System

Abstract

An object of a system according to an embodiment is to efficiently search for and propose necessary reference materials.SOLUTION: A system includes a reading unit, a learning unit, a reception unit, and a proposal unit. The reading unit reads a text of a material. The learning unit learns the material read by the reading unit. The receiving unit receives a prompt from a user. The suggestion unit suggests the material on the basis of the prompt received by the reception unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to efficiently search for and suggest necessary reference materials.

[0005] The system according to the embodiment aims to efficiently search for and suggest necessary reference materials. [Means for solving the problem]

[0006] The system according to the embodiment includes a reading unit, a learning unit, a receiving unit, and a suggestion unit. The reading unit reads the text of a document. The learning unit learns the document read by the reading unit. The receiving unit receives a prompt from a user. The suggestion unit suggests a document based on the prompt received by the receiving unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently search for and suggest necessary reference materials. [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 document search suggestion system according to an embodiment of the present invention utilizes a generative AI to search for and suggest reference materials that users want to consult or find. The document search suggestion system provides a storage service that stores all documents through a generative AI that learns them. Users input an image of the document they want using prompts, and the generative AI selects multiple optimal documents and even specifies slides. This mechanism allows users to efficiently find the documents they need. For example, the document search suggestion system scans documents such as PDFs or Word files and has the generative AI learn their contents. Next, the user inputs a specific prompt, such as "materials related to marketing strategies" or "slides related to the latest trends in AI technology." Based on the input prompt, the generative AI selects multiple optimal documents and suggests them to the user. It can also specify slides and present specific slides the user needs. This allows the document search suggestion system to efficiently find materials when researchers are looking for materials on a specific topic or when business people are preparing a presentation. This allows the document search suggestion system to efficiently search for and suggest reference materials that users want to consult or find. For example, if a researcher is looking for materials on a specific topic, generative AI can quickly suggest related materials, improving research efficiency. Similarly, if a businessman is preparing a presentation, generative AI can suggest appropriate slides, shortening preparation time.

[0029] A material search suggestion system according to an embodiment includes a reading unit, a learning unit, a receiving unit, and a suggestion unit. The reading unit reads text from materials. Examples of materials include, but are not limited to, PDFs, Word files, and presentation slides. The reading unit reads printed materials using, for example, OCR technology. The reading unit can also directly read materials submitted in digital format. For example, the reading unit reads PDF files with high accuracy and converts them into text data. The learning unit uses a generation AI to train the materials read by the reading unit. The training is performed using, for example, but is not limited to, a machine learning algorithm. For example, the learning unit trains materials in PDF or Word files using the generation AI. The receiving unit receives prompts from a user. Examples of prompts include, but are not limited to, text input and voice input. For example, the receiving unit receives a prompt such as "materials related to marketing strategies" input by a user. The suggestion unit uses the generation AI to suggest materials based on the prompt received by the receiving unit. The suggestions may be made based on, for example, a search result display method or a selection criterion for the suggestion content, but are not limited to such examples. For example, the suggestion unit may use a generation AI to present specific slides that the user needs. This allows the document search suggestion system according to the embodiment to efficiently find the documents the user needs.

[0030] The suggestion unit can use the generation AI to present specific slides that the user needs. For example, the generation AI searches for and presents relevant slides based on the user's prompts. For example, if the user inputs "slides on the latest trends in AI technology," the generation AI will select multiple related slides and suggest them to the user. The suggestion unit can also analyze the content of the slides and present specific slides that the user needs. For example, the generation AI analyzes the text and images of the slides and selects slides that meet the user's needs. This allows the user to efficiently find the specific slides they need.

[0031] The learning unit allows the generation AI to learn materials in PDF or Word files. For example, the learning unit allows the generation AI to read a PDF file and learn its contents. For example, the generation AI analyzes the text in a PDF file and extracts and learns important information. The learning unit can also allow the generation AI to read a Word file and learn its contents. For example, the generation AI analyzes the document structure of a Word file and efficiently learns the text. Furthermore, the learning unit can allow the generation AI to read presentation slides and learn their contents. For example, the generation AI analyzes the text and images in the slides and learns important information. This allows the generation AI to efficiently learn materials in a variety of formats.

[0032] The suggestion unit can use the generation AI to classify materials by category, making searches more efficient. For example, the generation AI can classify materials by topic, making searches more efficient. For example, the generation AI can analyze the content of the materials and classify them into categories such as marketing, technology, and business. The suggestion unit can also use the generation AI to classify materials by purpose, making searches more efficient. For example, the generation AI can classify materials by purpose such as for presentations, research, and education. The suggestion unit can also use the generation AI to classify materials into highly relevant categories, making searches more efficient. For example, the generation AI can analyze the keywords and topics of the materials and classify them into highly relevant categories. This makes searching for materials more efficient.

[0033] The reception unit can use the generation AI to analyze the prompt entered by the user. In the reception unit, for example, the generation AI analyzes the user's prompt using natural language processing technology. For example, the generation AI extracts keywords in the prompt and searches for related materials. The reception unit can also have the generation AI analyze the context of the prompt to understand the user's intention. For example, the generation AI analyzes the context of the prompt and identifies the type and content of the materials the user is looking for. Furthermore, the reception unit can have the generation AI analyze the content of the prompt and generate an optimal search query. For example, the generation AI generates an optimal search query based on the content of the prompt and searches for materials. This allows the user's prompt to be analyzed efficiently.

[0034] The suggestion unit can use the generation AI to select multiple appropriate materials based on the prompt entered by the user. For example, the generation AI searches for and selects multiple relevant materials based on the user's prompt. For example, if the user enters "materials related to the latest trends in AI technology," the generation AI selects multiple relevant materials and suggests them to the user. The suggestion unit can also have the generation AI analyze the content of the materials and select materials that meet the user's needs. For example, the generation AI analyzes the text and images of the materials and selects the materials that are most relevant to the user's prompt. Furthermore, the suggestion unit can also have the generation AI select the most appropriate materials based on evaluation criteria for the materials. For example, the generation AI evaluates the relevance and recency of the materials and selects the most appropriate materials. This allows users to efficiently find the materials they need.

[0035] The reading unit can select the appropriate reading method depending on the format of the document. For example, the generation AI analyzes the format of the document and selects the optimal reading method. For example, if the generation AI is a PDF file, it will read it using a text extraction algorithm. Also, if the generation AI is a Word file, the reading unit can analyze the document structure and efficiently extract text. Furthermore, if the generation AI is an image file, the reading unit can read the text using OCR technology. For example, the generation AI can recognize characters in the image with high accuracy and convert them into text data. This allows the optimal reading method to be selected depending on the format of the document, allowing the document to be read efficiently.

[0036] The reading unit can determine the reading priority based on the importance of the materials. For example, the generation AI evaluates the importance of the materials and determines the reading priority. For example, the generation AI sets it to read materials with high importance first. The reading unit can also cause the generation AI to read materials with high importance first, leaving materials with low importance for later. Furthermore, the reading unit can cause the generation AI to adjust the level of reading detail according to the importance of the materials. For example, the generation AI reads materials with high importance in detail and materials with low importance in a simplified manner. This allows materials to be managed efficiently by prioritizing the reading of important materials.

