system

Abstract

The system according to the embodiment aims to enable managers of small and medium-sized enterprises to find appropriate experts to efficiently solve business issues. [Solution] The system according to the embodiment includes a hearing unit, an analysis unit, a throwing unit, a generation unit, a sending unit, and an assignment unit. The hearing unit hears the consultation content of the manager. The analysis unit analyzes the consultation content heard by the hearing unit and generates an optimal expert to consult with. The throwing unit throws the consultation to multiple experts based on the expert list generated by the analysis unit. The generation unit aggregates responses from the experts and generates an optimal solution. The sending unit sends the solution generated by the generation unit to the manager. The assignment unit assigns the optimal expert when a request to implement the solution is made based on the solution sent by the sending unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies make it difficult for small and medium-sized business managers to find the right experts to efficiently solve a wide range of management issues, and there is room for improvement.

[0005] The system according to the embodiment aims to enable managers of small and medium-sized enterprises to find appropriate experts to efficiently solve business issues. [Means for solving the problem]

[0006] The system according to the embodiment includes a hearing unit, an analysis unit, a throwing unit, a generation unit, a sending unit, and an assignment unit. The hearing unit hears the consultation content of the manager. The analysis unit analyzes the consultation content heard by the hearing unit and generates an optimal expert to consult with. The throwing unit throws the consultation to multiple experts based on the expert list generated by the analysis unit. The generation unit aggregates responses from the experts and generates an optimal solution. The sending unit sends the solution generated by the generation unit to the manager. The assignment unit assigns the optimal expert when a request to implement the solution is made based on the solution sent by the sending unit. [Effects of the Invention]

[0007] The system according to the embodiment enables managers of small and medium-sized enterprises to efficiently find suitable experts to solve business issues. [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 consulting robot system according to an embodiment of the present invention uses a generation AI to solve a wide range of problems faced by managers of small and medium-sized enterprises. The consulting robot system listens to the manager's consultation, analyzes the consultation, and generates a recommendation for which expert to consult. The consultation is then sent to multiple experts based on the generated list of experts. The responses from the experts are aggregated, and the generation AI generates an optimal solution. The generated solution is sent to the manager, and when the manager requests the solution to be implemented, the generation AI assigns the most appropriate expert. For example, the consulting robot system listens to the manager's consultation. The manager communicates their specific concerns and problems to the consulting robot. Various management-related consultations are possible, such as cash flow issues or sales strategy reviews. Next, the generation AI analyzes the manager's consultation. The generation AI analyzes the consultation and generates a recommendation for which expert to consult. For example, if the problem is cash flow issues, consulting a financial expert or an accountant would be appropriate. The generation AI generates a list of optimal experts based on the consultation content, and then sends the consultation to multiple experts based on that list. The generation AI aggregates the answers from experts and generates the optimal solution. The generation AI analyzes the answers from experts and generates the optimal solution. For example, based on answers from multiple experts, it generates measures to improve cash flow or proposals to revise sales strategies. The generated solution is sent to the management. Finally, when the management requests the solution to be implemented, the generation AI assigns the most suitable expert. The generation AI selects the experts needed to implement the solution and requests them. This allows the management to put the specific solution into action. As a result, the consulting robot system allows small and medium-sized business managers to receive expert advice even if they do not have the funds to hire a consultant. In addition, because the generation AI selects the most appropriate expert and generates a solution, managers can solve problems efficiently. For example, they can receive quick and accurate advice on various management issues, such as cash flow problems and sales strategy revisions.

[0029] A consulting robot system according to an embodiment includes a hearing unit, an analysis unit, a pitching unit, a generation unit, a sending unit, and an assignment unit. The hearing unit hears the manager's consultation content. The manager's consultation content may include, but is not limited to, business strategy, finance, marketing, etc. The hearing unit, for example, records the manager's specific worries and problems in detail and sends them to the generation AI. The analysis unit uses the generation AI to analyze the consultation content heard by the hearing unit and generate an optimal expert to consult with. For example, the generation AI analyzes the consultation content and generates a list of optimal experts. The pitching unit pitches the consultation to multiple experts based on the expert list generated by the analysis unit. For example, the pitching unit sends the consultation to the experts via email or chat. The generation unit uses the generation AI to aggregate responses from the experts and generate an optimal solution. For example, the generation AI analyzes the responses from the experts and generates an optimal solution. The sending unit sends the solution generated by the generation unit to the manager. For example, the sending unit sends the solution by email or mail. The assignment unit assigns the most suitable expert when a request for solution implementation is received based on the solution sent by the sending unit. For example, the assignment unit selects an expert required for solution implementation and makes a request to that expert. This enables the consulting robot system according to the embodiment to efficiently hear, analyze, submit, generate, send, and assign the consultation content of the manager.

[0030] The analysis unit can refer to a database of experts and select an expert that is most suitable for the consultation content. The expert database includes, for example, but is not limited to, the expert's profile, skill set, past performance, etc. The analysis unit can refer to the database of experts and select an expert that is most suitable for the consultation content. For example, the analysis unit can select an expert depending on the consultation content, such as a financial expert or an accountant. The analysis unit can also periodically update the expert database and select an expert based on the latest information. This allows the optimal expert to be selected by referring to the expert database.

[0031] The generation unit can analyze the answers from the experts and generate an optimal solution. The generation unit, for example, uses a generation AI to analyze the answers from the experts. For example, the generation unit generates an optimal solution based on answers from multiple experts. The generation unit can also use an algorithm that integrates answers from experts and derives an optimal solution. For example, the generation unit generates an optimal solution using a statistical method or a machine learning algorithm. In this way, the optimal solution can be generated by analyzing the answers from the experts.

[0032] The assignment department can select the experts required to implement the solution and request the experts. The assignment department, for example, uses a generation AI to select the experts required to implement the solution. For example, the assignment department selects experts with the skills and experience required to implement the solution. The assignment department can also refer to a database of experts to select the most suitable expert. For example, the assignment department selects the most suitable expert based on the expert's past performance and evaluation. In this way, by selecting the experts required to implement the solution and making the request, the solution can be implemented smoothly.

[0033] The generation unit can use an algorithm that integrates answers from multiple experts and derives an optimal solution. The generation unit can integrate answers from multiple experts using, for example, a generation AI. For example, the generation unit can use statistical methods or machine learning algorithms to derive an optimal solution. The generation unit can also analyze answers from experts and develop an algorithm that generates an optimal solution. For example, the generation unit uses an algorithm that derives an optimal solution based on answers from experts. This makes it possible to generate a more accurate solution by integrating answers from multiple experts.

[0034] The company has a monitoring department. The monitoring department monitors the implementation status of the solution. For example, the monitoring department periodically checks the progress of the solution and reports to management as necessary. The monitoring department can also monitor the implementation status of the solution in real time. For example, the monitoring department monitors the implementation status of the solution in real time and responds immediately if a problem occurs. The monitoring department can also evaluate the implementation status of the solution and identify areas for improvement. For example, the monitoring department evaluates the implementation status of the solution, identifies areas for improvement, and provides feedback to management. In this way, by monitoring the implementation status of the solution, it is possible to understand the progress of implementation.

[0035] The hearing department can analyze the manager's past consultation history and select the optimal hearing method. The hearing department can, for example, use generative AI to analyze the manager's past consultation history. For example, the hearing department can select the optimal hearing method based on the content of past consultations and feedback. The hearing department can also prepare related questions based on the manager's past consultation history. For example, the hearing department can prioritize selecting hearing methods that the manager has preferred in the past. The hearing department can also improve the hearing method by referring to the manager's past feedback. In this way, a more appropriate hearing method can be selected by analyzing the past consultation history.

[0036] The interview department can customize the questions based on the manager's current work situation and areas of interest. The interview department, for example, uses generative AI to analyze the manager's current work situation and areas of interest. For example, the interview department customizes the questions based on the manager's current projects and work progress. The interview department can also prepare specific questions based on the manager's areas of interest. For example, the interview department can ask questions related to the project the manager is currently working on. The interview department can also adjust the difficulty and level of detail of the questions depending on the manager's work situation. This allows for more effective interviews by customizing the questions based on the manager's work situation and areas of interest.

[0037] The hearing unit can select the optimal hearing means depending on the manager's input method. The hearing unit can, for example, use generative AI to analyze the manager's input method. For example, if the manager prefers voice input, the hearing unit can conduct a voice hearing. Also, if the manager prefers text input, the hearing unit can conduct a text-based hearing. Furthermore, if the manager prefers explanations using images, the hearing unit can conduct a hearing using images. This improves convenience for the manager by selecting the optimal hearing means depending on the input method.

[0038] The interview department can prioritize relevant questions by taking into account the manager's geographic location information. The interview department can, for example, use generative AI to analyze the manager's geographic location information. For example, if the manager is active in a specific area, the interview department can ask questions related to that area. Also, if the manager is on a business trip, the interview department can ask questions related to the business trip destination. Furthermore, if the manager is working remotely from home, the interview department can ask questions related to the work done at home. In this way, by taking geographic location information into account, more relevant questions can be asked.

[0039] The interview department can analyze the manager's social media activity and ask relevant questions. The interview department can, for example, use generative AI to analyze the manager's social media activity. For example, the interview department can ask questions related to topics mentioned by the manager on social media. The interview department can also ask questions about areas of interest based on the manager's social media activity. Furthermore, the interview department can ask relevant questions based on the activity of the manager's friends and followers on social media. In this way, by analyzing social media activity, it is possible to ask questions based on the manager's interests.

[0040] The hearing department can customize the hearing method by reflecting the manager's past feedback. The hearing department, for example, uses generative AI to analyze the manager's past feedback. For example, the hearing department customizes the hearing method based on the past feedback. The hearing department can also improve the content of the questions by referring to the manager's past feedback. Furthermore, the hearing department can also adjust the way the hearing proceeds by referring to the manager's past feedback. In this way, by reflecting past feedback, a more effective hearing method can be selected.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the consultation content. The analysis unit, for example, uses a generation AI to evaluate the importance of the consultation content. For example, the analysis unit evaluates the importance of the consultation content based on the scope of impact, urgency, economic impact, etc. The analysis unit can also adjust the level of detail of the analysis based on the importance of the consultation content. For example, the analysis unit performs a detailed analysis for important consultation content. The analysis unit can also perform a concise analysis for general consultation content. Furthermore, the analysis unit can also perform a quick analysis for consultation content with a high level of urgency. In this way, by adjusting the level of detail of the analysis based on the importance, it is possible to provide appropriate analysis results.

