit applies a business-specific analysis algorithm to a business-related question. The analysis unit can also apply a technology-specific analysis algorithm to a technology-related question. The analysis unit can also apply a general-purpose analysis algorithm to a general question. For example, the analysis unit analyzes the category of the question and selects the optimal analysis algorithm accordingly. This makes it possible to apply different analysis algorithms depending on the category of the question.

[0086] During analysis, the analysis unit improves the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, optimizes the current analysis based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the analysis. The analysis unit can also adjust the analysis algorithm by referring to the user's past analysis results. For example, the analysis unit stores the user's past analysis results in a database and performs the current analysis based on them. This makes it possible to improve the accuracy of the analysis by referring to the user's past analysis results.

[0087] The analysis unit estimates the user's emotions and determines the analysis priority based on the estimated user emotions. For example, if the user is expressing an urgent emotion, the analysis unit performs analysis with the highest priority. Furthermore, if the user is relaxed, the analysis unit can also perform analysis with a normal priority. Furthermore, if the user is feeling stressed, the analysis unit can also adjust the priority to perform analysis quickly. For example, the analysis unit analyzes the user's tone of voice and facial expressions to estimate the user's emotions. This allows the analysis priority to be determined based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0088] During analysis, the analysis unit determines the priority of analysis based on the time of submission of the question. For example, the analysis unit prioritizes analysis of the most recently submitted question. The analysis unit can also postpone analysis of questions submitted earlier. The analysis unit can also appropriately allocate analysis resources based on the time of submission. For example, the analysis unit analyzes the submission date and time of the question and determines the priority based on that. This makes it possible to determine the priority of analysis based on the time of submission of the question.

[0089] During analysis, the analysis unit adjusts the order of analysis based on the relevance of the questions. For example, the analysis unit prioritizes analysis of highly relevant questions. The analysis unit can also postpone analysis of less relevant questions. The analysis unit can also appropriately allocate analysis resources based on the relevance of the questions. For example, the analysis unit analyzes the content of the questions and evaluates their relevance. This makes it possible to adjust the order of analysis based on the relevance of the questions.

[0090] During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides analysis results that make extensive use of technical terms. Furthermore, if the user does not have technical expertise, the analysis unit can also provide concise and easy-to-understand analysis results. Furthermore, the analysis unit can adjust the way in which the analysis results are presented according to the user's level of expertise. For example, the analysis unit analyzes the user's work history and past question content to evaluate the user's level of expertise. This makes it possible to adjust the use of technical terms in the analysis according to the user's level of expertise.

[0091] The search unit estimates the user's emotions and adjusts search criteria based on the estimated user emotions. For example, if the user is nervous, the search unit applies simple and quick search criteria. Alternatively, if the user is relaxed, the search unit can apply detailed search criteria. Alternatively, if the user is stressed, the search unit can apply quick and accurate search criteria. For example, the search unit analyzes the user's tone of voice and facial expressions to estimate the user's emotions. This allows the search criteria to be adjusted based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0092] The search unit improves search accuracy by taking into account the interrelationships between materials during a search. For example, the search unit analyzes the interrelationships between materials and prioritizes searching for related materials. The search unit can also filter search results based on the interrelationships between materials. The search unit can also optimize the search algorithm by taking into account the interrelationships between materials. For example, the search unit analyzes the citation relationships and co-author relationships between materials and displays search results based on the analysis. This makes it possible to improve search accuracy by taking into account the interrelationships between materials.

[0093] When searching, the search unit takes into consideration the attribute information of the document submitter. For example, the search unit searches for related documents based on the specialty of the document submitter. The search unit can also prioritize searching for important documents based on the document submitter's job title. The search unit can also search for related documents by referring to the document submitter's past submission history. For example, the search unit analyzes the document submitter's job title and department and displays search results based on that. This makes it possible to perform a search taking into consideration the attribute information of the document submitter.