[0037] The reading unit can apply an appropriate reading algorithm depending on the language of the material. For example, the generation AI analyzes the language of the material and applies the optimal reading algorithm. For example, the generation AI applies a text analysis algorithm specifically for English to English materials. The reading unit can also apply a text analysis algorithm specifically for Japanese to Japanese materials. Furthermore, the reading unit can apply text analysis algorithms compatible with each language to multilingual materials. For example, the generation AI applies text analysis algorithms compatible with multiple languages, such as English, Japanese, and French. This allows the material to be read efficiently by applying the optimal reading algorithm depending on the language of the material.

[0038] The reading unit can customize the reading method based on the attribute information of the document creator. For example, the generation AI analyzes the attribute information of the document creator and selects the optimal reading method. For example, if the document creator is an expert, the generation AI performs a detailed analysis. In addition, if the document creator is a general user, the reading unit can also perform a simplified analysis. Furthermore, if the document creator is an expert in a particular field, the reading unit can also perform an analysis specialized for that field. For example, if the document creator is an expert in a technical field, the generation AI performs an analysis specialized for technology. This allows documents to be read efficiently by selecting the optimal reading method based on the attribute information of the document creator.

[0039] The reading unit can prioritize reading the most recent documents, taking into account the publication date of the documents. For example, the reading unit can configure the generation AI to analyze the publication date of the documents and prioritize reading the most recent documents. For example, the generation AI prioritizes reading the most recent documents. The reading unit can also configure the generation AI to read the most recent documents first, leaving older documents for later. Furthermore, the reading unit can also configure the generation AI to determine reading priorities based on the publication date of the documents. For example, the generation AI can configure the generation AI to prioritize reading the most recent documents, based on the publication date of the documents. This allows the latest information to be managed efficiently by prioritizing reading the most recent documents.

[0040] The reading unit can adjust the level of reading detail based on the relevance of the material. For example, the generation AI evaluates the relevance of the material and adjusts the level of reading detail. For example, the generation AI is set to read highly relevant materials in detail. The reading unit can also set the generation AI to read less relevant materials more simply. Furthermore, the reading unit can adjust the level of reading detail based on the relevance of the material. For example, the generation AI evaluates the degree of match of keywords in the material and the similarity of topics, and sets it to read highly relevant materials in detail. This allows the material to be read efficiently by selecting the optimal level of reading detail based on the relevance of the material.

[0041] The learning unit can apply different appropriate learning algorithms for each category of material. For example, the generation AI analyzes the category of the material and applies the most appropriate learning algorithm. For example, the generation AI applies a learning algorithm specifically for technology to technical materials. The generation AI can also apply a learning algorithm specifically for business to business materials. Furthermore, the learning unit can apply a learning algorithm specifically for academic papers. For example, the generation AI applies learning algorithms such as deep learning and support vector machines depending on the material category. This allows for efficient learning by applying the most appropriate learning algorithm depending on the material category.

[0042] The learning unit can select an appropriate level of learning detail depending on the complexity of the content of the material. For example, the generation AI evaluates the complexity of the content of the material and adjusts the level of learning detail. For example, the generation AI is set to perform detailed learning for complex material. The learning unit can also be set to perform simplified learning for simple material. Furthermore, the learning unit can adjust the level of learning detail depending on the complexity of the content of the material. For example, the generation AI evaluates the amount of information and structural complexity of the material and sets it to perform detailed learning for complex material. This allows for efficient learning by selecting the optimal level of learning detail depending on the complexity of the content of the material.

[0043] The learning unit can improve the accuracy of learning based on the interrelationships between materials. For example, the generation AI analyzes the interrelationships between materials to improve the accuracy of learning. For example, the generation AI improves the accuracy of learning by studying related materials together. The learning unit can also adjust the level of detail of learning by having the generation AI analyze the interrelationships between materials. For example, the generation AI analyzes co-occurrence relationships and dependencies between materials to improve the accuracy of learning. The learning unit can also adjust the level of detail of learning by having the generation AI study related materials together. For example, the generation AI improves the accuracy of learning by studying related materials together. This improves the accuracy of learning by taking the interrelationships between materials into consideration.

[0044] The learning unit can customize the learning method based on the attribute information of the creator of the material. For example, the generation AI analyzes the attribute information of the creator of the material and selects the optimal learning method. For example, if the creator of the material is an expert, the generation AI performs detailed learning. In addition, the learning unit can also perform simplified learning if the creator of the material is a general user. Furthermore, if the creator of the material is an expert in a specific field, the learning unit can perform learning specialized for that field. For example, if the creator of the material is an expert in a technical field, the generation AI performs learning specialized for technology. This allows efficient learning by selecting the optimal learning method based on the attribute information of the creator of the material.

[0045] The learning unit can prioritize learning the latest materials based on the publication date of the materials. For example, the learning unit configures the generation AI to analyze the publication date of the materials and prioritize learning the latest materials. For example, the generation AI prioritizes learning the latest materials. The learning unit can also configure the generation AI to prioritize learning the latest materials, leaving older materials for later. Furthermore, the learning unit can determine the learning priority based on the publication date of the materials. For example, the generation AI configures the generation AI to prioritize learning the latest materials based on the publication date of the materials. This enables the latest information to be managed efficiently by prioritizing learning the latest materials.

[0046] The learning unit can select an appropriate level of learning detail based on the relevance of the material. In the learning unit, for example, the generation AI evaluates the relevance of the material and adjusts the level of learning detail. For example, the generation AI sets highly relevant material to be studied in detail. The learning unit can also set the generation AI to study less relevant material more simply. Furthermore, the learning unit can also adjust the level of learning detail based on the relevance of the material. For example, the generation AI evaluates the degree of match of keywords in the material or the similarity of topics, and sets highly relevant material to be studied in detail. This allows for efficient learning by selecting the optimal level of learning detail based on the relevance of the material.

[0047] The reception unit can select an appropriate analysis method by referring to the user's past search history. The reception unit, for example, has the generation AI analyze the user's past search history and select the optimal analysis method. For example, the generation AI selects the optimal prompt analysis method based on the user's past search history. The reception unit can also have the generation AI preferentially select a prompt analysis method that the user has used in the past. Furthermore, the reception unit can also have the generation AI suggest a specific analysis method based on the user's past search history. For example, the generation AI analyzes the user's past search keywords and search frequency and selects the optimal analysis method. This allows prompts to be analyzed efficiently by selecting the optimal analysis method based on the user's past search history.

[0048] The reception unit can select an appropriate analysis means according to the user's input method. In the reception unit, for example, the generation AI analyzes the user's input method and selects the optimal analysis means. For example, the generation AI performs voice analysis when the user uses voice input. Furthermore, the reception unit can also perform text analysis when the generation AI uses text input. Furthermore, the reception unit can also perform gesture analysis when the generation AI uses gesture input. For example, the generation AI selects the optimal analysis means according to the user's input method. In this way, prompts can be analyzed efficiently by selecting the optimal analysis means according to the user's input method.