[0042] The analysis unit can apply different analysis algorithms depending on the category of the consultation content. The analysis unit, for example, uses a generative AI to classify the category of the consultation content. For example, the analysis unit classifies the consultation content by industry or type of problem. The analysis unit can also apply different analysis algorithms depending on the category of the consultation content. For example, the analysis unit can apply a finance-specialized analysis algorithm to a consultation about cash flow. The analysis unit can also apply a marketing-specialized analysis algorithm to a consultation about sales strategy. Furthermore, the analysis unit can apply a human resources-specialized analysis algorithm to a consultation about human resources issues. In this way, by applying an analysis algorithm according to the category, it is possible to provide more accurate analysis results.

[0043] The analysis unit can improve the accuracy of the analysis by referring to the manager's past consultation results. The analysis unit, for example, uses generative AI to analyze the manager's past consultation results. For example, the analysis unit adjusts the analysis algorithm based on success stories and failure stories. The analysis unit can also improve the accuracy of the analysis by referring to the manager's past feedback. For example, the analysis unit compares the content and results of the manager's past consultations to identify areas for improvement in the analysis. Furthermore, the analysis unit can develop an algorithm that improves the accuracy of the analysis based on the manager's past consultation results. In this way, the accuracy of the analysis can be improved by referring to the past consultation results.

[0044] The analysis unit can determine the priority of analysis based on the time when the consultation content was submitted. The analysis unit, for example, uses a generation AI to evaluate the time when the consultation content was submitted. For example, the analysis unit evaluates the time when the consultation content was submitted based on the submission date, deadline, urgency, etc. The analysis unit can also determine the priority of analysis based on the time when the consultation content was submitted. For example, the analysis unit prioritizes analyzing consultation content with a high level of urgency. The analysis unit can also prioritize analyzing consultation content that was submitted earlier. Furthermore, the analysis unit can quickly analyze consultation content that was submitted more recently. In this way, by determining the priority based on the time of submission, consultation content with a high level of urgency can be quickly analyzed.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the consultation content. The analysis unit, for example, uses a generative AI to evaluate the relevance of the consultation content. For example, the analysis unit evaluates the relevance of the consultation content based on the similarity of the content, related topics, etc. The analysis unit can also adjust the order of analysis based on the relevance of the consultation content. For example, the analysis unit prioritizes analysis of highly relevant consultation content. The analysis unit can also postpone less relevant consultation content. Furthermore, the analysis unit can optimize the order of analysis based on the relevance of the consultation content. In this way, by adjusting the order of analysis based on relevance, highly relevant consultation content can be analyzed preferentially.

[0046] The analysis unit can adjust the use of technical terms in the analysis according to the manager's level of expertise. The analysis unit can, for example, use generative AI to evaluate the manager's level of expertise. For example, the analysis unit evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The analysis unit can also adjust the use of technical terms in the analysis according to the manager's level of expertise. For example, the analysis unit uses a lot of technical terms if the manager's level of expertise is high. The analysis unit can also avoid technical terms if the manager's level of expertise is low. Furthermore, the analysis unit can adjust the way the analysis results are presented according to the manager's level of expertise. In this way, by adjusting the use of technical terms according to the level of expertise, it is possible to provide analysis results that are easy for managers to understand.

[0047] The throwing unit can adjust the throwing order based on the importance of the consultation content. The throwing unit, for example, uses a generation AI to evaluate the importance of the consultation content. For example, the throwing unit evaluates the importance of the consultation content based on the scope of impact, urgency, economic impact, etc. The throwing unit can also adjust the throwing order based on the importance of the consultation content. For example, the throwing unit prioritizes throwing important consultation content. The throwing unit can also postpone general consultation content. Furthermore, the throwing unit can quickly throw consultation content with a high level of urgency. In this way, by adjusting the throwing order based on importance, important consultation content can be handled with priority.

[0048] The throwing unit can apply different throwing methods depending on the category of the consultation content. The throwing unit, for example, uses a generation AI to classify the category of the consultation content. For example, the throwing unit classifies the consultation content by industry or type of problem. The throwing unit can also apply different throwing methods depending on the category of the consultation content. For example, the throwing unit can apply a finance-specialized throwing method to a consultation about cash flow. The throwing unit can also apply a marketing-specialized throwing method to a consultation about sales strategy. Furthermore, the throwing unit can also apply a human resources-specialized throwing method to a consultation about human resources issues. This makes it possible to provide more appropriate consultations by applying a throwing method according to the category.

[0049] The Throwing Unit can adjust the throwing order based on when the consultation content was submitted. The Throwing Unit, for example, uses a generation AI to evaluate when the consultation content was submitted. For example, the Throwing Unit evaluates when the consultation content was submitted based on the submission date, deadline, urgency, etc. The Throwing Unit can also adjust the throwing order based on when the consultation content was submitted. For example, the Throwing Unit prioritizes throwing consultation content with a high level of urgency. The Throwing Unit can also prioritize throwing consultation content that was submitted earlier. Furthermore, the Throwing Unit can quickly throw consultation content that was submitted more recently. In this way, by adjusting the throwing order based on the submission time, consultation content with a high level of urgency can be handled quickly.

[0050] The throwing unit can adjust the throwing order based on the relevance of the consultation content. The throwing unit, for example, uses a generative AI to evaluate the relevance of the consultation content. For example, the throwing unit evaluates the relevance of the consultation content based on the similarity of the content, related topics, etc. The throwing unit can also adjust the throwing order based on the relevance of the consultation content. For example, the throwing unit prioritizes throwing highly relevant consultation content. The throwing unit can also postpone less relevant consultation content. Furthermore, the throwing unit can optimize the throwing order based on the relevance of the consultation content. In this way, by adjusting the throwing order based on relevance, highly relevant consultation content can be handled preferentially.

[0051] The Throwing Department can adjust the content of the message to be thrown according to the manager's level of expertise. The Throwing Department, for example, uses generative AI to evaluate the manager's level of expertise. For example, the Throwing Department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The Throwing Department can also adjust the content to be thrown according to the manager's level of expertise. For example, if the manager's level of expertise is high, the Throwing Department can throw specialized content. Also, if the manager's level of expertise is low, the Throwing Department can throw easy-to-understand content. Furthermore, the Throwing Department can adjust the level of detail of the content to be thrown according to the manager's level of expertise. In this way, by adjusting the content to be thrown according to the level of expertise, it is possible to provide content that is easy for the manager to understand.

[0052] The generation unit can adjust the level of detail of the solution based on the importance of the answer from the expert. The generation unit, for example, uses a generation AI to evaluate the importance of the answer from the expert. For example, the generation unit evaluates the importance of the answer from the expert based on the effectiveness, feasibility, cost, etc. of the answer. The generation unit can also adjust the level of detail of the solution based on the importance of the answer from the expert. For example, the generation unit generates a detailed solution based on an important answer. The generation unit can also generate a concise solution based on a general answer. Furthermore, the generation unit can quickly generate a solution based on an answer with a high urgency. In this way, by adjusting the level of detail of the solution based on the importance, it is possible to provide an appropriate solution.

[0053] The generation unit can apply different generation algorithms depending on the category of the consultation content. The generation unit, for example, uses a generation AI to classify the category of the consultation content. For example, the generation unit classifies the consultation content by industry or type of problem. The generation unit can also apply different generation algorithms depending on the category of the consultation content. For example, the generation unit can apply a generation algorithm specialized in finance to a consultation about cash flow. The generation unit can also apply a generation algorithm specialized in marketing to a consultation about sales strategy. Furthermore, the generation unit can apply a generation algorithm specialized in human resources to a consultation about human resources issues. In this way, by applying a generation algorithm according to the category, it is possible to provide a more accurate solution.

[0054] The generation unit can improve the accuracy of solutions by referring to the results of past consultations by the manager. The generation unit, for example, uses a generation AI to analyze the results of past consultations by the manager. For example, the generation unit adjusts the generation algorithm based on success stories and failure stories. The generation unit can also improve the accuracy of solutions by referring to past feedback from the manager. For example, the generation unit compares the content and results of past consultations by the manager to identify areas for improvement in the generation. Furthermore, the generation unit can develop an algorithm that improves the accuracy of solutions based on the results of past consultations by the manager. In this way, the accuracy of solutions can be improved by referring to the results of past consultations.

[0055] The generation unit can determine the priority of solutions based on the timing of submission of answers from experts. The generation unit, for example, uses a generation AI to evaluate the timing of submission of answers from experts. For example, the generation unit evaluates the timing of submission of answers from experts based on the submission date, deadline, urgency, etc. The generation unit can also determine the priority of solutions based on the timing of submission of answers from experts. For example, the generation unit can preferentially reflect answers with high urgency in the solution. The generation unit can also preferentially reflect answers that were submitted earlier in the solution. Furthermore, the generation unit can quickly reflect answers that were submitted more recently in the solution. In this way, by determining the priority based on the submission time, solutions with high urgency can be provided quickly.

[0056] The generation unit can adjust the order of solutions based on the relevance of answers from experts. The generation unit, for example, uses a generation AI to evaluate the relevance of answers from experts. For example, the generation unit evaluates the relevance of answers from experts based on similarity of content, related topics, etc. The generation unit can also adjust the order of solutions based on the relevance of answers from experts. For example, the generation unit preferentially reflects highly relevant answers in the solutions. The generation unit can also postpone less relevant answers. Furthermore, the generation unit can optimize the order of solutions based on the relevance of the answers. As a result, by adjusting the order of solutions based on relevance, highly relevant solutions can be provided preferentially.

[0057] The generation unit can adjust the use of technical terms in the solution according to the manager's level of expertise. The generation unit, for example, uses a generation AI to evaluate the manager's level of expertise. For example, the generation unit evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The generation unit can also adjust the use of technical terms in the solution according to the manager's level of expertise. For example, the generation unit uses a lot of technical terms if the manager's level of expertise is high. The generation unit can also avoid technical terms if the manager's level of expertise is low. Furthermore, the generation unit can adjust the way the solution is expressed according to the manager's level of expertise. In this way, by adjusting the use of technical terms according to the level of expertise, it is possible to provide a solution that is easy for the manager to understand.

[0058] The sending unit can adjust the level of detail in the sending based on the importance of the solution. The sending unit, for example, uses a generative AI to evaluate the importance of the solution. For example, the sending unit evaluates the importance of the solution based on the effectiveness, feasibility, cost, etc. of the solution. The sending unit can also adjust the level of detail in the sending based on the importance of the solution. For example, the sending unit uses a detailed sending method for an important solution. The sending unit can also use a simple sending method for a general solution. Furthermore, the sending unit can use a quick sending method for a highly urgent solution. In this way, by adjusting the level of detail in the sending based on the importance, an appropriate sending method can be provided.

