system

Abstract

The system according to this embodiment aims to efficiently search for and provide the materials that the user needs. [Solution] The system according to the embodiment comprises a learning unit, a reception unit, a search unit, and a provision unit. The learning unit learns the text data of the materials. The reception unit receives requests from users. The search unit searches for the most suitable materials based on the requests received by the reception unit. The provision unit provides the materials found by the search unit to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to efficiently search for and provide materials required by a user.

[0005] The system according to the embodiment aims to efficiently search for and provide materials required by a user.

Means for Solving the Problems

[0006] The system according to the embodiment includes a learning unit, a reception unit, a search unit, and a provision unit. The learning unit learns text data of materials. The reception unit receives a user request. The search unit searches for optimal materials based on the request received by the reception unit. The provision unit provides the materials searched by the search unit to the user. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently search for and provide the materials that the user needs. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

[0018] The data processing device 1 2 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The document search and suggestion system according to an embodiment of the present invention is a system that uses generative AI to search for and suggest documents that a user may want to refer to. The document search and suggestion system uses generative AI to learn from a large amount of documents and store them in storage. When a user conveys an image of the documents they want to the generative AI, the generative AI picks up several optimal documents. Because the generative AI has learned all the text of the documents, it can accurately suggest the relevant documents. As a result, the user can quickly find the documents they need, improving work efficiency. The generative AI learns the user's past search history and preferences and makes personalized suggestions. As a result, the user can find more appropriate documents, improving work efficiency. For example, the document search and suggestion system learns the user's preferences and interests based on the keywords the user has searched for in the past and the documents they have viewed. Next, when the user makes a new search, the document search and suggestion system suggests the most suitable documents considering the past history. Furthermore, if the user is interested in a particular field, the document search and suggestion system prioritizes suggesting the latest documents related to that field. As a result, the user can always obtain the latest information. Furthermore, the document search and suggestion system prioritizes suggesting documents in a specific format (e.g., PDF or Word documents) if the user prefers that format. This allows users to easily find documents in a format that suits their preferences. As a result, the document search and suggestion system can search for and provide the most suitable documents based on the user's requirements.

[0029] The document search suggestion system according to this embodiment comprises a learning unit, a reception unit, a search unit, and a provision unit. The learning unit learns the text data of documents. The learning unit analyzes a large amount of documents using, for example, a generative AI and learns their contents. The learning unit can analyze the text data of documents in detail and extract important information. The reception unit receives user requests. The reception unit provides, for example, an interface for the user to input keywords and conditions for the documents they want to search for. After receiving the user's request, the reception unit transmits the request to the search unit. The search unit searches for the most suitable documents based on the request received by the reception unit. The search unit uses, for example, a generative AI to search for documents that best suit the user's request. The search unit can analyze the text data of documents and identify documents that match the user's request. The provision unit provides the documents found by the search unit to the user. The provision unit provides, for example, an interface for displaying search results to the user. The provision unit can display summaries and previews of documents to make it easier for the user to view the search results. As a result, the document search and suggestion system according to this embodiment can search for and provide the most suitable documents based on the user's request.

[0030] The learning unit learns from the text data of the materials. For example, the learning unit analyzes a large amount of material using generative AI and learns its content. Specifically, the generative AI uses natural language processing technology to analyze the text data of the materials in detail. First, the generative AI tokenizes the text data of the materials and performs grammatical and semantic analysis to understand the meaning and context of each token. Next, the generative AI identifies keywords and phrases within the text data and evaluates their relationships in order to extract important information. For example, when the generative AI learns from materials on a specific field, it identifies specialized terminology and concepts specific to that field and understands their relationships. Furthermore, the generative AI also has the ability to summarize the content of the materials, extracting important points from long texts and summarizing them concisely. This allows the learning unit to efficiently learn from a vast amount of material and build a foundation for providing optimal materials that meet user needs. The learning unit regularly adds new materials to update the learning database and always maintains the latest information. In addition, the learning unit can improve its learning algorithms based on user feedback and improve search accuracy. This allows the learning unit to provide robust support for responding to diverse user needs and delivering optimal materials.

[0031] The reception desk receives user requests. For example, it provides an interface for users to input keywords and criteria for the materials they wish to search for. Specifically, the reception desk features an intuitive user interface, providing a search bar and filtering options. Users can not only enter keywords into the search bar but also use dropdown menus and checkboxes to set detailed criteria such as material type, publication date, and author name. The reception desk analyzes the information entered by the user in real time and converts it into an appropriate search query. For example, if a user wants to search for "papers on the latest AI technology," the reception desk extracts keywords such as "AI technology," "latest," and "papers," and generates a search query combining these. Furthermore, the reception desk can also provide personalized search suggestions, taking into account the user's past search history and preferences. This allows users to find the desired materials more efficiently. After receiving a user request, the reception desk sends it to the search department. The search department then begins processing the search query received from the reception desk to find the most suitable materials. Thus, the reception desk plays a crucial role in accurately receiving user requests and ensuring a smooth search process.

[0032] The search unit searches for the most suitable materials based on the requests received by the reception unit. For example, the search unit uses generative AI to find the materials best suited to the user's request. Specifically, the search unit leverages the natural language processing capabilities of the generative AI to analyze the text data of the materials and identify materials that match the user's request. The generative AI first analyzes the search query and understands its meaning. Next, the generative AI searches the material database, which it has learned from in the learning unit, to identify the materials most relevant to the query. For example, if a user searches for "papers on the latest AI technology," the generative AI identifies the latest papers on AI technology within the material database and selects the most relevant ones. Furthermore, the generative AI summarizes the content of the materials and evaluates whether they contain the information the user is looking for. This allows the search unit to provide highly accurate search results for the user's request. The search unit updates search results in real time and responds quickly when the user enters a new query. Additionally, the search unit can continuously improve its search algorithm and search accuracy based on user feedback. This allows the search function to play a crucial role in responding to diverse user needs and providing the most relevant information quickly and accurately.

[0033] The service provider provides users with materials retrieved by the search unit. For example, the service provider provides an interface for displaying search results to users. Specifically, it can display summaries and previews of materials to make the search results easier for users to view. The service provider displays search results in a list format, providing basic information such as the title, author, publication date, and summary of each material. Users can select materials of interest from the list and view detailed previews. These previews include excerpts of text and figures from the material, allowing users to easily grasp its content. Furthermore, the service provider can also provide download links and suggest related materials. For example, if a user is viewing a specific paper, the service provider can suggest other related materials to help the user explore the information more deeply. The service provider can also collect user feedback and continuously improve the quality of the information it provides. For example, it can evaluate whether users are satisfied with the search results and revise the search algorithm and display methods if satisfaction is low. In this way, the service provider plays a crucial role in providing users with high-quality information and improving the search experience.

