system

Abstract

The system according to this embodiment aims to ensure the reliability of the products generated by the AI ​​through expert supervision. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a request unit, a checking unit, and a storage unit. The reception unit receives requests from clients. The analysis unit analyzes the requests received by the reception unit. The request unit sends requests to experts identified by the analysis unit. The checking unit has experts who have been requested by the request unit perform checks. The storage unit stores the results obtained by the checking unit.

Description

Technical Field

[0004] ،

[0006] , , , , , ,

[0005] , , ,

[0003] , , , ,

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

Background Art

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is impossible to completely prevent the generation of incorrect information by generative AI, and it is difficult to ensure the reliability of the generated product.

[0005] The system according to the embodiment aims to ensure the reliability of the product by generative AI by an expert.

Means for Solving the Problems

[0007] The system according to this embodiment allows experts to ensure the reliability of the products generated by the AI. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The hallucination prevention system according to an embodiment of the present invention is a sharing economy service for addressing the "hallucination" problem where generating AI generates erroneous information. This system is based on the premise that once generating AI becomes capable of performing highly advanced reasoning at a doctoral level, only experts of the same level can judge its accuracy. The number of users using generating AI for professional purposes such as research and development and creative work is rapidly increasing, making the reliability of generating AI output an urgent issue. This system matches "clients who require advanced hallucination checks" with "experts in various fields registered in this system," and experts check the requested target output to ensure reliability. This aims to achieve both "hallucination prevention" and "utilization of expert resources." Specifically, it consists of the following steps. First, the client specifies a range of parts of the generating AI output that are suspected of being hallucinatory and submits a request to the system for content verification. At this time, the maximum reward and deadline are also specified. Next, the system analyzes the request from the client, identifies the necessary specialized fields and skill levels for the check, and simultaneously sends requests to all experts who match the case. Experts confirm the request conditions and accept the request. Experts utilize their specialized knowledge to combat hallucination. Furthermore, among the verification results by checkers, those that receive high ratings from clients are stored in the search-enhanced generation database and linked as reference information when similar requests are made in the future. This checker support database function improves the efficiency of checkers' work in subsequent tasks and increases the reliability of checks. This mechanism significantly improves the reliability of the output of the generating AI and allows for the effective use of expert resources. For example, the accuracy of the output of the generating AI is particularly important in research, technology development, due diligence, and business planning. By using this system, the reliability of AI-generated results is greatly improved. This system is also very effective for creators who require complex technical and historical research, such as screenwriters, science fiction writers, historical writers, and manga artists. By ensuring the accuracy of AI-generated results, this system greatly improves the quality of creative activities.This significantly improves the reliability of the hallucination prevention system's output from the generated AI and allows for the effective utilization of expert resources.

[0029] The hallucination prevention system according to this embodiment comprises a reception unit, an analysis unit, a request unit, a checking unit, and a storage unit. The reception unit receives requests from requesters. Requests from requesters include, but are not limited to, written requests, oral requests, and emails. For example, the reception unit can receive requests from requesters to check the content of output results of generated AI, specifying a range of parts that are suspected of being hallucinatory. The analysis unit analyzes the requests received by the reception unit. The analysis unit can analyze requests using methods such as text analysis, data mining, and statistical analysis. The analysis unit analyzes the requests and identifies the necessary areas of expertise and skill levels for checking. The request unit issues requests to the experts identified by the analysis unit. For example, the request unit can issue requests to all experts who match the case simultaneously. The request unit can issue requests using mass email or a notification system. The checking unit has the experts who have been requested by the request unit perform checks. The checking unit can perform checks using methods such as review, verification, and testing. The checking unit has experts confirm the request conditions, accept the request, and perform the check. The storage unit stores the results obtained by the checking unit. The storage unit can store the results, for example, by saving them to a database or in report format. The storage unit stores the results of the checker's verification that received high ratings from the requester in a search, extension, and generation database. As a result, the hallucination prevention system according to this embodiment can efficiently receive requests from clients, analyze them, request them from experts, perform checks, and store the results. Some or all of the above-described processes in the receiving unit, analysis unit, request unit, checking unit, and storage unit may be performed using AI, for example, or without using AI. For example, the receiving unit can input requests from clients into AI and have the AI ​​perform the request acceptance. The analysis unit can input requests into AI and have the AI ​​perform the analysis of requests. The request unit can input requests into AI and have the AI ​​perform requests to experts. The checking unit can input requests into AI and have the AI ​​perform checks.The data storage unit can input the check results into the AI ​​and have the AI ​​perform the task of storing the results.

