system

Abstract

The system according to the embodiment aims to improve the efficiency of handover work and quickly determine which products should be proposed. [Solution] The system according to the embodiment includes a reading unit, a sorting unit, a determination unit, a provision unit, and a response unit. The reading unit reads a document. The sorting unit analyzes the document read by the reading unit and organizes past proposal history. The determination unit determines which products to propose based on the information organized by the sorting unit. The provision unit provides the products determined by the determination unit. The response unit responds to questions from the person in charge.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that the handover process is time-consuming and laborious, making it difficult to carry out efficiently.

[0005] The system according to the embodiment aims to improve the efficiency of handover work and quickly determine which products should be proposed. [Means for solving the problem]

[0006] The system according to the embodiment includes a reading unit, a sorting unit, a determination unit, a provision unit, and a response unit. The reading unit reads a document. The sorting unit analyzes the document read by the reading unit and organizes past proposal history. The determination unit determines which products to propose based on the information organized by the sorting unit. The provision unit provides the products determined by the determination unit. The response unit responds to questions from the person in charge. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of handover work and quickly determine the products that should be proposed. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A handover chatbot system according to an embodiment of the present invention reads documents, organizes past proposal history, determines which products should be proposed, and responds to questions from staff. This handover chatbot system streamlines handover processes by reading documents such as proposals and proposal approvals for the target company and organizing the past proposal history. Furthermore, further efficiency can be achieved by having AI determine which products should be proposed simultaneously with the handover process. For example, the handover chatbot reads documents such as proposals and proposal approvals for the target company. At this time, the AI ​​analyzes the documents and organizes the past proposal history. For example, the AI ​​analyzes the contents of the proposal and the results of the proposal approval and extracts important information. This allows the staff performing the handover process to easily understand the past proposal history. Next, the AI ​​determines which products should be proposed simultaneously with the handover process. The AI ​​proposes the optimal products based on the past proposal history and the needs of the target company. For example, the AI ​​analyzes past proposals and their results to propose the products best suited to the current situation. This allows handover and proposal processes to be performed simultaneously, improving efficiency. Furthermore, the handover chatbot also responds to questions from the person in charge. For example, AI provides appropriate answers to questions about the history of past proposals or the products to be proposed. This allows the person in charge to quickly obtain the necessary information. This system not only improves the efficiency of the handover process, but also allows proposal work to be done simultaneously, improving overall work efficiency. For example, when a new person takes over, they can easily understand the history of past proposals and propose the most suitable products. In addition, since it can quickly respond to questions from the person in charge, it is expected that work will proceed smoothly. As a result, the handover chatbot system can efficiently read and analyze documents, organize the proposal history, determine and provide products, and respond to questions.

[0029] A handover chatbot system according to an embodiment includes a reading unit, a sorting unit, a determination unit, a providing unit, and a response unit. The reading unit reads documents. Examples of documents include, but are not limited to, proposals, proposal approvals, reports, and emails. The reading unit digitizes and reads documents such as proposals and proposal approvals using scanning technology. The reading unit can also directly read documents submitted in digital format. The reading unit can also read printed documents using OCR technology. For example, the reading unit scans a proposal with a high-resolution scanner and converts it into text information using OCR technology. Digital documents submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The sorting unit analyzes the documents read by the reading unit and organizes the history of past proposals. The analysis can be performed using, for example, text mining or natural language processing technology, but is not limited to these examples. For example, the sorting unit analyzes the content of the document and extracts important information using text mining technology. The sorting unit can also analyze the content of documents using natural language processing technology and organize the history of past proposals. For example, the sorting unit analyzes the content of proposals and the results of proposal approvals, extracting and organizing important information. The judgment unit determines which products to propose based on the information organized by the sorting unit. The judgment can be made, for example, using AI, but is not limited to this example. For example, the judgment unit can propose the optimal product based on the history of past proposals and the needs of the client company. The judgment unit can also use AI to analyze previously proposed products and their results and propose the product that is optimal for the current situation. For example, the judgment unit can use an AI model to input the organized information and output the optimal product. The provision unit provides the product determined by the judgment unit. The provision can be made, for example, using AI, but is not limited to this example. For example, the provision unit provides the determined product to the person in charge. The provision unit can also automatically provide the determined product using AI. For example, the provision unit can use an AI model to input the determined product and output a provision method. The response unit responds to questions from the person in charge.The response may be performed using, for example, AI, but is not limited to such an example. For example, the response unit may provide appropriate answers to questions from the person in charge about the history of past proposals and the products to be proposed. The response unit may also use AI to automatically respond to questions from the person in charge. For example, the response unit may use an AI model to input questions and output answers. This allows the handover chatbot system according to the embodiment to efficiently read and analyze documents, organize the history of proposals, determine and provide products, and respond to questions.

[0030] The reading unit can read a proposal or a proposal approval document. The proposal may include, but is not limited to, the purpose of the proposal, the content of the proposal, and the background of the proposal. The proposal approval may include, but is not limited to, the approval criteria and the approval process. For example, the reading unit may scan the proposal and save it as image data. The reading unit may then convert the image data into text data using OCR technology. The reading unit may also directly read a proposal submitted in digital format. For example, the reading unit may directly read a digital proposal submitted in a specific file format. The reading unit may also read a proposal approval document and analyze the results of the proposal and the approval criteria. For example, the reading unit may scan the proposal approval document and convert it into text information using OCR technology. This allows documents such as proposals and proposal approvals to be read efficiently. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without AI. For example, the reading unit can input the image data obtained by scanning a proposal or proposal approval document into the generation AI, and have the generation AI generate text data from the image data.

[0031] The organizer can analyze the loaded document and organize the past proposal history. Examples of the analysis include, but are not limited to, text mining and natural language processing. Examples of the past proposal history include, but are not limited to, the date and time of the proposal, the proposal content, and the proposal results. The organizer can, for example, use text mining technology to analyze the content of the document and extract important information. The organizer can also analyze the content of the document using natural language processing technology to organize the past proposal history. For example, the organizer can analyze the content of the proposal and the results of the proposal approval, extract and organize important information. The organizer can also calculate the success rate and failure rate of the proposal based on the past proposal history. For example, the organizer can calculate the success rate of the proposal based on the date and time of the proposal and the proposal content. This allows the past proposal history to be organized efficiently. Some or all of the above-described processing in the organizer can be performed using, for example, AI, or without AI. For example, the organizer can input the loaded document to a generation AI and have the generation AI organize the past proposal history.

[0032] The determination unit can determine which products to propose based on the organized information. Examples of the products to propose include, but are not limited to, products, services, and solutions. The determination unit can propose optimal products based on, for example, past proposal history and the needs of the client company. The determination unit can also use AI to analyze previously proposed products and their results to propose products that are optimal for the current situation. For example, the determination unit can input the organized information using an AI model and output optimal products. The determination unit can also determine products taking into account the attribute information of the client company. For example, the determination unit can determine optimal products based on the client company's industry and size. This allows for efficient determination of products to propose. Some or all of the above-described processing by the determination unit can be performed using, for example, AI, or without AI. For example, the determination unit can input the organized information to a generation AI and have the generation AI determine which products to propose.

[0033] The providing unit can provide the determined product. Examples of the product include, but are not limited to, products, services, and solutions. The providing unit, for example, provides the determined product to a person in charge. The providing unit can also automatically provide the determined product using AI. For example, the providing unit uses an AI model to input the determined product and output a provision method. The providing unit can also adjust the level of detail of the provision based on the importance of the product. For example, detailed information can be provided for products with high importance, and concise information can be provided for products with low importance. This allows the determined product to be provided efficiently. Some or all of the above-described processing in the providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the providing unit can input the determined product to a generation AI and cause the generation AI to provide the product.