[0034] The learning unit can analyze the text data of materials in detail. For example, the learning unit uses generative AI to analyze the text data of materials in detail and extract important information. The learning unit can deeply understand the content of materials and suggest materials that are most suitable for the user's needs. For example, the learning unit can analyze each section of a material and extract important keywords and phrases. The learning unit can also understand the context of the material and connect related information. This allows for more accurate material suggestions by analyzing the text data of materials in detail. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs the text data of the material into the generative AI, which then analyzes the data and extracts important information.

[0035] The learning unit can learn the user's past search history and preferences to provide personalized suggestions. For example, the learning unit learns the user's preferences and interests based on the keywords the user has searched for and the materials they have viewed in the past. The learning unit can analyze the user's past behavioral data to understand what kind of materials the user likes. For example, the learning unit can extract keywords that the user frequently searches for and the characteristics of materials that the user views for extended periods. Furthermore, the learning unit can prioritize suggesting relevant materials based on the user's preferences. In this way, by learning the user's past search history and preferences, it becomes possible to suggest more appropriate materials. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs data on the user's past search history and preferences into the generative AI, which then analyzes that data to provide personalized suggestions.

[0036] The service provider can evaluate the quality of the proposed materials. For example, the service provider can evaluate the reliability and accuracy of the information in the proposed materials. The service provider can set criteria for evaluating the quality of materials and evaluate the materials based on those criteria. For example, the service provider can evaluate the reliability of the publisher and author of the materials. The service provider can also evaluate the accuracy and consistency of the content of the materials. By evaluating the quality of the proposed materials, the service provider can provide users with high-quality materials. Some or all of the above processes in the service provider may be performed using AI or not. For example, the service provider can input data from the proposed materials into an AI, and the AI ​​can analyze that data and evaluate its quality.

[0037] The learning unit can analyze the structure of the text data of the material and prioritize learning important sections. For example, the learning unit can analyze the table of contents and headings of the material to identify and learn important sections. The learning unit can extract keywords from the material and prioritize learning sections containing frequently occurring keywords. For example, the learning unit can analyze the citations and references of the material and prioritize learning sections that are highly reliable. Furthermore, the learning unit can analyze the structure of the text data of the material and efficiently learn important information. This enables efficient learning by prioritizing the learning of important sections of the material. Some or all of the above processes in the learning unit are performed using generative AI. For example, the learning unit inputs the text data of the material into the generative AI, which then analyzes the data to identify important sections.

[0038] The learning unit can prioritize learning the latest information by considering the frequency of material updates. For example, the learning unit can analyze the publication date of a material and prioritize learning the most recent material. The learning unit can analyze the update history of a material and prioritize learning materials that are frequently updated. For example, the learning unit can analyze the version information of a material and prioritize learning the latest version of the material. Furthermore, the learning unit can always learn the latest information by considering the frequency of material updates. This ensures that the latest information is always provided by prioritizing the learning of the latest information. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit inputs the material update history data into the generative AI, which then analyzes the data to identify the latest information.

[0039] The learning unit can apply different learning algorithms to each type of material. For example, the learning unit can apply an algorithm specialized in analyzing technical terms to scientific and technological materials. For literary materials, it can apply an algorithm specialized in analyzing writing style and expression. For business materials, it can apply an algorithm specialized in data analysis and statistical information analysis. Furthermore, by applying the appropriate learning algorithm to each type of material, the learning unit can achieve efficient learning. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit inputs material genre data into the generative AI, which then analyzes the data and applies the appropriate learning algorithm.

[0040] The learning unit can apply different learning methods depending on the language and format of the materials. For example, for English materials, the learning unit applies methods that analyze English-specific grammar and expressions. For PDF materials, the learning unit can apply methods specialized in text extraction and layout analysis. For materials containing images, the learning unit applies methods that analyze the relationship between text and images using image recognition technology. Furthermore, by applying appropriate learning methods according to the language and format of the materials, the learning unit enables efficient learning. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs language and format data of the materials into the generative AI, which analyzes that data and applies appropriate learning methods.

[0041] The reception unit can select the optimal reception method by referring to the user's past request history. For example, the reception unit may prioritize suggesting request methods that the user has frequently used in the past. By referring to the user's past request history, the reception unit can process requests more efficiently. For example, the reception unit may predict and suggest request methods to be used during specific time periods based on the user's past request history. The reception unit can also analyze the user's past request history and suggest the most efficient reception method. This allows for more efficient request processing by referring to the user's past request history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit may input the user's past request history data into the AI, which then analyzes the data to select the optimal reception method.

[0042] The reception desk can prioritize requests based on the user's current situation and environment. For example, if the user is in a hurry, the reception desk will prioritize high-priority requests. The reception desk can also accept more appropriate requests based on the user's current situation and environment. For example, if the user is relaxed, the reception desk will prioritize detailed requests. The reception desk can also prioritize appropriate requests based on the user's current environment (e.g., in a meeting or on the move). This allows for more appropriate requests to be accepted by prioritizing requests based on the user's current situation and environment. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input data on the user's current situation and environment into the AI, which then analyzes the data to determine the priority of requests.

[0043] The reception unit can select the optimal reception method by considering the user's device information. For example, if the user is using a smartphone, the reception unit can provide a reception method optimized for touch operation. By considering the user's device information, the reception unit can process requests more efficiently. For example, if the user is using a tablet, the reception unit can provide a reception method optimized for a large screen. Also, if the user is using a desktop computer, the reception unit can provide a reception method optimized for keyboard input. This allows for more efficient request processing by considering the user's device information. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's device information into the AI, and the AI ​​will analyze that data to select the optimal reception method.

[0044] The reception desk can prioritize receiving requests that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific region, the reception desk will prioritize receiving requests related to that region. By considering the user's geographical location, the reception desk can receive more appropriate requests. For example, if the user is on the move, the reception desk will prioritize receiving requests related to their destination. Also, if the user is inside a specific facility, the reception desk can prioritize receiving requests related to that facility. This allows for more appropriate requests to be received by prioritizing highly relevant requests while considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk may input the user's geographical location into the AI, and the AI ​​may analyze that data to identify highly relevant requests.