[0059] The sending department can apply different sending methods depending on the category of the solution. The sending department, for example, uses a generative AI to classify the category of solutions. For example, the sending department classifies solutions by industry or type of problem. The sending department can also apply different sending methods depending on the category of the solution. For example, the sending department can apply a sending method specialized for finance to a solution to cash flow. The sending department can also apply a sending method specialized for marketing to a solution to a sales strategy. Furthermore, the sending department can apply a sending method specialized for human resources to a solution to a human resources problem. In this way, more appropriate sending is possible by applying a sending method according to the category.

[0060] The sending department can improve the accuracy of sending by referring to the manager's past sending results. The sending department, for example, uses generative AI to analyze the manager's past sending results. For example, the sending department adjusts the sending method based on success stories and failure stories. The sending department can also improve the accuracy of sending by referring to the manager's past feedback. For example, the sending department compares the content and results of the manager's past sendings to identify areas for improvement in the sending method. Furthermore, the sending department can develop an algorithm to improve the accuracy of sending based on the manager's past sending results. In this way, the accuracy of sending can be improved by referring to past sending results.

[0061] The sending department can adjust the sending order based on the time when the solutions were submitted. The sending department, for example, uses a generative AI to evaluate the time when the solutions were submitted. For example, the sending department evaluates the time when the solutions were submitted based on the submission date, deadline, urgency, etc. The sending department can also adjust the sending order based on the time when the solutions were submitted. For example, the sending department can prioritize sending solutions with high urgency. The sending department can also prioritize sending solutions with older submission dates. Furthermore, the sending department can quickly send solutions with more recent submission dates. In this way, by adjusting the sending order based on the submission time, solutions with higher urgency can be sent quickly.

[0062] The sending unit can adjust the sending order based on the relevance of the solutions. The sending unit, for example, uses a generative AI to evaluate the relevance of the solutions. For example, the sending unit evaluates the relevance of the solutions based on the similarity of content, related topics, etc. The sending unit can also adjust the sending order based on the relevance of the solutions. For example, the sending unit prioritizes sending highly relevant solutions. The sending unit can also postpone solutions with low relevance. Furthermore, the sending unit can optimize the sending order based on the relevance of the solutions. In this way, by adjusting the sending order based on relevance, highly relevant solutions can be sent with priority.

[0063] The sending department can adjust the content to be sent according to the manager's level of expertise. The sending department, for example, uses a generative AI to evaluate the manager's level of expertise. For example, the sending department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The sending department can also adjust the content to be sent according to the manager's level of expertise. For example, if the manager's level of expertise is high, the sending department can send specialized content. Also, if the manager's level of expertise is low, the sending department can send easy-to-understand content. Furthermore, the sending department can adjust the level of detail of the content to be sent according to the manager's level of expertise. In this way, by adjusting the content to be sent according to the level of expertise, it is possible to provide content that is easy for the manager to understand.

[0064] The assignment unit can adjust the level of detail of the assignment based on the importance of the solution. The assignment unit can, for example, use a generative AI to evaluate the importance of the solution. For example, the assignment unit can evaluate the importance of the solution based on the effectiveness, feasibility, cost, etc. of the solution. The assignment unit can also adjust the level of detail of the assignment based on the importance of the solution. For example, the assignment unit can use a detailed assignment method for important solutions. The assignment unit can also use a simple assignment method for general solutions. Furthermore, the assignment unit can use a quick assignment method for solutions with high urgency. In this way, by adjusting the level of detail of the assignment based on the importance, it is possible to provide an appropriate assignment method.

[0065] The assignment department can apply different assignment methods depending on the category of the solution. The assignment department, for example, uses generative AI to classify the category of solutions. For example, the assignment department classifies solutions by industry or type of problem. The assignment department can also apply different assignment methods depending on the category of the solution. For example, the assignment department can apply a finance-specialized assignment method to a solution to cash flow. The assignment department can also apply a marketing-specialized assignment method to a solution to a sales strategy. Furthermore, the assignment department can apply a human resources-specialized assignment method to a solution to a human resources problem. This allows for more appropriate assignment by applying assignment methods according to the category.

[0066] The assignment department can improve the accuracy of assignments by referring to the manager's past assignment results. The assignment department, for example, uses generative AI to analyze the manager's past assignment results. For example, the assignment department adjusts the assignment method based on success and failure cases. The assignment department can also improve the accuracy of assignments by referring to the manager's past feedback. For example, the assignment department compares the manager's past assignment content and results to identify areas for improvement in the assignment method. Furthermore, the assignment department can develop an algorithm to improve the accuracy of assignments based on the manager's past assignment results. In this way, the accuracy of assignments can be improved by referring to past assignment results.

[0067] The assignment department can adjust the order of assignments based on the time when the solutions are submitted. The assignment department, for example, uses a generative AI to evaluate the time when the solutions are submitted. For example, the assignment department evaluates the time when the solutions are submitted based on the submission date, deadline, urgency, etc. The assignment department can also adjust the order of assignments based on the time when the solutions are submitted. For example, the assignment department can assign solutions with high urgency with priority. The assignment department can also assign solutions with older submissions with priority. Furthermore, the assignment department can quickly assign solutions with more recent submissions. In this way, by adjusting the order of assignments based on the submission time, solutions with higher urgency can be quickly assigned.

[0068] The assignment unit can adjust the order of assignments based on the relevance of the solutions. The assignment unit, for example, uses generative AI to evaluate the relevance of the solutions. For example, the assignment unit evaluates the relevance of the solutions based on the similarity of content, related topics, etc. The assignment unit can also adjust the order of assignments based on the relevance of the solutions. For example, the assignment unit assigns highly relevant solutions with priority. The assignment unit can also postpone less relevant solutions. Furthermore, the assignment unit can optimize the order of assignments based on the relevance of the solutions. In this way, by adjusting the order of assignments based on relevance, highly relevant solutions can be assigned with priority.

[0069] The assignment department can adjust the assignment content according to the manager's level of expertise. The assignment department, for example, uses generative AI to evaluate the manager's level of expertise. For example, the assignment department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The assignment department can also adjust the assignment content according to the manager's level of expertise. For example, if the manager's level of expertise is high, the assignment department can assign specialized content. Also, if the manager's level of expertise is low, the assignment department can assign easy-to-understand content. Furthermore, the assignment department can adjust the level of detail of the assignment content according to the manager's level of expertise. In this way, by adjusting the assignment content according to the level of expertise, it is possible to provide content that is easy for the manager to understand.

[0070] The monitoring unit can adjust the level of monitoring detail based on the importance of the implementation status of the solution. The monitoring unit, for example, uses a generative AI to evaluate the importance of the implementation status of the solution. For example, the monitoring unit evaluates the importance of the implementation status of the solution based on the effectiveness, feasibility, cost, etc. of the solution. The monitoring unit can also adjust the level of monitoring detail based on the importance of the implementation status of the solution. For example, the monitoring unit uses a detailed monitoring method for important solutions. The monitoring unit can also use a simple monitoring method for general solutions. Furthermore, the monitoring unit can use a quick monitoring method for solutions with high urgency. In this way, by adjusting the level of monitoring detail based on the importance, it is possible to provide an appropriate monitoring method.

[0071] The monitoring department can apply different monitoring methods depending on the category of the solution. The monitoring department, for example, uses generative AI to classify the category of the solution. For example, the monitoring department classifies the solutions by industry or type of problem. The monitoring department can also apply different monitoring methods depending on the category of the solution. For example, the monitoring department can apply a finance-specialized monitoring method to a solution to cash flow. The monitoring department can also apply a marketing-specialized monitoring method to a solution to a sales strategy. Furthermore, the monitoring department can apply a human resources-specialized monitoring method to a solution to a human resources problem. In this way, more appropriate monitoring is possible by applying monitoring methods according to the category.

[0072] The monitoring department can improve the accuracy of monitoring by referring to the manager's past monitoring results. The monitoring department, for example, uses generative AI to analyze the manager's past monitoring results. For example, the monitoring department adjusts the monitoring method based on success and failure cases. The monitoring department can also improve the accuracy of monitoring by referring to the manager's past feedback. For example, the monitoring department compares the manager's past monitoring content and results to identify areas for improvement in the monitoring method. Furthermore, the monitoring department can develop an algorithm to improve the accuracy of monitoring based on the manager's past monitoring results. In this way, the accuracy of monitoring can be improved by referring to past monitoring results.

[0073] The monitoring department can adjust the monitoring order based on the time when the solution was submitted. The monitoring department, for example, uses a generative AI to evaluate the time when the solution was submitted. For example, the monitoring department evaluates the time when the solution was submitted based on the submission date, deadline, urgency, etc. The monitoring department can also adjust the monitoring order based on the time when the solution was submitted. For example, the monitoring department prioritizes monitoring solutions with high urgency. The monitoring department can also prioritize monitoring solutions that were submitted earlier. Furthermore, the monitoring department can quickly monitor solutions that were submitted more recently. In this way, by adjusting the monitoring order based on the time when the solution was submitted, solutions with high urgency can be quickly monitored.

[0074] The monitoring unit can adjust the monitoring order based on the relevance of the solutions. The monitoring unit, for example, uses generative AI to evaluate the relevance of the solutions. For example, the monitoring unit evaluates the relevance of the solutions based on similarity of content, related topics, etc. The monitoring unit can also adjust the monitoring order based on the relevance of the solutions. For example, the monitoring unit prioritizes monitoring of highly relevant solutions. The monitoring unit can also postpone solutions with low relevance. Furthermore, the monitoring unit can optimize the monitoring order based on the relevance of the solutions. In this way, by adjusting the monitoring order based on relevance, highly relevant solutions can be monitored with priority.

[0075] The monitoring department can adjust the monitoring content according to the manager's level of expertise. The monitoring department, for example, uses generative AI to evaluate the manager's level of expertise. For example, the monitoring department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The monitoring department can also adjust the monitoring content according to the manager's level of expertise. For example, if the manager's level of expertise is high, the monitoring department will monitor specialized content. On the other hand, if the manager's level of expertise is low, the monitoring department can monitor content that is easy to understand. Furthermore, the monitoring department can adjust the level of detail of the monitoring content according to the manager's level of expertise. In this way, by adjusting the monitoring content according to the level of expertise, it is possible to provide content that is easy for the manager to understand.

[0076] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0077] The consulting robot system further includes a feedback unit. The feedback unit can collect feedback from the manager and use it to improve the system. For example, the feedback unit can collect how the manager felt about the provided solution. The feedback unit can also collect feedback from the manager about the results of implementing the solution. Furthermore, the feedback unit can collect the manager's opinions about the ease of use of the system and provide data to improve the usability of the system. This makes it possible to continuously improve the system through the feedback unit.