[0034] The response unit can respond to questions from the staff. Questions include, but are not limited to, technical questions and business questions. For example, the response unit provides appropriate answers to questions from the staff, such as about the history of past proposals and the products to be proposed. The response unit can also automatically answer questions from the staff using AI. For example, the response unit inputs questions and outputs answers using an AI model. The response unit can also provide optimal answers by referring to past question history. For example, if a similar question has been asked in the past, the response unit can provide optimal answers based on those answers. This allows for quick responses to questions from the staff. Some or all of the above-described processing in the response unit may be performed using AI, or may be performed without using AI. For example, the response unit can input questions from the staff to a generation AI and have the generation AI execute an optimal answer.

[0035] The reading unit can determine the reading priority based on the document type and importance during reading. Examples of document types include, but are not limited to, proposals, reports, and emails. Examples of document importance include, but are not limited to, business impact and urgency. The reading unit prioritizes reading important documents, such as proposals and proposal approval documents. The reading unit can also postpone documents with lower importance, such as daily reports and memos. Furthermore, the reading unit can prioritize reading documents with higher urgency for quicker response. For example, the reading unit determines the priority based on the document type and importance and prioritizes reading important documents. Thus, by prioritizing documents based on the document type and importance, important documents can be prioritized for reading. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or without AI. For example, the reading unit can input the document type and importance to the generation AI and have the generation AI determine the reading priority.

[0036] The reading unit can apply different reading algorithms depending on the document format and language during reading. Examples of document formats include, but are not limited to, PDF, Word, and Excel. Examples of document languages ​​include, but are not limited to, Japanese, English, and Chinese. For example, the reading unit applies a text extraction algorithm to a PDF document to read it. The reading unit can also apply a translation algorithm to a document written in English or another language to read it. Furthermore, the reading unit can also apply a handwriting recognition algorithm to a handwritten document to read it. For example, the reading unit applies an appropriate algorithm depending on the document format and language to efficiently read the document. This enables efficient reading by applying an appropriate algorithm depending on the document format and language. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input the document format and language to the generation AI and cause the generation AI to apply a reading algorithm.

[0037] The reading unit can improve the accuracy of reading by taking into account the attribute information of the document creator during reading. The attribute information of the document creator includes, for example, the creator's job title, field of expertise, etc., but is not limited to these examples. For example, if the document creator is an expert, the reading unit accurately reads technical terms. Furthermore, if the document creator is a novice, the reading unit can prioritize reading concise expressions. Furthermore, if the document creator is busy, the reading unit can prioritize reading important points. For example, the reading unit improves the accuracy of reading by taking into account the attribute information of the document creator. Thus, by taking into account the attribute information of the document creator, the accuracy of reading is improved. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input the attribute information of the document creator into the generation AI and cause the generation AI to improve the accuracy of reading.

[0038] The reading unit can adjust the reading order based on the relevance of the documents during reading. Examples of document relevance include, but are not limited to, content similarity and related topics. For example, the reading unit sequentially reads documents related to the same project. The reading unit can also prioritize reading documents related to past proposal history. Furthermore, the reading unit can also read documents created by the same person all at once. For example, the reading unit adjusts the reading order based on the relevance of the documents to efficiently acquire information. By adjusting the reading order based on the relevance of the documents, efficient information acquisition becomes possible. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input the relevance of the documents to a generation AI and have the generation AI adjust the reading order.

[0039] The organizing unit can extract important information based on the content of the document during organizing, thereby improving the accuracy of the organizing. The content of the document includes, for example, the proposal content of a proposal and the result of the proposal approval, but is not limited to these examples. For example, the organizing unit extracts and organizes important proposal content from a proposal. The organizing unit can also extract the result of the proposal approval and organize it in association with past proposal history. Furthermore, the organizing unit can extract keywords from a document and organize related information. For example, the organizing unit analyzes the content of a document, extracts important information, and organizes it. This improves the accuracy of the organizing by extracting important information based on the content of the document. Some or all of the above-mentioned processing in the organizing unit may be performed, for example, using AI, or may be performed without AI. For example, the organizing unit can input the content of a document to a generation AI and have the generation AI extract and organize important information.

[0040] The sorting unit can apply different sorting algorithms depending on the document category during sorting. Document categories include, but are not limited to, proposals, proposal approvals, reports, and emails. For example, the sorting unit can apply an algorithm that organizes documents based on proposal content to proposals. The sorting unit can also apply an algorithm that organizes documents based on approval results to proposal approvals. Furthermore, the sorting unit can apply an algorithm that organizes documents based on report content to daily reports. For example, the sorting unit can apply an appropriate algorithm depending on the document category to efficiently organize information. This enables efficient information organization by applying an appropriate algorithm depending on the document category. Some or all of the above-mentioned processing in the sorting unit can be performed using, for example, AI, or without AI. For example, the sorting unit can input the document category to a generation AI and have the generation AI apply a sorting algorithm.

[0041] The organizing unit can adjust the order of organizing based on the creation date of the documents when organizing. The creation date of the documents includes, but is not limited to, the most recent documents, the oldest documents, and documents created within a specific period. For example, the organizing unit prioritizes organizing the most recent documents. The organizing unit can also organize older documents later. Furthermore, the organizing unit can organize documents created within a specific period all at once. For example, the organizing unit adjusts the order of organizing based on the creation date of the documents to efficiently organize information. This enables efficient information organization by adjusting the order of organizing based on the creation date of the documents. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can input the creation date of the documents into the generation AI and have the generation AI adjust the order of organizing.

[0042] The organizing unit can customize the organizing method based on the relevance of documents when organizing them. Document relevance includes, but is not limited to, similarity of content and related topics. For example, the organizing unit organizes documents related to the same project together. The organizing unit can also prioritize organizing documents related to past proposal history. Furthermore, the organizing unit can also organize documents created by the same person together. For example, the organizing unit customizes the organizing method based on the relevance of documents to efficiently organize information. Customizing the organizing method based on the relevance of documents enables efficient information organization. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can input the relevance of documents to a generation AI and have the generation AI customize the organizing method.

[0043] The determination unit can improve the accuracy of product judgment by referring to past proposal results when making a judgment. Past proposal results include, for example, the success rate of the proposal, the content of the proposal, etc., but are not limited to these examples. For example, the determination unit determines the current product based on products proposed successfully in the past. The determination unit can also determine the current product by avoiding products proposed unsuccessfully in the past. Furthermore, the determination unit can analyze past proposal results and determine the optimal product. For example, the determination unit can improve the accuracy of product judgment by referring to past proposal results. As a result, the accuracy of product judgment is improved by referring to past proposal results. Some or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or without AI. For example, the determination unit can input past proposal results into the generation AI and cause the generation AI to improve the accuracy of product judgment.

[0044] When making a judgment, the judgment unit can determine the product by taking into account the attribute information of the assigned company. The attribute information of the assigned company includes, for example, the company's size, industry, past transaction history, etc., but is not limited to these examples. The judgment unit, for example, determines the optimal product based on the assigned company's industry. The judgment unit can also determine the optimal product based on the assigned company's size. Furthermore, the judgment unit can determine the optimal product based on the assigned company's past transaction history. For example, the judgment unit determines the optimal product by taking into account the attribute information of the assigned company. In this way, the optimal product can be determined by taking into account the attribute information of the assigned company. Some or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input the attribute information of the assigned company into the generation AI and have the generation AI perform the product judgment.