[0045] The search unit can evaluate the relevance of materials and prioritize searching for the most relevant materials. For example, the search unit can evaluate the degree of keyword matching of materials and prioritize searching for the materials with the highest degree of matching. The search unit can evaluate the degree of content matching of materials and prioritize searching for the materials with the highest degree of matching. For example, the search unit can evaluate the degree of matching of citations and references of materials and prioritize searching for the materials with the highest degree of matching. In addition, the search unit can set criteria for evaluating the relevance of materials and evaluate materials based on those criteria. This allows for the search of more appropriate materials by evaluating the relevance of materials. Some or all of the above processing in the search unit is performed using generative AI. For example, the search unit inputs material data into the generative AI, and the generative AI analyzes that data and evaluates the relevance.

[0046] The search unit can evaluate the reliability of materials and prioritize searching for highly reliable materials. For example, the search unit can evaluate the publisher of materials and prioritize searching for materials from reliable publishers. The search unit can evaluate the number of citations of materials and prioritize searching for materials with a high number of citations. For example, the search unit can evaluate the author of materials and prioritize searching for materials by reliable authors. In addition, the search unit can set criteria for evaluating the reliability of materials and evaluate materials based on those criteria. This allows for the search of more reliable materials by evaluating their reliability. Some or all of the above processing in the search unit is performed using a generative AI. For example, the search unit inputs material data into the generative AI, which then analyzes the data and evaluates its reliability.

[0047] The search unit can apply different search methods depending on the language and format of the document. For example, for English documents, the search unit applies a search method that analyzes English-specific grammar and expressions. For PDF documents, the search unit can apply a search method specialized in text extraction and layout analysis. For documents containing images, the search unit applies a search method that analyzes the relationship between text and images using image recognition technology. Furthermore, by applying the appropriate search method according to the language and format of the document, the search unit enables efficient searching. Some or all of the above processing in the search unit is performed using a generative AI. For example, the search unit inputs the language and format data of the document into the generative AI, which then analyzes the data and applies the appropriate search method.

[0048] The search unit can prioritize searching for the latest information, taking into account the frequency of document updates. For example, the search unit can analyze the publication date of a document and prioritize searching for the most recent document. The search unit can analyze the update history of a document and prioritize searching for documents that are frequently updated. For example, the search unit can analyze the version information of a document and prioritize searching for the latest version. Furthermore, the search unit can always search for the latest information, taking into account the frequency of document updates. This ensures that the latest information is always provided by prioritizing the search for the most up-to-date information. Some or all of the above processing in the search unit is performed using a generating AI. For example, the search unit inputs the document's update history data into the generating AI, which then analyzes the data to identify the latest information.

[0049] The service provider can select the optimal service delivery method by referring to the user's past usage history. For example, the service provider can prioritize suggesting service delivery methods that the user has frequently used in the past. By referring to the user's past usage history, the service provider can deliver materials more efficiently. For example, the service provider can predict and suggest a service delivery method to be used during a specific time period based on the user's past usage history. Furthermore, the service provider can analyze the user's past usage history and suggest the most efficient service delivery method. This makes it possible to deliver materials more efficiently by referring to the user's past usage history. Some or all of the above processes in the service provider may be performed using AI, or not. For example, the service provider can input the user's past usage history data into an AI, which then analyzes the data and selects the optimal service delivery method.

[0050] The provisioning department can determine the priority of provision based on the importance of the materials. For example, the provisioning department can evaluate the importance of the materials and provide the most important materials first. The provisioning department can evaluate the urgency of the materials and provide the most urgent materials first. For example, the provisioning department can evaluate the relevance of the materials and provide the most relevant materials first. The provisioning department can also set criteria for evaluating the importance of the materials and evaluate the materials based on those criteria. This allows for the provision of more important materials to be provided first by determining the priority of provision based on the importance of the materials. Some or all of the above processes in the provisioning department may be performed using AI or not. For example, the provisioning department can input the data of the materials into an AI, and the AI ​​can analyze that data and evaluate its importance.

[0051] The service provider can select the optimal service delivery method by considering the user's device information. For example, if the user is using a smartphone, the service provider can provide a service delivery method optimized for touch operation. By considering the user's device information, the service provider can deliver materials more efficiently. For example, if the user is using a tablet, the service provider can provide a service delivery method optimized for a large screen. Furthermore, if the user is using a desktop computer, the service provider can provide a service delivery method optimized for keyboard operation. This allows for more efficient material delivery by considering the user's device information. Some or all of the above processing in the service provider may be performed using AI, or not. For example, the service provider can input the user's device information into the AI, and the AI ​​will analyze that data to select the optimal service delivery method.

[0052] The delivery unit can adjust the order of delivery based on the relevance of the materials. For example, the delivery unit can evaluate the relevance of the materials and provide the most relevant materials first. The delivery unit can evaluate the importance of the materials and provide the most important materials first. For example, the delivery unit can evaluate the urgency of the materials and provide the most urgent materials first. The delivery unit can also set criteria for evaluating the relevance of the materials and evaluate the materials based on those criteria. This allows for the provision of more appropriate materials by adjusting the order of delivery based on the relevance of the materials. Some or all of the above processes in the delivery unit may be performed using AI or not. For example, the delivery unit can input material data into AI, and the AI ​​can analyze that data, evaluate the relevance, and adjust the order of delivery.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The document search and suggestion system can automatically cluster related documents based on the user's past search history. For example, it analyzes keywords the user has previously searched for and the content of documents they have viewed, and groups highly relevant documents together. Furthermore, if the user has an interest in a particular field, it can prioritize clustering documents related to that field. It can also cluster documents based on the user's preferred document format (e.g., PDF or Word document), efficiently providing the information the user is looking for. This allows for more efficient information delivery by clustering documents based on the user's past search history.

[0055] The data search suggestion system can select the optimal display method for search results, taking into account the user's device information. For example, if the user is using a smartphone, the system provides a mobile-optimized display method to improve visibility. If the user is using a tablet, it provides a display method optimized for large screens, making it easier to view information. Furthermore, if the user is using a desktop, it provides a display method optimized for keyboard operation, supporting efficient information retrieval. In this way, by considering the user's device information, it becomes possible to provide information more efficiently.

[0056] The document search and suggestion system can prioritize searching for highly relevant documents by considering the user's geographical location. For example, if the user is in a specific region, it will prioritize searching for documents related to that region. Similarly, if the user is on the move, it will prioritize searching for documents related to their destination. Furthermore, if the user is inside a specific facility, it will prioritize searching for documents related to that facility. This allows for the provision of more appropriate information by prioritizing the search for highly relevant documents based on the user's geographical location.

[0057] The document search and suggestion system can automatically tag relevant documents based on the user's past usage history. For example, it analyzes keywords the user has previously searched for and the content of documents they have viewed, and assigns highly relevant tags. Furthermore, if the user has an interest in a particular field, it can prioritize assigning tags related to that field. In addition, it tags documents based on the user's preferred document format (e.g., PDF or Word document), efficiently providing the information the user is looking for. This allows for more efficient information delivery by tagging documents based on the user's past usage history.