[0030] The reception department receives requests from clients. These requests may include, but are not limited to, written documents, verbal requests, and emails. For example, a client can request a review of the output of the generated AI, specifying the portion suspected of being hallucinatory. Specifically, the reception department has interfaces for receiving information from clients in various formats. For instance, when receiving requests via a web portal, clients can enter the necessary information into a dedicated form and highlight the portions suspected of being hallucinatory. In the case of verbal requests, speech recognition technology can be used to transcribe the request into text and input it into the system. For email requests, there is a mechanism to automatically analyze emails sent to a dedicated email address and extract the request content. Furthermore, the reception department performs initial filtering of request content, automatically detecting clearly inappropriate requests or incomplete information and prompting the client to make corrections. This allows the reception department to efficiently and accurately receive requests and smoothly pass them on to the next processing step.

[0031] The analysis department analyzes requests received by the reception department. The analysis department can analyze requests using methods such as text analysis, data mining, and statistical analysis. Specifically, the analysis department utilizes natural language processing techniques to analyze the request in detail and identify areas suspected of hallucination. For example, text analysis can be used to understand the context of the request and extract suspicious sections using topic modeling and sentiment analysis. Data mining involves referencing past request data and similar cases to identify patterns and trends. Statistical analysis uses statistical methods to evaluate the reliability and consistency of the request. Furthermore, based on the request, the analysis department identifies the necessary expertise and skill levels for the check. For example, a request concerning hallucination in the medical field would require medical professionals or experts with skills in medical data analysis. This allows the analysis department to accurately understand the request and prepare to refer it to the appropriate experts.

[0032] The requesting department issues requests to experts identified by the analysis department. For example, the requesting department can issue requests to all experts who match the project simultaneously. Specifically, the requesting department refers to an expert database and selects the expert best suited to the request. The expert database contains detailed records of each expert's skill set, past performance, and evaluations, which are used to identify the most suitable expert. The requesting department can issue requests using mass email or a notification system. For example, after matching the request content with the experts' skills, it can send request emails to the selected experts simultaneously, requesting a prompt response. It is also possible to send real-time notifications to experts' smartphones or computers using a notification system. The requesting department also has functions to manage the progress of requests and track responses from experts. This allows the requesting department to efficiently issue requests to experts and encourage prompt responses.

[0033] The checking department employs experts who have been commissioned by the requesting department to perform checks. The checking department can perform checks using methods such as review, verification, and testing. Specifically, the checking department manages the process by which experts confirm the request conditions, accept the request, and perform the checks. Based on the request, experts thoroughly review the output results of the generative AI and check for hallucination. In the review, they refer to literature and databases to verify whether the output of the generative AI is accurate. In the verification, they use actual data and experiments to confirm whether the output of the generative AI matches reality. In the test, they reproduce the output of the generative AI and check whether similar results can be obtained. The checking department records the results of the checks performed by the experts and creates a report to report to the requesting department. Furthermore, the checking department can collect feedback from experts and use it to improve the system. This allows the checking department to perform accurate checks on the request and provide reliable results to the requesting department.

[0034] The storage unit stores the results obtained by the checking unit. The storage unit can store results, for example, by saving them to a database or in report format. Specifically, the storage unit centrally manages the results provided by the checking unit, making them available for future reference and analysis. The database stores detailed information for each request, check results, and expert feedback. This enables trend analysis and pattern recognition based on past request data. Furthermore, the storage unit stores the results of the checkers' evaluations that received high ratings from the requesters in a search-enhanced generation database. This allows the system to respond to future requests with greater accuracy based on past high-rated results. The storage unit also prioritizes data security and privacy protection; stored data is encrypted and protected from unauthorized access. This enables the storage unit to achieve highly reliable data management and improve the overall performance and reliability of the system.