[0094] During a search, the search unit weights the search based on the frequency of submission of the documents. For example, the search unit prioritizes searches for documents that are submitted frequently. The search unit can also postpone searching for documents that are submitted less frequently. The search unit can also adjust the weighting of search results based on the submission frequency. For example, the search unit analyzes the number of times a document is submitted and the submission interval, and displays search results based on this. This allows the search to be weighted based on the frequency of submission of the document.

[0095] The search unit estimates the user's emotions and adjusts the order in which search results are displayed based on the estimated user emotions. For example, if the user is expressing an urgent emotion, the search unit displays important materials first. Furthermore, if the user is relaxed, the search unit can also display search results in a normal order. Furthermore, if the user is feeling stressed, the search unit can also display important materials first to enable a quick response. For example, the search unit analyzes the user's tone of voice and facial expressions to estimate the user's emotions. This allows the order in which search results are displayed to be adjusted based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0096] The search unit performs a search while taking into account the geographical distribution of materials. For example, the search unit searches for related materials based on the location of creation of the materials. The search unit can also filter search results by taking into account the geographical distribution of materials. The search unit can also optimize the search algorithm based on the geographical distribution of materials. For example, the search unit analyzes data on the location of creation of materials or by region, and displays search results based on that. This allows searches to be performed while taking into account the geographical distribution of materials.

[0097] The search unit improves the accuracy of the search by referring to the related literature of the material during the search. For example, the search unit refers to the related literature of the material and searches for related materials preferentially. The search unit can also filter search results based on the related literature of the material. The search unit can also optimize the search algorithm by taking the related literature of the material into consideration. For example, the search unit analyzes the cited literature and references of the material and displays search results based on the results. This makes it possible to improve the accuracy of the search by referring to the related literature of the material.

[0098] The search unit takes into consideration the market value of the materials when searching. For example, the search unit may search preferentially for materials with high market value. The search unit may also search for materials with low market value later. The search unit may also adjust the weighting of search results based on market value. For example, the search unit may analyze the sales data or market share of the materials and display search results based on that. This allows searches to be performed taking into consideration the market value of the materials.

[0099] The summarization unit estimates the user's emotions and adjusts the way the summary is presented based on the estimated user emotions. For example, if the user is nervous, the summarization unit provides a simple summary that focuses on the main points. Furthermore, if the user is relaxed, the summarization unit can provide a summary that includes detailed information. Furthermore, if the user is stressed, the summarization unit can provide a quick and accurate summary. For example, the summarization unit analyzes the user's tone of voice and facial expression to estimate the user's emotions. This allows the way the summary is presented to be adjusted based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0100] During summarization, the summarization unit adjusts the level of detail of the summarization based on the importance of the material. For example, the summarization unit performs detailed summarization for highly important materials. The summarization unit can also perform simplified summarization for less important materials. The summarization unit can also appropriately allocate summarization resources according to the importance of the material. For example, the summarization unit evaluates the business impact and technical value of the material and adjusts the level of detail of the summarization based on that. This makes it possible to adjust the level of detail of the summarization based on the importance of the material.

[0101] The summarization unit applies different summarization algorithms depending on the category of the material during summarization. For example, the summarization unit applies a business-specific summarization algorithm to business-related materials. The summarization unit can also apply a technology-specific summarization algorithm to technology-related materials. The summarization unit can also apply a general-purpose summarization algorithm to general materials. For example, the summarization unit analyzes the category of the material and selects the optimal summarization algorithm accordingly. This makes it possible to apply different summarization algorithms depending on the category of the material.

[0102] The summarization unit improves the accuracy of summarization by referring to the user's past summarization results during summarization. For example, the summarization unit optimizes the current summarization based on the user's past summarization results. The summarization unit can also extract specific patterns from the user's past summarization results and reflect them in the summarization. The summarization unit can also adjust the summarization algorithm by referring to the user's past summarization results. For example, the summarization unit stores the user's past summarization results in a database and performs the current summarization based on them. This makes it possible to improve the accuracy of summarization by referring to the user's past summarization results.