[0049] The reception unit can select an appropriate level of analysis detail depending on the user's level of expertise. The reception unit, for example, causes the generation AI to analyze the user's level of expertise and select an optimal level of analysis detail. For example, if the user is an expert, the generation AI performs a detailed prompt analysis. The reception unit can also cause the generation AI to perform a simplified prompt analysis if the user is a general user. Furthermore, the reception unit can also cause the generation AI to adjust the level of detail of the prompt analysis based on the user's level of expertise. For example, the generation AI selects whether to perform a detailed analysis or a simplified analysis depending on the user's level of expertise. This allows the generation AI to efficiently analyze prompts by selecting an optimal level of analysis detail based on the user's level of expertise.

[0050] The reception unit can prioritize analyzing highly relevant prompts based on the user's geographical location information. In the reception unit, for example, the generation AI analyzes the user's geographical location information and selects the optimal prompt. For example, if the user is in a specific area, the generation AI prioritizes analyzing prompts related to that area. The reception unit can also allow the generation AI to suggest highly relevant prompts based on the user's current location. Furthermore, the reception unit can also allow the generation AI to analyze the optimal prompt based on the user's geographical location information. For example, the generation AI prioritizes analyzing highly relevant prompts based on the user's geographical location information. This allows the prompt to be analyzed efficiently by selecting the optimal prompt based on the user's geographical location information.

[0051] The reception unit can analyze the user's social media activity and analyze relevant prompts. In the reception unit, for example, the generation AI analyzes the user's social media activity and selects the optimal prompt. For example, the generation AI analyzes relevant prompts based on the content of the user's social media posts. The reception unit can also suggest relevant prompts by using the generation AI to refer to the activity of the user's friends on social media. Furthermore, the reception unit can also analyze relevant prompts based on the user's social media check-in information. For example, the generation AI prioritizes analysis of highly relevant prompts based on the user's social media activity. This allows prompts to be analyzed efficiently by selecting the optimal prompt based on the user's social media activity.

[0052] The reception unit can select an appropriate analysis method by reflecting the user's past feedback. In the reception unit, for example, the generation AI analyzes the user's past feedback and selects the optimal analysis method. For example, the generation AI customizes the prompt analysis method based on feedback provided by the user in the past. The reception unit can also allow the generation AI to select the optimal analysis method from the user's past feedback. Furthermore, the reception unit can also allow the generation AI to adjust the level of detail of the prompt analysis based on the user's feedback history. For example, the generation AI selects the optimal analysis method based on the user's past feedback. In this way, prompts can be analyzed efficiently by selecting the optimal analysis method based on the user's past feedback.

[0053] The suggestion unit can select an appropriate level of detail in the proposal based on the importance of the document. For example, the generation AI evaluates the importance of the document and adjusts the level of detail in the proposal. For example, the generation AI makes a detailed proposal for a document that is highly important. The suggestion unit can also make a simplified proposal for a document that is less important. Furthermore, the suggestion unit can adjust the level of detail in the proposal based on the importance of the document. For example, the generation AI selects whether to make a detailed proposal or a simplified proposal based on the importance of the document. This allows efficient proposals to be made by selecting the optimal level of detail in the proposal based on the importance of the document.

[0054] The proposal unit can apply an appropriate proposal algorithm depending on the category of the material. For example, the generation AI analyzes the category of the material and applies the optimal proposal algorithm. For example, the generation AI applies a proposal algorithm dedicated to technology to technical materials. The proposal unit can also apply a proposal algorithm dedicated to business to business materials. The proposal unit can also apply a proposal algorithm dedicated to academic papers. For example, the generation AI applies a proposal algorithm such as a recommendation system or collaborative filtering depending on the category of the material. This allows efficient proposals to be made by applying the optimal proposal algorithm depending on the category of the material.

[0055] The suggestion unit can make appropriate suggestions by referring to the user's past suggestion results. In the suggestion unit, for example, the generation AI analyzes the user's past suggestion results and makes optimal suggestions. For example, the generation AI improves the accuracy of the suggestions based on the user's past suggestion results. The suggestion unit can also analyze the user's past suggestion history and make optimal suggestions. Furthermore, the suggestion unit can adjust the level of detail of the suggestion based on the user's past suggestion results. For example, the generation AI makes optimal suggestions based on the user's past suggestion results. This allows efficient suggestions to be made by making optimal suggestions based on the user's past suggestion results.

[0056] The suggestion unit can make appropriate suggestions based on the publication date of the materials. For example, the generation AI analyzes the publication date of the materials and makes optimal suggestions. For example, the generation AI prioritizes suggesting the latest materials. The suggestion unit can also have the generation AI postpone older materials and suggest the latest materials first. Furthermore, the suggestion unit can also determine the priority of suggestions based on the publication date of the materials. For example, the generation AI can be set to prioritize suggesting the latest materials based on the publication date of the materials. This allows efficient suggestions to be made by making optimal suggestions based on the publication date of the materials.

[0057] The suggestion unit can adjust the order of suggestions based on the relevance of the materials. For example, the generation AI evaluates the relevance of the materials and adjusts the order of suggestions. For example, the generation AI prioritizes suggesting highly relevant materials. The suggestion unit can also have the generation AI postpone suggesting less relevant materials and suggest highly relevant materials first. Furthermore, the suggestion unit can also adjust the order of suggestions based on the relevance of the materials. For example, the generation AI evaluates the degree of match of keywords and the similarity of topics between the materials and prioritizes suggesting highly relevant materials. This allows efficient suggestions to be made by selecting the optimal suggestion order based on the relevance of the materials.

[0058] The suggestion unit can make appropriate suggestions according to the user's level of expertise. For example, the generation AI analyzes the user's level of expertise and makes optimal suggestions. For example, if the user is an expert, the generation AI makes suggestions that use a lot of technical terms. In addition, if the user is a general user, the suggestion unit can also make simplified suggestions. Furthermore, the suggestion unit can adjust the use of technical terms in the suggestions based on the user's level of expertise. For example, the generation AI selects whether to use a lot of technical terms or simplified terms depending on the user's level of expertise. This allows for efficient suggestions by making optimal suggestions based on the user's level of expertise.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The suggestion unit can prioritize suggesting materials that the user has previously shown interest in based on the user's past search history. For example, if the user has frequently searched for materials related to "marketing strategies" in the past, the suggestion unit will prioritize suggesting marketing-related materials in response to new prompts. The suggestion unit can also prioritize suggesting materials that the user has previously given high ratings to. For example, if the user has given high ratings to a particular material, the suggestion unit will prioritize suggesting similar materials. Furthermore, the suggestion unit can analyze the user's past search history and suggest new materials based on the user's interests. This enables more personalized suggestions based on the user's past behavior.

[0061] The suggestion unit can suggest optimal materials based on the user's current task or project progress. For example, if the user is preparing a presentation, the suggestion unit can prioritize materials related to the presentation. Alternatively, if the user is writing a research paper, the suggestion unit can suggest related academic papers and data. Furthermore, the suggestion unit can adjust the type and level of detail of required materials depending on the user's task progress. This allows the system to efficiently provide materials that best suit the user's current needs.

[0062] The suggestion unit can suggest region-specific materials based on the user's geographic location information. For example, if the user is in a particular country or region, the suggestion unit can suggest marketing data or business reports related to that region. If the user is traveling, the suggestion unit can also suggest tourist information or cultural materials related to the travel destination. Furthermore, if the user is preparing for a business meeting in a particular region, the suggestion unit can suggest materials related to the economic situation and market trends of that region. This allows the user to be provided with more relevant materials based on the user's geographic location information.