[0035] The reception department can receive requests from clients to specify a range of parts of the output of the generated AI that are suspected of being hallucinatory and submit a request for content verification. For example, the reception department can receive requests from clients to specify a range of parts of the output of the generated AI that are suspected of being hallucinatory and submit a request for content verification. The reception department can also receive requests from clients to specify a maximum reward and a deadline for content verification. This allows clients to request content verification by specifying a range of parts that are suspected of being hallucinatory. Parts that are suspected of being hallucinatory include, but are not limited to, information that is contrary to the facts or erroneous inferences. Some or all of the above processing in the reception department may be performed using, for example, AI, or not using AI. For example, the reception department can input a request from a client into the AI ​​and have the AI ​​process the acceptance of the request.

[0036] The analysis department can analyze requests from clients and identify the necessary areas of expertise and skill levels for the checks. For example, the analysis department can analyze requests from clients using methods such as text analysis, data mining, and statistical analysis. The analysis department analyzes requests and identifies the necessary areas of expertise and skill levels for the checks. This allows the analysis department to analyze requests from clients and identify the necessary areas of expertise and skill levels for the checks. Required areas of expertise include, but are not limited to, medical, legal, and technical fields. Required skill levels include, but are not limited to, beginner, intermediate, and advanced levels. Some or all of the above processing in the analysis department may be performed using, for example, AI, or not. For example, the analysis department can input requests into an AI and have the AI ​​perform the analysis of the requests.

[0037] The requesting department can simultaneously issue requests to all experts who match the case. The requesting department can, for example, issue requests to all experts who match the case simultaneously. The requesting department can issue requests using mass email or notification systems. This allows requests to be issued simultaneously to all experts who match the case. Methods for issuing requests simultaneously include, but are not limited to, mass email or notification systems. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input the request into AI and have the AI ​​execute the request to experts.

[0038] The checking unit allows experts to review the request conditions, accept the request, and perform the check. For example, the checking unit can perform the check using methods such as review, verification, and testing. This allows experts to review the request conditions, accept the request, and perform the check. Request conditions include, but are not limited to, deadlines, quality standards, and compensation. Some or all of the processes described above in the checking unit may be performed using, for example, AI, or not using AI. For example, the checking unit can input the request into AI and have the AI ​​perform the check.

[0039] The storage unit can store the results of the checker's verification that received high ratings from the client in the search extension generation database. For example, the storage unit stores the results of the checker's verification that received high ratings from the client in the search extension generation database. This allows the storage unit to store the results that received high ratings from the client in the search extension generation database. Results that received high ratings include, but are not limited to, client feedback and evaluation scores. Some or all of the above processing in the storage unit may be performed using, for example, AI, or not using AI. For example, the storage unit can input the check results into AI and have AI perform the storage of the results.

[0040] The reception department can analyze the client's past request history and select the most suitable reception method. For example, the reception department may prioritize suggesting reception methods that the client has frequently used in the past. The reception department can also select the most efficient reception method based on the client's past request history. Based on the client's past request history, the reception department can also suggest the most suitable reception method for a specific time slot. This allows the reception department to analyze the client's past request history and select the most suitable reception method. The most suitable reception method includes, but is not limited to, online forms and telephone reception. Some or all of the above processes in the reception department may be performed using AI, for example, or not. For example, the reception department can input the client's past request history into AI and have the AI ​​select the most suitable reception method.