[0078] The generator can adjust the level of detail of the solution based on the importance of the answer from the expert. For example, the generator can generate a detailed solution based on an important answer. The generator can also generate a concise solution based on a general answer. Furthermore, the generator can quickly generate a solution based on an answer with a high urgency. In this way, by adjusting the level of detail of the solution based on the importance, it is possible to provide an appropriate solution.

[0079] The monitoring unit can adjust the level of detail of monitoring based on the importance of the implementation status of a solution. For example, the monitoring unit uses a detailed monitoring method for an important solution. The monitoring unit can also use a simple monitoring method for a general solution. Furthermore, the monitoring unit can also use a quick monitoring method for a highly urgent solution. In this way, by adjusting the level of detail of monitoring based on the importance, it is possible to provide an appropriate monitoring method.

[0080] The analysis unit can apply different analysis algorithms depending on the category of the consultation content. For example, the analysis unit can apply an analysis algorithm specialized in finance to a consultation about cash flow. The analysis unit can also apply an analysis algorithm specialized in marketing to a consultation about sales strategy. Furthermore, the analysis unit can also apply an analysis algorithm specialized in human resources to a consultation about human resources issues. In this way, by applying an analysis algorithm according to the category, it is possible to provide more accurate analysis results.

[0081] The sending unit can adjust the sending order based on the time of submission of the solutions. For example, the sending unit can send solutions with high urgency first. The sending unit can also send solutions with older submission dates first. Furthermore, the sending unit can quickly send solutions with more recent submission dates. In this way, by adjusting the sending order based on the time of submission, solutions with high urgency can be quickly sent.

[0082] The assignment department can apply different assignment methods depending on the category of the solution. For example, the assignment department can apply a finance-specialized assignment method to a solution to a cash flow problem. The assignment department can also apply a marketing-specialized assignment method to a solution to a sales strategy. Furthermore, the assignment department can apply a human resources-specialized assignment method to a solution to a human resources problem. In this way, applying an assignment method according to the category enables more appropriate assignment.

[0083] The processing flow of the first embodiment will be briefly explained below.

[0084] Step 1: The hearing department listens to the manager's concerns, including business strategy, finance, and marketing. The hearing department records the manager's specific concerns and problems in detail and sends them to the generation AI. Step 2: The analysis unit uses the generation AI to analyze the consultation content heard by the hearing unit and generate a list of the most suitable experts to consult. The generation AI analyzes the consultation content and generates a list of the most suitable experts. Step 3: The submission unit submits the consultation to multiple experts based on the expert list generated by the analysis unit. The submission unit sends the consultation to the experts via email or chat. Step 4: The generation unit uses the generation AI to aggregate the answers from the experts and generate the optimal solution. The generation AI analyzes the answers from the experts and generates the optimal solution. Step 5: The sending section sends the solution generated by the generating section to the manager. The sending section sends the solution by email or mail. Step 6: The Assignment Department assigns the most suitable expert based on the solution sent by the Sending Department when a request for solution implementation is made. The Assignment Department selects the expert required for solution implementation and makes a request to that expert.

[0085] (Example 2) A consulting robot system according to an embodiment of the present invention uses a generation AI to solve a wide range of problems faced by managers of small and medium-sized enterprises. The consulting robot system listens to the manager's consultation, analyzes the consultation, and generates a recommendation for which expert to consult. The consultation is then sent to multiple experts based on the generated list of experts. The responses from the experts are aggregated, and the generation AI generates an optimal solution. The generated solution is sent to the manager, and when the manager requests the solution to be implemented, the generation AI assigns the most appropriate expert. For example, the consulting robot system listens to the manager's consultation. The manager communicates their specific concerns and problems to the consulting robot. Various management-related consultations are possible, such as cash flow issues or sales strategy reviews. Next, the generation AI analyzes the manager's consultation. The generation AI analyzes the consultation and generates a recommendation for which expert to consult. For example, if the problem is cash flow issues, consulting a financial expert or an accountant would be appropriate. The generation AI generates a list of optimal experts based on the consultation content, and then sends the consultation to multiple experts based on that list. The generation AI aggregates the answers from experts and generates the optimal solution. The generation AI analyzes the answers from experts and generates the optimal solution. For example, based on answers from multiple experts, it generates measures to improve cash flow or proposals to revise sales strategies. The generated solution is sent to the management. Finally, when the management requests the solution to be implemented, the generation AI assigns the most suitable expert. The generation AI selects the experts needed to implement the solution and requests them. This allows the management to put the specific solution into action. As a result, the consulting robot system allows small and medium-sized business managers to receive expert advice even if they do not have the funds to hire a consultant. In addition, because the generation AI selects the most appropriate expert and generates a solution, managers can solve problems efficiently. For example, they can receive quick and accurate advice on various management issues, such as cash flow problems and sales strategy revisions.

[0086] A consulting robot system according to an embodiment includes a hearing unit, an analysis unit, a pitching unit, a generation unit, a sending unit, and an assignment unit. The hearing unit hears the manager's consultation content. The manager's consultation content may include, but is not limited to, business strategy, finance, marketing, etc. The hearing unit, for example, records the manager's specific worries and problems in detail and sends them to the generation AI. The analysis unit uses the generation AI to analyze the consultation content heard by the hearing unit and generate an optimal expert to consult with. For example, the generation AI analyzes the consultation content and generates a list of optimal experts. The pitching unit pitches the consultation to multiple experts based on the expert list generated by the analysis unit. For example, the pitching unit sends the consultation to the experts via email or chat. The generation unit uses the generation AI to aggregate responses from the experts and generate an optimal solution. For example, the generation AI analyzes the responses from the experts and generates an optimal solution. The sending unit sends the solution generated by the generation unit to the manager. For example, the sending unit sends the solution by email or mail. The assignment unit assigns the most suitable expert when a request for solution implementation is received based on the solution sent by the sending unit. For example, the assignment unit selects an expert required for solution implementation and makes a request to that expert. This enables the consulting robot system according to the embodiment to efficiently hear, analyze, submit, generate, send, and assign the consultation content of the manager.

[0087] The analysis unit can refer to a database of experts and select an expert that is most suitable for the consultation content. The expert database includes, for example, but is not limited to, the expert's profile, skill set, past performance, etc. The analysis unit can refer to the database of experts and select an expert that is most suitable for the consultation content. For example, the analysis unit can select an expert depending on the consultation content, such as a financial expert or an accountant. The analysis unit can also periodically update the expert database and select an expert based on the latest information. This allows the optimal expert to be selected by referring to the expert database.

[0088] The generation unit can analyze the answers from the experts and generate an optimal solution. The generation unit, for example, uses a generation AI to analyze the answers from the experts. For example, the generation unit generates an optimal solution based on answers from multiple experts. The generation unit can also use an algorithm that integrates answers from experts and derives an optimal solution. For example, the generation unit generates an optimal solution using a statistical method or a machine learning algorithm. In this way, the optimal solution can be generated by analyzing the answers from the experts.

[0089] The assignment department can select the experts required to implement the solution and request the experts. The assignment department, for example, uses a generation AI to select the experts required to implement the solution. For example, the assignment department selects experts with the skills and experience required to implement the solution. The assignment department can also refer to a database of experts to select the most suitable expert. For example, the assignment department selects the most suitable expert based on the expert's past performance and evaluation. In this way, by selecting the experts required to implement the solution and making the request, the solution can be implemented smoothly.

[0090] The generation unit can use an algorithm that integrates answers from multiple experts and derives an optimal solution. The generation unit can integrate answers from multiple experts using, for example, a generation AI. For example, the generation unit can use statistical methods or machine learning algorithms to derive an optimal solution. The generation unit can also analyze answers from experts and develop an algorithm that generates an optimal solution. For example, the generation unit uses an algorithm that derives an optimal solution based on answers from experts. This makes it possible to generate a more accurate solution by integrating answers from multiple experts.

[0091] The company has a monitoring department. The monitoring department monitors the implementation status of the solution. For example, the monitoring department periodically checks the progress of the solution and reports to management as necessary. The monitoring department can also monitor the implementation status of the solution in real time. For example, the monitoring department monitors the implementation status of the solution in real time and responds immediately if a problem occurs. The monitoring department can also evaluate the implementation status of the solution and identify areas for improvement. For example, the monitoring department evaluates the implementation status of the solution, identifies areas for improvement, and provides feedback to management. In this way, by monitoring the implementation status of the solution, it is possible to understand the progress of implementation.

[0092] The hearing department can estimate the manager's emotions and adjust the timing of the hearing based on the estimated manager's emotions. The hearing department, for example, uses generative AI to estimate the manager's emotions. For example, the hearing department estimates the manager's emotions using facial expression recognition or voice analysis. The hearing department can also adjust the timing of the hearing based on the manager's emotions. For example, if the manager is feeling stressed, the hearing department can conduct the hearing at a time when the manager is able to relax. Furthermore, if the manager is busy, the hearing department can conduct the hearing efficiently in a short amount of time. Furthermore, if the manager is relaxed, the hearing department can conduct a detailed hearing. This makes it possible to adjust the timing of the hearing according to the manager's emotions, thereby enabling more effective hearings.

[0093] The hearing department can analyze the manager's past consultation history and select the optimal hearing method. The hearing department can, for example, use generative AI to analyze the manager's past consultation history. For example, the hearing department can select the optimal hearing method based on the content of past consultations and feedback. The hearing department can also prepare related questions based on the manager's past consultation history. For example, the hearing department can prioritize selecting hearing methods that the manager has preferred in the past. The hearing department can also improve the hearing method by referring to the manager's past feedback. In this way, a more appropriate hearing method can be selected by analyzing the past consultation history.

[0094] The interview department can customize the questions based on the manager's current work situation and areas of interest. The interview department, for example, uses generative AI to analyze the manager's current work situation and areas of interest. For example, the interview department customizes the questions based on the manager's current projects and work progress. The interview department can also prepare specific questions based on the manager's areas of interest. For example, the interview department can ask questions related to the project the manager is currently working on. The interview department can also adjust the difficulty and level of detail of the questions depending on the manager's work situation. This allows for more effective interviews by customizing the questions based on the manager's work situation and areas of interest.

[0095] The hearing unit can select the optimal hearing means depending on the manager's input method. The hearing unit can, for example, use generative AI to analyze the manager's input method. For example, if the manager prefers voice input, the hearing unit can conduct a voice hearing. Also, if the manager prefers text input, the hearing unit can conduct a text-based hearing. Furthermore, if the manager prefers explanations using images, the hearing unit can conduct a hearing using images. This improves convenience for the manager by selecting the optimal hearing means depending on the input method.