[0063] The suggestion unit can analyze the user's social media activity and suggest related materials. For example, if the user frequently posts about "AI technology" on social media, the suggestion unit can suggest the latest materials on AI technology. Also, if the user uses a specific hashtag, the suggestion unit can suggest materials related to that hashtag. Furthermore, the suggestion unit can suggest materials that the user's friends are interested in based on the activities of the user's friends on social media. This makes it possible to provide more personalized materials based on the user's social media activity.

[0064] The suggestion unit can suggest appropriate materials depending on the user's level of expertise. For example, if the user is a beginner, the suggestion unit can suggest basic concepts and introductory materials. If the user is an intermediate user, the suggestion unit can suggest more detailed technical materials and application examples. Furthermore, if the user is an expert, the suggestion unit can suggest the latest research papers and advanced technical materials. This makes it possible to provide optimal materials depending on the user's level of expertise.

[0065] The suggestion unit can improve the accuracy of suggestions based on the user's past feedback. For example, it can analyze feedback provided by the user in the past and adjust the content and format of suggestions. Also, if the user gives a high rating to a specific document, it can preferentially suggest similar documents. Furthermore, it can adjust the level of detail and frequency of suggestions based on the user's feedback history. This enables more accurate suggestions based on the user's past feedback.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The reader reads the text of the document. The document can be a PDF, Word file, presentation slides, etc. The reader can read printed documents using OCR technology, or directly read documents submitted in digital format. For example, it can read PDF files with high accuracy and convert them into text data. Step 2: The learning unit uses the generation AI to learn the material read by the reading unit. Learning is performed using a machine learning algorithm. For example, the material is learned from a PDF or Word file. Step 3: The reception unit receives a prompt from the user. The prompt may be a text input or a voice input. For example, the reception unit receives a prompt such as "materials related to marketing strategies" input by the user. Step 4: The suggestion section uses the generation AI to suggest materials based on the prompts received by the reception section. Suggestions are made based on the search result display method and selection criteria for the suggestion content. For example, it may present specific slides that the user needs.

[0068] (Example 2) A document search suggestion system according to an embodiment of the present invention utilizes a generative AI to search for and suggest reference materials that users want to consult or find. The document search suggestion system provides a storage service that stores all documents through a generative AI that learns them. Users input an image of the document they want using prompts, and the generative AI selects multiple optimal documents and even specifies slides. This mechanism allows users to efficiently find the documents they need. For example, the document search suggestion system scans documents such as PDFs or Word files and has the generative AI learn their contents. Next, the user inputs a specific prompt, such as "materials related to marketing strategies" or "slides related to the latest trends in AI technology." Based on the input prompt, the generative AI selects multiple optimal documents and suggests them to the user. It can also specify slides and present specific slides the user needs. This allows the document search suggestion system to efficiently find materials when researchers are looking for materials on a specific topic or when business people are preparing a presentation. This allows the document search suggestion system to efficiently search for and suggest reference materials that users want to consult or find. For example, if a researcher is looking for materials on a specific topic, generative AI can quickly suggest related materials, improving research efficiency. Similarly, if a businessman is preparing a presentation, generative AI can suggest appropriate slides, shortening preparation time.

[0069] A material search suggestion system according to an embodiment includes a reading unit, a learning unit, a receiving unit, and a suggestion unit. The reading unit reads text from materials. Examples of materials include, but are not limited to, PDFs, Word files, and presentation slides. The reading unit reads printed materials using, for example, OCR technology. The reading unit can also directly read materials submitted in digital format. For example, the reading unit reads PDF files with high accuracy and converts them into text data. The learning unit uses a generation AI to train the materials read by the reading unit. The training is performed using, for example, but is not limited to, a machine learning algorithm. For example, the learning unit trains materials in PDF or Word files using the generation AI. The receiving unit receives prompts from a user. Examples of prompts include, but are not limited to, text input and voice input. For example, the receiving unit receives a prompt such as "materials related to marketing strategies" input by a user. The suggestion unit uses the generation AI to suggest materials based on the prompt received by the receiving unit. The suggestions may be made based on, for example, a search result display method or a selection criterion for the suggestion content, but are not limited to such examples. For example, the suggestion unit may use a generation AI to present specific slides that the user needs. This allows the document search suggestion system according to the embodiment to efficiently find the documents the user needs.

[0070] The suggestion unit can use the generation AI to present specific slides that the user needs. For example, the generation AI searches for and presents relevant slides based on the user's prompts. For example, if the user inputs "slides on the latest trends in AI technology," the generation AI will select multiple related slides and suggest them to the user. The suggestion unit can also analyze the content of the slides and present specific slides that the user needs. For example, the generation AI analyzes the text and images of the slides and selects slides that meet the user's needs. This allows the user to efficiently find the specific slides they need.

[0071] The learning unit allows the generation AI to learn materials in PDF or Word files. For example, the learning unit allows the generation AI to read a PDF file and learn its contents. For example, the generation AI analyzes the text in a PDF file and extracts and learns important information. The learning unit can also allow the generation AI to read a Word file and learn its contents. For example, the generation AI analyzes the document structure of a Word file and efficiently learns the text. Furthermore, the learning unit can allow the generation AI to read presentation slides and learn their contents. For example, the generation AI analyzes the text and images in the slides and learns important information. This allows the generation AI to efficiently learn materials in a variety of formats.

[0072] The suggestion unit can use the generation AI to classify materials by category, making searches more efficient. For example, the generation AI can classify materials by topic, making searches more efficient. For example, the generation AI can analyze the content of the materials and classify them into categories such as marketing, technology, and business. The suggestion unit can also use the generation AI to classify materials by purpose, making searches more efficient. For example, the generation AI can classify materials by purpose such as for presentations, research, and education. The suggestion unit can also use the generation AI to classify materials into highly relevant categories, making searches more efficient. For example, the generation AI can analyze the keywords and topics of the materials and classify them into highly relevant categories. This makes searching for materials more efficient.

[0073] The reception unit can use the generation AI to analyze the prompt entered by the user. In the reception unit, for example, the generation AI analyzes the user's prompt using natural language processing technology. For example, the generation AI extracts keywords in the prompt and searches for related materials. The reception unit can also have the generation AI analyze the context of the prompt to understand the user's intention. For example, the generation AI analyzes the context of the prompt and identifies the type and content of the materials the user is looking for. Furthermore, the reception unit can have the generation AI analyze the content of the prompt and generate an optimal search query. For example, the generation AI generates an optimal search query based on the content of the prompt and searches for materials. This allows the user's prompt to be analyzed efficiently.

[0074] The suggestion unit can use the generation AI to select multiple appropriate materials based on the prompt entered by the user. For example, the generation AI searches for and selects multiple relevant materials based on the user's prompt. For example, if the user enters "materials related to the latest trends in AI technology," the generation AI selects multiple relevant materials and suggests them to the user. The suggestion unit can also have the generation AI analyze the content of the materials and select materials that meet the user's needs. For example, the generation AI analyzes the text and images of the materials and selects the materials that are most relevant to the user's prompt. Furthermore, the suggestion unit can also have the generation AI select the most appropriate materials based on evaluation criteria for the materials. For example, the generation AI evaluates the relevance and recency of the materials and selects the most appropriate materials. This allows users to efficiently find the materials they need.

