system

Abstract

The system according to the embodiment aims to select and combine optimal LLMs based on the user's requirements to provide a solution. [Solution] A system according to an embodiment includes a receiving unit, a selecting unit, a combining unit, a generating unit, and a providing unit. The receiving unit receives user requirements. The selecting unit selects multiple LLMs based on the requirements received by the receiving unit. The combining unit combines the LLMs selected by the selecting unit. The generating unit generates a solution based on the LLMs combined by the combining unit. The providing unit provides the solution generated by the generating 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 do not adequately select and combine LLMs that best suit user requirements to provide a solution, and there is room for improvement.

[0005] The system according to the embodiment aims to select and combine optimal LLMs based on the user's requirements to provide a solution. [Means for solving the problem]

[0006] A system according to an embodiment includes a receiving unit, a selecting unit, a combining unit, a generating unit, and a providing unit. The receiving unit receives user requirements. The selecting unit selects multiple LLMs based on the requirements received by the receiving unit. The combining unit combines the LLMs selected by the selecting unit. The generating unit generates a solution based on the LLMs combined by the combining unit. The providing unit provides the solution generated by the generating unit. [Effects of the Invention]

[0007] The system according to the embodiment can select and combine optimal LLMs based on the user's requirements to provide a solution. [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 system according to an embodiment of the present invention combines multiple large-scale language models (LLMs) to provide a solution optimized for a specific use case. The system begins with a user inputting requirements for a specific use case. The system then combines multiple LLMs to generate an optimal solution by leveraging the strengths of each LLM. For example, if one LLM excels in natural language understanding, that LLM is used primarily, while another LLM excels in data analysis, that LLM is used as a secondary LLM. This provides an optimal solution that maximizes the characteristics of each LLM. The generated solution is provided to the user, who can use it to address a specific use case. Specific use cases include diagnostic support in the medical field and risk assessment in the financial field. For example, if a user inputs "I want to improve the accuracy of medical diagnoses," an LLM with excellent natural language understanding and an LLM with excellent medical data analysis are selected and combined to generate an optimal diagnostic support solution. This allows the system to select and combine multiple LLMs based on the user's requirements and generate and provide an optimal solution.

[0029] A solution generation system according to an embodiment includes a receiving unit, a selecting unit, a combining unit, a generating unit, and a providing unit. The receiving unit receives user requirements. The user requirements may include, but are not limited to, requirements in text format, audio format, or specific fields. The receiving unit, for example, analyzes text data entered by the user to extract requirements. The receiving unit may also analyze audio input and convert the requirements into text data. For example, the receiving unit may convert the user's audio into text data using speech recognition technology. The selecting unit selects multiple LLMs based on the requirements received by the receiving unit. For example, the selecting unit may select an LLM specialized for a specific task or a general-purpose LLM based on the user's requirements. The selecting unit may select, for example, an LLM with excellent natural language understanding or an LLM with excellent data analysis capabilities. The combining unit combines the LLMs selected by the selecting unit. The combining unit effectively combines the selected LLMs using algorithms such as weighted averaging and boosting. The combining unit may integrate the outputs of the selected LLMs to generate an optimal solution. The generation unit generates a solution based on the LLMs combined by the combination unit. The generation unit generates solutions such as report formats, action plans, and technical proposals based on the output of the combined LLMs. The generation unit can generate, for example, a diagnosis support solution in the medical field or a risk assessment solution in the financial field. The provision unit provides the solution generated by the generation unit to a user. The provision unit displays the generated solution to the user through, for example, a web application or a mobile application. The provision unit can also send the generated solution by email. As a result, the solution generation system according to the embodiment can select and combine multiple LLMs based on user requirements, and generate and provide an optimal solution.

[0030] The selection unit can select an LLM based on user requirements. For example, the selection unit can select an LLM specialized for a specific task or a general-purpose LLM based on the user requirements. For example, the selection unit can select an LLM that excels in natural language understanding or an LLM that excels in data analysis. The selection unit uses an algorithm to analyze the user requirements and select the optimal LLM. For example, the selection unit can select an LLM using an AI model that inputs the user requirements and outputs the optimal LLM. This allows the selection unit to select the optimal LLM based on the user requirements.

[0031] The combiner may use an algorithm to combine the selected LLMs. The combiner may use an algorithm such as weighted averaging or boosting to effectively combine the selected LLMs. The combiner may, for example, integrate the outputs of the selected LLMs to generate an optimal solution. The combiner may use an AI model that executes the algorithm to combine the selected LLMs. For example, the combiner may combine the LLMs using an AI model that takes the outputs of the selected LLMs as inputs and generates an integrated output. This allows the combiner to effectively combine the selected LLMs.

[0032] The generation unit can generate a solution based on the combined LLMs. For example, the generation unit generates a solution such as a report format, an action plan, or a technical proposal based on the output of the combined LLMs. For example, the generation unit can generate a diagnosis support solution in the medical field or a risk assessment solution in the financial field. The generation unit can use an AI model that executes an algorithm to generate a solution based on the combined LLMs. For example, the generation unit can generate a solution using an AI model that uses the output of the combined LLMs as input and generates a solution. This allows the generation unit to generate an optimal solution based on the combined LLMs.

[0033] The providing unit can provide the generated solution to the user. For example, the providing unit displays the generated solution to the user through a web application or a mobile application. The providing unit can also send the generated solution by email. The providing unit can use an AI model that executes an algorithm for providing the generated solution to the user. For example, the providing unit can provide the solution using an AI model that receives the generated solution as input and outputs an optimal method for providing the solution to the user. In this way, the providing unit can provide the generated solution to the user.

[0034] The generation unit can generate a diagnostic support solution in the medical field. The generation unit generates the diagnostic support solution, for example, using an LLM specialized for medical data analysis. The generation unit can generate the diagnostic support solution, for example, using an AI model that receives patient symptom data as input and outputs a diagnosis result. The generation unit can use an AI model that executes an algorithm for generating a diagnostic support solution in the medical field. For example, the generation unit can generate the diagnostic support solution using an AI model that analyzes medical data and generates a diagnosis result. This allows the generation unit to generate a diagnostic support solution in the medical field.

[0035] The generation unit can generate a risk assessment solution in the financial field. The generation unit can generate the risk assessment solution using, for example, an LLM specialized in financial data analysis. The generation unit can generate the risk assessment solution using, for example, an AI model that takes a company's financial data as input and outputs a risk assessment result. The generation unit can use an AI model that executes an algorithm for generating a risk assessment solution in the financial field. For example, the generation unit can generate the risk assessment solution using an AI model that analyzes financial data and generates a risk assessment result. This allows the generation unit to generate a risk assessment solution in the financial field.