[0096] The hearing department can estimate the manager's emotions and determine the priority of the interview content based on the estimated manager's emotions. The hearing department, for example, uses generative AI to estimate the manager's emotions. For example, the hearing department can estimate the manager's emotions using facial expression recognition or voice analysis. The hearing department can also determine the priority of the interview content based on the manager's emotions. For example, if the manager is feeling stressed, the hearing department can prioritize important questions. Also, if the manager is relaxed, the hearing department can ask detailed questions. Furthermore, if the manager is in a hurry, the hearing department can ask questions that focus on the main points. In this way, by determining the priority of the interview content according to the manager's emotions, important content can be prioritized.

[0097] The interview department can prioritize relevant questions by taking into account the manager's geographic location information. The interview department can, for example, use generative AI to analyze the manager's geographic location information. For example, if the manager is active in a specific area, the interview department can ask questions related to that area. Also, if the manager is on a business trip, the interview department can ask questions related to the business trip destination. Furthermore, if the manager is working remotely from home, the interview department can ask questions related to the work done at home. In this way, by taking geographic location information into account, more relevant questions can be asked.

[0098] The interview department can analyze the manager's social media activity and ask relevant questions. The interview department can, for example, use generative AI to analyze the manager's social media activity. For example, the interview department can ask questions related to topics mentioned by the manager on social media. The interview department can also ask questions about areas of interest based on the manager's social media activity. Furthermore, the interview department can ask relevant questions based on the activity of the manager's friends and followers on social media. In this way, by analyzing social media activity, it is possible to ask questions based on the manager's interests.

[0099] The hearing department can customize the hearing method by reflecting the manager's past feedback. The hearing department, for example, uses generative AI to analyze the manager's past feedback. For example, the hearing department customizes the hearing method based on the past feedback. The hearing department can also improve the content of the questions by referring to the manager's past feedback. Furthermore, the hearing department can also adjust the way the hearing proceeds by referring to the manager's past feedback. In this way, by reflecting past feedback, a more effective hearing method can be selected.

[0100] The analysis unit can estimate the manager's emotions and adjust the way the analysis is presented based on the estimated manager's emotions. The analysis unit, for example, uses generative AI to estimate the manager's emotions. For example, the analysis unit can estimate the manager's emotions using facial expression recognition or voice analysis. The analysis unit can also adjust the way the analysis is presented based on the manager's emotions. For example, if the manager is feeling stressed, the analysis unit uses a simple and easy-to-understand presentation method. If the manager is relaxed, the analysis unit can also provide detailed analysis results. Furthermore, if the manager is in a hurry, the analysis unit can provide analysis results that are concise. In this way, by adjusting the way the analysis is presented according to the manager's emotions, it is possible to provide analysis results that are easier to understand.

[0101] The analysis unit can adjust the level of detail of the analysis based on the importance of the consultation content. The analysis unit, for example, uses a generation AI to evaluate the importance of the consultation content. For example, the analysis unit evaluates the importance of the consultation content based on the scope of impact, urgency, economic impact, etc. The analysis unit can also adjust the level of detail of the analysis based on the importance of the consultation content. For example, the analysis unit performs a detailed analysis for important consultation content. The analysis unit can also perform a concise analysis for general consultation content. Furthermore, the analysis unit can also perform a quick analysis for consultation content with a high level of urgency. In this way, by adjusting the level of detail of the analysis based on the importance, it is possible to provide appropriate analysis results.

[0102] The analysis unit can apply different analysis algorithms depending on the category of the consultation content. The analysis unit, for example, uses a generative AI to classify the category of the consultation content. For example, the analysis unit classifies the consultation content by industry or type of problem. The analysis unit can also apply different analysis algorithms depending on the category of the consultation content. For example, the analysis unit can apply a finance-specialized analysis algorithm to a consultation about cash flow. The analysis unit can also apply a marketing-specialized analysis algorithm to a consultation about sales strategy. Furthermore, the analysis unit can apply a human resources-specialized analysis algorithm to a consultation about human resources issues. In this way, by applying an analysis algorithm according to the category, it is possible to provide more accurate analysis results.

[0103] The analysis unit can improve the accuracy of the analysis by referring to the manager's past consultation results. The analysis unit, for example, uses generative AI to analyze the manager's past consultation results. For example, the analysis unit adjusts the analysis algorithm based on success stories and failure stories. The analysis unit can also improve the accuracy of the analysis by referring to the manager's past feedback. For example, the analysis unit compares the content and results of the manager's past consultations to identify areas for improvement in the analysis. Furthermore, the analysis unit can develop an algorithm that improves the accuracy of the analysis based on the manager's past consultation results. In this way, the accuracy of the analysis can be improved by referring to the past consultation results.

[0104] The analysis unit can estimate the manager's emotions and adjust the length of the analysis based on the estimated manager's emotions. The analysis unit, for example, uses generative AI to estimate the manager's emotions. For example, the analysis unit can estimate the manager's emotions using facial expression recognition or voice analysis. The analysis unit can also adjust the length of the analysis based on the manager's emotions. For example, if the manager is feeling stressed, the analysis unit can perform a short, to-the-point analysis. If the manager is relaxed, the analysis unit can also perform a detailed analysis. Furthermore, if the manager is in a hurry, the analysis unit can perform a quick analysis. In this way, by adjusting the length of the analysis according to the manager's emotions, it is possible to provide analysis results of an appropriate length.

[0105] The analysis unit can determine the priority of analysis based on the time when the consultation content was submitted. The analysis unit, for example, uses a generation AI to evaluate the time when the consultation content was submitted. For example, the analysis unit evaluates the time when the consultation content was submitted based on the submission date, deadline, urgency, etc. The analysis unit can also determine the priority of analysis based on the time when the consultation content was submitted. For example, the analysis unit prioritizes analyzing consultation content with a high level of urgency. The analysis unit can also prioritize analyzing consultation content that was submitted earlier. Furthermore, the analysis unit can quickly analyze consultation content that was submitted more recently. In this way, by determining the priority based on the time of submission, consultation content with a high level of urgency can be quickly analyzed.

[0106] The analysis unit can adjust the order of analysis based on the relevance of the consultation content. The analysis unit, for example, uses a generative AI to evaluate the relevance of the consultation content. For example, the analysis unit evaluates the relevance of the consultation content based on the similarity of the content, related topics, etc. The analysis unit can also adjust the order of analysis based on the relevance of the consultation content. For example, the analysis unit prioritizes analysis of highly relevant consultation content. The analysis unit can also postpone less relevant consultation content. Furthermore, the analysis unit can optimize the order of analysis based on the relevance of the consultation content. In this way, by adjusting the order of analysis based on relevance, highly relevant consultation content can be analyzed preferentially.

[0107] The analysis unit can adjust the use of technical terms in the analysis according to the manager's level of expertise. The analysis unit can, for example, use generative AI to evaluate the manager's level of expertise. For example, the analysis unit evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The analysis unit can also adjust the use of technical terms in the analysis according to the manager's level of expertise. For example, the analysis unit uses a lot of technical terms if the manager's level of expertise is high. The analysis unit can also avoid technical terms if the manager's level of expertise is low. Furthermore, the analysis unit can adjust the way the analysis results are presented according to the manager's level of expertise. In this way, by adjusting the use of technical terms according to the level of expertise, it is possible to provide analysis results that are easy for managers to understand.

[0108] The throwing unit can estimate the manager's emotions and adjust the timing of pitching the consultation based on the estimated manager's emotions. The throwing unit, for example, uses generative AI to estimate the manager's emotions. For example, the throwing unit estimates the manager's emotions using facial expression recognition or voice analysis. The throwing unit can also adjust the timing of pitching the consultation based on the manager's emotions. For example, if the manager is feeling stressed, the throwing unit pitches the consultation at a time when the manager can relax. Furthermore, if the manager is busy, the throwing unit can pitch the consultation efficiently in a short amount of time. Furthermore, if the manager is relaxed, the throwing unit can pitch a detailed consultation. This allows for more effective consultations by adjusting the timing of pitching the consultation based on the manager's emotions.

[0109] The throwing unit can adjust the throwing order based on the importance of the consultation content. The throwing unit, for example, uses a generation AI to evaluate the importance of the consultation content. For example, the throwing unit evaluates the importance of the consultation content based on the scope of impact, urgency, economic impact, etc. The throwing unit can also adjust the throwing order based on the importance of the consultation content. For example, the throwing unit prioritizes throwing important consultation content. The throwing unit can also postpone general consultation content. Furthermore, the throwing unit can quickly throw consultation content with a high level of urgency. In this way, by adjusting the throwing order based on importance, important consultation content can be handled with priority.

[0110] The throwing unit can apply different throwing methods depending on the category of the consultation content. The throwing unit, for example, uses a generation AI to classify the category of the consultation content. For example, the throwing unit classifies the consultation content by industry or type of problem. The throwing unit can also apply different throwing methods depending on the category of the consultation content. For example, the throwing unit can apply a finance-specialized throwing method to a consultation about cash flow. The throwing unit can also apply a marketing-specialized throwing method to a consultation about sales strategy. Furthermore, the throwing unit can also apply a human resources-specialized throwing method to a consultation about human resources issues. This makes it possible to provide more appropriate consultations by applying a throwing method according to the category.

[0111] The throwing unit can estimate the manager's emotions and prioritize the content to be thrown based on the estimated manager's emotions. The throwing unit, for example, uses generative AI to estimate the manager's emotions. For example, the throwing unit estimates the manager's emotions using facial expression recognition or voice analysis. The throwing unit can also prioritize the content to be thrown based on the manager's emotions. For example, if the manager is feeling stressed, the throwing unit can prioritize important consultation content. Also, if the manager is relaxed, the throwing unit can throw detailed consultation content. Furthermore, if the manager is in a hurry, the throwing unit can throw consultation content that focuses on the main points. In this way, by prioritizing the content to be thrown according to the manager's emotions, important content can be thrown preferentially.

[0112] The Throwing Unit can adjust the throwing order based on when the consultation content was submitted. The Throwing Unit, for example, uses a generation AI to evaluate when the consultation content was submitted. For example, the Throwing Unit evaluates when the consultation content was submitted based on the submission date, deadline, urgency, etc. The Throwing Unit can also adjust the throwing order based on when the consultation content was submitted. For example, the Throwing Unit prioritizes throwing consultation content with a high level of urgency. The Throwing Unit can also prioritize throwing consultation content that was submitted earlier. Furthermore, the Throwing Unit can quickly throw consultation content that was submitted more recently. In this way, by adjusting the throwing order based on the submission time, consultation content with a high level of urgency can be handled quickly.