[0045] When making a judgment, the judgment unit can judge a product by referring to market trends of the product. Market trends of the product include, but are not limited to, market growth rates and trends of competitors. For example, the judgment unit can judge a product that is in high demand based on current market trends. The judgment unit can also judge a product with future potential by referring to market trends. Furthermore, the judgment unit can determine a competitive product by taking into account the competitive situation in the market. For example, the judgment unit can judge the optimal product by referring to market trends of the product. In this way, a product that is in high demand can be determined by referring to market trends of the product. Some or all of the above-mentioned processing by the judgment unit can be performed, for example, using AI or without AI. For example, the judgment unit can input market trends of the product into a generation AI and have the generation AI execute a product judgment.

[0046] The judgment unit can improve the accuracy of the judgment by referring to literature related to the product when making a judgment. Literature related to the product includes, but is not limited to, technical literature and industry reports. For example, the judgment unit can make a judgment by referring to the latest research papers on the product. The judgment unit can also make a judgment by referring to patent information on the product. Furthermore, the judgment unit can make a judgment by referring to market reports on the product. For example, the judgment unit can improve the accuracy of the judgment by referring to literature related to the product. Thus, by referring to literature related to the product, the accuracy of the judgment is improved. Some or all of the above-described processing in the judgment unit can be performed, for example, using AI, or can be performed without using AI. For example, the judgment unit can input literature related to the product into the generation AI and cause the generation AI to improve the accuracy of the judgment.

[0047] The providing unit can adjust the level of detail of the provided information based on the importance of the product when providing it. The importance of the product includes, but is not limited to, the impact on the business and the urgency of the product. For example, the providing unit can provide detailed information for a product with high importance. The providing unit can also provide concise information for a product with low importance. Furthermore, the providing unit can prioritize information that can be provided quickly for a product with high urgency. For example, the providing unit can adjust the level of detail of the provided information based on the importance of the product to provide the product efficiently. This enables efficient product provision by adjusting the level of detail of the provided information based on the importance of the product. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the importance of the product to the generation AI and cause the generation AI to adjust the level of detail of the provided information.

[0048] The providing unit can apply different provision algorithms depending on the category of the product when providing the product. Product categories include, but are not limited to, technical products and business products. For example, the providing unit can apply an algorithm that provides detailed technical information to technical products. The providing unit can also apply an algorithm that provides consumer-oriented information to consumer goods products. Furthermore, the providing unit can apply an algorithm that provides detailed service content to service products. For example, the providing unit can apply an appropriate algorithm depending on the category of the product to efficiently provide the product. This enables efficient product provision by applying an appropriate algorithm depending on the category of the product. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the category of the product into the generation AI and cause the generation AI to apply the provision algorithm.

[0049] The providing unit can adjust the order of providing the products based on the relevance of the products when providing them. The relevance of the products includes, but is not limited to, similarity of content and related topics. For example, the providing unit can provide products of the same category consecutively. The providing unit can also prioritize providing products related to past proposal history. Furthermore, the providing unit can provide products proposed by the same person together. For example, the providing unit can adjust the order of providing the products based on the relevance of the products to efficiently provide the products. This enables efficient product provision by adjusting the order of providing the products based on the relevance of the products. Some or all of the above-described processing by the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the relevance of the products to a generation AI and cause the generation AI to adjust the order of providing the products.

[0050] The providing unit can improve the accuracy of the provision by referring to market trends of the product when providing it. Market trends of the product include, but are not limited to, market growth rates and trends of competitors. For example, the providing unit provides products that are in high demand based on current market trends. The providing unit can also provide products with future potential by referring to market trends. Furthermore, the providing unit can provide competitive products by taking into account the competitive situation in the market. For example, the providing unit can provide optimal products by referring to market trends of the product. This makes it possible to provide products that are in high demand by referring to market trends of the product. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input market trends of the product into the generation AI and cause the generation AI to improve the accuracy of the provision.

[0051] When responding to a question, the response unit can provide an optimal answer by referring to a past question history. The past question history includes, for example, the content of the question and the content of the answer, but is not limited to such examples. For example, if a similar question has been asked in the past, the response unit can provide an optimal answer based on the answer. The response unit can also extract related information from the past question history and provide an answer. Furthermore, the response unit can analyze the past question history and provide the most appropriate answer. For example, the response unit can provide an optimal answer by referring to the past question history. In this way, the optimal answer can be provided by referring to the past question history. Some or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input the past question history into a generation AI and cause the generation AI to provide an optimal answer.

[0052] The response unit can apply different response algorithms depending on the question category when responding to a question. Question categories include, but are not limited to, technical questions and business-related questions. For example, the response unit can apply an algorithm that provides detailed technical information to technical questions. For questions about commercial products, the response unit can also apply an algorithm that provides detailed information about the commercial products. For questions about services, the response unit can also apply an algorithm that provides detailed explanations of the services. For example, the response unit can apply an appropriate algorithm depending on the question category to efficiently respond to questions. This enables efficient responses by applying an appropriate algorithm depending on the question category. Some or all of the above-described processing in the response unit can be performed using, for example, AI, or without AI. For example, the response unit can input the question category to a generation AI and cause the generation AI to apply a response algorithm.

[0053] The response unit can adjust the order of responses based on the relevance of questions when responding to them. The relevance of questions includes, but is not limited to, similarity in content and related topics. For example, the response unit can respond to questions in the same category consecutively. The response unit can also prioritize questions related to past proposal history. Furthermore, the response unit can also respond to questions asked by the same person all at once. For example, the response unit can adjust the order of responses based on the relevance of questions to efficiently respond to questions. Adjusting the order of responses based on the relevance of questions enables efficient responses. Some or all of the above-described processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input the relevance of questions to a generation AI and have the generation AI adjust the order of responses.

[0054] The correspondence unit can improve the accuracy of the correspondence by referring to literature related to the question when responding. Literature related to the question includes, but is not limited to, technical literature, industry reports, etc. The correspondence unit can, for example, refer to the latest research papers related to the question when responding. The correspondence unit can also refer to patent information related to the question when responding. Furthermore, the correspondence unit can also refer to market reports related to the question when responding. For example, the correspondence unit can improve the accuracy of the correspondence by referring to literature related to the question. In this way, the accuracy of the correspondence is improved by referring to literature related to the question. Some or all of the above-mentioned processing in the correspondence unit can be performed, for example, using AI or without AI. For example, the correspondence unit can input literature related to the question into the generation AI and cause the generation AI to improve the accuracy of the correspondence.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] When reading a document, the reading unit can estimate the intention of the document's author and improve the accuracy of reading based on that intention. For example, if the author of a proposal emphasizes a particular point, that part will be read first. Also, if the author is comparing multiple proposals, the information being compared can be read in detail. Furthermore, if the author uses logical development to lead to a particular conclusion, the logical development can be read in an easy-to-understand manner. In this way, the accuracy of reading is improved by taking into account the intention of the document's author.

[0057] The organizer can analyze the success and failure factors of proposals based on the content of the documents, improving the accuracy of the organization. For example, commonalities between successful proposals can be extracted and organized as success factors. Commonalities between unsuccessful proposals can also be extracted and organized as failure factors. Furthermore, the organizer can compare the success and failure factors and organize areas for improvement in the proposals. In this way, the accuracy of the organization can be improved by analyzing the success and failure factors of proposals.

[0058] When determining which products to propose, the decision unit can improve the accuracy of the decision by taking into account the product's life cycle. For example, if the product is in the introduction stage, a proactive proposal can be made. Also, if the product is in the growth stage, a proposal can be made that differentiates the product from competitors. Furthermore, if the product is in the maturity stage, a proposal can be made that emphasizes cost reduction and efficiency. In this way, by taking the product's life cycle into consideration, the accuracy of proposals can be improved.