[0036] The reception unit can analyze the user's past requirement submission history and select the reception method. The reception unit, for example, analyzes the user's past requirement submission history and selects the optimal reception method. The reception unit, for example, prioritizes accepting requirements that the user has frequently submitted in the past. The reception unit can also suggest the optimal reception time based on the user's past submission history. For example, the reception unit analyzes the user's past requirement submission patterns and selects the optimal reception method. This allows the reception unit to select the optimal reception method based on the user's past requirement submission history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the reception method using an AI model that inputs the user's past requirement submission history and outputs the optimal reception method.

[0037] When receiving requirements, the reception unit may filter the requirements based on the user's current project or areas of interest. For example, the reception unit may preferentially receive requirements related to the user's ongoing project. The reception unit may filter related requirements based on the user's areas of interest. The reception unit may also suggest optimal requirements based on the user's project progress. For example, the reception unit may use data from a project management tool or survey results to identify the user's current project or areas of interest. This allows the reception unit to filter requirements based on the user's current project or areas of interest. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may filter requirements using an AI model that inputs data from a project management tool and outputs related requirements.

[0038] When receiving requirements, the reception unit can prioritize receiving highly relevant requirements by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit can prioritize receiving requirements related to that area. For example, the reception unit can propose optimal requirements based on the user's current location. The reception unit can also analyze the user's geographical location information and prioritize receiving highly relevant requirements. For example, the reception unit can acquire the user's geographical location information using GPS data or an IP address and identify relevant requirements. This allows the reception unit to prioritize receiving highly relevant requirements based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can prioritize receiving requirements using an AI model that inputs the user's geographical location information and outputs relevant requirements.

[0039] The reception unit may analyze the user's social media activities and receive related requirements when receiving requirements. The reception unit may, for example, analyze the content of the user's social media posts and prioritize receiving related requirements. The reception unit may, for example, suggest optimal requirements based on the user's social media activity history. The reception unit may also analyze the user's social media interests and receive related requirements. For example, the reception unit may analyze the content of social media posts, the number of likes, the number of followers, etc. to identify related requirements. This allows the reception unit to receive related requirements based on the user's social media activities. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may receive requirements using an AI model that inputs the user's social media activity data and outputs related requirements.

[0040] The selection unit can improve the accuracy of selection by taking into account the interrelationships between LLMs during selection. The selection unit can, for example, select the optimal combination by taking into account the mutual complementarity between LLMs. The selection unit can, for example, analyze the interrelationships between LLMs and select the most effective combination. The selection unit can also improve the accuracy of selection by taking into account the interactions between LLMs. For example, the selection unit can evaluate the interrelationships between LLMs using correlation coefficients or co-occurrence networks of LLMs. This allows the selection unit to improve the accuracy of selection by taking into account the interrelationships between LLMs. Some or all of the above-described processing in the selection unit can be performed using, for example, AI, or can be performed without using AI. For example, the selection unit can improve the accuracy of selection by using an AI model that inputs LLM interrelationship data and outputs the optimal LLM combination.

[0041] The selection unit may make a selection while taking into consideration attribute information of the LLM provider. The selection unit may select the most appropriate LLM, for example, by taking into consideration the specialty of the LLM provider. The selection unit may, for example, evaluate the reliability of the LLM provider and use this as a selection criterion. The selection unit may also make a selection while taking into consideration the past performance of the LLM provider. For example, the selection unit may collect attribute information of the provider to evaluate the provider's specialty and past performance. This allows the selection unit to make a selection while taking into consideration the attribute information of the LLM provider. Some or all of the above-described processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit may make a selection using an AI model that inputs attribute information of the provider and outputs the most appropriate LLM.

[0042] The selection unit may make the selection taking into consideration the geographic distribution of LLMs. For example, the selection unit may select an LLM that is optimal for the user's region. For example, the selection unit may analyze the geographic distribution of LLMs and select an optimal LLM. The selection unit may also select an optimal LLM taking into consideration the characteristics of each region. For example, the selection unit may collect geographic distribution data to evaluate the number of LLMs per region and regional characteristics. This allows the selection unit to make the selection taking into consideration the geographic distribution of LLMs. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may make the selection using an AI model that inputs geographic distribution data and outputs an optimal LLM.

[0043] The selection unit can improve the accuracy of the selection by referring to literature related to the LLM. For example, the selection unit can refer to literature related to the LLM and select the optimal LLM. For example, the selection unit can improve the accuracy of the selection based on past research results on the LLM. The selection unit can also analyze literature related to the LLM and select the most effective LLM. For example, the selection unit can collect related information by referring to academic papers, technical reports, patent documents, etc. This allows the selection unit to improve the accuracy of the selection by referring to literature related to the LLM. Some or all of the above-mentioned processing in the selection unit can be performed using, for example, AI, or can be performed without AI. For example, the selection unit can improve the accuracy of the selection by using an AI model that inputs related literature data and outputs the optimal LLM.

[0044] The combining unit can improve the accuracy of combining by taking into account the interrelationships between LLMs during combining. The combining unit can, for example, perform optimal combining by taking into account the mutual complementarity between LLMs. The combining unit can, for example, analyze the interrelationships between LLMs and perform the most effective combining. The combining unit can also improve the accuracy of combining by taking into account the interactions between LLMs. For example, the combining unit can evaluate the interrelationships between LLMs using correlation coefficients or co-occurrence networks of LLMs. This allows the combining unit to improve the accuracy of combining by taking into account the interrelationships between LLMs. Some or all of the above-described processing in the combining unit can be performed using, for example, AI, or can be performed without using AI. For example, the combining unit can improve the accuracy of combining by using an AI model that inputs LLM interrelationship data and outputs the optimal LLM combination.

[0045] When combining, the combining unit can perform the combining while taking into account attribute information of the LLM provider. The combining unit performs optimal combining, for example, taking into account the specialty field of the LLM provider. The combining unit can, for example, evaluate the reliability of the LLM provider and use this as a criterion for combining. The combining unit can also perform combining while taking into account the past performance of the LLM provider. For example, the combining unit collects attribute information of the provider to evaluate the provider's specialty field and past performance. This allows the combining unit to perform combining while taking into account the attribute information of the LLM provider. Some or all of the above-described processing in the combining unit may be performed using, for example, AI, or may be performed without using AI. For example, the combining unit can perform combining using an AI model that inputs attribute information of the provider and outputs optimal LLM combination.