[0103] The summarization unit estimates the user's emotion and adjusts the length of the summary based on the estimated user emotion. For example, if the user is in a hurry, the summarization unit provides a short, to-the-point summary. Alternatively, if the user is relaxed, the summarization unit can provide a longer summary with detailed explanations. Alternatively, if the user is stressed, the summarization unit can provide a quick and accurate summary. For example, the summarization unit analyzes the user's tone of voice and facial expression to estimate the user's emotion. This allows the length of the summary to be adjusted based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0104] During summarization, the summarization section determines the priority of summarization based on the submission date of the materials. For example, the summarization section prioritizes summarization of recently submitted materials. The summarization section can also postpone summarization of older submitted materials. The summarization section can also appropriately allocate summarization resources based on the submission date. For example, the summarization section analyzes the submission date and time of the materials and determines the priority based on that. This makes it possible to determine the priority of summarization based on the submission date of the materials.

[0105] The summarization unit adjusts the order of summarization based on the relevance of the materials during summarization. For example, the summarization unit prioritizes summarization of highly relevant materials. The summarization unit can also postpone summarization of less relevant materials. The summarization unit can also appropriately allocate summarization resources based on the relevance of the materials. For example, the summarization unit analyzes the content of the materials and evaluates their relevance. This makes it possible to adjust the order of summarization based on the relevance of the materials.

[0106] The summarization unit adjusts the use of technical terms in the summary according to the user's level of expertise during summarization. For example, if the user has technical expertise, the summarization unit provides a summary that uses a lot of technical terms. Also, if the user does not have technical expertise, the summarization unit can provide a concise and easy-to-understand summary. The summarization unit can also adjust the way the summary results are presented according to the user's level of expertise. For example, the summarization unit analyzes the user's work history and past questions to evaluate the user's level of expertise. This allows the use of technical terms in the summary to be adjusted according to the user's level of expertise.

[0107] The collection and organization unit estimates the user's emotions and determines the priority of information to be collected based on the estimated user emotions. For example, when the user is expressing an urgent emotion, the collection and organization unit prioritizes collecting important information. Furthermore, when the user is relaxed, the collection and organization unit can also collect information in a normal order. Furthermore, when the user is stressed, the collection and organization unit can prioritize collecting important information for a quick response. For example, the collection and organization unit analyzes the user's tone of voice and facial expressions to estimate the user's emotions. This allows the priority of information to be collected to be determined based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0108] The collection and organization unit optimizes the collection algorithm by referring to past collected data when collecting and organizing data. For example, the collection and organization unit analyzes past collected data and applies an optimal collection algorithm. The collection and organization unit can also extract specific patterns from past collected data and reflect them in the collection algorithm. The collection and organization unit can also adjust the collection algorithm based on past collected data. For example, the collection and organization unit stores past collected data in a database and performs current collection based on that data. This makes it possible to optimize the collection algorithm by referring to past collected data.

[0109] The collection and organization unit updates the collected data by reflecting user feedback during collection and organization. The collection and organization unit updates the collected data based on, for example, user feedback. The collection and organization unit can also prioritize collection of specific data based on user feedback. The collection and organization unit can also adjust the collection algorithm by reflecting user feedback. For example, the collection and organization unit analyzes feedback provided by the user and updates the collected data based on the results. In this way, the collected data can be updated by reflecting user feedback.

[0110] The collection and organization unit estimates the user's emotions and adjusts the collection frequency based on the estimated user emotions. For example, the collection and organization unit increases the collection frequency when the user is expressing an urgent emotion. Furthermore, the collection and organization unit can also collect information at a normal collection frequency when the user is relaxed. Furthermore, the collection and organization unit can adjust the collection frequency to respond quickly when the user is feeling stressed. For example, the collection and organization unit analyzes the user's tone of voice and facial expressions to estimate the user's emotions. This makes it possible to adjust the collection frequency based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0111] During collection and organization, the collection and organization unit weights the collected data based on the time of submission of the information. For example, the collection and organization unit prioritizes collection of recently submitted information. The collection and organization unit can also postpone collection of information that was submitted earlier. The collection and organization unit can also adjust the weighting of the collected data based on the time of submission. For example, the collection and organization unit analyzes the submission date and time of the information and weights the collected data based on that. This makes it possible to weight the collected data based on the time of submission of the information.