[0041] The reception department can filter requests based on the requester's current projects and areas of interest when receiving them. For example, the reception department can prioritize requests related to projects the requester is currently working on. The reception department can also filter requests based on the requester's areas of interest to ensure they are relevant. The reception department can also suggest the most suitable requests based on the progress of the requester's current projects. This allows for filtering based on the requester's current projects and areas of interest. Current projects and areas of interest include, but are not limited to, project management tools and survey results. Some or all of the above processing in the reception department may be performed using AI, for example, or not. For example, the reception department can input data on the requester's current projects and areas of interest into an AI and have the AI ​​perform the filtering.

[0042] The reception department can prioritize requests based on their relevance, taking into account the requester's geographical location. For example, if a requester is in a specific region, the reception department will prioritize requests related to that region. The reception department can also suggest the most relevant requests based on the requester's current location. The reception department can also filter requests based on the requester's geographical location. This allows the reception department to prioritize requests based on their relevance, taking into account the requester's geographical location. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the reception department may be performed using AI, for example, or without AI. For example, the reception department can input the requester's geographical location information into AI and have the AI ​​perform the filtering.

[0043] The reception department can analyze the requester's social media activity upon receiving a request and accept relevant requests. For example, the reception department can prioritize requests related to the requester's areas of interest based on their social media activity. The reception department can also suggest the most suitable requests based on the requester's social media activity. The reception department can also analyze the requester's social media activity and filter out highly relevant requests. This allows the reception department to analyze the requester's social media activity and accept relevant requests. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the above processing in the reception department may be performed using, for example, AI, or not. For example, the reception department can input the requester's social media activity data into an AI and have the AI ​​perform the analysis.

[0044] The analysis department can adjust the level of detail of the analysis based on the importance of the request. For example, the analysis department will perform a detailed analysis for high-priority requests. The analysis department can also perform a simplified analysis for low-priority requests. The analysis department can also dynamically adjust the level of detail of the analysis according to the importance of the request. This allows the level of detail of the analysis to be adjusted based on the importance of the request. The importance of the request includes, but is not limited to, business impact and urgency. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input request importance data into AI and have the AI ​​adjust the level of detail of the analysis.

[0045] The analysis department can apply different analysis algorithms depending on the category of the request during analysis. For example, the analysis department can apply a specialized analysis algorithm to a technical request. The analysis department can also apply a creative analysis algorithm to a creative request. The analysis department can also select the most suitable analysis algorithm depending on the category of the request. This allows for the application of different analysis algorithms depending on the category of the request. The categories of requests include, but are not limited to, technology, marketing, and legal. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input the category data of the request into an AI and have the AI ​​perform the application of the analysis algorithm.

[0046] The analysis department can determine the priority of analyses based on the submission timing of the requests. For example, the analysis department can prioritize analyses for urgent requests. The analysis department can also prioritize analyses for requests with approaching deadlines. The analysis department can also dynamically adjust the priority of analyses according to the submission timing of the requests. This allows the analysis priority to be determined based on the submission timing of the requests. The submission timing of requests includes, but is not limited to, the submission date and deadline. Some or all of the above processes in the analysis department may be performed using AI, for example, or not. For example, the analysis department can input the submission timing data of the requests into an AI and have the AI ​​perform the priority determination.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the requests during the analysis process. For example, the analysis unit will prioritize analyzing requests that are related to other requests. The analysis unit can also determine the optimal order of analysis based on the relevance of the requests. The analysis unit can also dynamically adjust the order of analysis, taking into account the relevance of the requests. This allows the order of analysis to be adjusted based on the relevance of the requests. The relevance of the requests includes, but is not limited to, the degree of theme matching and past relevance. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the relevance data of the requests into AI and have the AI ​​perform the order adjustment.

[0048] The requesting department can adjust the level of detail of a request based on the importance of the expert at the time of the request. For example, the requesting department can provide detailed requests to highly important experts. The requesting department can also provide simplified requests to less important experts. The requesting department can also dynamically adjust the level of detail of a request according to the importance of the expert. This allows the level of detail of a request to be adjusted based on the importance of the expert. The importance of an expert includes, but is not limited to, years of experience and past performance. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input expert importance data into AI and have the AI ​​perform the adjustment of the level of detail.