[0046] The combining unit may combine the LLMs taking into account the geographic distribution of the LLMs. For example, the combining unit may combine the LLMs that are optimal for the user's region. For example, the combining unit may analyze the geographic distribution of the LLMs and perform the optimal combination. The combining unit may also combine the optimal LLMs taking into account the characteristics of each region. For example, the combining unit may collect geographic distribution data to evaluate the number of LLMs per region and characteristics unique to each region. This allows the combining unit to perform the combination taking into account the geographic distribution of the LLMs. Some or all of the above-described processing in the combining unit may be performed using, for example, AI, or may be performed without using AI. For example, the combining unit may perform the combination using an AI model that inputs geographic distribution data and outputs the optimal LLM combination.

[0047] The combining unit can improve the accuracy of the combination by referring to literature related to the LLM during the combination. For example, the combining unit can refer to literature related to the LLM to perform optimal combination. For example, the combining unit can improve the accuracy of the combination based on past research results of the LLM. The combining unit can also analyze literature related to the LLM to perform the most effective combination. For example, the combining unit can refer to academic papers, technical reports, patent documents, etc. to collect related information. This allows the combining unit to improve the accuracy of the combination by referring to literature related to the LLM. Some or all of the above-mentioned processing in the combining unit can be performed using, for example, AI, or can be performed without AI. For example, the combining unit can improve the accuracy of the combination by using an AI model that inputs related literature data and outputs optimal LLM combinations.

[0048] The generation unit can adjust the level of detail of the generated solution based on the importance of the solution during generation. For example, the generation unit can include detailed information in a solution with high importance. For example, the generation unit can include concise information in a solution with low importance. The generation unit can also adjust the level of detail of the generated solution according to the importance of the solution. For example, the generation unit can evaluate the importance of the solution using impact analysis or prioritization. This allows the generation unit to adjust the level of detail of the generated solution according to the importance of the solution. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the level of detail of the generated solution using an AI model that inputs solution importance data and outputs the level of detail of the generated solution.

[0049] The generation unit can apply different generation algorithms depending on the category of the solution during generation. For example, the generation unit can apply an algorithm specialized for medical data analysis to a solution in the medical field. For example, the generation unit can apply an algorithm specialized for risk assessment to a solution in the financial field. The generation unit can also apply an optimal generation algorithm depending on the category of the solution. For example, the generation unit can identify the category of the solution using a classification method such as a technology category or a business category. This allows the generation unit to apply an optimal generation algorithm depending on the category of the solution. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can apply a generation algorithm using an AI model that inputs solution category data and outputs an optimal generation algorithm.

[0050] The generation unit can determine the generation priority based on the submission time of the solution at the time of generation. For example, the generation unit can prioritize generating solutions with a high level of urgency. For example, the generation unit can prioritize generating solutions with an upcoming submission deadline. The generation unit can also determine the generation priority based on the submission time. For example, the generation unit collects submission time data to evaluate the submission deadline and the progress of the project. This allows the generation unit to determine the generation priority based on the submission time of the solution. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can determine the generation priority using an AI model that inputs submission time data and outputs the generation priority.

[0051] The generation unit can adjust the order of generation based on the relevance of the solutions during generation. For example, the generation unit prioritizes generating highly relevant solutions. For example, the generation unit can postpone generating less relevant solutions. The generation unit can also adjust the order of generation based on the relevance of the solutions. For example, the generation unit evaluates the relevance of the solutions using a relevance score or co-occurrence analysis. This allows the generation unit to adjust the order of generation based on the relevance of the solutions. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the order of generation using an AI model that receives relevance data of the solutions as input and outputs the order of generation.

[0052] The providing unit can select the optimal solution delivery method by referring to the user's past solution usage history when providing the solution. For example, the providing unit preferentially selects a solution delivery method that the user has used favorably in the past. For example, the providing unit can suggest the optimal solution delivery method based on the user's past usage history. The providing unit can also analyze the user's past solution usage patterns and select the optimal solution delivery method. For example, the providing unit collects solution usage history data to evaluate past usage frequency and usage results. This allows the providing unit to select the optimal solution delivery method based on the user's past solution usage history. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can select the delivery method using an AI model that inputs solution usage history data and outputs the optimal solution delivery method.

[0053] The providing unit can select the optimal delivery method by taking into account the user's device information when providing the information. For example, if the user is using a smartphone, the providing unit selects a delivery method that matches the screen size. For example, if the user is using a tablet, the providing unit can select a delivery method optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can select a delivery method that is concise and highly visible. For example, the providing unit collects device information to evaluate the device type, OS, and browser information. This allows the providing unit to select the optimal delivery method based on the user's device information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can select the delivery method using an AI model that inputs device information and outputs the optimal delivery method.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] When accepting requirements from a user, the acceptance unit can analyze the user's past requirement submission history and select the optimal acceptance method. For example, the acceptance unit can prioritize requirements that the user has frequently submitted in the past. The acceptance unit can also suggest the optimal acceptance time based on the user's past submission history. For example, the acceptance unit can analyze the user's past requirement submission patterns and select the optimal acceptance method. This allows the acceptance unit to select the optimal acceptance method based on the user's past requirement submission history. Some or all of the above-described processing in the acceptance unit may be performed using, for example, AI, or may be performed without using AI. For example, the acceptance unit can select the acceptance method using an AI model that inputs the user's past requirement submission history and outputs the optimal acceptance method.

[0056] When selecting an LLM based on user requirements, the selection unit may take into consideration attribute information of the LLM provider. For example, the selection unit may select the optimal LLM by taking into consideration the specialty of the LLM provider. For example, the selection unit may evaluate the reliability of the LLM provider and use this as a selection criterion. The selection unit may also take into consideration the past performance of the LLM provider when making a selection. For example, the selection unit may collect attribute information of the provider to evaluate the provider's specialty and past performance. This allows the selection unit to make a selection by taking into consideration the attribute information of the LLM provider. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may make a selection using an AI model that inputs attribute information of the provider and outputs the optimal LLM.