[0112] During collection and organization, the collection and organization unit integrates information from different data sources to expand the collected data. For example, the collection and organization unit integrates information from different data sources to expand the collected data. The collection and organization unit can also analyze information from different data sources and apply the optimal collection method. The collection and organization unit can also adjust the collection algorithm based on information from different data sources. For example, the collection and organization unit integrates information from an in-house database or an external API and expands the collected data based on that information. In this way, the collected data can be expanded by integrating information from different data sources.

[0113] During collection and organization, the collection and organization unit refers to the user's calendar information to collect information based on the schedule. For example, the collection and organization unit refers to the schedules registered in the user's calendar and collects related information. The collection and organization unit can also preferentially collect information related to specific events from the user's calendar information. The collection and organization unit can also adjust the collection algorithm based on the user's calendar information. For example, the collection and organization unit analyzes the user's calendar information and updates the collected data based on that analysis. This makes it possible to collect information based on the schedule by referring to the user's calendar information. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, search unit, and summarization unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives a user's spoken question. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the question. The search unit is realized by the specific processing unit 290 of the data processing device 12 and searches for related materials. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the contents of the searched materials. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, search unit, and summarization unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives a user's spoken question. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the question. The search unit is realized by the specific processing unit 290 of the data processing device 12 and searches for related materials. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the contents of the searched materials. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, search unit, and summarization unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives a query in spoken language from the user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the query. The search unit is realized by the specific processing unit 290 of the data processing device 12 and searches for related materials. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the contents of the searched materials. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, search unit, and summarization unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives a query in spoken language from a user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the query. The search unit is realized by the specific processing unit 290 of the data processing device 12 and searches for related materials. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the contents of the searched materials.

[0114] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0115] The reception unit can analyze the user's voice tone and facial expressions to estimate the user's emotions. For example, if the user is feeling stressed, the reception unit can provide a simple interface and minimize input steps. If the user is relaxed, the reception unit can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and quickly accept questions. This makes it possible to adjust the method of accepting questions according to the user's emotions.

[0116] The analysis unit may include a priority presentation unit that prioritizes the presentation of highly relevant materials based on the user's past search history. For example, materials related to keywords or themes that the user has frequently searched for in the past may be displayed preferentially. The analysis unit may also predict and present materials to be used during a specific time period based on the user's past search history. Furthermore, if the user searches for a specific report every Monday, the priority presentation unit may prioritize the presentation of that report. This allows highly relevant materials to be displayed preferentially based on the user's past search history.

[0117] The Collection and Organizing Department can collect and organize information such as internal emails, chat logs, and documents in real time. For example, whenever new meeting minutes or reports are created, the information is automatically collected and organized. It can also organize collected information by category and save it in an easy-to-search format. Furthermore, it can organize and save meeting minutes by meeting date and time and participants. This allows internal information to be collected and organized in real time.

[0118] The reception unit can estimate the user's emotions and adjust the method of receiving questions based on the estimated user emotions. For example, if the user is feeling stressed, a simple interface can be provided to minimize input steps. Alternatively, if the user is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized to quickly receive questions. In this way, the method of receiving questions can be adjusted according to the user's emotions.

[0119] When receiving a call, the reception unit can select an appropriate reception method by referring to the user's past inquiry history. For example, it can prioritize and suggest inquiry methods (voice, text, etc.) that the user has frequently used in the past. It can also predict and suggest a method to use during a specific time period based on the user's past inquiry history. Furthermore, it can automatically complete similar inquiries by referring to content entered by the user in the past. This makes it possible to select the optimal reception method based on the user's past inquiry history.

[0120] The reception unit can filter questions based on the user's current situation and areas of interest when receiving the questions. For example, questions related to a project in which the user is currently participating are preferentially received. Related questions can also be filtered based on the user's areas of interest. Furthermore, appropriate questions can be suggested depending on the user's current situation (e.g., in a meeting, traveling, etc.). This makes it possible to filter questions based on the user's current situation and areas of interest.