[0049] The requesting unit can apply different requesting algorithms depending on the category of the expert when a request is made. For example, the requesting unit can apply a specialized requesting algorithm to a technical expert. The requesting unit can also apply a creative requesting algorithm to a creative expert. The requesting unit can also select the most suitable requesting algorithm depending on the category of the expert. This allows for the application of different requesting algorithms depending on the category of the expert. Examples of expert categories include, but are not limited to, medical, legal, and technical fields. Some or all of the above processing in the requesting unit may be performed using AI, for example, or not using AI. For example, the requesting unit can input expert category data into an AI and have the AI ​​perform the application of the requesting algorithm.

[0050] The requesting department can determine the priority of requests based on the submission timing of experts. For example, the requesting department will give the highest priority to urgent requests. The requesting department may also give priority to requests with approaching deadlines. The requesting department can also dynamically adjust the priority of requests according to the submission timing of experts. This allows the priority of requests to be determined based on the submission timing of experts. The submission timing of experts includes, but is not limited to, the submission date and deadline. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input expert submission timing data into AI and have the AI ​​perform the priority determination.

[0051] The requesting unit can adjust the order of requests based on the relevance of experts when a request is made. For example, the requesting unit will prioritize requests if the expert is related to other requests. The requesting unit can also determine the optimal order of requests based on the relevance of experts. The requesting unit can also dynamically adjust the order of requests, taking into account the relevance of experts. This allows the order of requests to be adjusted based on the relevance of experts. Expert relevance includes, but is not limited to, the degree of theme matching and past relevance. Some or all of the above processing in the requesting unit may be performed using AI, for example, or not using AI. For example, the requesting unit can input expert relevance data into AI and have the AI ​​perform the order adjustment.

[0052] The checking unit can analyze the past history of the request content during the checking process to select the optimal checking method. For example, the checking unit can select the most efficient checking method from the past history of the request content. The checking unit can also propose the optimal checking method for a specific time period based on the past history of the request content. The checking unit can also analyze the past history of the request content and dynamically adjust the optimal checking method. This allows the checking unit to analyze the past history of the request content and select the optimal checking method. The optimal checking method includes, but is not limited to, past history analysis and algorithm selection. Some or all of the above processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input past history data of the request content into AI and have the AI ​​perform the selection of the checking method.

[0053] The checking unit can customize the checking methods based on the current status of the request during the checking process. For example, the checking unit can select the optimal checking method according to the current status of the request. The checking unit can also propose a specific checking method based on the current status of the request. The checking unit can also dynamically customize the checking methods considering the current status of the request. This allows the checking methods to be customized based on the current status of the request. The current status of the request includes, but is not limited to, progress status and resource status. Some or all of the above-described processes in the checking unit may be performed using, for example, AI, or not using AI. For example, the checking unit can input data on the current status of the request into the AI ​​and have the AI ​​perform the customization of the methods.

[0054] The checking unit can select the optimal checking method while considering the geographical location information of the request. For example, if the requester is in a specific region, the checking unit will prioritize processing checks related to that region. The checking unit can also suggest the optimal checking method based on the requester's current location. The checking unit can also filter highly relevant checks based on the requester's geographical location information. This allows the checking unit to select the optimal checking method while considering the geographical location information of the request. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the geographical location information of the request into AI and have the AI ​​select the checking method.

[0055] The checking unit can analyze the social media activity of the request and propose checking methods during the checking process. For example, the checking unit can prioritize processing checking items related to the client's areas of interest from the client's social media activity. The checking unit can also propose the most suitable checking method based on the client's social media activity. The checking unit can also analyze the client's social media activity and filter out highly relevant checking items. This allows the checking unit to analyze the social media activity of the request and propose checking methods. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the processing described above in the checking unit may be performed using AI, for example, or not. For example, the checking unit can input the social media activity data of the request into AI and have the AI ​​propose methods.