[0057] When combining selected LLMs, the combination unit can improve the accuracy of the combination by taking into account the interrelationships between the LLMs. For example, the combination unit can perform optimal combinations by taking into account the mutual complementarity between the LLMs. For example, the combination unit can analyze the interrelationships between the LLMs and perform the most effective combination. The combination unit can also improve the accuracy of the combination by taking into account the interactions between the LLMs. For example, the combination unit can evaluate the interrelationships between the LLMs using correlation coefficients or co-occurrence networks of the LLMs. This allows the combination unit to improve the accuracy of the combination by taking into account the interrelationships between the LLMs. Some or all of the above-described processing in the combination unit may be performed using, for example, AI, or may be performed without using AI. For example, the combination unit can improve the accuracy of the combination by using an AI model that inputs LLM interrelationship data and outputs the optimal LLM combination.

[0058] When generating a solution based on the combined LLM, the generation unit can apply different generation algorithms depending on the category of the solution. For example, to a solution in the medical field, the generation unit can apply an algorithm specialized for medical data analysis. For example, to a solution in the financial field, the generation unit can apply an algorithm specialized for risk assessment. The generation unit can also apply an optimal generation algorithm depending on the category of the solution. For example, the generation unit can identify the category of the solution using a classification method such as a technology category or a business category. This allows the generation unit to apply an optimal generation algorithm depending on the category of the solution. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can apply a generation algorithm using an AI model that inputs solution category data and outputs an optimal generation algorithm.

[0059] When providing a generated solution to a user, the providing unit can select the optimal delivery method by taking into account the user's device information. For example, if the user is using a smartphone, the providing unit can select a delivery method that matches the screen size. For example, if the user is using a tablet, the providing unit can select a delivery method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can select a delivery method that is concise and highly visible. For example, the providing unit collects device information to evaluate the device type, OS, and browser information. This allows the providing unit to select the optimal delivery method based on the user's device information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can select the delivery method using an AI model that inputs device information and outputs the optimal delivery method.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The reception unit receives user requirements. The user requirements may be in text format, voice format, or requirements related to specific fields. The reception unit analyzes the text data entered by the user and extracts the requirements. It can also analyze voice input and convert the requirements into text data. For example, voice recognition technology can be used to convert the user's voice into text data. Step 2: The selection unit selects multiple LLMs based on the requirements received by the reception unit. Based on the user's requirements, the selection unit selects an LLM specialized for a specific task or a general-purpose LLM. For example, it can select an LLM that excels in natural language understanding or data analysis. Step 3: The combiner combines the LLMs selected by the selector. The combiner effectively combines the selected LLMs using algorithms such as weighted averaging and boosting. The combiner integrates the outputs of the selected LLMs to generate an optimal solution. Step 4: The generator generates a solution based on the LLMs combined by the combiner. Based on the output of the combined LLMs, the generator generates solutions such as report formats, action plans, and technical proposals. For example, it can generate a diagnostic support solution in the medical field or a risk assessment solution in the financial field. Step 5: The providing unit provides the solution generated by the generating unit to the user. The providing unit displays the generated solution to the user through a web application or a mobile application. The providing unit can also send the generated solution by email.

[0062] (Example 2) A system according to an embodiment of the present invention combines multiple large-scale language models (LLMs) to provide a solution optimized for a specific use case. The system begins with a user inputting requirements for a specific use case. The system then combines multiple LLMs to generate an optimal solution by leveraging the strengths of each LLM. For example, if one LLM excels in natural language understanding, that LLM is used primarily, while another LLM excels in data analysis, that LLM is used as a secondary LLM. This provides an optimal solution that maximizes the characteristics of each LLM. The generated solution is provided to the user, who can use it to address a specific use case. Specific use cases include diagnostic support in the medical field and risk assessment in the financial field. For example, if a user inputs "I want to improve the accuracy of medical diagnoses," an LLM with excellent natural language understanding and an LLM with excellent medical data analysis are selected and combined to generate an optimal diagnostic support solution. This allows the system to select and combine multiple LLMs based on the user's requirements and generate and provide an optimal solution.

[0063] A solution generation system according to an embodiment includes a receiving unit, a selecting unit, a combining unit, a generating unit, and a providing unit. The receiving unit receives user requirements. The user requirements may include, but are not limited to, requirements in text format, audio format, or specific fields. The receiving unit, for example, analyzes text data entered by the user to extract requirements. The receiving unit may also analyze audio input and convert the requirements into text data. For example, the receiving unit may convert the user's audio into text data using speech recognition technology. The selecting unit selects multiple LLMs based on the requirements received by the receiving unit. For example, the selecting unit may select an LLM specialized for a specific task or a general-purpose LLM based on the user's requirements. The selecting unit may select, for example, an LLM with excellent natural language understanding or an LLM with excellent data analysis capabilities. The combining unit combines the LLMs selected by the selecting unit. The combining unit effectively combines the selected LLMs using algorithms such as weighted averaging and boosting. The combining unit may integrate the outputs of the selected LLMs to generate an optimal solution. The generation unit generates a solution based on the LLMs combined by the combination unit. The generation unit generates solutions such as report formats, action plans, and technical proposals based on the output of the combined LLMs. The generation unit can generate, for example, a diagnosis support solution in the medical field or a risk assessment solution in the financial field. The provision unit provides the solution generated by the generation unit to a user. The provision unit displays the generated solution to the user through, for example, a web application or a mobile application. The provision unit can also send the generated solution by email. As a result, the solution generation system according to the embodiment can select and combine multiple LLMs based on user requirements, and generate and provide an optimal solution.

[0064] The selection unit can select an LLM based on user requirements. For example, the selection unit can select an LLM specialized for a specific task or a general-purpose LLM based on the user requirements. For example, the selection unit can select an LLM that excels in natural language understanding or an LLM that excels in data analysis. The selection unit uses an algorithm to analyze the user requirements and select the optimal LLM. For example, the selection unit can select an LLM using an AI model that inputs the user requirements and outputs the optimal LLM. This allows the selection unit to select the optimal LLM based on the user requirements.

[0065] The combiner may use an algorithm to combine the selected LLMs. The combiner may use an algorithm such as weighted averaging or boosting to effectively combine the selected LLMs. The combiner may, for example, integrate the outputs of the selected LLMs to generate an optimal solution. The combiner may use an AI model that executes the algorithm to combine the selected LLMs. For example, the combiner may combine the LLMs using an AI model that takes the outputs of the selected LLMs as inputs and generates an integrated output. This allows the combiner to effectively combine the selected LLMs.