[0058] The document search suggestion system can prioritize search results based on the user's current situation and environment. For example, if the user is in a hurry, it will prioritize displaying documents of high urgency. Conversely, if the user is relaxed, it can prioritize displaying documents containing detailed information. Furthermore, if the user is in a specific environment (e.g., during a meeting or while traveling), it will prioritize displaying documents relevant to that environment. By prioritizing search results based on the user's current situation and environment, it becomes possible to provide more relevant information.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The learning unit learns from the text data of the materials. For example, it analyzes a large amount of material using a generative AI and learns its content. The learning unit can analyze the text data of the materials in detail and extract important information. Step 2: The reception unit receives the user's request. For example, it provides an interface for the user to enter keywords or criteria for the materials they want to search for. After receiving the user's request, the reception unit sends the request to the search unit. Step 3: The search unit searches for the most suitable materials based on the request received by the reception unit. For example, it may use a generative AI to search for materials that best suit the user's request. The search unit can analyze the text data of the materials and identify materials that match the user's request. Step 4: The provider unit provides the user with the materials retrieved by the search unit. For example, it provides an interface for displaying the search results to the user. The provider unit can display summaries and previews of the materials to make it easier for the user to view the search results.

[0061] (Example of form 2) The document search and suggestion system according to an embodiment of the present invention is a system that uses generative AI to search for and suggest documents that a user may want to refer to. The document search and suggestion system uses generative AI to learn from a large amount of documents and store them in storage. When a user conveys an image of the documents they want to the generative AI, the generative AI picks up several optimal documents. Because the generative AI has learned all the text of the documents, it can accurately suggest the relevant documents. As a result, the user can quickly find the documents they need, improving work efficiency. The generative AI learns the user's past search history and preferences and makes personalized suggestions. As a result, the user can find more appropriate documents, improving work efficiency. For example, the document search and suggestion system learns the user's preferences and interests based on the keywords the user has searched for in the past and the documents they have viewed. Next, when the user makes a new search, the document search and suggestion system suggests the most suitable documents considering the past history. Furthermore, if the user is interested in a particular field, the document search and suggestion system prioritizes suggesting the latest documents related to that field. As a result, the user can always obtain the latest information. Furthermore, the document search and suggestion system prioritizes suggesting documents in a specific format (e.g., PDF or Word documents) if the user prefers that format. This allows users to easily find documents in a format that suits their preferences. As a result, the document search and suggestion system can search for and provide the most suitable documents based on the user's requirements.

[0062] The document search suggestion system according to this embodiment comprises a learning unit, a reception unit, a search unit, and a provision unit. The learning unit learns the text data of documents. The learning unit analyzes a large amount of documents using, for example, a generative AI and learns their contents. The learning unit can analyze the text data of documents in detail and extract important information. The reception unit receives user requests. The reception unit provides, for example, an interface for the user to input keywords and conditions for the documents they want to search for. After receiving the user's request, the reception unit transmits the request to the search unit. The search unit searches for the most suitable documents based on the request received by the reception unit. The search unit uses, for example, a generative AI to search for documents that best suit the user's request. The search unit can analyze the text data of documents and identify documents that match the user's request. The provision unit provides the documents found by the search unit to the user. The provision unit provides, for example, an interface for displaying search results to the user. The provision unit can display summaries and previews of documents to make it easier for the user to view the search results. As a result, the document search and suggestion system according to this embodiment can search for and provide the most suitable documents based on the user's request.

[0063] The learning unit learns from the text data of the materials. For example, the learning unit analyzes a large amount of material using generative AI and learns its content. Specifically, the generative AI uses natural language processing technology to analyze the text data of the materials in detail. First, the generative AI tokenizes the text data of the materials and performs grammatical and semantic analysis to understand the meaning and context of each token. Next, the generative AI identifies keywords and phrases within the text data and evaluates their relationships in order to extract important information. For example, when the generative AI learns from materials on a specific field, it identifies specialized terminology and concepts specific to that field and understands their relationships. Furthermore, the generative AI also has the ability to summarize the content of the materials, extracting important points from long texts and summarizing them concisely. This allows the learning unit to efficiently learn from a vast amount of material and build a foundation for providing optimal materials that meet user needs. The learning unit regularly adds new materials to update the learning database and always maintains the latest information. In addition, the learning unit can improve its learning algorithms based on user feedback and improve search accuracy. This allows the learning unit to provide robust support for responding to diverse user needs and delivering optimal materials.

[0064] The reception desk receives user requests. For example, it provides an interface for users to input keywords and criteria for the materials they wish to search for. Specifically, the reception desk features an intuitive user interface, providing a search bar and filtering options. Users can not only enter keywords into the search bar but also use dropdown menus and checkboxes to set detailed criteria such as material type, publication date, and author name. The reception desk analyzes the information entered by the user in real time and converts it into an appropriate search query. For example, if a user wants to search for "papers on the latest AI technology," the reception desk extracts keywords such as "AI technology," "latest," and "papers," and generates a search query combining these. Furthermore, the reception desk can also provide personalized search suggestions, taking into account the user's past search history and preferences. This allows users to find the desired materials more efficiently. After receiving a user request, the reception desk sends it to the search department. The search department then begins processing the search query received from the reception desk to find the most suitable materials. Thus, the reception desk plays a crucial role in accurately receiving user requests and ensuring a smooth search process.

[0065] The search unit searches for the most suitable materials based on the requests received by the reception unit. For example, the search unit uses generative AI to find the materials best suited to the user's request. Specifically, the search unit leverages the natural language processing capabilities of the generative AI to analyze the text data of the materials and identify materials that match the user's request. The generative AI first analyzes the search query and understands its meaning. Next, the generative AI searches the material database, which it has learned from in the learning unit, to identify the materials most relevant to the query. For example, if a user searches for "papers on the latest AI technology," the generative AI identifies the latest papers on AI technology within the material database and selects the most relevant ones. Furthermore, the generative AI summarizes the content of the materials and evaluates whether they contain the information the user is looking for. This allows the search unit to provide highly accurate search results for the user's request. The search unit updates search results in real time and responds quickly when the user enters a new query. Additionally, the search unit can continuously improve its search algorithm and search accuracy based on user feedback. This allows the search function to play a crucial role in responding to diverse user needs and providing the most relevant information quickly and accurately.