[0056] The storage unit can optimize the storage algorithm by referring to past stored data during storage. For example, the storage unit can select the optimal storage algorithm based on past stored data. The storage unit can also propose the optimal storage algorithm for a specific time period by referring to past stored data. The storage unit can also analyze past stored data and dynamically adjust the optimal storage algorithm. This allows the storage algorithm to be optimized by referring to past stored data. The storage algorithm includes, but is not limited to, referring to past data and adjusting the algorithm. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input past stored data into AI and have the AI ​​perform algorithm optimization.

[0057] The storage unit can select storage data based on the current status of the request during storage. For example, the storage unit can select the optimal storage data according to the current status of the request. The storage unit can also suggest specific storage data based on the current status of the request. The storage unit can also dynamically select storage data considering the current status of the request. This allows for the selection of storage data based on the current status of the request. The current status of the request includes, but is not limited to, progress status and resource status. Some or all of the above processing in the storage unit may be performed using, for example, AI, or not using AI. For example, the storage unit can input the current status data of the request into AI and have AI perform the data selection.

[0058] The storage unit can weight the stored data based on the submission timing of the requests during storage. For example, the storage unit will store requests with approaching deadlines with higher weighting. The storage unit can also store requests with distant deadlines with normal weighting. The storage unit can also dynamically adjust the weighting of the stored data according to the submission timing of the requests. This allows the storage unit to weight the stored data based on the submission timing of the requests. The submission timing includes, but is not limited to, the submission date and deadline. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the request submission timing data into AI and have AI perform the weighting.

[0059] The storage unit can select data to store based on the relevance of the requests during storage. For example, the storage unit will prioritize storing requests that are related to other requests. The storage unit can also select the most suitable data to store based on the relevance of the requests. The storage unit can also dynamically select data to store, taking into account the relevance of the requests. This allows for the selection of data to be stored based on the relevance of the requests. The relevance of the requests includes, but is not limited to, the degree of theme matching and past relevance. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input request relevance data into AI and have AI perform data selection.

[0060] The storage unit can select data to store based on the importance of the request during storage. For example, the storage unit will prioritize storing requests with high importance. The storage unit can also perform normal storage for requests with low importance. The storage unit can also dynamically adjust the selection of data to store according to the importance of the request. This allows for the selection of data to be stored based on the importance of the request. The importance of a request includes, but is not limited to, business impact and urgency. Some or all of the above processing in the storage unit may be performed using, for example, AI, or not using AI. For example, the storage unit can input request importance data into AI and have the AI ​​perform the data selection.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The reception department can analyze a client's past request history and select the most suitable reception method. For example, it can prioritize suggesting reception methods that the client has frequently used in the past. It can also select the most efficient reception method based on the client's past request history. Based on the client's past request history, it can also suggest the most suitable reception method for a specific time slot. This allows the reception department to analyze the client's past request history and select the most suitable reception method. The most suitable reception method includes, but is not limited to, online forms and telephone reception. Some or all of the above processes in the reception department may be performed using AI, for example, or not. For example, the reception department can input the client's past request history into AI and have the AI ​​select the most suitable reception method.

[0063] The requesting department can adjust the level of detail of a request based on the importance of the expert at the time of the request. For example, it can provide detailed request information to highly important experts and simplified request information to less important experts. It can also dynamically adjust the level of detail of a request according to the importance of the expert. This allows for adjustment of the level of detail of a request based on the importance of the expert. The importance of an expert includes, but is not limited to, years of experience and past performance. Some or all of the above processing in the requesting department may be performed using AI, for example, or not using AI. For example, the requesting department can input expert importance data into AI and have the AI ​​perform the adjustment of the level of detail.

[0064] The checking unit can analyze the past history of the request content during the checking process to select the optimal checking method. For example, it can select the most efficient checking method from the past history of the request content. It can also propose the optimal checking method for a specific time period based on the past history of the request content. It can also dynamically adjust the optimal checking method by analyzing the past history of the request content. This allows for the selection of the optimal checking method by analyzing the past history of the request content. The optimal checking method includes, but is not limited to, past history analysis and algorithm selection. Some or all of the above-described processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input past history data of the request content into AI and have the AI ​​perform the selection of the checking method.