[0066] The generation unit can generate a solution based on the combined LLMs. For example, the generation unit generates a solution such as a report format, an action plan, or a technical proposal based on the output of the combined LLMs. For example, the generation unit can generate a diagnosis support solution in the medical field or a risk assessment solution in the financial field. The generation unit can use an AI model that executes an algorithm to generate a solution based on the combined LLMs. For example, the generation unit can generate a solution using an AI model that uses the output of the combined LLMs as input and generates a solution. This allows the generation unit to generate an optimal solution based on the combined LLMs.

[0067] The providing unit can provide the generated solution to the user. For example, the providing unit displays the generated solution to the user through a web application or a mobile application. The providing unit can also send the generated solution by email. The providing unit can use an AI model that executes an algorithm for providing the generated solution to the user. For example, the providing unit can provide the solution using an AI model that receives the generated solution as input and outputs an optimal method for providing the solution to the user. In this way, the providing unit can provide the generated solution to the user.

[0068] The generation unit can generate a diagnostic support solution in the medical field. The generation unit generates the diagnostic support solution, for example, using an LLM specialized for medical data analysis. The generation unit can generate the diagnostic support solution, for example, using an AI model that receives patient symptom data as input and outputs a diagnosis result. The generation unit can use an AI model that executes an algorithm for generating a diagnostic support solution in the medical field. For example, the generation unit can generate the diagnostic support solution using an AI model that analyzes medical data and generates a diagnosis result. This allows the generation unit to generate a diagnostic support solution in the medical field.

[0069] The generation unit can generate a risk assessment solution in the financial field. The generation unit can generate the risk assessment solution using, for example, an LLM specialized in financial data analysis. The generation unit can generate the risk assessment solution using, for example, an AI model that takes a company's financial data as input and outputs a risk assessment result. The generation unit can use an AI model that executes an algorithm for generating a risk assessment solution in the financial field. For example, the generation unit can generate the risk assessment solution using an AI model that analyzes financial data and generates a risk assessment result. This allows the generation unit to generate a risk assessment solution in the financial field.

[0070] The reception unit can estimate the user's emotions and adjust the timing of receiving requirements based on the estimated user emotions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice and calculates an emotion score. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations. This allows the reception unit to adjust the timing of receiving requirements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0071] The reception unit can analyze the user's past requirement submission history and select the reception method. The reception unit, for example, analyzes the user's past requirement submission history and selects the optimal reception method. The reception unit, for example, prioritizes accepting requirements that the user has frequently submitted in the past. The reception unit can also suggest the optimal reception time based on the user's past submission history. For example, the reception unit analyzes the user's past requirement submission patterns and selects the optimal reception method. This allows the reception unit to select the optimal reception method based on the user's past requirement submission history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the reception method using an AI model that inputs the user's past requirement submission history and outputs the optimal reception method.

[0072] When receiving requirements, the reception unit may filter the requirements based on the user's current project or areas of interest. For example, the reception unit may preferentially receive requirements related to the user's ongoing project. The reception unit may filter related requirements based on the user's areas of interest. The reception unit may also suggest optimal requirements based on the user's project progress. For example, the reception unit may use data from a project management tool or survey results to identify the user's current project or areas of interest. This allows the reception unit to filter requirements based on the user's current project or areas of interest. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may filter requirements using an AI model that inputs data from a project management tool and outputs related requirements.

[0073] The reception unit can estimate the user's emotions and determine the priority of requirements to be received based on the estimated user emotions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice and calculates the emotion score. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates the emotion score based on heart rate fluctuations. This allows the reception unit to determine the priority of requirements to be received based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0074] When receiving requirements, the reception unit can prioritize receiving highly relevant requirements by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit can prioritize receiving requirements related to that area. For example, the reception unit can propose optimal requirements based on the user's current location. The reception unit can also analyze the user's geographical location information and prioritize receiving highly relevant requirements. For example, the reception unit can acquire the user's geographical location information using GPS data or an IP address and identify relevant requirements. This allows the reception unit to prioritize receiving highly relevant requirements based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can prioritize receiving requirements using an AI model that inputs the user's geographical location information and outputs relevant requirements.

[0075] The reception unit may analyze the user's social media activities and receive related requirements when receiving requirements. The reception unit may, for example, analyze the content of the user's social media posts and prioritize receiving related requirements. The reception unit may, for example, suggest optimal requirements based on the user's social media activity history. The reception unit may also analyze the user's social media interests and receive related requirements. For example, the reception unit may analyze the content of social media posts, the number of likes, the number of followers, etc. to identify related requirements. This allows the reception unit to receive related requirements based on the user's social media activities. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may receive requirements using an AI model that inputs the user's social media activity data and outputs related requirements.

[0076] The selection unit can estimate the user's emotion and adjust the criteria of the LLM to be selected based on the estimated user's emotion. For example, the selection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the selection unit calculates an emotion score based on changes in facial expression. The selection unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the selection unit analyzes the tone and speed of the voice and calculates an emotion score. The selection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the selection unit calculates an emotion score based on heart rate fluctuations. This allows the selection unit to adjust the criteria of the LLM to be selected according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., an LLM) or a multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0077] The selection unit can improve the accuracy of selection by taking into account the interrelationships between LLMs during selection. The selection unit can, for example, select the optimal combination by taking into account the mutual complementarity between LLMs. The selection unit can, for example, analyze the interrelationships between LLMs and select the most effective combination. The selection unit can also improve the accuracy of selection by taking into account the interactions between LLMs. For example, the selection unit can evaluate the interrelationships between LLMs using correlation coefficients or co-occurrence networks of LLMs. This allows the selection unit to improve the accuracy of selection by taking into account the interrelationships between LLMs. Some or all of the above-described processing in the selection unit can be performed using, for example, AI, or can be performed without using AI. For example, the selection unit can improve the accuracy of selection by using an AI model that inputs LLM interrelationship data and outputs the optimal LLM combination.

[0078] The selection unit may make a selection while taking into consideration attribute information of the LLM provider. The selection unit may select the most appropriate LLM, for example, by taking into consideration the specialty of the LLM provider. The selection unit may, for example, evaluate the reliability of the LLM provider and use this as a selection criterion. The selection unit may also make a selection while taking into consideration the past performance of the LLM provider. For example, the selection unit may collect attribute information of the provider to evaluate the provider's specialty and past performance. This allows the selection unit to make a selection while taking into consideration the attribute information of the LLM provider. Some or all of the above-described processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit may make a selection using an AI model that inputs attribute information of the provider and outputs the most appropriate LLM.