[0066] The service provider provides users with materials retrieved by the search unit. For example, the service provider provides an interface for displaying search results to users. Specifically, it can display summaries and previews of materials to make the search results easier for users to view. The service provider displays search results in a list format, providing basic information such as the title, author, publication date, and summary of each material. Users can select materials of interest from the list and view detailed previews. These previews include excerpts of text and figures from the material, allowing users to easily grasp its content. Furthermore, the service provider can also provide download links and suggest related materials. For example, if a user is viewing a specific paper, the service provider can suggest other related materials to help the user explore the information more deeply. The service provider can also collect user feedback and continuously improve the quality of the information it provides. For example, it can evaluate whether users are satisfied with the search results and revise the search algorithm and display methods if satisfaction is low. In this way, the service provider plays a crucial role in providing users with high-quality information and improving the search experience.

[0067] The learning unit can analyze the text data of materials in detail. For example, the learning unit uses generative AI to analyze the text data of materials in detail and extract important information. The learning unit can deeply understand the content of materials and suggest materials that are most suitable for the user's needs. For example, the learning unit can analyze each section of a material and extract important keywords and phrases. The learning unit can also understand the context of the material and connect related information. This allows for more accurate material suggestions by analyzing the text data of materials in detail. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs the text data of the material into the generative AI, which then analyzes the data and extracts important information.

[0068] The learning unit can learn the user's past search history and preferences to provide personalized suggestions. For example, the learning unit learns the user's preferences and interests based on the keywords the user has searched for and the materials they have viewed in the past. The learning unit can analyze the user's past behavioral data to understand what kind of materials the user likes. For example, the learning unit can extract keywords that the user frequently searches for and the characteristics of materials that the user views for extended periods. Furthermore, the learning unit can prioritize suggesting relevant materials based on the user's preferences. In this way, by learning the user's past search history and preferences, it becomes possible to suggest more appropriate materials. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs data on the user's past search history and preferences into the generative AI, which then analyzes that data to provide personalized suggestions.

[0069] The service provider can evaluate the quality of the proposed materials. For example, the service provider can evaluate the reliability and accuracy of the information in the proposed materials. The service provider can set criteria for evaluating the quality of materials and evaluate the materials based on those criteria. For example, the service provider can evaluate the reliability of the publisher and author of the materials. The service provider can also evaluate the accuracy and consistency of the content of the materials. By evaluating the quality of the proposed materials, the service provider can provide users with high-quality materials. Some or all of the above processes in the service provider may be performed using AI or not. For example, the service provider can input data from the proposed materials into an AI, and the AI ​​can analyze that data and evaluate its quality.

[0070] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is stressed, the learning unit will prioritize learning materials that promote relaxation. The learning unit uses an emotion estimation function, such as an emotion engine or generative AI, to estimate the user's emotions. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the user is excited, the learning unit will prioritize learning materials with stimulating content. Also, if the user is tired, the learning unit can prioritize learning materials with simple and easy-to-understand content. This allows for the suggestion of more appropriate materials by selecting training data based on the user's emotions. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs user emotion data into the generative AI, which then analyzes that data to select training data.

[0071] The learning unit can analyze the structure of the text data of the material and prioritize learning important sections. For example, the learning unit can analyze the table of contents and headings of the material to identify and learn important sections. The learning unit can extract keywords from the material and prioritize learning sections containing frequently occurring keywords. For example, the learning unit can analyze the citations and references of the material and prioritize learning sections that are highly reliable. Furthermore, the learning unit can analyze the structure of the text data of the material and efficiently learn important information. This enables efficient learning by prioritizing the learning of important sections of the material. Some or all of the above processes in the learning unit are performed using generative AI. For example, the learning unit inputs the text data of the material into the generative AI, which then analyzes the data to identify important sections.

[0072] The learning unit can prioritize learning the latest information by considering the frequency of material updates. For example, the learning unit can analyze the publication date of a material and prioritize learning the most recent material. The learning unit can analyze the update history of a material and prioritize learning materials that are frequently updated. For example, the learning unit can analyze the version information of a material and prioritize learning the latest version of the material. Furthermore, the learning unit can always learn the latest information by considering the frequency of material updates. This ensures that the latest information is always provided by prioritizing the learning of the latest information. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit inputs the material update history data into the generative AI, which then analyzes the data to identify the latest information.

[0073] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit will reduce the learning frequency to alleviate the burden. The learning unit uses an emotion estimation function, such as an emotion engine or generative AI, to estimate the user's emotions. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the user is relaxed, the learning unit will increase the learning frequency to improve efficiency. Also, if the user is tired, the learning unit can adjust the learning frequency to proceed at an appropriate pace. In this way, by adjusting the learning frequency based on the user's emotions, the burden on the user is reduced and efficient learning becomes possible. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs user emotion data into the generative AI, and the generative AI analyzes that data to adjust the learning frequency.

[0074] The learning unit can apply different learning algorithms to each type of material. For example, the learning unit can apply an algorithm specialized in analyzing technical terms to scientific and technological materials. For literary materials, it can apply an algorithm specialized in analyzing writing style and expression. For business materials, it can apply an algorithm specialized in data analysis and statistical information analysis. Furthermore, by applying the appropriate learning algorithm to each type of material, the learning unit can achieve efficient learning. Some or all of the above processing in the learning unit is performed using a generative AI. For example, the learning unit inputs material genre data into the generative AI, which then analyzes the data and applies the appropriate learning algorithm.

[0075] The learning unit can apply different learning methods depending on the language and format of the materials. For example, for English materials, the learning unit applies methods that analyze English-specific grammar and expressions. For PDF materials, the learning unit can apply methods specialized in text extraction and layout analysis. For materials containing images, the learning unit applies methods that analyze the relationship between text and images using image recognition technology. Furthermore, by applying appropriate learning methods according to the language and format of the materials, the learning unit enables efficient learning. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit inputs language and format data of the materials into the generative AI, which analyzes that data and applies appropriate learning methods.

[0076] The reception desk can estimate the user's emotions and adjust the request processing method based on the estimated emotions. For example, if the user is stressed, the reception desk will provide a simple interface and minimize the input steps. The reception desk is implemented using emotion estimation functionality, such as an emotion engine or generative AI, to estimate the user's emotions. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the user is relaxed, the reception desk will provide detailed input options and suggest a customizable input method. Also, if the user is in a hurry, the reception desk can prioritize voice input and process the request quickly. This allows for more appropriate request processing by adjusting the request processing method based on the user's emotions. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk may input user emotion data into an AI, which then analyzes the data and adjusts the request processing method.

[0077] The reception unit can select the optimal reception method by referring to the user's past request history. For example, the reception unit may prioritize suggesting request methods that the user has frequently used in the past. By referring to the user's past request history, the reception unit can process requests more efficiently. For example, the reception unit may predict and suggest request methods to be used during specific time periods based on the user's past request history. The reception unit can also analyze the user's past request history and suggest the most efficient reception method. This allows for more efficient request processing by referring to the user's past request history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit may input the user's past request history data into the AI, which then analyzes the data to select the optimal reception method.