[0059] When providing products, the product delivery department can adjust the delivery method by taking into account the client's corporate culture. For example, for conservative companies, a delivery method that provides detailed data and evidence can be adopted. For innovative companies, a delivery method that emphasizes new ideas and technologies can be adopted. Furthermore, for global companies, a delivery method that includes multilingual support and international examples can be adopted. In this way, the product delivery method can be optimized by taking into account the client's corporate culture.

[0060] The support department can provide answers to questions from staff members by taking into account the background information of the question. For example, if the question is related to a past proposal, detailed background information on that proposal can be provided. Also, if the question is related to current market trends, the latest market data can be provided. Furthermore, if the question is related to a technical issue, detailed technical information and solutions can be provided. In this way, appropriate answers can be provided by taking into account the background information of the question.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The reading unit reads the document. Documents include proposals, proposal approval documents, reports, emails, etc. The reading unit uses scanning technology to digitize and read documents such as proposals and proposal approval documents. It can also directly read documents submitted in digital format. It can also read printed documents using OCR technology. For example, a proposal can be scanned with a high-resolution scanner and converted into text information using OCR technology. Digital documents submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. Step 2: The organizer analyzes the documents read by the reader and organizes the history of past proposals. The analysis is performed using text mining and natural language processing technology. For example, the organizer uses text mining technology to analyze the content of the documents and extract important information. It can also analyze the content of the documents and organize the history of past proposals using natural language processing technology. For example, it analyzes the content of proposals and the results of proposal approvals, and extracts and organizes important information. Step 3: The judgment unit determines which products to propose based on the information organized by the organization unit. The judgment is made using AI. For example, the judgment unit proposes the most suitable products based on the history of past proposals and the needs of the client company. AI can also be used to analyze products proposed in the past and their results, to propose the products that are best suited to the current situation. For example, an AI model can be used to input the organized information and output the most suitable products. Step 4: The provision unit provides the product determined by the determination unit. This provision is performed using AI. For example, the provision unit provides the determined product to the person in charge. The determined product can also be provided automatically using AI. For example, an AI model is used to input the determined product and output a provision method. Step 5: The response department responds to questions from the staff member. This is done using AI. For example, the response department responds to questions from the staff member by providing appropriate answers about the history of past proposals and the products to be proposed. It is also possible to automatically answer questions from the staff member using AI. For example, an AI model is used to input questions and output answers.

[0063] (Example 2) A handover chatbot system according to an embodiment of the present invention reads documents, organizes past proposal history, determines which products should be proposed, and responds to questions from staff. This handover chatbot system streamlines handover processes by reading documents such as proposals and proposal approvals for the target company and organizing the past proposal history. Furthermore, further efficiency can be achieved by having AI determine which products should be proposed simultaneously with the handover process. For example, the handover chatbot reads documents such as proposals and proposal approvals for the target company. At this time, the AI ​​analyzes the documents and organizes the past proposal history. For example, the AI ​​analyzes the contents of the proposal and the results of the proposal approval and extracts important information. This allows the staff performing the handover process to easily understand the past proposal history. Next, the AI ​​determines which products should be proposed simultaneously with the handover process. The AI ​​proposes the optimal products based on the past proposal history and the needs of the target company. For example, the AI ​​analyzes past proposals and their results to propose the products best suited to the current situation. This allows handover and proposal processes to be performed simultaneously, improving efficiency. Furthermore, the handover chatbot also responds to questions from the person in charge. For example, AI provides appropriate answers to questions about the history of past proposals or the products to be proposed. This allows the person in charge to quickly obtain the necessary information. This system not only improves the efficiency of the handover process, but also allows proposal work to be done simultaneously, improving overall work efficiency. For example, when a new person takes over, they can easily understand the history of past proposals and propose the most suitable products. In addition, since it can quickly respond to questions from the person in charge, it is expected that work will proceed smoothly. As a result, the handover chatbot system can efficiently read and analyze documents, organize the proposal history, determine and provide products, and respond to questions.

[0064] A handover chatbot system according to an embodiment includes a reading unit, a sorting unit, a determination unit, a providing unit, and a response unit. The reading unit reads documents. Examples of documents include, but are not limited to, proposals, proposal approvals, reports, and emails. The reading unit digitizes and reads documents such as proposals and proposal approvals using scanning technology. The reading unit can also directly read documents submitted in digital format. The reading unit can also read printed documents using OCR technology. For example, the reading unit scans a proposal with a high-resolution scanner and converts it into text information using OCR technology. Digital documents submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The sorting unit analyzes the documents read by the reading unit and organizes the history of past proposals. The analysis can be performed using, for example, text mining or natural language processing technology, but is not limited to these examples. For example, the sorting unit analyzes the content of the document and extracts important information using text mining technology. The sorting unit can also analyze the content of documents using natural language processing technology and organize the history of past proposals. For example, the sorting unit analyzes the content of proposals and the results of proposal approvals, extracting and organizing important information. The judgment unit determines which products to propose based on the information organized by the sorting unit. The judgment can be made, for example, using AI, but is not limited to this example. For example, the judgment unit can propose the optimal product based on the history of past proposals and the needs of the client company. The judgment unit can also use AI to analyze previously proposed products and their results and propose the product that is optimal for the current situation. For example, the judgment unit can use an AI model to input the organized information and output the optimal product. The provision unit provides the product determined by the judgment unit. The provision can be made, for example, using AI, but is not limited to this example. For example, the provision unit provides the determined product to the person in charge. The provision unit can also automatically provide the determined product using AI. For example, the provision unit can use an AI model to input the determined product and output a provision method. The response unit responds to questions from the person in charge.The response may be performed using, for example, AI, but is not limited to such an example. For example, the response unit may provide appropriate answers to questions from the person in charge about the history of past proposals and the products to be proposed. The response unit may also use AI to automatically respond to questions from the person in charge. For example, the response unit may use an AI model to input questions and output answers. This allows the handover chatbot system according to the embodiment to efficiently read and analyze documents, organize the history of proposals, determine and provide products, and respond to questions.

[0065] The reading unit can read a proposal or a proposal approval document. The proposal may include, but is not limited to, the purpose of the proposal, the content of the proposal, and the background of the proposal. The proposal approval may include, but is not limited to, the approval criteria and the approval process. For example, the reading unit may scan the proposal and save it as image data. The reading unit may then convert the image data into text data using OCR technology. The reading unit may also directly read a proposal submitted in digital format. For example, the reading unit may directly read a digital proposal submitted in a specific file format. The reading unit may also read a proposal approval document and analyze the results of the proposal and the approval criteria. For example, the reading unit may scan the proposal approval document and convert it into text information using OCR technology. This allows documents such as proposals and proposal approvals to be read efficiently. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without AI. For example, the reading unit can input the image data obtained by scanning a proposal or proposal approval document into the generation AI, and have the generation AI generate text data from the image data.

[0066] The organizer can analyze the loaded document and organize the past proposal history. Examples of the analysis include, but are not limited to, text mining and natural language processing. Examples of the past proposal history include, but are not limited to, the date and time of the proposal, the proposal content, and the proposal results. The organizer can, for example, use text mining technology to analyze the content of the document and extract important information. The organizer can also analyze the content of the document using natural language processing technology to organize the past proposal history. For example, the organizer can analyze the content of the proposal and the results of the proposal approval, extract and organize important information. The organizer can also calculate the success rate and failure rate of the proposal based on the past proposal history. For example, the organizer can calculate the success rate of the proposal based on the date and time of the proposal and the proposal content. This allows the past proposal history to be organized efficiently. Some or all of the above-described processing in the organizer can be performed using, for example, AI, or without AI. For example, the organizer can input the loaded document to a generation AI and have the generation AI organize the past proposal history.