[0075] The reading unit can estimate the user's emotions and adjust the reading speed of the document based on the estimated user's emotions. For example, the generation AI in the reading unit analyzes the user's facial expressions to estimate emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate stress or relaxation. The reading unit can also analyze the user's voice to estimate emotions. For example, the generation AI analyzes the tone and speed of the user's voice to estimate emotions. Furthermore, the reading unit can analyze the user's biometric data to estimate emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate emotions. Based on the estimated emotions, the reading unit adjusts the reading speed of the document. For example, if the user is feeling stressed, the generation AI slows down the reading speed of the document to allow the user to relax. Also, if the user is relaxed, the generation AI sets the reading speed of the document to a normal speed. Furthermore, if the user is in a hurry, the generation AI increases the reading speed of the document to read the document more quickly. This reduces the burden on the user by adjusting the reading speed of the material according to the user's emotions.

[0076] The reading unit can select the appropriate reading method depending on the format of the document. For example, the generation AI analyzes the format of the document and selects the optimal reading method. For example, if the generation AI is a PDF file, it will read it using a text extraction algorithm. Also, if the generation AI is a Word file, the reading unit can analyze the document structure and efficiently extract text. Furthermore, if the generation AI is an image file, the reading unit can read the text using OCR technology. For example, the generation AI can recognize characters in the image with high accuracy and convert them into text data. This allows the optimal reading method to be selected depending on the format of the document, allowing the document to be read efficiently.

[0077] The reading unit can determine the reading priority based on the importance of the materials. For example, the generation AI evaluates the importance of the materials and determines the reading priority. For example, the generation AI sets it to read materials with high importance first. The reading unit can also cause the generation AI to read materials with high importance first, leaving materials with low importance for later. Furthermore, the reading unit can cause the generation AI to adjust the level of reading detail according to the importance of the materials. For example, the generation AI reads materials with high importance in detail and materials with low importance in a simplified manner. This allows materials to be managed efficiently by prioritizing the reading of important materials.

[0078] The reading unit can apply an appropriate reading algorithm depending on the language of the material. For example, the generation AI analyzes the language of the material and applies the optimal reading algorithm. For example, the generation AI applies a text analysis algorithm specifically for English to English materials. The reading unit can also apply a text analysis algorithm specifically for Japanese to Japanese materials. Furthermore, the reading unit can apply text analysis algorithms compatible with each language to multilingual materials. For example, the generation AI applies text analysis algorithms compatible with multiple languages, such as English, Japanese, and French. This allows the material to be read efficiently by applying the optimal reading algorithm depending on the language of the material.

[0079] The reading unit can estimate the user's emotions and adjust the order of materials to be read based on the estimated user emotions. For example, the generation AI analyzes the user's facial expressions to estimate emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate stress or relaxation levels. The reading unit can also analyze the user's voice to estimate emotions. For example, the generation AI analyzes the tone and speed of the user's voice to estimate emotions. Furthermore, the reading unit can analyze the user's biometric data to estimate emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate emotions. Based on the estimated emotions, the reading unit adjusts the order of materials to be read. For example, if the user is feeling stressed, the generation AI starts reading easier materials. Also, if the user is relaxed, the generation AI starts reading more difficult materials. Furthermore, if the user is in a hurry, the generation AI starts reading more important materials. This allows for efficient material management by adjusting the reading order according to the user's emotions.

[0080] The reading unit can customize the reading method based on the attribute information of the document creator. For example, the generation AI analyzes the attribute information of the document creator and selects the optimal reading method. For example, if the document creator is an expert, the generation AI performs a detailed analysis. In addition, if the document creator is a general user, the reading unit can also perform a simplified analysis. Furthermore, if the document creator is an expert in a particular field, the reading unit can also perform an analysis specialized for that field. For example, if the document creator is an expert in a technical field, the generation AI performs an analysis specialized for technology. This allows documents to be read efficiently by selecting the optimal reading method based on the attribute information of the document creator.

[0081] The reading unit can prioritize reading the most recent documents, taking into account the publication date of the documents. For example, the reading unit can configure the generation AI to analyze the publication date of the documents and prioritize reading the most recent documents. For example, the generation AI prioritizes reading the most recent documents. The reading unit can also configure the generation AI to read the most recent documents first, leaving older documents for later. Furthermore, the reading unit can also configure the generation AI to determine reading priorities based on the publication date of the documents. For example, the generation AI can configure the generation AI to prioritize reading the most recent documents, based on the publication date of the documents. This allows the latest information to be managed efficiently by prioritizing reading the most recent documents.

[0082] The reading unit can adjust the level of reading detail based on the relevance of the material. For example, the generation AI evaluates the relevance of the material and adjusts the level of reading detail. For example, the generation AI is set to read highly relevant materials in detail. The reading unit can also set the generation AI to read less relevant materials more simply. Furthermore, the reading unit can adjust the level of reading detail based on the relevance of the material. For example, the generation AI evaluates the degree of match of keywords in the material and the similarity of topics, and sets it to read highly relevant materials in detail. This allows the material to be read efficiently by selecting the optimal level of reading detail based on the relevance of the material.

[0083] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, the generation AI in the learning unit analyzes the user's facial expressions to estimate emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate stress or relaxation levels. The learning unit can also analyze the user's voice to estimate emotions. For example, the generation AI analyzes the tone and speed of the user's voice to estimate emotions. Furthermore, the learning unit can analyze the user's biometric data to estimate emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate emotions. The learning unit selects training data based on the estimated emotions. For example, if the user is stressed, the generation AI prioritizes learning easy materials. Furthermore, if the user is relaxed, the generation AI prioritizes learning difficult materials. Furthermore, if the user is in a hurry, the generation AI prioritizes learning important materials. This allows for efficient learning by selecting training data according to the user's emotions.

[0084] The learning unit can apply different appropriate learning algorithms for each category of material. For example, the generation AI analyzes the category of the material and applies the most appropriate learning algorithm. For example, the generation AI applies a learning algorithm specifically for technology to technical materials. The generation AI can also apply a learning algorithm specifically for business to business materials. Furthermore, the learning unit can apply a learning algorithm specifically for academic papers. For example, the generation AI applies learning algorithms such as deep learning and support vector machines depending on the material category. This allows for efficient learning by applying the most appropriate learning algorithm depending on the material category.

[0085] The learning unit can select an appropriate level of learning detail depending on the complexity of the content of the material. For example, the generation AI evaluates the complexity of the content of the material and adjusts the level of learning detail. For example, the generation AI is set to perform detailed learning for complex material. The learning unit can also be set to perform simplified learning for simple material. Furthermore, the learning unit can adjust the level of learning detail depending on the complexity of the content of the material. For example, the generation AI evaluates the amount of information and structural complexity of the material and sets it to perform detailed learning for complex material. This allows for efficient learning by selecting the optimal level of learning detail depending on the complexity of the content of the material.

[0086] The learning unit can improve the accuracy of learning based on the interrelationships between materials. For example, the generation AI analyzes the interrelationships between materials to improve the accuracy of learning. For example, the generation AI improves the accuracy of learning by studying related materials together. The learning unit can also adjust the level of detail of learning by having the generation AI analyze the interrelationships between materials. For example, the generation AI analyzes co-occurrence relationships and dependencies between materials to improve the accuracy of learning. The learning unit can also adjust the level of detail of learning by having the generation AI study related materials together. For example, the generation AI improves the accuracy of learning by studying related materials together. This improves the accuracy of learning by taking the interrelationships between materials into consideration.