[0079] The selection unit can estimate the user's emotion and adjust the display order of the selected LLMs based on the estimated user emotion. For example, the selection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the selection unit calculates an emotion score based on changes in facial expression. The selection unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the selection unit analyzes the tone and speed of the voice and calculates an emotion score. The selection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the selection unit calculates an emotion score based on heart rate fluctuations. This allows the selection unit to adjust the display order of the selected LLMs based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0080] The selection unit may make the selection taking into consideration the geographic distribution of LLMs. For example, the selection unit may select an LLM that is optimal for the user's region. For example, the selection unit may analyze the geographic distribution of LLMs and select an optimal LLM. The selection unit may also select an optimal LLM taking into consideration the characteristics of each region. For example, the selection unit may collect geographic distribution data to evaluate the number of LLMs per region and regional characteristics. This allows the selection unit to make the selection taking into consideration the geographic distribution of LLMs. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may make the selection using an AI model that inputs geographic distribution data and outputs an optimal LLM.

[0081] The selection unit can improve the accuracy of the selection by referring to literature related to the LLM. For example, the selection unit can refer to literature related to the LLM and select the optimal LLM. For example, the selection unit can improve the accuracy of the selection based on past research results on the LLM. The selection unit can also analyze literature related to the LLM and select the most effective LLM. For example, the selection unit can collect related information by referring to academic papers, technical reports, patent documents, etc. This allows the selection unit to improve the accuracy of the selection by referring to literature related to the LLM. Some or all of the above-mentioned processing in the selection unit can be performed using, for example, AI, or can be performed without AI. For example, the selection unit can improve the accuracy of the selection by using an AI model that inputs related literature data and outputs the optimal LLM.

[0082] The combining unit can estimate the user's emotion and adjust the combining algorithm based on the estimated user's emotion. For example, the combining unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the combining unit calculates an emotion score based on changes in facial expression. The combining unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the combining unit analyzes the tone and speed of the voice and calculates an emotion score. The combining unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the combining unit calculates an emotion score based on heart rate fluctuations. This allows the combining unit to adjust the combining algorithm according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the combining unit may be performed using, for example, AI, or without AI. For example, the combining unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0083] The combining unit can improve the accuracy of combining by taking into account the interrelationships between LLMs during combining. The combining unit can, for example, perform optimal combining by taking into account the mutual complementarity between LLMs. The combining unit can, for example, analyze the interrelationships between LLMs and perform the most effective combining. The combining unit can also improve the accuracy of combining by taking into account the interactions between LLMs. For example, the combining unit can evaluate the interrelationships between LLMs using correlation coefficients or co-occurrence networks of LLMs. This allows the combining unit to improve the accuracy of combining by taking into account the interrelationships between LLMs. Some or all of the above-described processing in the combining unit can be performed using, for example, AI, or can be performed without using AI. For example, the combining unit can improve the accuracy of combining by using an AI model that inputs LLM interrelationship data and outputs the optimal LLM combination.

[0084] When combining, the combining unit can perform the combining while taking into account attribute information of the LLM provider. The combining unit performs optimal combining, for example, taking into account the specialty field of the LLM provider. The combining unit can, for example, evaluate the reliability of the LLM provider and use this as a criterion for combining. The combining unit can also perform combining while taking into account the past performance of the LLM provider. For example, the combining unit collects attribute information of the provider to evaluate the provider's specialty field and past performance. This allows the combining unit to perform combining while taking into account the attribute information of the LLM provider. Some or all of the above-described processing in the combining unit may be performed using, for example, AI, or may be performed without using AI. For example, the combining unit can perform combining using an AI model that inputs attribute information of the provider and outputs optimal LLM combination.

[0085] The combining unit can estimate the user's emotion and adjust the display order of the combined results based on the estimated user's emotion. For example, the combining unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the combining unit calculates an emotion score based on changes in facial expression. The combining unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the combining unit analyzes the tone and speed of the voice and calculates an emotion score. The combining unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the combining unit calculates an emotion score based on heart rate fluctuations. This allows the combining unit to adjust the display order of the combined results according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the combining unit can be performed using, for example, AI, or without AI. For example, the combining unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0086] The combining unit may combine the LLMs taking into account the geographic distribution of the LLMs. For example, the combining unit may combine the LLMs that are optimal for the user's region. For example, the combining unit may analyze the geographic distribution of the LLMs and perform the optimal combination. The combining unit may also combine the optimal LLMs taking into account the characteristics of each region. For example, the combining unit may collect geographic distribution data to evaluate the number of LLMs per region and characteristics unique to each region. This allows the combining unit to perform the combination taking into account the geographic distribution of the LLMs. Some or all of the above-described processing in the combining unit may be performed using, for example, AI, or may be performed without using AI. For example, the combining unit may perform the combination using an AI model that inputs geographic distribution data and outputs the optimal LLM combination.

[0087] The combining unit can improve the accuracy of the combination by referring to literature related to the LLM during the combination. For example, the combining unit can refer to literature related to the LLM to perform optimal combination. For example, the combining unit can improve the accuracy of the combination based on past research results of the LLM. The combining unit can also analyze literature related to the LLM to perform the most effective combination. For example, the combining unit can refer to academic papers, technical reports, patent documents, etc. to collect related information. This allows the combining unit to improve the accuracy of the combination by referring to literature related to the LLM. Some or all of the above-mentioned processing in the combining unit can be performed using, for example, AI, or can be performed without AI. For example, the combining unit can improve the accuracy of the combination by using an AI model that inputs related literature data and outputs optimal LLM combinations.

[0088] The generation unit can estimate the user's emotion and adjust the expression method of the generated solution based on the estimated user's emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expression. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice and calculates an emotion score. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations. This allows the generation unit to adjust the expression method of the generated solution based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0089] The generation unit can adjust the level of detail of the generated solution based on the importance of the solution during generation. For example, the generation unit can include detailed information in a solution with high importance. For example, the generation unit can include concise information in a solution with low importance. The generation unit can also adjust the level of detail of the generated solution according to the importance of the solution. For example, the generation unit can evaluate the importance of the solution using impact analysis or prioritization. This allows the generation unit to adjust the level of detail of the generated solution according to the importance of the solution. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the level of detail of the generated solution using an AI model that inputs solution importance data and outputs the level of detail of the generated solution.