[0067] The determination unit can determine which products to propose based on the organized information. Examples of the products to propose include, but are not limited to, products, services, and solutions. The determination unit can propose optimal products based on, for example, past proposal history and the needs of the client company. The determination unit can also use AI to analyze previously proposed products and their results to propose products that are optimal for the current situation. For example, the determination unit can input the organized information using an AI model and output optimal products. The determination unit can also determine products taking into account the attribute information of the client company. For example, the determination unit can determine optimal products based on the client company's industry and size. This allows for efficient determination of products to propose. Some or all of the above-described processing by the determination unit can be performed using, for example, AI, or without AI. For example, the determination unit can input the organized information to a generation AI and have the generation AI determine which products to propose.

[0068] The providing unit can provide the determined product. Examples of the product include, but are not limited to, products, services, and solutions. The providing unit, for example, provides the determined product to a person in charge. The providing unit can also automatically provide the determined product using AI. For example, the providing unit uses an AI model to input the determined product and output a provision method. The providing unit can also adjust the level of detail of the provision based on the importance of the product. For example, detailed information can be provided for products with high importance, and concise information can be provided for products with low importance. This allows the determined product to be provided efficiently. Some or all of the above-described processing in the providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the providing unit can input the determined product to a generation AI and cause the generation AI to provide the product.

[0069] The response unit can respond to questions from the staff. Questions include, but are not limited to, technical questions and business questions. For example, the response unit provides appropriate answers to questions from the staff, such as about the history of past proposals and the products to be proposed. The response unit can also automatically answer questions from the staff using AI. For example, the response unit inputs questions and outputs answers using an AI model. The response unit can also provide optimal answers by referring to past question history. For example, if a similar question has been asked in the past, the response unit can provide optimal answers based on those answers. This allows for quick responses to questions from the staff. Some or all of the above-described processing in the response unit may be performed using AI, or may be performed without using AI. For example, the response unit can input questions from the staff to a generation AI and have the generation AI execute an optimal answer.

[0070] The reading unit can estimate a user's emotions and adjust the timing of document reading based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. For example, if the user is feeling stressed, the reading unit temporarily delays document reading and resumes reading at a time when the user is able to relax. Furthermore, if the user is concentrating, the reading unit can immediately begin document reading to efficiently acquire information. Furthermore, if the user is tired, the reading unit can prioritize document summaries so that they can be read in a short time. For example, the reading unit can monitor the user's emotions in real time and adjust the timing of document reading according to changes in emotions. This allows for efficient information acquisition by adjusting the timing of document reading according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or without AI. For example, the reading unit can input user emotion data into the generation AI and cause the generation AI to adjust the timing of document reading.

[0071] The reading unit can determine the reading priority based on the document type and importance during reading. Examples of document types include, but are not limited to, proposals, reports, and emails. Examples of document importance include, but are not limited to, business impact and urgency. The reading unit prioritizes reading important documents, such as proposals and proposal approval documents. The reading unit can also postpone documents with lower importance, such as daily reports and memos. Furthermore, the reading unit can prioritize reading documents with higher urgency for quicker response. For example, the reading unit determines the priority based on the document type and importance and prioritizes reading important documents. Thus, by prioritizing documents based on the document type and importance, important documents can be prioritized for reading. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or without AI. For example, the reading unit can input the document type and importance to the generation AI and have the generation AI determine the reading priority.

[0072] The reading unit can apply different reading algorithms depending on the document format and language during reading. Examples of document formats include, but are not limited to, PDF, Word, and Excel. Examples of document languages ​​include, but are not limited to, Japanese, English, and Chinese. For example, the reading unit applies a text extraction algorithm to a PDF document to read it. The reading unit can also apply a translation algorithm to a document written in English or another language to read it. Furthermore, the reading unit can also apply a handwriting recognition algorithm to a handwritten document to read it. For example, the reading unit applies an appropriate algorithm depending on the document format and language to efficiently read the document. This enables efficient reading by applying an appropriate algorithm depending on the document format and language. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input the document format and language to the generation AI and cause the generation AI to apply a reading algorithm.

[0073] The reading unit can estimate the user's emotions and determine the priority of documents to be read based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of document priority include, but are not limited to, importance and urgency. For example, if the user is stressed, the reading unit postpones documents of low importance. Furthermore, if the user is relaxed, the reading unit can prioritize documents of high importance. Furthermore, if the user is in a hurry, the reading unit can prioritize documents of high urgency. For example, the reading unit monitors the user's emotions in real time and determines the priority of documents according to changes in emotions. This enables efficient information acquisition by determining the priority of documents according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit may input user emotion data into the generation AI and have the generation AI determine the priority of documents.

[0074] The reading unit can improve the accuracy of reading by taking into account the attribute information of the document creator during reading. The attribute information of the document creator includes, for example, the creator's job title, field of expertise, etc., but is not limited to these examples. For example, if the document creator is an expert, the reading unit accurately reads technical terms. Furthermore, if the document creator is a novice, the reading unit can prioritize reading concise expressions. Furthermore, if the document creator is busy, the reading unit can prioritize reading important points. For example, the reading unit improves the accuracy of reading by taking into account the attribute information of the document creator. Thus, by taking into account the attribute information of the document creator, the accuracy of reading is improved. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input the attribute information of the document creator into the generation AI and cause the generation AI to improve the accuracy of reading.

[0075] The reading unit can adjust the reading order based on the relevance of the documents during reading. Examples of document relevance include, but are not limited to, content similarity and related topics. For example, the reading unit sequentially reads documents related to the same project. The reading unit can also prioritize reading documents related to past proposal history. Furthermore, the reading unit can also read documents created by the same person all at once. For example, the reading unit adjusts the reading order based on the relevance of the documents to efficiently acquire information. By adjusting the reading order based on the relevance of the documents, efficient information acquisition becomes possible. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input the relevance of the documents to a generation AI and have the generation AI adjust the reading order.

[0076] The organizing unit can estimate the user's emotions and adjust the organizing method based on the estimated user's emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of organizing methods include, but are not limited to, categorization and order of importance. For example, the organizing unit applies a simple organizing method when the user is stressed. Furthermore, the organizing unit can apply an organizing method that includes detailed information when the user is relaxed. Furthermore, the organizing unit can apply an organizing method that focuses on the main points when the user is in a hurry. For example, the organizing unit monitors the user's emotions in real time and adjusts the organizing method according to changes in emotions. This enables efficient information organization by adjusting the organizing method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or without AI. For example, the organizing unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the organizing method.

[0077] The organizing unit can extract important information based on the content of the document during organizing, thereby improving the accuracy of the organizing. The content of the document includes, for example, the proposal content of a proposal and the result of the proposal approval, but is not limited to these examples. For example, the organizing unit extracts and organizes important proposal content from a proposal. The organizing unit can also extract the result of the proposal approval and organize it in association with past proposal history. Furthermore, the organizing unit can extract keywords from a document and organize related information. For example, the organizing unit analyzes the content of a document, extracts important information, and organizes it. This improves the accuracy of the organizing by extracting important information based on the content of the document. Some or all of the above-mentioned processing in the organizing unit may be performed, for example, using AI, or may be performed without AI. For example, the organizing unit can input the content of a document to a generation AI and have the generation AI extract and organize important information.