[0113] The throwing unit can adjust the throwing order based on the relevance of the consultation content. The throwing unit, for example, uses a generative AI to evaluate the relevance of the consultation content. For example, the throwing unit evaluates the relevance of the consultation content based on the similarity of the content, related topics, etc. The throwing unit can also adjust the throwing order based on the relevance of the consultation content. For example, the throwing unit prioritizes throwing highly relevant consultation content. The throwing unit can also postpone less relevant consultation content. Furthermore, the throwing unit can optimize the throwing order based on the relevance of the consultation content. In this way, by adjusting the throwing order based on relevance, highly relevant consultation content can be handled preferentially.

[0114] The Throwing Department can adjust the content of the message to be thrown according to the manager's level of expertise. The Throwing Department, for example, uses generative AI to evaluate the manager's level of expertise. For example, the Throwing Department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The Throwing Department can also adjust the content to be thrown according to the manager's level of expertise. For example, if the manager's level of expertise is high, the Throwing Department can throw specialized content. Also, if the manager's level of expertise is low, the Throwing Department can throw easy-to-understand content. Furthermore, the Throwing Department can adjust the level of detail of the content to be thrown according to the manager's level of expertise. In this way, by adjusting the content to be thrown according to the level of expertise, it is possible to provide content that is easy for the manager to understand.

[0115] The generation unit can estimate the manager's emotions and adjust the way the solution is expressed based on the estimated manager's emotions. The generation unit, for example, uses a generation AI to estimate the manager's emotions. For example, the generation unit estimates the manager's emotions using facial expression recognition or voice analysis. The generation unit can also adjust the way the solution is expressed based on the manager's emotions. For example, the generation unit can generate a simple and easy-to-understand solution if the manager is feeling stressed. The generation unit can also generate a detailed solution if the manager is relaxed. Furthermore, the generation unit can generate a solution that focuses on the main points if the manager is in a hurry. In this way, by adjusting the way the solution is expressed according to the manager's emotions, it is possible to provide a more understandable solution.

[0116] The generation unit can adjust the level of detail of the solution based on the importance of the answer from the expert. The generation unit, for example, uses a generation AI to evaluate the importance of the answer from the expert. For example, the generation unit evaluates the importance of the answer from the expert based on the effectiveness, feasibility, cost, etc. of the answer. The generation unit can also adjust the level of detail of the solution based on the importance of the answer from the expert. For example, the generation unit generates a detailed solution based on an important answer. The generation unit can also generate a concise solution based on a general answer. Furthermore, the generation unit can quickly generate a solution based on an answer with a high urgency. In this way, by adjusting the level of detail of the solution based on the importance, it is possible to provide an appropriate solution.

[0117] The generation unit can apply different generation algorithms depending on the category of the consultation content. The generation unit, for example, uses a generation AI to classify the category of the consultation content. For example, the generation unit classifies the consultation content by industry or type of problem. The generation unit can also apply different generation algorithms depending on the category of the consultation content. For example, the generation unit can apply a generation algorithm specialized in finance to a consultation about cash flow. The generation unit can also apply a generation algorithm specialized in marketing to a consultation about sales strategy. Furthermore, the generation unit can apply a generation algorithm specialized in human resources to a consultation about human resources issues. In this way, by applying a generation algorithm according to the category, it is possible to provide a more accurate solution.

[0118] The generation unit can improve the accuracy of solutions by referring to the results of past consultations by the manager. The generation unit, for example, uses a generation AI to analyze the results of past consultations by the manager. For example, the generation unit adjusts the generation algorithm based on success stories and failure stories. The generation unit can also improve the accuracy of solutions by referring to past feedback from the manager. For example, the generation unit compares the content and results of past consultations by the manager to identify areas for improvement in the generation. Furthermore, the generation unit can develop an algorithm that improves the accuracy of solutions based on the results of past consultations by the manager. In this way, the accuracy of solutions can be improved by referring to the results of past consultations.

[0119] The generation unit can estimate the manager's emotions and adjust the length of the solution based on the estimated manager's emotions. The generation unit estimates the manager's emotions using, for example, a generation AI. For example, the generation unit estimates the manager's emotions using facial expression recognition or voice analysis. The generation unit can also adjust the length of the solution based on the manager's emotions. For example, if the manager is feeling stressed, the generation unit generates a short and to-the-point solution. Also, if the manager is relaxed, the generation unit can generate a detailed solution. Furthermore, if the manager is in a hurry, the generation unit can quickly generate a solution. In this way, by adjusting the length of the solution according to the manager's emotions, a solution of appropriate length can be provided.

[0120] The generation unit can determine the priority of solutions based on the timing of submission of answers from experts. The generation unit, for example, uses a generation AI to evaluate the timing of submission of answers from experts. For example, the generation unit evaluates the timing of submission of answers from experts based on the submission date, deadline, urgency, etc. The generation unit can also determine the priority of solutions based on the timing of submission of answers from experts. For example, the generation unit can preferentially reflect answers with high urgency in the solution. The generation unit can also preferentially reflect answers that were submitted earlier in the solution. Furthermore, the generation unit can quickly reflect answers that were submitted more recently in the solution. In this way, by determining the priority based on the submission time, solutions with high urgency can be provided quickly.

[0121] The generation unit can adjust the order of solutions based on the relevance of answers from experts. The generation unit, for example, uses a generation AI to evaluate the relevance of answers from experts. For example, the generation unit evaluates the relevance of answers from experts based on similarity of content, related topics, etc. The generation unit can also adjust the order of solutions based on the relevance of answers from experts. For example, the generation unit preferentially reflects highly relevant answers in the solutions. The generation unit can also postpone less relevant answers. Furthermore, the generation unit can optimize the order of solutions based on the relevance of the answers. As a result, by adjusting the order of solutions based on relevance, highly relevant solutions can be provided preferentially.

[0122] The generation unit can adjust the use of technical terms in the solution according to the manager's level of expertise. The generation unit, for example, uses a generation AI to evaluate the manager's level of expertise. For example, the generation unit evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The generation unit can also adjust the use of technical terms in the solution according to the manager's level of expertise. For example, the generation unit uses a lot of technical terms if the manager's level of expertise is high. The generation unit can also avoid technical terms if the manager's level of expertise is low. Furthermore, the generation unit can adjust the way the solution is expressed according to the manager's level of expertise. In this way, by adjusting the use of technical terms according to the level of expertise, it is possible to provide a solution that is easy for the manager to understand.

[0123] The sending unit can estimate the manager's emotions and adjust the method of sending the solution based on the estimated manager's emotions. The sending unit, for example, uses generative AI to estimate the manager's emotions. For example, the sending unit can estimate the manager's emotions using facial expression recognition or voice analysis. The sending unit can also adjust the method of sending the solution based on the manager's emotions. For example, if the manager is feeling stressed, the sending unit can use a simple and easy-to-understand sending method. Also, if the manager is relaxed, the sending unit can use a detailed sending method. Furthermore, if the manager is in a hurry, the sending unit can use a quick sending method. This makes it possible to send the solution more effectively by adjusting the sending method according to the manager's emotions.

[0124] The sending unit can adjust the level of detail in the sending based on the importance of the solution. The sending unit, for example, uses a generative AI to evaluate the importance of the solution. For example, the sending unit evaluates the importance of the solution based on the effectiveness, feasibility, cost, etc. of the solution. The sending unit can also adjust the level of detail in the sending based on the importance of the solution. For example, the sending unit uses a detailed sending method for an important solution. The sending unit can also use a simple sending method for a general solution. Furthermore, the sending unit can use a quick sending method for a highly urgent solution. In this way, by adjusting the level of detail in the sending based on the importance, an appropriate sending method can be provided.

[0125] The sending department can apply different sending methods depending on the category of the solution. The sending department, for example, uses a generative AI to classify the category of solutions. For example, the sending department classifies solutions by industry or type of problem. The sending department can also apply different sending methods depending on the category of the solution. For example, the sending department can apply a sending method specialized for finance to a solution to cash flow. The sending department can also apply a sending method specialized for marketing to a solution to a sales strategy. Furthermore, the sending department can apply a sending method specialized for human resources to a solution to a human resources problem. In this way, more appropriate sending is possible by applying a sending method according to the category.

[0126] The sending department can improve the accuracy of sending by referring to the manager's past sending results. The sending department, for example, uses generative AI to analyze the manager's past sending results. For example, the sending department adjusts the sending method based on success stories and failure stories. The sending department can also improve the accuracy of sending by referring to the manager's past feedback. For example, the sending department compares the content and results of the manager's past sendings to identify areas for improvement in the sending method. Furthermore, the sending department can develop an algorithm to improve the accuracy of sending based on the manager's past sending results. In this way, the accuracy of sending can be improved by referring to past sending results.

[0127] The sending unit can estimate the manager's emotions and determine the priority of the content to be sent based on the estimated manager's emotions. The sending unit, for example, uses a generation AI to estimate the manager's emotions. For example, the sending unit can estimate the manager's emotions using facial expression recognition or voice analysis. The sending unit can also determine the priority of the content to be sent based on the manager's emotions. For example, if the manager is feeling stressed, the sending unit can prioritize sending important content. Also, if the manager is relaxed, the sending unit can send detailed content. Furthermore, if the manager is in a hurry, the sending unit can send content that focuses on the main points. In this way, by determining the priority of the content to be sent based on the manager's emotions, important content can be sent preferentially.

[0128] The sending department can adjust the sending order based on the time when the solutions were submitted. The sending department, for example, uses a generative AI to evaluate the time when the solutions were submitted. For example, the sending department evaluates the time when the solutions were submitted based on the submission date, deadline, urgency, etc. The sending department can also adjust the sending order based on the time when the solutions were submitted. For example, the sending department can prioritize sending solutions with high urgency. The sending department can also prioritize sending solutions with older submission dates. Furthermore, the sending department can quickly send solutions with more recent submission dates. In this way, by adjusting the sending order based on the submission time, solutions with higher urgency can be sent quickly.

[0129] The sending unit can adjust the sending order based on the relevance of the solutions. The sending unit, for example, uses a generative AI to evaluate the relevance of the solutions. For example, the sending unit evaluates the relevance of the solutions based on the similarity of content, related topics, etc. The sending unit can also adjust the sending order based on the relevance of the solutions. For example, the sending unit prioritizes sending highly relevant solutions. The sending unit can also postpone solutions with low relevance. Furthermore, the sending unit can optimize the sending order based on the relevance of the solutions. In this way, by adjusting the sending order based on relevance, highly relevant solutions can be sent with priority.