[0090] The generation unit can apply different generation algorithms depending on the category of the solution during generation. For example, the generation unit can apply an algorithm specialized for medical data analysis to a solution in the medical field. For example, the generation unit can apply an algorithm specialized for risk assessment to a solution in the financial field. The generation unit can also apply an optimal generation algorithm depending on the category of the solution. For example, the generation unit can identify the category of the solution using a classification method such as a technology category or a business category. This allows the generation unit to apply an optimal generation algorithm depending on the category of the solution. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can apply a generation algorithm using an AI model that inputs solution category data and outputs an optimal generation algorithm.

[0091] The generation unit can estimate the user's emotion and adjust the length of the generated solution based on the estimated user's emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expression. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice and calculates the emotion score. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates the emotion score based on heart rate fluctuations. This allows the generation unit to adjust the length of the generated solution based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, AI or without AI. For example, the generation unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0092] The generation unit can determine the generation priority based on the submission time of the solution at the time of generation. For example, the generation unit can prioritize generating solutions with a high level of urgency. For example, the generation unit can prioritize generating solutions with an upcoming submission deadline. The generation unit can also determine the generation priority based on the submission time. For example, the generation unit collects submission time data to evaluate the submission deadline and the progress of the project. This allows the generation unit to determine the generation priority based on the submission time of the solution. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can determine the generation priority using an AI model that inputs submission time data and outputs the generation priority.

[0093] The generation unit can adjust the order of generation based on the relevance of the solutions during generation. For example, the generation unit prioritizes generating highly relevant solutions. For example, the generation unit can postpone generating less relevant solutions. The generation unit can also adjust the order of generation based on the relevance of the solutions. For example, the generation unit evaluates the relevance of the solutions using a relevance score or co-occurrence analysis. This allows the generation unit to adjust the order of generation based on the relevance of the solutions. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the order of generation using an AI model that receives relevance data of the solutions as input and outputs the order of generation.

[0094] The providing unit can estimate the user's emotion and adjust the solution provision method based on the estimated user's emotion. For example, the providing unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on changes in facial expression. The providing unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the providing unit analyzes the tone and speed of the voice and calculates an emotion score. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on heart rate fluctuations. This allows the providing unit to adjust the solution provision method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0095] The providing unit can select the optimal solution delivery method by referring to the user's past solution usage history when providing the solution. For example, the providing unit preferentially selects a solution delivery method that the user has used favorably in the past. For example, the providing unit can suggest the optimal solution delivery method based on the user's past usage history. The providing unit can also analyze the user's past solution usage patterns and select the optimal solution delivery method. For example, the providing unit collects solution usage history data to evaluate past usage frequency and usage results. This allows the providing unit to select the optimal solution delivery method based on the user's past solution usage history. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can select the delivery method using an AI model that inputs solution usage history data and outputs the optimal solution delivery method.

[0096] The providing unit can estimate the user's emotion and adjust the solution provision procedure based on the estimated user's emotion. For example, the providing unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on changes in facial expression. The providing unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the providing unit analyzes the tone and speed of the voice and calculates an emotion score. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on heart rate fluctuations. This allows the providing unit to adjust the solution provision procedure according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0097] The providing unit can select the optimal delivery method by taking into account the user's device information when providing the information. For example, if the user is using a smartphone, the providing unit selects a delivery method that matches the screen size. For example, if the user is using a tablet, the providing unit can select a delivery method optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can select a delivery method that is concise and highly visible. For example, the providing unit collects device information to evaluate the device type, OS, and browser information. This allows the providing unit to select the optimal delivery method based on the user's device information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can select the delivery method using an AI model that inputs device information and outputs the optimal delivery method. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, selection unit, combination unit, generation unit, and provision unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the reception device 38 of the smart device 14 and receives user requirements. The selection unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and selects multiple LLMs based on the user requirements. The combination unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and combines the selected LLMs. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and generates a solution based on the combined LLMs. The provision unit is implemented, for example, by the output device 40 of the smart device 14 and provides the generated solution to the user. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned receiving unit, selecting unit, combining unit, generating unit, and providing unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the receiving unit is realized by the microphone 238 of the smart glasses 214 and receives a user's requirements. The selecting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects multiple LLMs based on the user's requirements. The combining unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and combines the selected LLMs. The generating unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a solution based on the combined LLMs. The providing unit is realized, for example, by the speaker 240 of the smart glasses 214 and provides the generated solution to the user. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned receiving unit, selecting unit, combining unit, generating unit, and providing unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the receiving unit is realized by the microphone 238 of the headset-type terminal 314 and receives a user's requirements. The selecting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects multiple LLMs based on the user's requirements. The combining unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and combines the selected LLMs. The generating unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a solution based on the combined LLMs. The providing unit is realized, for example, by the display 343 of the headset-type terminal 314 and provides the generated solution to the user. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned reception unit, selection unit, combination unit, generation unit, and provision unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives a user's requirements. The selection unit is realized by the specific processing unit 290 of the data processing device 12 and selects multiple LLMs based on the user's requirements. The combination unit is realized by the specific processing unit 290 of the data processing device 12 and combines the selected LLMs. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a solution based on the combined LLMs. The provision unit is realized by the speaker 240 of the robot 414 and provides the generated solution to the user.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] When accepting requirements from a user, the acceptance unit can analyze the user's past requirement submission history and select the optimal acceptance method. For example, the acceptance unit can prioritize requirements that the user has frequently submitted in the past. The acceptance unit can also suggest the optimal acceptance time based on the user's past submission history. For example, the acceptance unit can analyze the user's past requirement submission patterns and select the optimal acceptance method. This allows the acceptance unit to select the optimal acceptance method based on the user's past requirement submission history. Some or all of the above-described processing in the acceptance unit may be performed using, for example, AI, or may be performed without using AI. For example, the acceptance unit can select the acceptance method using an AI model that inputs the user's past requirement submission history and outputs the optimal acceptance method.

[0100] When selecting an LLM based on user requirements, the selection unit may take into consideration attribute information of the LLM provider. For example, the selection unit may select the optimal LLM by taking into consideration the specialty of the LLM provider. For example, the selection unit may evaluate the reliability of the LLM provider and use this as a selection criterion. The selection unit may also take into consideration the past performance of the LLM provider when making a selection. For example, the selection unit may collect attribute information of the provider to evaluate the provider's specialty and past performance. This allows the selection unit to make a selection by taking into consideration the attribute information of the LLM provider. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may make a selection using an AI model that inputs attribute information of the provider and outputs the optimal LLM.