[0087] The learning unit can estimate the user's emotions and determine learning priorities based on the estimated user emotions. For example, the generation AI in the learning unit analyzes the user's facial expressions to estimate emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate stress or relaxation. The learning unit can also analyze the user's voice to estimate emotions. For example, the generation AI analyzes the tone and speed of the user's voice to estimate emotions. Furthermore, the learning unit can analyze the user's biometric data to estimate emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate emotions. Based on the estimated emotions, the learning unit determines learning priorities. For example, if the user is stressed, the generation AI prioritizes learning easy materials. Furthermore, if the user is relaxed, the generation AI prioritizes learning difficult materials. Furthermore, if the user is in a hurry, the generation AI prioritizes learning important materials. This allows efficient learning by prioritizing learning according to the user's emotions.

[0088] The learning unit can customize the learning method based on the attribute information of the creator of the material. For example, the generation AI analyzes the attribute information of the creator of the material and selects the optimal learning method. For example, if the creator of the material is an expert, the generation AI performs detailed learning. In addition, the learning unit can also perform simplified learning if the creator of the material is a general user. Furthermore, if the creator of the material is an expert in a specific field, the learning unit can perform learning specialized for that field. For example, if the creator of the material is an expert in a technical field, the generation AI performs learning specialized for technology. This allows efficient learning by selecting the optimal learning method based on the attribute information of the creator of the material.

[0089] The learning unit can prioritize learning the latest materials based on the publication date of the materials. For example, the learning unit configures the generation AI to analyze the publication date of the materials and prioritize learning the latest materials. For example, the generation AI prioritizes learning the latest materials. The learning unit can also configure the generation AI to prioritize learning the latest materials, leaving older materials for later. Furthermore, the learning unit can determine the learning priority based on the publication date of the materials. For example, the generation AI configures the generation AI to prioritize learning the latest materials based on the publication date of the materials. This enables the latest information to be managed efficiently by prioritizing learning the latest materials.

[0090] The learning unit can select an appropriate level of learning detail based on the relevance of the material. In the learning unit, for example, the generation AI evaluates the relevance of the material and adjusts the level of learning detail. For example, the generation AI sets highly relevant material to be studied in detail. The learning unit can also set the generation AI to study less relevant material more simply. Furthermore, the learning unit can also adjust the level of learning detail based on the relevance of the material. For example, the generation AI evaluates the degree of match of keywords in the material or the similarity of topics, and sets highly relevant material to be studied in detail. This allows for efficient learning by selecting the optimal level of learning detail based on the relevance of the material.

[0091] The reception unit can estimate the user's emotions and adjust the prompt analysis method based on the estimated user emotions. In the reception unit, for example, the generation AI analyzes the user's facial expressions to estimate emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate the user's state of stress or relaxation. The reception unit can also have the generation AI analyze the user's voice to estimate emotions. For example, the generation AI analyzes the tone and speed of the user's voice to estimate emotions. Furthermore, the reception unit can have the generation AI analyze the user's biometric data to estimate emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate emotions. Based on the estimated emotions, the reception unit adjusts the prompt analysis method. For example, if the user is stressed, the generation AI performs a simple prompt analysis. If the user is relaxed, the generation AI performs a detailed prompt analysis. Furthermore, if the user is in a hurry, the generation AI performs a quick prompt analysis. This allows the prompt analysis method to be adjusted according to the user's emotions, thereby enabling efficient prompt analysis.

[0092] The reception unit can select an appropriate analysis method by referring to the user's past search history. The reception unit, for example, has the generation AI analyze the user's past search history and select the optimal analysis method. For example, the generation AI selects the optimal prompt analysis method based on the user's past search history. The reception unit can also have the generation AI preferentially select a prompt analysis method that the user has used in the past. Furthermore, the reception unit can also have the generation AI suggest a specific analysis method based on the user's past search history. For example, the generation AI analyzes the user's past search keywords and search frequency and selects the optimal analysis method. This allows prompts to be analyzed efficiently by selecting the optimal analysis method based on the user's past search history.

[0093] The reception unit can select an appropriate analysis means according to the user's input method. In the reception unit, for example, the generation AI analyzes the user's input method and selects the optimal analysis means. For example, the generation AI performs voice analysis when the user uses voice input. Furthermore, the reception unit can also perform text analysis when the generation AI uses text input. Furthermore, the reception unit can also perform gesture analysis when the generation AI uses gesture input. For example, the generation AI selects the optimal analysis means according to the user's input method. In this way, prompts can be analyzed efficiently by selecting the optimal analysis means according to the user's input method.

[0094] The reception unit can select an appropriate level of analysis detail depending on the user's level of expertise. The reception unit, for example, causes the generation AI to analyze the user's level of expertise and select an optimal level of analysis detail. For example, if the user is an expert, the generation AI performs a detailed prompt analysis. The reception unit can also cause the generation AI to perform a simplified prompt analysis if the user is a general user. Furthermore, the reception unit can also cause the generation AI to adjust the level of detail of the prompt analysis based on the user's level of expertise. For example, the generation AI selects whether to perform a detailed analysis or a simplified analysis depending on the user's level of expertise. This allows the generation AI to efficiently analyze prompts by selecting an optimal level of analysis detail based on the user's level of expertise.

[0095] The reception unit can estimate the user's emotions and prioritize prompts based on the estimated user emotions. For example, the reception unit allows the generation AI to analyze the user's facial expressions and estimate the user's emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate the user's state of stress or relaxation. The reception unit can also allow the generation AI to analyze the user's voice and estimate the user's emotions. For example, the generation AI analyzes the user's tone and speed of voice to estimate the user's emotions. Furthermore, the reception unit can also allow the generation AI to analyze the user's biometric data and estimate the user's emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate the user's emotions. Based on the estimated emotions, the reception unit prioritizes prompts. For example, if the user is stressed, the generation AI prioritizes easy prompts. Furthermore, if the user is relaxed, the generation AI prioritizes difficult prompts. Furthermore, if the user is in a hurry, the generation AI prioritizes important prompts. This allows prompts to be analyzed efficiently by prioritizing prompts according to the user's emotions.

[0096] The reception unit can prioritize analyzing highly relevant prompts based on the user's geographical location information. In the reception unit, for example, the generation AI analyzes the user's geographical location information and selects the optimal prompt. For example, if the user is in a specific area, the generation AI prioritizes analyzing prompts related to that area. The reception unit can also allow the generation AI to suggest highly relevant prompts based on the user's current location. Furthermore, the reception unit can also allow the generation AI to analyze the optimal prompt based on the user's geographical location information. For example, the generation AI prioritizes analyzing highly relevant prompts based on the user's geographical location information. This allows the prompt to be analyzed efficiently by selecting the optimal prompt based on the user's geographical location information.