[0130] The sending department can adjust the content to be sent according to the manager's level of expertise. The sending department, for example, uses a generative AI to evaluate the manager's level of expertise. For example, the sending department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The sending department can also adjust the content to be sent according to the manager's level of expertise. For example, if the manager's level of expertise is high, the sending department can send specialized content. Also, if the manager's level of expertise is low, the sending department can send easy-to-understand content. Furthermore, the sending department can adjust the level of detail of the content to be sent according to the manager's level of expertise. In this way, by adjusting the content to be sent according to the level of expertise, it is possible to provide content that is easy for the manager to understand.

[0131] The assignment unit can estimate the manager's emotions and adjust the expert assignment method based on the estimated manager's emotions. The assignment unit, for example, uses generative AI to estimate the manager's emotions. For example, the assignment unit can estimate the manager's emotions using facial expression recognition or voice analysis. The assignment unit can also adjust the expert assignment method based on the manager's emotions. For example, if the manager is feeling stressed, the assignment unit can assign an expert who can relax. Also, if the manager is relaxed, the assignment unit can assign an expert who can provide detailed explanations. Furthermore, if the manager is in a hurry, the assignment unit can assign an expert who can respond quickly. This allows for more effective assignment by adjusting the assignment method according to the manager's emotions.

[0132] The assignment unit can adjust the level of detail of the assignment based on the importance of the solution. The assignment unit can, for example, use a generative AI to evaluate the importance of the solution. For example, the assignment unit can evaluate the importance of the solution based on the effectiveness, feasibility, cost, etc. of the solution. The assignment unit can also adjust the level of detail of the assignment based on the importance of the solution. For example, the assignment unit can use a detailed assignment method for important solutions. The assignment unit can also use a simple assignment method for general solutions. Furthermore, the assignment unit can use a quick assignment method for solutions with high urgency. In this way, by adjusting the level of detail of the assignment based on the importance, it is possible to provide an appropriate assignment method.

[0133] The assignment department can apply different assignment methods depending on the category of the solution. The assignment department, for example, uses generative AI to classify the category of solutions. For example, the assignment department classifies solutions by industry or type of problem. The assignment department can also apply different assignment methods depending on the category of the solution. For example, the assignment department can apply a finance-specialized assignment method to a solution to cash flow. The assignment department can also apply a marketing-specialized assignment method to a solution to a sales strategy. Furthermore, the assignment department can apply a human resources-specialized assignment method to a solution to a human resources problem. This allows for more appropriate assignment by applying assignment methods according to the category.

[0134] The assignment department can improve the accuracy of assignments by referring to the manager's past assignment results. The assignment department, for example, uses generative AI to analyze the manager's past assignment results. For example, the assignment department adjusts the assignment method based on success and failure cases. The assignment department can also improve the accuracy of assignments by referring to the manager's past feedback. For example, the assignment department compares the manager's past assignment content and results to identify areas for improvement in the assignment method. Furthermore, the assignment department can develop an algorithm to improve the accuracy of assignments based on the manager's past assignment results. In this way, the accuracy of assignments can be improved by referring to past assignment results.

[0135] The assignment unit can estimate the manager's emotions and prioritize assignments based on the estimated manager's emotions. The assignment unit, for example, uses generative AI to estimate the manager's emotions. For example, the assignment unit can estimate the manager's emotions using facial expression recognition or voice analysis. The assignment unit can also prioritize assignments based on the manager's emotions. For example, the assignment unit can prioritize important assignments if the manager is feeling stressed. The assignment unit can also assign detailed assignments if the manager is relaxed. Furthermore, the assignment unit can assign assignments that focus on the main points if the manager is in a hurry. In this way, by prioritizing assignments based on the manager's emotions, important assignments can be prioritized.

[0136] The assignment department can adjust the order of assignments based on the time when the solutions are submitted. The assignment department, for example, uses a generative AI to evaluate the time when the solutions are submitted. For example, the assignment department evaluates the time when the solutions are submitted based on the submission date, deadline, urgency, etc. The assignment department can also adjust the order of assignments based on the time when the solutions are submitted. For example, the assignment department can assign solutions with high urgency with priority. The assignment department can also assign solutions with older submissions with priority. Furthermore, the assignment department can quickly assign solutions with more recent submissions. In this way, by adjusting the order of assignments based on the submission time, solutions with higher urgency can be quickly assigned.

[0137] The assignment unit can adjust the order of assignments based on the relevance of the solutions. The assignment unit, for example, uses generative AI to evaluate the relevance of the solutions. For example, the assignment unit evaluates the relevance of the solutions based on the similarity of content, related topics, etc. The assignment unit can also adjust the order of assignments based on the relevance of the solutions. For example, the assignment unit assigns highly relevant solutions with priority. The assignment unit can also postpone less relevant solutions. Furthermore, the assignment unit can optimize the order of assignments based on the relevance of the solutions. In this way, by adjusting the order of assignments based on relevance, highly relevant solutions can be assigned with priority.

[0138] The assignment department can adjust the assignment content according to the manager's level of expertise. The assignment department, for example, uses generative AI to evaluate the manager's level of expertise. For example, the assignment department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The assignment department can also adjust the assignment content according to the manager's level of expertise. For example, if the manager's level of expertise is high, the assignment department can assign specialized content. Also, if the manager's level of expertise is low, the assignment department can assign easy-to-understand content. Furthermore, the assignment department can adjust the level of detail of the assignment content according to the manager's level of expertise. In this way, by adjusting the assignment content according to the level of expertise, it is possible to provide content that is easy for the manager to understand.

[0139] The monitoring unit can estimate the manager's emotions and adjust the monitoring method based on the estimated manager's emotions. The monitoring unit, for example, uses generative AI to estimate the manager's emotions. For example, the monitoring unit can estimate the manager's emotions using facial expression recognition or voice analysis. The monitoring unit can also adjust the monitoring method based on the manager's emotions. For example, if the manager is feeling stressed, the monitoring unit can use a simple and easy-to-understand monitoring method. If the manager is relaxed, the monitoring unit can also use a detailed monitoring method. Furthermore, if the manager is in a hurry, the monitoring unit can use a quick monitoring method. This allows for more effective monitoring by adjusting the monitoring method according to the manager's emotions.

[0140] The monitoring unit can adjust the level of monitoring detail based on the importance of the implementation status of the solution. The monitoring unit, for example, uses a generative AI to evaluate the importance of the implementation status of the solution. For example, the monitoring unit evaluates the importance of the implementation status of the solution based on the effectiveness, feasibility, cost, etc. of the solution. The monitoring unit can also adjust the level of monitoring detail based on the importance of the implementation status of the solution. For example, the monitoring unit uses a detailed monitoring method for important solutions. The monitoring unit can also use a simple monitoring method for general solutions. Furthermore, the monitoring unit can use a quick monitoring method for solutions with high urgency. In this way, by adjusting the level of monitoring detail based on the importance, it is possible to provide an appropriate monitoring method.

[0141] The monitoring department can apply different monitoring methods depending on the category of the solution. The monitoring department, for example, uses generative AI to classify the category of the solution. For example, the monitoring department classifies the solutions by industry or type of problem. The monitoring department can also apply different monitoring methods depending on the category of the solution. For example, the monitoring department can apply a finance-specialized monitoring method to a solution to cash flow. The monitoring department can also apply a marketing-specialized monitoring method to a solution to a sales strategy. Furthermore, the monitoring department can apply a human resources-specialized monitoring method to a solution to a human resources problem. In this way, more appropriate monitoring is possible by applying monitoring methods according to the category.

[0142] The monitoring department can improve the accuracy of monitoring by referring to the manager's past monitoring results. The monitoring department, for example, uses generative AI to analyze the manager's past monitoring results. For example, the monitoring department adjusts the monitoring method based on success and failure cases. The monitoring department can also improve the accuracy of monitoring by referring to the manager's past feedback. For example, the monitoring department compares the manager's past monitoring content and results to identify areas for improvement in the monitoring method. Furthermore, the monitoring department can develop an algorithm to improve the accuracy of monitoring based on the manager's past monitoring results. In this way, the accuracy of monitoring can be improved by referring to past monitoring results.

[0143] The monitoring unit can estimate the manager's emotions and determine the priority of monitoring content based on the estimated manager's emotions. The monitoring unit, for example, uses generative AI to estimate the manager's emotions. For example, the monitoring unit can estimate the manager's emotions using facial expression recognition or voice analysis. The monitoring unit can also determine the priority of monitoring content based on the manager's emotions. For example, if the manager is feeling stressed, the monitoring unit can prioritize important monitoring content. Furthermore, if the manager is relaxed, the monitoring unit can monitor detailed monitoring content. Furthermore, if the manager is in a hurry, the monitoring unit can monitor monitoring content that focuses on the main points. In this way, by determining the priority of monitoring content according to the manager's emotions, important content can be monitored preferentially.

[0144] The monitoring department can adjust the monitoring order based on the time when the solution was submitted. The monitoring department, for example, uses a generative AI to evaluate the time when the solution was submitted. For example, the monitoring department evaluates the time when the solution was submitted based on the submission date, deadline, urgency, etc. The monitoring department can also adjust the monitoring order based on the time when the solution was submitted. For example, the monitoring department prioritizes monitoring solutions with high urgency. The monitoring department can also prioritize monitoring solutions that were submitted earlier. Furthermore, the monitoring department can quickly monitor solutions that were submitted more recently. In this way, by adjusting the monitoring order based on the time when the solution was submitted, solutions with high urgency can be quickly monitored.

[0145] The monitoring unit can adjust the monitoring order based on the relevance of the solutions. The monitoring unit, for example, uses generative AI to evaluate the relevance of the solutions. For example, the monitoring unit evaluates the relevance of the solutions based on similarity of content, related topics, etc. The monitoring unit can also adjust the monitoring order based on the relevance of the solutions. For example, the monitoring unit prioritizes monitoring of highly relevant solutions. The monitoring unit can also postpone solutions with low relevance. Furthermore, the monitoring unit can optimize the monitoring order based on the relevance of the solutions. In this way, by adjusting the monitoring order based on relevance, highly relevant solutions can be monitored with priority.