[0121] The reception unit can select an appropriate reception means depending on the user's input method when receiving the request. For example, if the user makes a voice inquiry, the reception can be performed using voice recognition technology. If the user makes a text inquiry, the reception can also be performed using text analysis technology. Furthermore, if the user makes a text inquiry using an image, the reception can also be performed using image recognition technology. This makes it possible to select the optimal reception means depending on the user's input method.

[0122] The reception unit can estimate the user's emotions and determine the priority of the questions to be received based on the estimated user's emotions. For example, if the user is expressing an urgent emotion, the reception unit can receive the question with the highest priority. If the user is relaxed, the reception unit can also receive the question with normal priority. Furthermore, if the user is feeling stressed, the reception unit can also receive the question with priority in order to respond quickly. In this way, the priority of the questions can be determined based on the user's emotions.

[0123] When receiving a question, the reception unit can prioritize receiving highly relevant questions by taking into consideration the user's geographical location information. For example, if the user is in a specific office, it can prioritize receiving questions related to the office. Also, if the user is on a business trip, it can prioritize receiving questions related to the business trip destination. Furthermore, if the user is at home, it can prioritize receiving questions related to the home. In this way, it is possible to prioritize receiving highly relevant questions by taking into consideration the user's geographical location information.

[0124] The reception unit can analyze the user's social media activity and receive related questions at the time of reception. For example, it can preferentially receive questions related to content mentioned by the user on social media. It can also analyze the user's social media activity and suggest related questions. Furthermore, it can also receive related questions by referring to the activity of the user's friends on social media. In this way, it is possible to analyze the user's social media activity and receive related questions.

[0125] The processing flow of the second embodiment will be briefly explained below.

[0126] Step 1: The reception unit receives a user's spoken inquiry. For example, if the user makes a request such as "Show me the sales report used in last week's meeting," the reception unit receives the request. Step 2: The analysis unit analyzes the query received by the reception unit. For example, the analysis unit uses natural language processing technology to understand the intent of the query and extract information to search for related materials. Step 3: The search unit searches for materials based on the results of the analysis by the analysis unit. For example, the search unit searches for last week's meeting minutes or sales reports. Step 4: The summarization section summarizes the contents of the documents retrieved by the search section. For example, the summarization section extracts the main points and important data from a sales report, summarizes them concisely, and provides them to the user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

[0131] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0132] 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.

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

[0134] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0138] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0141] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0148] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0164] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0165] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0167] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0169] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0170] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0171] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0172] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0173] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0174] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0175] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0176] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0177] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0178] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0179] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0180] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0181] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0182] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0183] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0184] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0185] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0187] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0188] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0189] 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.

[0190] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0191] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0192] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0193] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0194] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0195] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0196] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0197] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0198] [Explanation of symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives a user's spoken question; an analysis unit that analyzes the question received by the reception unit; a search unit that searches for materials based on the results of the analysis by the analysis unit; a summarization unit that summarizes the contents of the materials searched by the search unit; Equipped with A system characterized by:

2. The search unit Equipped with a priority presentation unit that prioritizes the presentation of highly relevant materials based on the user's past search history 2. The system of claim 1.

3. The analysis unit Equipped with a collection and organization department that collects and organizes continuously generated internal information in real time 2. The system of claim 1.

4. The reception unit Estimate the user's emotions and adjust the way questions are received based on the estimated user emotions.

2. The system of claim 1.

5. The reception unit At the time of reception, the appropriate reception method is selected by referring to the user's past inquiry history.

2. The system of claim 1.

6. The reception unit At the check-in stage, filter questions based on the user's current situation and interests 2. The system of claim 1.

7. The reception unit At the time of reception, the appropriate reception method is selected according to the user's input method.

2. The system of claim 1.

8. The reception unit Estimate the user's emotions and prioritize the inquiries to be received based on the estimated user emotions.

2. The system of claim 1.

9. The reception unit At the time of reception, the system takes into account the user's geographical location information to prioritize relevant inquiries.

2. The system of claim 1.

Images