[0097] The reception unit can analyze the user's social media activity and analyze relevant prompts. In the reception unit, for example, the generation AI analyzes the user's social media activity and selects the optimal prompt. For example, the generation AI analyzes relevant prompts based on the content of the user's social media posts. The reception unit can also suggest relevant prompts by using the generation AI to refer to the activity of the user's friends on social media. Furthermore, the reception unit can also analyze relevant prompts based on the user's social media check-in information. For example, the generation AI prioritizes analysis of highly relevant prompts based on the user's social media activity. This allows prompts to be analyzed efficiently by selecting the optimal prompt based on the user's social media activity.

[0098] The reception unit can select an appropriate analysis method by reflecting the user's past feedback. In the reception unit, for example, the generation AI analyzes the user's past feedback and selects the optimal analysis method. For example, the generation AI customizes the prompt analysis method based on feedback provided by the user in the past. The reception unit can also allow the generation AI to select the optimal analysis method from the user's past feedback. Furthermore, the reception unit can also allow the generation AI to adjust the level of detail of the prompt analysis based on the user's feedback history. For example, the generation AI selects the optimal analysis method based on the user's past feedback. In this way, prompts can be analyzed efficiently by selecting the optimal analysis method based on the user's past feedback.

[0099] The suggestion unit can estimate the user's emotions and adjust the way suggestions are expressed based on the estimated user emotions. For example, the suggestion unit uses a generation AI to analyze the user's facial expressions and estimate emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate the user's state of stress or relaxation. The suggestion unit can also analyze the user's voice and estimate emotions. For example, the generation AI analyzes the tone and speed of the user's voice to estimate emotions. Furthermore, the suggestion unit can analyze the user's biometric data and estimate emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate emotions. Based on the estimated emotions, the suggestion unit adjusts the way suggestions are expressed. For example, if the user is stressed, the generation AI makes simple and easy-to-understand suggestions. Furthermore, if the user is relaxed, the generation AI makes detailed suggestions. Furthermore, if the user is in a hurry, the generation AI makes suggestions that focus on the key points. This allows suggestions to be made efficiently by adjusting the way suggestions are expressed according to the user's emotions.

[0100] The suggestion unit can select an appropriate level of detail in the proposal based on the importance of the document. For example, the generation AI evaluates the importance of the document and adjusts the level of detail in the proposal. For example, the generation AI makes a detailed proposal for a document that is highly important. The suggestion unit can also make a simplified proposal for a document that is less important. Furthermore, the suggestion unit can adjust the level of detail in the proposal based on the importance of the document. For example, the generation AI selects whether to make a detailed proposal or a simplified proposal based on the importance of the document. This allows efficient proposals to be made by selecting the optimal level of detail in the proposal based on the importance of the document.

[0101] The proposal unit can apply an appropriate proposal algorithm depending on the category of the material. For example, the generation AI analyzes the category of the material and applies the optimal proposal algorithm. For example, the generation AI applies a proposal algorithm dedicated to technology to technical materials. The proposal unit can also apply a proposal algorithm dedicated to business to business materials. The proposal unit can also apply a proposal algorithm dedicated to academic papers. For example, the generation AI applies a proposal algorithm such as a recommendation system or collaborative filtering depending on the category of the material. This allows efficient proposals to be made by applying the optimal proposal algorithm depending on the category of the material.

[0102] The suggestion unit can make appropriate suggestions by referring to the user's past suggestion results. In the suggestion unit, for example, the generation AI analyzes the user's past suggestion results and makes optimal suggestions. For example, the generation AI improves the accuracy of the suggestions based on the user's past suggestion results. The suggestion unit can also analyze the user's past suggestion history and make optimal suggestions. Furthermore, the suggestion unit can adjust the level of detail of the suggestion based on the user's past suggestion results. For example, the generation AI makes optimal suggestions based on the user's past suggestion results. This allows efficient suggestions to be made by making optimal suggestions based on the user's past suggestion results.

[0103] The suggestion unit can estimate the user's emotions and adjust the length of the suggestions based on the estimated user emotions. For example, the suggestion unit uses a generation AI to analyze the user's facial expressions and estimate emotions. For example, the generation AI analyzes changes in the user's facial expressions to estimate the user's state of stress or relaxation. The suggestion unit can also analyze the user's voice and estimate emotions. For example, the generation AI analyzes the user's tone and speed of voice to estimate emotions. Furthermore, the suggestion unit can analyze the user's biometric data and estimate emotions. For example, the generation AI analyzes the user's heart rate and electrodermal activity to estimate emotions. Based on the estimated emotions, the suggestion unit adjusts the length of the suggestions. For example, if the user is stressed, the generation AI makes short, concise suggestions. Furthermore, if the user is relaxed, the generation AI makes detailed suggestions. Furthermore, if the user is in a hurry, the generation AI makes concise suggestions. This allows for efficient suggestions by adjusting the length of suggestions according to the user's emotions.

[0104] The suggestion unit can make appropriate suggestions based on the publication date of the materials. For example, the generation AI analyzes the publication date of the materials and makes optimal suggestions. For example, the generation AI prioritizes suggesting the latest materials. The suggestion unit can also have the generation AI postpone older materials and suggest the latest materials first. Furthermore, the suggestion unit can also determine the priority of suggestions based on the publication date of the materials. For example, the generation AI can be set to prioritize suggesting the latest materials based on the publication date of the materials. This allows efficient suggestions to be made by making optimal suggestions based on the publication date of the materials.

[0105] The suggestion unit can adjust the order of suggestions based on the relevance of the materials. For example, the generation AI evaluates the relevance of the materials and adjusts the order of suggestions. For example, the generation AI prioritizes suggesting highly relevant materials. The suggestion unit can also have the generation AI postpone suggesting less relevant materials and suggest highly relevant materials first. Furthermore, the suggestion unit can also adjust the order of suggestions based on the relevance of the materials. For example, the generation AI evaluates the degree of match of keywords and the similarity of topics between the materials and prioritizes suggesting highly relevant materials. This allows efficient suggestions to be made by selecting the optimal suggestion order based on the relevance of the materials.

[0106] The suggestion unit can make appropriate suggestions according to the user's level of expertise. For example, the generation AI analyzes the user's level of expertise and makes optimal suggestions. For example, if the user is an expert, the generation AI makes suggestions that use a lot of technical terms. In addition, if the user is a general user, the suggestion unit can also make simplified suggestions. Furthermore, the suggestion unit can adjust the use of technical terms in the suggestions based on the user's level of expertise. For example, the generation AI selects whether to use a lot of technical terms or simplified terms depending on the user's level of expertise. This allows for efficient suggestions by making optimal suggestions based on the user's level of expertise. === Hard Collateral 1-1 === Each of the multiple elements including the reading unit, learning unit, reception unit, and suggestion unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reading unit is realized by the camera 42 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and reads the text of the material. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns the material using a generation AI. The reception unit is realized, for example, by the reception device 38 of the smart device 14 or the specific processing unit 290 of the data processing device 12, and accepts prompts from the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests materials using a generation AI. === Hard Collateral 1-2 === Each of the multiple elements including the reading unit, learning unit, reception unit, and suggestion unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reading unit is realized by the camera 42 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and reads the text of the material. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and learns the material using a generation AI. The reception unit is realized, for example, by the microphone 238 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and accepts prompts from the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests material using a generation AI. === Hard Collateral 1-3 === Each of the multiple elements including the reading unit, learning unit, reception unit, and suggestion unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reading unit is realized by the camera 42 of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12, and reads the text of the material. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns the material using a generation AI. The reception unit is realized, for example, by the microphone 238 of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12, and accepts prompts from the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests material using a generation AI. === Hard Collateral 1-4 === Each of the multiple elements including the reading unit, learning unit, reception unit, and suggestion unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reading unit is realized by the camera 42 of the robot 414 or the specific processing unit 290 of the data processing device 12, and reads the text of the material. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns the material using a generation AI. The reception unit is realized, for example, by the microphone 238 of the robot 414 or the specific processing unit 290 of the data processing device 12, and receives prompts from the user. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests material using a generation AI.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The suggestion unit can prioritize suggesting materials that the user has previously shown interest in based on the user's past search history. For example, if the user has frequently searched for materials related to "marketing strategies" in the past, the suggestion unit will prioritize suggesting marketing-related materials in response to new prompts. The suggestion unit can also prioritize suggesting materials that the user has previously given high ratings to. For example, if the user has given high ratings to a particular material, the suggestion unit will prioritize suggesting similar materials. Furthermore, the suggestion unit can analyze the user's past search history and suggest new materials based on the user's interests. This enables more personalized suggestions based on the user's past behavior.