[0078] The reception desk can prioritize requests based on the user's current situation and environment. For example, if the user is in a hurry, the reception desk will prioritize high-priority requests. The reception desk can also accept more appropriate requests based on the user's current situation and environment. For example, if the user is relaxed, the reception desk will prioritize detailed requests. The reception desk can also prioritize appropriate requests based on the user's current environment (e.g., in a meeting or on the move). This allows for more appropriate requests to be accepted by prioritizing requests based on the user's current situation and environment. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input data on the user's current situation and environment into the AI, which then analyzes the data to determine the priority of requests.

[0079] The reception desk can estimate the user's emotions and adjust the level of detail of requests based on the estimated emotions. For example, if the user is stressed, the reception desk will prioritize accepting concise requests. The reception desk is implemented using emotion estimation functionality, such as an emotion engine or generative AI, to estimate the user's emotions. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the user is relaxed, the reception desk will prioritize accepting detailed requests. Also, if the user is in a hurry, the reception desk can prioritize accepting requests that can be processed quickly. This allows for more appropriate request acceptance by adjusting the level of detail of requests based on the user's emotions. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk may input user emotion data into the AI, and the AI ​​may analyze that data to adjust the level of detail of requests.

[0080] The reception unit can select the optimal reception method by considering the user's device information. For example, if the user is using a smartphone, the reception unit can provide a reception method optimized for touch operation. By considering the user's device information, the reception unit can process requests more efficiently. For example, if the user is using a tablet, the reception unit can provide a reception method optimized for a large screen. Also, if the user is using a desktop computer, the reception unit can provide a reception method optimized for keyboard input. This allows for more efficient request processing by considering the user's device information. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's device information into the AI, and the AI ​​will analyze that data to select the optimal reception method.

[0081] The reception desk can prioritize receiving requests that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific region, the reception desk will prioritize receiving requests related to that region. By considering the user's geographical location, the reception desk can receive more appropriate requests. For example, if the user is on the move, the reception desk will prioritize receiving requests related to their destination. Also, if the user is inside a specific facility, the reception desk can prioritize receiving requests related to that facility. This allows for more appropriate requests to be received by prioritizing highly relevant requests while considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk may input the user's geographical location into the AI, and the AI ​​may analyze that data to identify highly relevant requests.

[0082] The search unit can estimate the user's emotions and adjust the search algorithm based on those emotions. For example, if the user is stressed, the search unit applies a simple and fast search algorithm. The search unit uses emotion estimation capabilities, such as an emotion engine or generative AI, to estimate the user's emotions. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the user is relaxed, the search unit applies a detailed search algorithm. Also, if the user is in a hurry, the search unit can apply a search algorithm that produces results in the shortest possible time. By adjusting the search algorithm based on the user's emotions, more appropriate search results can be provided. Some or all of the above processing in the search unit is performed using generative AI. For example, the search unit inputs user emotion data into the generative AI, which analyzes that data and adjusts the search algorithm.

[0083] The search unit can evaluate the relevance of materials and prioritize searching for the most relevant materials. For example, the search unit can evaluate the degree of keyword matching of materials and prioritize searching for the materials with the highest degree of matching. The search unit can evaluate the degree of content matching of materials and prioritize searching for the materials with the highest degree of matching. For example, the search unit can evaluate the degree of matching of citations and references of materials and prioritize searching for the materials with the highest degree of matching. In addition, the search unit can set criteria for evaluating the relevance of materials and evaluate materials based on those criteria. This allows for the search of more appropriate materials by evaluating the relevance of materials. Some or all of the above processing in the search unit is performed using generative AI. For example, the search unit inputs material data into the generative AI, and the generative AI analyzes that data and evaluates the relevance.

[0084] The search unit can evaluate the reliability of materials and prioritize searching for highly reliable materials. For example, the search unit can evaluate the publisher of materials and prioritize searching for materials from reliable publishers. The search unit can evaluate the number of citations of materials and prioritize searching for materials with a high number of citations. For example, the search unit can evaluate the author of materials and prioritize searching for materials by reliable authors. In addition, the search unit can set criteria for evaluating the reliability of materials and evaluate materials based on those criteria. This allows for the search of more reliable materials by evaluating their reliability. Some or all of the above processing in the search unit is performed using a generative AI. For example, the search unit inputs material data into the generative AI, which then analyzes the data and evaluates its reliability.

[0085] The search unit can apply different search methods depending on the language and format of the document. For example, for English documents, the search unit applies a search method that analyzes English-specific grammar and expressions. For PDF documents, the search unit can apply a search method specialized in text extraction and layout analysis. For documents containing images, the search unit applies a search method that analyzes the relationship between text and images using image recognition technology. Furthermore, by applying the appropriate search method according to the language and format of the document, the search unit enables efficient searching. Some or all of the above processing in the search unit is performed using a generative AI. For example, the search unit inputs the language and format data of the document into the generative AI, which then analyzes the data and applies the appropriate search method.

[0086] The search unit can prioritize searching for the latest information, taking into account the frequency of document updates. For example, the search unit can analyze the publication date of a document and prioritize searching for the most recent document. The search unit can analyze the update history of a document and prioritize searching for documents that are frequently updated. For example, the search unit can analyze the version information of a document and prioritize searching for the latest version. Furthermore, the search unit can always search for the latest information, taking into account the frequency of document updates. This ensures that the latest information is always provided by prioritizing the search for the most up-to-date information. Some or all of the above processing in the search unit is performed using a generating AI. For example, the search unit inputs the document's update history data into the generating AI, which then analyzes the data to identify the latest information.

[0087] The service provider can estimate the user's emotions and adjust the display method of the materials based on the estimated emotions. For example, if the user is stressed, the service provider will provide a simple and highly visible display method. The service provider uses an emotion estimation function, such as an emotion engine or generative AI, to estimate the user's emotions. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the user is relaxed, the service provider will provide a display method that includes detailed information. Also, if the user is in a hurry, the service provider can provide a display method that gets straight to the point. This makes it possible to provide more appropriate materials by adjusting the display method of the materials based on the user's emotions. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider may input user emotion data into the AI, and the AI ​​will analyze that data to adjust the display method of the materials.