[0101] When combining selected LLMs, the combination unit can improve the accuracy of the combination by taking into account the interrelationships between the LLMs. For example, the combination unit can perform optimal combinations by taking into account the mutual complementarity between the LLMs. For example, the combination unit can analyze the interrelationships between the LLMs and perform the most effective combination. The combination unit can also improve the accuracy of the combination by taking into account the interactions between the LLMs. For example, the combination unit can evaluate the interrelationships between the LLMs using correlation coefficients or co-occurrence networks of the LLMs. This allows the combination unit to improve the accuracy of the combination by taking into account the interrelationships between the LLMs. Some or all of the above-described processing in the combination unit may be performed using, for example, AI, or may be performed without using AI. For example, the combination unit can improve the accuracy of the combination by using an AI model that inputs LLM interrelationship data and outputs the optimal LLM combination.

[0102] When generating a solution based on the combined LLM, the generation unit can apply different generation algorithms depending on the category of the solution. For example, to a solution in the medical field, the generation unit can apply an algorithm specialized for medical data analysis. For example, to a solution in the financial field, the generation unit can apply an algorithm specialized for risk assessment. The generation unit can also apply an optimal generation algorithm depending on the category of the solution. For example, the generation unit can identify the category of the solution using a classification method such as a technology category or a business category. This allows the generation unit to apply an optimal generation algorithm depending on the category of the solution. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can apply a generation algorithm using an AI model that inputs solution category data and outputs an optimal generation algorithm.

[0103] When providing a generated solution to a user, the providing unit can select the optimal delivery method by taking into account the user's device information. For example, if the user is using a smartphone, the providing unit can select a delivery method that matches the screen size. For example, if the user is using a tablet, the providing unit can select a delivery method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can select a delivery method that is concise and highly visible. For example, the providing unit collects device information to evaluate the device type, OS, and browser information. This allows the providing unit to select the optimal delivery method based on the user's device information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can select the delivery method using an AI model that inputs device information and outputs the optimal delivery method.

[0104] The reception unit can estimate the user's emotions and adjust the timing of receiving requirements based on the estimated user emotions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice and calculates an emotion score. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations. This allows the reception unit to adjust the timing of receiving requirements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0105] The selection unit can estimate the user's emotion and adjust the criteria of the LLM to be selected based on the estimated user's emotion. For example, the selection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the selection unit calculates an emotion score based on changes in facial expression. The selection unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the selection unit analyzes the tone and speed of the voice and calculates an emotion score. The selection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the selection unit calculates an emotion score based on heart rate fluctuations. This allows the selection unit to adjust the criteria of the LLM to be selected according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or without AI. For example, the selection unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0106] The combining unit can estimate the user's emotion and adjust the combining algorithm based on the estimated user's emotion. For example, the combining unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the combining unit calculates an emotion score based on changes in facial expression. The combining unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the combining unit analyzes the tone and speed of the voice and calculates an emotion score. The combining unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the combining unit calculates an emotion score based on heart rate fluctuations. This allows the combining unit to adjust the combining algorithm according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the combining unit may be performed using, for example, AI, or without AI. For example, the combining unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0107] The generation unit can estimate the user's emotion and adjust the expression method of the generated solution based on the estimated user's emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expression. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice and calculates an emotion score. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations. This allows the generation unit to adjust the expression method of the generated solution based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0108] The providing unit can estimate the user's emotion and adjust the solution provision method based on the estimated user's emotion. For example, the providing unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on changes in facial expression. The providing unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the providing unit analyzes the tone and speed of the voice and calculates an emotion score. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on heart rate fluctuations. This allows the providing unit to adjust the solution provision method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or without AI. For example, the providing unit can input image data of a user taken with a camera into the generating AI and have the generating AI estimate the user's emotions.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The reception unit receives user requirements. The user requirements may be in text format, voice format, or requirements related to specific fields. The reception unit analyzes the text data entered by the user and extracts the requirements. It can also analyze voice input and convert the requirements into text data. For example, voice recognition technology can be used to convert the user's voice into text data. Step 2: The selection unit selects multiple LLMs based on the requirements received by the reception unit. Based on the user's requirements, the selection unit selects an LLM specialized for a specific task or a general-purpose LLM. For example, it can select an LLM that excels in natural language understanding or data analysis. Step 3: The combiner combines the LLMs selected by the selector. The combiner effectively combines the selected LLMs using algorithms such as weighted averaging and boosting. The combiner integrates the outputs of the selected LLMs to generate an optimal solution. Step 4: The generator generates a solution based on the LLMs combined by the combiner. Based on the output of the combined LLMs, the generator generates solutions such as report formats, action plans, and technical proposals. For example, it can generate a diagnostic support solution in the medical field or a risk assessment solution in the financial field. Step 5: The providing unit provides the solution generated by the generating unit to the user. The providing unit displays the generated solution to the user through a web application or a mobile application. The providing unit can also send the generated solution by email.

[0111] 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.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0113] 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.

[0114] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0129] 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.

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

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0134] The 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.

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

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

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

[0138] Fig. 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.

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

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

[0141] In the 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.

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

[0143] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0145] 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.

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

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0150] The 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.

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

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

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

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0162] 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.

[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] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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, in order to avoid confusion and to 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.

[0181] 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.

[0182] [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives user requirements; a selection unit that selects a plurality of LLMs based on the requirements received by the reception unit; a combining unit that combines the LLMs selected by the selecting unit; a generating unit for generating a solution based on the LLMs combined by the combining unit; a providing unit that provides the solution generated by the generating unit. A system characterized by:

2. The selection unit Choose an LLM based on your requirements 2. The system of claim 1.

3. The coupling portion is Use an algorithm to combine selected LLMs 2. The system of claim 1.

4. The generation unit Generate solutions based on combined LLMs 2. The system of claim 1.

5. The providing unit Providing the generated solution to the user 2. The system of claim 1.

6. The generation unit Generate diagnostic support solutions in the medical field 2. The system of claim 1.

7. The generation unit Generate risk assessment solutions for the financial sector 2. The system of claim 1.

8. The reception unit Estimate user emotions and adjust the timing of accepting requirements based on the estimated user emotions 2. The system of claim 1.

9. The reception unit Analyze the user's past requirements submission history and select the reception method 2. The system of claim 1.

10. The reception unit Filtering requirements based on users' current projects and areas of interest as they arrive 2. The system of claim 1.

Images