[0078] The organizing unit can apply different organizing algorithms depending on the document category during organizing. Document categories include, but are not limited to, proposals, proposal approvals, reports, and emails. For example, the organizing unit can apply an algorithm that organizes documents based on proposal content to proposals. The organizing unit can also apply an algorithm that organizes documents based on approval results to proposal approvals. Furthermore, the organizing unit can apply an algorithm that organizes documents based on report content to daily reports. For example, the organizing unit can apply an appropriate algorithm depending on the document category to efficiently organize information. This enables efficient information organization by applying an appropriate algorithm depending on the document category. Some or all of the above-mentioned processing in the organizing unit can be performed using, for example, AI, or without AI. For example, the organizing unit can input the document category to a generation AI and have the generation AI apply an organizing algorithm.

[0079] The organizing unit can estimate the user's emotions and determine the organization priority based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of organization priority include, but are not limited to, importance and urgency. For example, when the user is stressed, the organizing unit postpones less important information. Furthermore, when the user is relaxed, the organizing unit can prioritize more important information. Furthermore, when the user is in a hurry, the organizing unit can prioritize more urgent information. For example, the organizing unit monitors the user's emotions in real time and determines the organization priority according to changes in emotions. This enables efficient information organization by determining the organization priority according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the organizing unit may be performed using, for example, an AI, or without an AI. For example, the organizing unit can input the user's emotional data into the generating AI and have the generating AI determine the priorities for organizing.

[0080] The organizing unit can adjust the order of organizing based on the creation date of the documents when organizing. The creation date of the documents includes, but is not limited to, the most recent documents, the oldest documents, and documents created within a specific period. For example, the organizing unit prioritizes organizing the most recent documents. The organizing unit can also organize older documents later. Furthermore, the organizing unit can organize documents created within a specific period all at once. For example, the organizing unit adjusts the order of organizing based on the creation date of the documents to efficiently organize information. This enables efficient information organization by adjusting the order of organizing based on the creation date of the documents. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can input the creation date of the documents into the generation AI and have the generation AI adjust the order of organizing.

[0081] The organizing unit can customize the organizing method based on the relevance of documents when organizing them. Examples of document relevance include, but are not limited to, similarity of content and related topics. For example, the organizing unit organizes documents related to the same project together. The organizing unit can also prioritize organizing documents related to past proposal history. Furthermore, the organizing unit can also organize documents created by the same person together. For example, the organizing unit customizes the organizing method based on the relevance of documents to efficiently organize information. Customizing the organizing method based on the relevance of documents enables efficient information organization. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can input the relevance of documents to a generation AI and have the generation AI customize the organizing method.

[0082] The determination unit can estimate the user's emotions and adjust product evaluation criteria based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of product evaluation criteria include, but are not limited to, demand, cost, and profit margin. For example, the determination unit applies simple evaluation criteria when the user is stressed. The determination unit can also apply detailed evaluation criteria when the user is relaxed. Furthermore, the determination unit can apply criteria that enable quick judgment when the user is in a hurry. For example, the determination unit monitors the user's emotions in real time and adjusts the product evaluation criteria according to changes in emotions. This enables efficient product evaluation by adjusting the product evaluation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the determination unit may be performed using, for example, AI, or without AI. For example, the judgment unit can input user emotion data into the generation AI and cause the generation AI to adjust the judgment criteria for the product.

[0083] The determination unit can improve the accuracy of product judgment by referring to past proposal results when making a judgment. Past proposal results include, for example, the success rate of the proposal, the content of the proposal, etc., but are not limited to these examples. For example, the determination unit determines the current product based on products proposed successfully in the past. The determination unit can also determine the current product by avoiding products proposed unsuccessfully in the past. Furthermore, the determination unit can analyze past proposal results and determine the optimal product. For example, the determination unit can improve the accuracy of product judgment by referring to past proposal results. As a result, the accuracy of product judgment is improved by referring to past proposal results. Some or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or without AI. For example, the determination unit can input past proposal results into the generation AI and cause the generation AI to improve the accuracy of product judgment.

[0084] When making a judgment, the judgment unit can determine the product by taking into account the attribute information of the assigned company. The attribute information of the assigned company includes, for example, the company's size, industry, past transaction history, etc., but is not limited to these examples. The judgment unit, for example, determines the optimal product based on the assigned company's industry. The judgment unit can also determine the optimal product based on the assigned company's size. Furthermore, the judgment unit can determine the optimal product based on the assigned company's past transaction history. For example, the judgment unit determines the optimal product by taking into account the attribute information of the assigned company. In this way, the optimal product can be determined by taking into account the attribute information of the assigned company. Some or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input the attribute information of the assigned company into the generation AI and have the generation AI perform the product judgment.

[0085] The determination unit can estimate the user's emotions and prioritize products based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of product priorities include, but are not limited to, importance and urgency. For example, if the user is stressed, the determination unit postpones products of lower importance. Furthermore, if the user is relaxed, the determination unit can prioritize products of higher importance. Furthermore, if the user is in a hurry, the determination unit can prioritize products of higher urgency. For example, the determination unit monitors the user's emotions in real time and prioritizes products according to changes in emotions. This enables efficient product selection by prioritizing products according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit may input user emotion data into the generation AI and have the generation AI determine the priority of the products.

[0086] When making a judgment, the judgment unit can judge a product by referring to market trends of the product. Market trends of the product include, but are not limited to, market growth rates and trends of competitors. For example, the judgment unit can judge a product that is in high demand based on current market trends. The judgment unit can also judge a product with future potential by referring to market trends. Furthermore, the judgment unit can determine a competitive product by taking into account the competitive situation in the market. For example, the judgment unit can judge the optimal product by referring to market trends of the product. In this way, a product that is in high demand can be determined by referring to market trends of the product. Some or all of the above-mentioned processing by the judgment unit can be performed, for example, using AI or without AI. For example, the judgment unit can input market trends of the product into a generation AI and have the generation AI execute a product judgment.

[0087] The judgment unit can improve the accuracy of the judgment by referring to literature related to the product when making a judgment. Literature related to the product includes, but is not limited to, technical literature and industry reports. For example, the judgment unit can make a judgment by referring to the latest research papers on the product. The judgment unit can also make a judgment by referring to patent information on the product. Furthermore, the judgment unit can make a judgment by referring to market reports on the product. For example, the judgment unit can improve the accuracy of the judgment by referring to literature related to the product. Thus, by referring to literature related to the product, the accuracy of the judgment is improved. Some or all of the above-described processing in the judgment unit can be performed, for example, using AI, or can be performed without using AI. For example, the judgment unit can input literature related to the product into the generation AI and cause the generation AI to improve the accuracy of the judgment.

[0088] The providing unit can estimate a user's emotions and adjust the product delivery method based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of product delivery methods include, but are not limited to, online delivery and face-to-face delivery. For example, the providing unit applies a simple delivery method when the user is stressed. Furthermore, the providing unit can apply a delivery method that includes detailed information when the user is relaxed. Furthermore, the providing unit can apply a quick delivery method when the user is in a hurry. For example, the providing unit monitors the user's emotions in real time and adjusts the product delivery method according to changes in emotions. This enables efficient product delivery by adjusting the product delivery method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or without AI. For example, the providing unit can input user emotion data into the generating AI and have the generating AI adjust the method of providing the product.

[0089] The providing unit can adjust the level of detail of the provided information based on the importance of the product when providing it. The importance of the product includes, but is not limited to, the impact on the business and the urgency of the product. For example, the providing unit can provide detailed information for a product with high importance. The providing unit can also provide concise information for a product with low importance. Furthermore, the providing unit can prioritize information that can be provided quickly for a product with high urgency. For example, the providing unit can adjust the level of detail of the provided information based on the importance of the product to provide the product efficiently. This enables efficient product provision by adjusting the level of detail of the provided information based on the importance of the product. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the importance of the product to the generation AI and cause the generation AI to adjust the level of detail of the provided information.