[0088] The service provider can select the optimal service delivery method by referring to the user's past usage history. For example, the service provider can prioritize suggesting service delivery methods that the user has frequently used in the past. By referring to the user's past usage history, the service provider can deliver materials more efficiently. For example, the service provider can predict and suggest a service delivery method to be used during a specific time period based on the user's past usage history. Furthermore, the service provider can analyze the user's past usage history and suggest the most efficient service delivery method. This makes it possible to deliver materials more efficiently by referring to the user's past usage history. Some or all of the above processes in the service provider may be performed using AI, or not. For example, the service provider can input the user's past usage history data into an AI, which then analyzes the data and selects the optimal service delivery method.

[0089] The provisioning department can determine the priority of provision based on the importance of the materials. For example, the provisioning department can evaluate the importance of the materials and provide the most important materials first. The provisioning department can evaluate the urgency of the materials and provide the most urgent materials first. For example, the provisioning department can evaluate the relevance of the materials and provide the most relevant materials first. The provisioning department can also set criteria for evaluating the importance of the materials and evaluate the materials based on those criteria. This allows for the provision of more important materials to be provided first by determining the priority of provision based on the importance of the materials. Some or all of the above processes in the provisioning department may be performed using AI or not. For example, the provisioning department can input the data of the materials into an AI, and the AI ​​can analyze that data and evaluate its importance.

[0090] The service provider can estimate the user's emotions and adjust the level of detail in the materials provided based on the estimated emotions. For example, if the user is stressed, the service provider will provide concise and to-the-point materials. The service provider's ability to estimate the user's emotions is implemented using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the user is relaxed, the service provider will provide materials containing detailed information. Also, if the user is in a hurry, the service provider can provide materials that can be quickly understood. By adjusting the level of detail in the materials based on the user's emotions, it becomes possible to provide more appropriate materials. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider may input user emotion data into the AI, and the AI ​​may analyze that data to adjust the level of detail in the materials.

[0091] The service provider can select the optimal service delivery method by considering the user's device information. For example, if the user is using a smartphone, the service provider can provide a service delivery method optimized for touch operation. By considering the user's device information, the service provider can deliver materials more efficiently. For example, if the user is using a tablet, the service provider can provide a service delivery method optimized for a large screen. Furthermore, if the user is using a desktop computer, the service provider can provide a service delivery method optimized for keyboard operation. This allows for more efficient material delivery by considering the user's device information. Some or all of the above processing in the service provider may be performed using AI, or not. For example, the service provider can input the user's device information into the AI, and the AI ​​will analyze that data to select the optimal service delivery method.

[0092] The delivery unit can adjust the order of delivery based on the relevance of the materials. For example, the delivery unit can evaluate the relevance of the materials and provide the most relevant materials first. The delivery unit can evaluate the importance of the materials and provide the most important materials first. For example, the delivery unit can evaluate the urgency of the materials and provide the most urgent materials first. The delivery unit can also set criteria for evaluating the relevance of the materials and evaluate the materials based on those criteria. This allows for the provision of more appropriate materials by adjusting the order of delivery based on the relevance of the materials. Some or all of the above processes in the delivery unit may be performed using AI or not. For example, the delivery unit can input material data into AI, and the AI ​​can analyze that data, evaluate the relevance, and adjust the order of delivery.

[0093] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0094] The document search suggestion system can estimate the user's emotions and adjust the display order of search results based on those emotions. For example, if the user is stressed, the system will prioritize displaying the most relevant documents, providing the necessary information quickly. If the user is relaxed, the system will prioritize displaying documents containing detailed information, allowing the user to learn more deeply. Furthermore, if the user is in a hurry, the system will prioritize displaying documents that get straight to the point, allowing the user to obtain the necessary information in a short amount of time. In this way, by adjusting the display order of search results based on the user's emotions, it becomes possible to provide more appropriate information.

[0095] The document search and suggestion system can automatically cluster related documents based on the user's past search history. For example, it analyzes keywords the user has previously searched for and the content of documents they have viewed, and groups highly relevant documents together. Furthermore, if the user has an interest in a particular field, it can prioritize clustering documents related to that field. It can also cluster documents based on the user's preferred document format (e.g., PDF or Word document), efficiently providing the information the user is looking for. This allows for more efficient information delivery by clustering documents based on the user's past search history.

[0096] The document search suggestion system can estimate the user's emotions and filter search results based on those emotions. For example, if the user is stressed, the system will display only highly reliable documents to ensure the reliability of the information. If the user is relaxed, the system will display documents with diverse perspectives to allow the user to obtain a wide range of information. Furthermore, if the user is in a hurry, the system will display documents that get straight to the point, allowing the user to obtain the necessary information in a short time. In this way, filtering search results based on the user's emotions enables the provision of more appropriate information.

[0097] The data search suggestion system can select the optimal display method for search results, taking into account the user's device information. For example, if the user is using a smartphone, the system provides a mobile-optimized display method to improve visibility. If the user is using a tablet, it provides a display method optimized for large screens, making it easier to view information. Furthermore, if the user is using a desktop, it provides a display method optimized for keyboard operation, supporting efficient information retrieval. In this way, by considering the user's device information, it becomes possible to provide information more efficiently.

[0098] The information search suggestion system can estimate the user's emotions and adjust the display format of search results based on those emotions. For example, if the user is stressed, the system provides a simple and highly visible display format to facilitate information comprehension. If the user is relaxed, the system provides a display format that includes detailed information, allowing the user to learn more deeply. Furthermore, if the user is in a hurry, the system provides a concise display format, enabling them to obtain the necessary information quickly. In this way, by adjusting the display format of search results based on the user's emotions, it becomes possible to provide more appropriate information.

[0099] The document search and suggestion system can prioritize searching for highly relevant documents by considering the user's geographical location. For example, if the user is in a specific region, it will prioritize searching for documents related to that region. Similarly, if the user is on the move, it will prioritize searching for documents related to their destination. Furthermore, if the user is inside a specific facility, it will prioritize searching for documents related to that facility. This allows for the provision of more appropriate information by prioritizing the search for highly relevant documents based on the user's geographical location.

[0100] The data search suggestion system can estimate the user's emotions and adjust the display speed of search results based on those emotions. For example, if the user is stressed, the system will display search results quickly to reduce the user's stress. If the user is relaxed, the system will display search results with more detailed information to allow the user to learn more deeply. Furthermore, if the user is in a hurry, the system will display results in the shortest possible time, allowing the user to quickly obtain the necessary information. In this way, by adjusting the display speed of search results based on the user's emotions, it becomes possible to provide more appropriate information.

[0101] The document search and suggestion system can automatically tag relevant documents based on the user's past usage history. For example, it analyzes keywords the user has previously searched for and the content of documents they have viewed, and assigns highly relevant tags. Furthermore, if the user has an interest in a particular field, it can prioritize assigning tags related to that field. In addition, it tags documents based on the user's preferred document format (e.g., PDF or Word document), efficiently providing the information the user is looking for. This allows for more efficient information delivery by tagging documents based on the user's past usage history.