[0109] The suggestion unit can suggest optimal materials based on the user's current task or project progress. For example, if the user is preparing a presentation, the suggestion unit can prioritize materials related to the presentation. Alternatively, if the user is writing a research paper, the suggestion unit can suggest related academic papers and data. Furthermore, the suggestion unit can adjust the type and level of detail of required materials depending on the user's task progress. This allows the system to efficiently provide materials that best suit the user's current needs.

[0110] The suggestion unit can estimate the user's emotions and adjust the timing of suggestions based on the estimated emotions. For example, if the user is feeling stressed, the suggestion unit can reduce the frequency of suggestions, and if the user is relaxed, the suggestion unit can increase the frequency of suggestions. In addition, if the user is concentrating, the suggestion unit can refrain from suggestions, and if the user is taking a break, the suggestion unit can suggest new materials. Furthermore, if the user is in a hurry, the suggestion unit can quickly suggest the most appropriate materials. This makes it possible to suggest materials at the optimal timing according to the user's emotional state.

[0111] The suggestion unit can suggest region-specific materials based on the user's geographic location information. For example, if the user is in a particular country or region, the suggestion unit can suggest marketing data or business reports related to that region. If the user is traveling, the suggestion unit can also suggest tourist information or cultural materials related to the travel destination. Furthermore, if the user is preparing for a business meeting in a particular region, the suggestion unit can suggest materials related to the economic situation and market trends of that region. This allows the user to be provided with more relevant materials based on the user's geographic location information.

[0112] The suggestion unit can analyze the user's social media activity and suggest related materials. For example, if the user frequently posts about "AI technology" on social media, the suggestion unit can suggest the latest materials on AI technology. Also, if the user uses a specific hashtag, the suggestion unit can suggest materials related to that hashtag. Furthermore, the suggestion unit can suggest materials that the user's friends are interested in based on the activities of the user's friends on social media. This makes it possible to provide more personalized materials based on the user's social media activity.

[0113] The suggestion unit can estimate the user's emotions and adjust the content of the suggestions based on the estimated emotions. For example, if the user is feeling stressed, the suggestion unit can suggest light-hearted materials that will help the user relax. If the user is relaxed, the suggestion unit can suggest detailed and specialized materials. Furthermore, if the user is in a hurry, the suggestion unit can suggest concise materials that focus on the main points. This makes it possible to provide materials with optimal content according to the user's emotional state.

[0114] The suggestion unit can suggest appropriate materials depending on the user's level of expertise. For example, if the user is a beginner, the suggestion unit can suggest basic concepts and introductory materials. If the user is an intermediate user, the suggestion unit can suggest more detailed technical materials and application examples. Furthermore, if the user is an expert, the suggestion unit can suggest the latest research papers and advanced technical materials. This makes it possible to provide optimal materials depending on the user's level of expertise.

[0115] The suggestion unit can estimate the user's emotions and adjust the way the suggestions are expressed based on the estimated emotions. For example, if the user is feeling stressed, the suggestion unit can use simple, easy-to-understand expressions. If the user is relaxed, the suggestion unit can use expressions that include detailed explanations. Furthermore, if the user is in a hurry, the suggestion unit can use concise expressions that focus on the main points. This makes it possible to suggest materials in the most appropriate way according to the user's emotional state.

[0116] The suggestion unit can improve the accuracy of suggestions based on the user's past feedback. For example, it can analyze feedback provided by the user in the past and adjust the content and format of suggestions. Also, if the user gives a high rating to a specific document, it can preferentially suggest similar documents. Furthermore, it can adjust the level of detail and frequency of suggestions based on the user's feedback history. This enables more accurate suggestions based on the user's past feedback.

[0117] The suggestion unit can estimate the user's emotions and adjust the length of the suggestions based on the estimated emotions. For example, if the user is feeling stressed, the suggestion unit can make short, to-the-point suggestions. If the user is relaxed, the suggestion unit can make detailed suggestions. Furthermore, if the user is in a hurry, the suggestion unit can also make concise suggestions. This allows materials to be suggested at an optimal length depending on the user's emotional state.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The reader reads the text of the document. The document can be a PDF, Word file, presentation slides, etc. The reader can read printed documents using OCR technology, or directly read documents submitted in digital format. For example, it can read PDF files with high accuracy and convert them into text data. Step 2: The learning unit uses the generation AI to learn the material read by the reading unit. Learning is performed using a machine learning algorithm. For example, the material is learned from a PDF or Word file. Step 3: The reception unit receives a prompt from the user. The prompt may be a text input or a voice input. For example, the reception unit receives a prompt such as "materials related to marketing strategies" input by the user. Step 4: The suggestion section uses the generation AI to suggest materials based on the prompts received by the reception section. Suggestions are made based on the search result display method and selection criteria for the suggestion content. For example, it may present specific slides that the user needs.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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 AI 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.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 AI 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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 AI 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.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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."

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] [Explanation of symbols]

[0192] 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 reading unit that reads the text of the material; a learning unit that learns the material read by the reading unit; a reception unit that receives a prompt from a user; a suggestion unit that suggests materials based on the prompt received by the reception unit; Equipped with A system characterized by:

2. The proposal unit Generative AI presents specific slides that users need 2. The system of claim 1.

3. The learning unit Generate PDF and Word file documents and let AI learn them 2. The system of claim 1.

4. The proposal unit Generative AI categorizes materials and streamlines searches 2. The system of claim 1.

5. The reception unit Generative AI analyzes the prompt entered by the user 2. The system of claim 1.

6. The proposal unit Generative AI picks out multiple suitable materials based on user-entered prompts 2. The system of claim 1.

7. The reading unit Estimate the user's emotions and adjust the reading speed of the material based on the estimated user emotions.

2. The system of claim 1.

8. The reading unit Select the appropriate reading method depending on the format of the material 2. The system of claim 1.

9. The reading unit Prioritize reading based on material importance 2. The system of claim 1.

10. The reading unit Applying appropriate reading algorithms depending on the language of the material 2. The system of claim 1.

Images