[0090] The providing unit can apply different provision algorithms depending on the category of the product when providing the product. Product categories include, but are not limited to, technical products and business products. For example, the providing unit can apply an algorithm that provides detailed technical information to technical products. The providing unit can also apply an algorithm that provides consumer-oriented information to consumer goods products. Furthermore, the providing unit can apply an algorithm that provides detailed service content to service products. For example, the providing unit can apply an appropriate algorithm depending on the category of the product to efficiently provide the product. This enables efficient product provision by applying an appropriate algorithm depending on the category of the product. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the category of the product into the generation AI and cause the generation AI to apply the provision algorithm.

[0091] The providing unit can estimate a user's emotions and determine the order in which products are provided based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of product provision orders include, but are not limited to, importance and urgency. For example, if the user is stressed, the providing unit postpones providing products of lower importance. Furthermore, if the user is relaxed, the providing unit can prioritize providing products of higher importance. Furthermore, if the user is in a hurry, the providing unit can prioritize providing products of higher urgency. For example, the providing unit monitors the user's emotions in real time and determines the order in which products are provided based on changes in emotions. This enables efficient product provision by determining the order in which products are provided based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input user emotion data to the generating AI and have the generating AI determine the order in which the products are provided.

[0092] The providing unit can adjust the order of providing the products based on the relevance of the products when providing them. The relevance of the products includes, but is not limited to, similarity of content and related topics. For example, the providing unit can provide products of the same category consecutively. The providing unit can also prioritize providing products related to past proposal history. Furthermore, the providing unit can provide products proposed by the same person together. For example, the providing unit can adjust the order of providing the products based on the relevance of the products to efficiently provide the products. This enables efficient product provision by adjusting the order of providing the products based on the relevance of the products. Some or all of the above-described processing by the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the relevance of the products to a generation AI and cause the generation AI to adjust the order of providing the products.

[0093] The providing unit can improve the accuracy of the provision by referring to market trends of the product when providing it. Market trends of the product include, but are not limited to, market growth rates and trends of competitors. For example, the providing unit provides products that are in high demand based on current market trends. The providing unit can also provide products with future potential by referring to market trends. Furthermore, the providing unit can provide competitive products by taking into account the competitive situation in the market. For example, the providing unit can provide optimal products by referring to market trends of the product. This makes it possible to provide products that are in high demand by referring to market trends of the product. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input market trends of the product into the generation AI and cause the generation AI to improve the accuracy of the provision.

[0094] The response unit can estimate the user's emotions and adjust the response method to the question based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, anger, etc. Examples of response methods to the question include, but are not limited to, online responses and face-to-face responses. For example, the response unit can provide a simple and quick response when the user is stressed. The response unit can also provide an answer with detailed information when the user is relaxed. Furthermore, the response unit can provide a quick answer when the user is in a hurry. For example, the response unit can monitor the user's emotions in real time and adjust the response method to the question according to changes in emotions. This enables efficient responses by adjusting the response method to the question according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the response unit can be performed using, for example, an AI or without an AI. For example, the response unit can input the user's emotional data into the generation AI and have the generation AI adjust how it responds to questions.

[0095] When responding to a question, the response unit can provide an optimal answer by referring to a past question history. The past question history includes, for example, the content of the question and the content of the answer, but is not limited to such examples. For example, if a similar question has been asked in the past, the response unit can provide an optimal answer based on the answer. The response unit can also extract related information from the past question history and provide an answer. Furthermore, the response unit can analyze the past question history and provide the most appropriate answer. For example, the response unit can provide an optimal answer by referring to the past question history. In this way, the optimal answer can be provided by referring to the past question history. Some or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input the past question history into a generation AI and cause the generation AI to provide an optimal answer.

[0096] The response unit can apply different response algorithms depending on the question category when responding to a question. Question categories include, but are not limited to, technical questions and business-related questions. For example, the response unit can apply an algorithm that provides detailed technical information to technical questions. For questions about commercial products, the response unit can also apply an algorithm that provides detailed information about the commercial products. For questions about services, the response unit can also apply an algorithm that provides detailed explanations of the services. For example, the response unit can apply an appropriate algorithm depending on the question category to efficiently respond to questions. This enables efficient responses by applying an appropriate algorithm depending on the question category. Some or all of the above-described processing in the response unit can be performed using, for example, AI, or without AI. For example, the response unit can input the question category to a generation AI and cause the generation AI to apply a response algorithm.

[0097] The response unit can estimate the user's emotions and determine the order in which to respond to questions based on the estimated user emotions. Examples of user emotions include, but are not limited to, joy, sadness, and anger. Examples of the order in which to respond to questions include, but are not limited to, importance and urgency. For example, if the user is stressed, the response unit postpones questions of lower importance. Furthermore, if the user is relaxed, the response unit can prioritize questions of higher importance. Furthermore, if the user is in a hurry, the response unit can prioritize questions of higher urgency. For example, the response unit monitors the user's emotions in real time and determines the order in which to respond to questions based on changes in emotions. This enables efficient responses by determining the order in which to respond to questions based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit may input user emotion data to the generation AI and have the generation AI determine the order in which to respond to questions.

[0098] The response unit can adjust the order of responses based on the relevance of questions when responding to them. The relevance of questions includes, but is not limited to, similarity in content and related topics. For example, the response unit can respond to questions in the same category consecutively. The response unit can also prioritize questions related to past proposal history. Furthermore, the response unit can also respond to questions asked by the same person all at once. For example, the response unit can adjust the order of responses based on the relevance of questions to efficiently respond to questions. Adjusting the order of responses based on the relevance of questions enables efficient responses. Some or all of the above-described processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can input the relevance of questions to a generation AI and have the generation AI adjust the order of responses.

[0099] The correspondence unit can improve the accuracy of the correspondence by referring to literature related to the question when responding. Literature related to the question includes, but is not limited to, technical literature, industry reports, etc. The correspondence unit can, for example, refer to the latest research papers related to the question when responding. The correspondence unit can also refer to patent information related to the question when responding. Furthermore, the correspondence unit can also refer to market reports related to the question when responding. For example, the correspondence unit can improve the accuracy of the correspondence by referring to literature related to the question. In this way, the accuracy of the correspondence is improved by referring to literature related to the question. Some or all of the above-mentioned processing in the correspondence unit can be performed, for example, using AI or without AI. For example, the correspondence unit can input literature related to the question into the generation AI and cause the generation AI to improve the accuracy of the correspondence. === Hard Collateral 1-1 === Each of the multiple elements, including the reading unit, organizing unit, determining unit, providing unit, and responding unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the smart device 14 and reads a document. The organizing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the read document and organizes past proposal history. The determining unit is realized by the specific processing unit 290 of the data processing device 12 and determines which product to propose based on the organized information. The providing unit is realized by the control unit 46A of the smart device 14 and provides the determined product to the person in charge. The responding unit is realized by the control unit 46A of the smart device 14 and provides appropriate answers to questions from the person in charge. === Hard Collateral 1-2 === Each of the multiple elements, including the reading unit, organizing unit, determining unit, providing unit, and responding unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the smart glasses 214 and reads a document. The organizing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the read document and organizes past proposal history. The determining unit is realized by the specific processing unit 290 of the data processing device 12 and determines which product to propose based on the organized information. The providing unit is realized by the control unit 46A of the smart glasses 214 and provides the determined product to the person in charge. The responding unit is realized by the control unit 46A of the smart glasses 214 and provides appropriate answers to questions from the person in charge. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reading unit, organizing unit, determining unit, providing unit, and responding unit is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the headset terminal 314 and reads a document. The organizing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the read document and organizes past proposal history. The determining unit is realized by the specific processing unit 290 of the data processing device 12 and determines which products to propose based on the organized information. The providing unit is realized by the control unit 46A of the headset terminal 314 and provides the determined products to the person in charge. The responding unit is realized by the control unit 46A of the headset terminal 314 and provides appropriate answers to questions from the person in charge. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reading unit, organizing unit, determination unit, providing unit, and response unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reading unit is realized by the computer 36 of the robot 414 and reads a document. The organizing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the read document and organizes past proposal history. The determination unit is realized by the specific processing unit 290 of the data processing device 12 and determines which products to propose based on the organized information. The providing unit is realized by the control unit 46A of the robot 414 and provides the determined products to the person in charge. The response unit is realized by the control unit 46A of the robot 414 and provides appropriate answers to questions from the person in charge.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] When reading a document, the reading unit can estimate the intention of the document's author and improve the accuracy of reading based on that intention. For example, if the author of a proposal emphasizes a particular point, that part will be read first. Also, if the author is comparing multiple proposals, the information being compared can be read in detail. Furthermore, if the author uses logical development to lead to a particular conclusion, the logical development can be read in an easy-to-understand manner. In this way, the accuracy of reading is improved by taking into account the intention of the document's author.