[0146] The monitoring department can adjust the monitoring content according to the manager's level of expertise. The monitoring department, for example, uses generative AI to evaluate the manager's level of expertise. For example, the monitoring department evaluates the manager's level of expertise based on qualifications, years of experience, past performance, etc. The monitoring department can also adjust the monitoring content according to the manager's level of expertise. For example, if the manager's level of expertise is high, the monitoring department will monitor specialized content. On the other hand, if the manager's level of expertise is low, the monitoring department can monitor content that is easy to understand. Furthermore, the monitoring department can adjust the level of detail of the monitoring content according to the manager's level of expertise. In this way, by adjusting the monitoring content according to the level of expertise, it is possible to provide content that is easy for the manager to understand. === Hard Collateral 1-1 === Each of the multiple elements, including the hearing unit, analysis unit, throwing unit, generation unit, sending unit, assignment unit, and monitoring unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the hearing unit hears the manager's consultation content using the microphone 38B of the smart device 14 and transmits it to the generation AI via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the consultation content using the generation AI to generate a list of optimal experts. The throwing unit transmits the consultation to experts using the communication I / F 44 of the smart device 14. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and aggregates responses from experts to generate an optimal solution. The sending unit sends the generated solution to the manager using the communication I / F 44 of the smart device 14. The assignment unit is realized by the specific processing unit 290 of the data processing device 12 and selects experts required to implement the solution and requests the experts. The monitoring unit monitors the implementation status of the solution using the camera 42 of the smart device 14 and reports it to the manager via the control unit 46A. The assignment unit can estimate the manager's emotions and adjust the expert assignment method based on the estimated manager's emotions. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned hearing unit, analysis unit, throwing unit, generation unit, sending unit, assignment unit, and monitoring unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the hearing unit hears the manager's consultation content using the microphone 238 of the smart glasses 214 and transmits it to the generation AI via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the consultation content using the generation AI to generate a list of optimal experts. The throwing unit transmits the consultation to experts using the communication I / F 44 of the smart glasses 214. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and aggregates responses from experts to generate an optimal solution. The sending unit sends the generated solution to the manager using the communication I / F 44 of the smart glasses 214. The assignment unit is realized by the specific processing unit 290 of the data processing device 12 and selects experts required to implement the solution and requests the experts. The monitoring unit monitors the implementation status of the solution using the camera 42 of the smart glasses 214 and reports to the manager via the control unit 46A. The assignment unit can estimate the manager's emotions and adjust the expert assignment method based on the estimated manager's emotions. === Hard Collateral 1-3 === Each of the multiple elements, including the hearing unit, analysis unit, throwing unit, generation unit, sending unit, assignment unit, and monitoring unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the hearing unit hears the manager's consultation content using the microphone 238 of the headset terminal 314 and transmits it to the generation AI via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the consultation content using the generation AI to generate a list of optimal experts. The throwing unit transmits the consultation to experts using the communication I / F 44 of the headset terminal 314. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and aggregates responses from experts to generate an optimal solution. The sending unit sends the generated solution to the manager using the communication I / F 44 of the headset terminal 314. The assignment unit is realized by the specific processing unit 290 of the data processing device 12 and selects experts required to implement the solution and requests the experts. The monitoring unit monitors the implementation status of the solution using the camera 42 of the headset terminal 314 and reports to the manager via the control unit 46A. The assignment unit can estimate the manager's emotions and adjust the method of assigning experts based on the estimated manager's emotions. === Hard Collateral 1-4 === Each of the multiple elements, including the hearing unit, analysis unit, throwing unit, generation unit, sending unit, assignment unit, and monitoring unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the hearing unit hears the manager's consultation content using the microphone 238 of the robot 414 and transmits it to the generation AI via the control unit 46A. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the consultation content using the generation AI to generate a list of optimal experts. The throwing unit transmits the consultation to experts using the communication I / F 44 of the robot 414. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and aggregates responses from experts to generate an optimal solution. The sending unit sends the generated solution to the manager using the communication I / F 44 of the robot 414. The assignment unit is realized by the specific processing unit 290 of the data processing device 12 and selects experts required to implement the solution and requests the experts. The monitoring unit monitors the implementation status of the solution using the camera 42 of the robot 414 and reports to the manager via the control unit 46A. The assignment unit can estimate the manager's emotions and adjust the expert assignment method based on the estimated manager's emotions.

[0147] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0148] The consulting robot system further includes a feedback unit. The feedback unit can collect feedback from the manager and use it to improve the system. For example, the feedback unit can collect how the manager felt about the provided solution. The feedback unit can also collect feedback from the manager about the results of implementing the solution. Furthermore, the feedback unit can collect the manager's opinions about the ease of use of the system and provide data to improve the usability of the system. This makes it possible to continuously improve the system through the feedback unit.

[0149] The analysis unit can estimate the manager's emotions and adjust the way the analysis is presented based on the estimated manager's emotions. For example, if the manager is feeling stressed, the analysis unit uses a simple and easy-to-understand presentation method. If the manager is relaxed, the analysis unit can also provide detailed analysis results. Furthermore, if the manager is in a hurry, the analysis unit can also provide analysis results that focus on the main points. In this way, by adjusting the way the analysis is presented according to the manager's emotions, it is possible to provide analysis results that are easier to understand.

[0150] The generator can adjust the level of detail of the solution based on the importance of the answer from the expert. For example, the generator can generate a detailed solution based on an important answer. The generator can also generate a concise solution based on a general answer. Furthermore, the generator can quickly generate a solution based on an answer with a high urgency. In this way, by adjusting the level of detail of the solution based on the importance, it is possible to provide an appropriate solution.

[0151] The assignment unit can estimate the manager's emotions and adjust the expert assignment method based on the estimated manager's emotions. For example, if the manager is feeling stressed, the assignment unit can assign an expert who can help the manager relax. Also, if the manager is relaxed, the assignment unit can assign an expert who can provide detailed explanations. Furthermore, if the manager is in a hurry, the assignment unit can assign an expert who can respond quickly. This allows for more effective assignment by adjusting the assignment method according to the manager's emotions.

[0152] The monitoring unit can adjust the level of detail of monitoring based on the importance of the implementation status of a solution. For example, the monitoring unit uses a detailed monitoring method for an important solution. The monitoring unit can also use a simple monitoring method for a general solution. Furthermore, the monitoring unit can also use a quick monitoring method for a highly urgent solution. In this way, by adjusting the level of detail of monitoring based on the importance, it is possible to provide an appropriate monitoring method.

[0153] The hearing department can estimate the manager's emotions and adjust the timing of the hearing based on the estimated manager's emotions. For example, if the manager is feeling stressed, the hearing department can conduct the hearing at a time when the manager is able to relax. Also, if the manager is busy, the hearing department can conduct the hearing efficiently in a short amount of time. Furthermore, if the manager is relaxed, the hearing department can conduct a detailed hearing. This allows for more effective hearings by adjusting the timing of the hearing according to the manager's emotions.

[0154] The analysis unit can apply different analysis algorithms depending on the category of the consultation content. For example, the analysis unit can apply an analysis algorithm specialized in finance to a consultation about cash flow. The analysis unit can also apply an analysis algorithm specialized in marketing to a consultation about sales strategy. Furthermore, the analysis unit can also apply an analysis algorithm specialized in human resources to a consultation about human resources issues. In this way, by applying an analysis algorithm according to the category, it is possible to provide more accurate analysis results.

[0155] The generation unit can estimate the manager's emotions and adjust the way the solution is expressed based on the estimated manager's emotions. For example, if the manager is feeling stressed, the generation unit can generate a simple and easy-to-understand solution. If the manager is relaxed, the generation unit can also generate a detailed solution. Furthermore, if the manager is in a hurry, the generation unit can also generate a solution that focuses on the main points. In this way, by adjusting the way the solution is expressed according to the manager's emotions, it is possible to provide a more understandable solution.

[0156] The sending unit can adjust the sending order based on the time of submission of the solutions. For example, the sending unit can send solutions with high urgency first. The sending unit can also send solutions with older submission dates first. Furthermore, the sending unit can quickly send solutions with more recent submission dates. In this way, by adjusting the sending order based on the time of submission, solutions with high urgency can be quickly sent.

[0157] The assignment department can apply different assignment methods depending on the category of the solution. For example, the assignment department can apply a finance-specialized assignment method to a solution to a cash flow problem. The assignment department can also apply a marketing-specialized assignment method to a solution to a sales strategy. Furthermore, the assignment department can apply a human resources-specialized assignment method to a solution to a human resources problem. In this way, applying an assignment method according to the category enables more appropriate assignment.

[0158] The processing flow of the second embodiment will be briefly explained below.

[0159] Step 1: The hearing department listens to the manager's concerns, including business strategy, finance, and marketing. The hearing department records the manager's specific concerns and problems in detail and sends them to the generation AI. Step 2: The analysis unit uses the generation AI to analyze the consultation content heard by the hearing unit and generate a list of the most suitable experts to consult. The generation AI analyzes the consultation content and generates a list of the most suitable experts. Step 3: The submission unit submits the consultation to multiple experts based on the expert list generated by the analysis unit. The submission unit sends the consultation to the experts via email or chat. Step 4: The generation unit uses the generation AI to aggregate the answers from the experts and generate the optimal solution. The generation AI analyzes the answers from the experts and generates the optimal solution. Step 5: The sending section sends the solution generated by the generating section to the manager. The sending section sends the solution by email or mail. Step 6: The Assignment Department assigns the most suitable expert based on the solution sent by the Sending Department when a request for solution implementation is made. The Assignment Department selects the expert required for solution implementation and makes a request to that expert.

[0160] 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.

[0161] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0162] 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.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0165] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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).

[0170] 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.

[0171] 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.

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

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

[0174] In the 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.

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

[0176] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0178] The data processing system 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.

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

[0180] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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).

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0194] 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.

[0195] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0196] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0197] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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).

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0211] 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.

[0212] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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."

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] [Explanation of symbols]

[0232] 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. The hearing department listens to the concerns of business owners, an analysis unit that analyzes the consultation content heard by the hearing unit and determines which expert is best to consult; a sending unit that sends the consultation to a plurality of experts based on the expert list generated by the analysis unit; a generation unit that aggregates the responses from the experts and generates an optimal solution; a sending unit that sends the solution generated by the generating unit to a manager; an assignment unit that assigns an optimal expert when a request for solution execution is received based on the solution sent by the sending unit; Equipped with A system characterized by:

2. The analysis unit Refer to the database of experts and select the expert most suited to your inquiry 2. The system of claim 1.

3. The generation unit Analyze expert responses and generate optimal solutions 2. The system of claim 1.

4. The assignment unit Identify the experts needed to implement the solution and request them 2. The system of claim 1.

5. The generation unit Use an algorithm that combines answers from multiple experts to find the optimal solution 2. The system of claim 1.

6. Equipping a monitoring department to monitor the implementation of solutions 2. The system of claim 1.

7. The hearing section Estimate the manager's feelings and adjust the timing of interviews based on the estimated manager's feelings 2. The system of claim 1.

8. The hearing section Analyze the manager's past consultation history and select the most appropriate interview method 2. The system of claim 1.

9. The hearing section Customize questions based on the business owner's current business situation and areas of interest 2. The system of claim 1.

Images