[0102] The information search suggestion system can estimate the user's emotions and adjust the layout of search results based on those emotions. For example, if the user is stressed, the system provides a simple and highly visible layout to facilitate understanding of the information. If the user is relaxed, the system provides a layout with detailed information to allow the user to learn more deeply. Furthermore, if the user is in a hurry, the system provides a concise layout to allow them to obtain the necessary information quickly. In this way, by adjusting the layout of search results based on the user's emotions, it becomes possible to provide more appropriate information.

[0103] The document search suggestion system can prioritize search results based on the user's current situation and environment. For example, if the user is in a hurry, it will prioritize displaying documents of high urgency. Conversely, if the user is relaxed, it can prioritize displaying documents containing detailed information. Furthermore, if the user is in a specific environment (e.g., during a meeting or while traveling), it will prioritize displaying documents relevant to that environment. By prioritizing search results based on the user's current situation and environment, it becomes possible to provide more relevant information.

[0104] The following briefly describes the processing flow for example form 2.

[0105] Step 1: The learning unit learns from the text data of the materials. For example, it analyzes a large amount of material using a generative AI and learns its content. The learning unit can analyze the text data of the materials in detail and extract important information. Step 2: The reception unit receives the user's request. For example, it provides an interface for the user to enter keywords or criteria for the materials they want to search for. After receiving the user's request, the reception unit sends the request to the search unit. Step 3: The search unit searches for the most suitable materials based on the request received by the reception unit. For example, it may use a generative AI to search for materials that best suit the user's request. The search unit can analyze the text data of the materials and identify materials that match the user's request. Step 4: The provider unit provides the user with the materials retrieved by the search unit. For example, it provides an interface for displaying the search results to the user. The provider unit can display summaries and previews of the materials to make it easier for the user to view the search results.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0108] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] Each of the multiple elements described above, including the learning unit, reception unit, search unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes a large amount of data using a generation AI and learns its contents. The reception unit is implemented by the control unit 46A of the smart device 14, which provides an interface for the user to input keywords and conditions for the data they want to search for. The search unit is implemented by the specific processing unit 290 of the data processing unit 12, which searches for the data that best suits the user's request. The provision unit is implemented by the control unit 46A of the smart device 14, which provides an interface for displaying the search results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0110] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0111] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0116] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0117] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0118] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0119] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0120] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0124] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] Each of the multiple elements described above, including the learning unit, reception unit, search unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes a large amount of material using a generating AI and learns its contents. The reception unit is implemented by the control unit 46A of the smart glasses 214, which provides an interface for the user to input keywords and conditions for the material they want to search for. The search unit is implemented by the specific processing unit 290 of the data processing unit 12, which searches for the material that best suits the user's request. The provision unit is implemented by the control unit 46A of the smart glasses 214, which provides an interface for displaying the search results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0126] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0127] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0129] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0130] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0132] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0133] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0134] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0135] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0136] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements described above, including the learning unit, reception unit, search unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes a large amount of material using a generation AI and learns its contents. The reception unit is implemented by the control unit 46A of the headset terminal 314, which provides an interface for the user to input keywords and conditions for the material they want to search for. The search unit is implemented by the specific processing unit 290 of the data processing unit 12, which searches for the material that best suits the user's request. The provision unit is implemented by the control unit 46A of the headset terminal 314, which provides an interface for displaying the search results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0142] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0143] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0146] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0150] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the learning unit, reception unit, search unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes a large amount of data using a generating AI and learns its contents. The reception unit is implemented by the control unit 46A of the robot 414, which provides an interface for the user to input keywords and conditions for the data they want to search for. The search unit is implemented by the specific processing unit 290 of the data processing unit 12, which searches for the data that best suits the user's request. The provision unit is implemented by the control unit 46A of the robot 414, which provides an interface for displaying the search results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0159] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0161] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0162] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0163] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0167] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0168] 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.

[0169] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0170] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0171] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0172] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0174] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0175] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0176] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0177] (Note 1) A learning unit that learns from the text data of the materials, A reception desk that receives user requests, A search unit that searches for the most suitable materials based on the request received by the reception unit, The system includes a provisioning unit that provides the materials retrieved by the search unit to the user. A system characterized by the following features. (Note 2) The aforementioned learning unit, Analyze the text data of the document in detail. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned learning unit, It learns the user's past search history and preferences to provide personalized suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, Evaluate the quality of the proposed materials. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, Analyze the structure of the text data in the document and prioritize learning the important sections. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, Prioritize learning the latest information, taking into account the frequency of material updates. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, Apply different learning algorithms to each type of material. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, Apply different learning methods depending on the language and format of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is It estimates the user's emotions and adjusts how requests are received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is The system selects the optimal request acceptance method by referring to the user's past request history. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is Prioritize requests based on the user's current situation and environment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is It estimates the user's emotions and adjusts the level of detail of the request based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reception unit is The optimal reception method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned reception unit is The system prioritizes requests that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned search unit, It estimates the user's sentiment and adjusts the search algorithm based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned search unit, Evaluate the relevance of the materials and prioritize searching for the most relevant materials. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned search unit, Evaluate the reliability of the materials and prioritize searching for highly reliable materials. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned search unit, Apply different search methods depending on the language and format of the document. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned search unit, Prioritize searching for the latest information, taking into account the frequency of document updates. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, It estimates the user's emotions and adjusts how the materials are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, The optimal delivery method is selected by referring to the user's past usage history. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, Prioritize the provision of materials based on their importance. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, It estimates the user's emotions and adjusts the level of detail in the materials provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, The optimal delivery method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, The order in which materials are provided will be adjusted based on their relevance. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning unit that learns from the text data of the materials, A reception desk that receives user requests, A search unit that searches for the most suitable materials based on the request received by the reception unit, The system includes a provisioning unit that provides the materials retrieved by the search unit to the user. A system characterized by the following features.

2. The aforementioned learning unit, Analyze the text data of the document in detail. The system according to feature 1.

3. The aforementioned learning unit, It learns the user's past search history and preferences to provide personalized suggestions. The system according to feature 1.

4. The aforementioned supply unit is, Evaluate the quality of the proposed materials. The system according to feature 1.

5. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

6. The aforementioned learning unit, Analyze the structure of the text data in the document and prioritize learning the important sections. The system according to feature 1.

7. The aforementioned learning unit, Prioritize learning the latest information, taking into account the frequency of material updates. The system according to feature 1.

8. The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system according to feature 1.

Images