[0102] The organizer can analyze the success and failure factors of proposals based on the content of the documents, improving the accuracy of the organization. For example, commonalities between successful proposals can be extracted and organized as success factors. Commonalities between unsuccessful proposals can also be extracted and organized as failure factors. Furthermore, the organizer can compare the success and failure factors and organize areas for improvement in the proposals. In this way, the accuracy of the organization can be improved by analyzing the success and failure factors of proposals.

[0103] When determining which products to propose, the decision unit can improve the accuracy of the decision by taking into account the product's life cycle. For example, if the product is in the introduction stage, a proactive proposal can be made. Also, if the product is in the growth stage, a proposal can be made that differentiates the product from competitors. Furthermore, if the product is in the maturity stage, a proposal can be made that emphasizes cost reduction and efficiency. In this way, by taking the product's life cycle into consideration, the accuracy of proposals can be improved.

[0104] When providing products, the product delivery department can adjust the delivery method by taking into account the client's corporate culture. For example, for conservative companies, a delivery method that provides detailed data and evidence can be adopted. For innovative companies, a delivery method that emphasizes new ideas and technologies can be adopted. Furthermore, for global companies, a delivery method that includes multilingual support and international examples can be adopted. In this way, the product delivery method can be optimized by taking into account the client's corporate culture.

[0105] The support department can provide answers to questions from staff members by taking into account the background information of the question. For example, if the question is related to a past proposal, detailed background information on that proposal can be provided. Also, if the question is related to current market trends, the latest market data can be provided. Furthermore, if the question is related to a technical issue, detailed technical information and solutions can be provided. In this way, appropriate answers can be provided by taking into account the background information of the question.

[0106] The reading unit can estimate the user's emotions and adjust the document reading order based on the estimated user emotions. For example, if the user is feeling stressed, documents of low importance can be postponed. Also, if the user is relaxed, documents of high importance can be read with priority. Furthermore, if the user is in a hurry, documents of high urgency can be read with top priority. In this way, adjusting the document reading order according to the user's emotions enables efficient information acquisition.

[0107] The organizing unit can estimate the user's emotions and adjust the organizing method based on the estimated user's emotions. For example, if the user is feeling stressed, a simple organizing method can be applied. If the user is relaxed, an organizing method including detailed information can be applied. Furthermore, if the user is in a hurry, an organizing method that focuses on the main points can be applied. In this way, by adjusting the organizing method according to the user's emotions, efficient information organization is possible.

[0108] The judgment unit can estimate the user's emotions and adjust the product judgment criteria based on the estimated user emotions. For example, if the user is feeling stressed, simple judgment criteria can be applied. If the user is relaxed, detailed judgment criteria can be applied. Furthermore, if the user is in a hurry, criteria that allow for quick judgment can be applied. In this way, by adjusting the product judgment criteria according to the user's emotions, efficient product judgment is possible.

[0109] The provision unit can estimate the user's emotions and adjust the method of providing the product based on the estimated user's emotions. For example, if the user is feeling stressed, a simple method of providing the product can be applied. If the user is relaxed, a method of providing the product that includes detailed information can be applied. Furthermore, if the user is in a hurry, a method that can provide the product quickly can be applied. This allows for efficient product provision by adjusting the method of providing the product according to the user's emotions.

[0110] The response unit can estimate the user's emotions and adjust the response method to the question based on the estimated user's emotions. For example, if the user is feeling stressed, a simple and quick response can be provided. If the user is relaxed, an answer including detailed information can be provided. Furthermore, if the user is in a hurry, an answer that focuses on the main points can be provided. This allows for efficient responses by adjusting the response method to the question according to the user's emotions.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The reading unit reads the document. Documents include proposals, proposal approval documents, reports, emails, etc. The reading unit uses scanning technology to digitize and read documents such as proposals and proposal approval documents. It can also directly read documents submitted in digital format. It can also read printed documents using OCR technology. For example, a proposal can be scanned with a high-resolution scanner and converted into text information using OCR technology. Digital documents submitted in a specific file format can be directly read. OCR technology recognizes printed characters with high accuracy and converts them into digital text. Step 2: The organizer analyzes the documents read by the reader and organizes the history of past proposals. The analysis is performed using text mining and natural language processing technology. For example, the organizer uses text mining technology to analyze the content of the documents and extract important information. It can also analyze the content of the documents and organize the history of past proposals using natural language processing technology. For example, it analyzes the content of proposals and the results of proposal approvals, and extracts and organizes important information. Step 3: The judgment unit determines which products to propose based on the information organized by the organization unit. The judgment is made using AI. For example, the judgment unit proposes the most suitable products based on the history of past proposals and the needs of the client company. AI can also be used to analyze products proposed in the past and their results, to propose the products that are best suited to the current situation. For example, an AI model can be used to input the organized information and output the most suitable products. Step 4: The provision unit provides the product determined by the determination unit. This provision is performed using AI. For example, the provision unit provides the determined product to the person in charge. The determined product can also be provided automatically using AI. For example, an AI model is used to input the determined product and output a provision method. Step 5: The response department responds to questions from the staff member. This is done using AI. For example, the response department responds to questions from the staff member by providing appropriate answers about the history of past proposals and the products to be proposed. It is also possible to automatically answer questions from the staff member using AI. For example, an AI model is used to input questions and output answers.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 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.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0156] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0157] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0158] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0160] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0165] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0166] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0168] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0169] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0170] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0174] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0175] 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.

[0176] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0177] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0178] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0179] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0181] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0182] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0183] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0184] [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reading unit for reading a document; a compilation unit that analyzes the document read by the reading unit and compiles past proposal history; a determination unit that determines which products to propose based on the information organized by the organization unit; a providing unit that provides the commercial material determined by the determining unit; A response unit that responds to questions from the person in charge is provided. A system characterized by:

2. The reading unit Load a proposal or proposal approval document 2. The system of claim 1.

3. The organizing unit Analyze the loaded documents and organize the history of past proposals 2. The system of claim 1.

4. The determination unit Decide which products to propose based on organized information 2. The system of claim 1.

5. The providing unit Providing the judged products 2. The system of claim 1.

6. The corresponding part is Responding to questions from staff 2. The system of claim 1.

7. The reading unit Estimate user emotions and adjust document loading timing based on the estimated user emotions 2. The system of claim 1.

8. The reading unit Prioritize loading based on document type and importance during loading 2. The system of claim 1.

Images