[0065] The storage unit can optimize the storage algorithm by referring to past stored data during storage. For example, it can select the optimal storage algorithm based on past stored data. It can also propose the optimal storage algorithm for a specific time period by referring to past stored data. It can also dynamically adjust the optimal storage algorithm by analyzing past stored data. This allows the storage algorithm to be optimized by referring to past stored data. The storage algorithm includes, but is not limited to, referring to past data and adjusting the algorithm. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input past stored data into AI and have the AI ​​perform algorithm optimization.

[0066] The storage unit can weight the stored data based on the submission timing of the requests during storage. For example, requests with approaching deadlines can be stored with a higher weight. Requests with distant deadlines can be stored with the normal weighting. The weighting of the stored data can also be dynamically adjusted according to the submission timing of the requests. This allows the stored data to be weighted based on the submission timing of the requests. The submission timing includes, but is not limited to, the submission date and deadline. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the submission timing data of the requests into the AI ​​and have the AI ​​perform the weighting.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The reception department receives requests from clients. Requests from clients can be in written form, verbally, or via email. For example, a client can request a review of the output of the generated AI, specifying a range of parts that they suspect may contain hallucinations. Step 2: The Analysis Department analyzes the requests received by the Reception Department. The Analysis Department analyzes the requests using methods such as text analysis, data mining, and statistical analysis to identify the areas of expertise and skill levels required for the checks. Step 3: The requesting department issues a request to the experts identified by the analysis department. The requesting department can issue a request to all experts who match the case simultaneously, and can do so via mass email or a notification system. Step 4: The checking department employs experts who have been commissioned by the requesting department to perform the checks. The checking department uses methods such as review, verification, and testing to perform the checks, and the experts confirm the request conditions and accept the commission to perform the checks. Step 5: The storage unit stores the results obtained by the checking unit. The storage unit stores the results in a database or in report format, and stores the results that received high ratings from the client among the checker's verification results in the search and extension generation database.

[0069] (Example of form 2) The hallucination prevention system according to an embodiment of the present invention is a sharing economy service for addressing the "hallucination" problem where generating AI generates erroneous information. This system is based on the premise that once generating AI becomes capable of performing highly advanced reasoning at a doctoral level, only experts of the same level can judge its accuracy. The number of users using generating AI for professional purposes such as research and development and creative work is rapidly increasing, making the reliability of generating AI output an urgent issue. This system matches "clients who require advanced hallucination checks" with "experts in various fields registered in this system," and experts check the requested target output to ensure reliability. This aims to achieve both "hallucination prevention" and "utilization of expert resources." Specifically, it consists of the following steps. First, the client specifies a range of parts of the generating AI output that are suspected of being hallucinatory and submits a request to the system for content verification. At this time, the maximum reward and deadline are also specified. Next, the system analyzes the request from the client, identifies the necessary specialized fields and skill levels for the check, and simultaneously sends requests to all experts who match the case. Experts confirm the request conditions and accept the request. Experts utilize their specialized knowledge to combat hallucination. Furthermore, among the verification results by checkers, those that receive high ratings from clients are stored in the search-enhanced generation database and linked as reference information when similar requests are made in the future. This checker support database function improves the efficiency of checkers' work in subsequent tasks and increases the reliability of checks. This mechanism significantly improves the reliability of the output of the generating AI and allows for the effective use of expert resources. For example, the accuracy of the output of the generating AI is particularly important in research, technology development, due diligence, and business planning. By using this system, the reliability of AI-generated results is greatly improved. This system is also very effective for creators who require complex technical and historical research, such as screenwriters, science fiction writers, historical writers, and manga artists. By ensuring the accuracy of AI-generated results, this system greatly improves the quality of creative activities.This significantly improves the reliability of the hallucination prevention system's output from the generated AI and allows for the effective utilization of expert resources.

[0070] The hallucination prevention system according to this embodiment comprises a reception unit, an analysis unit, a request unit, a checking unit, and a storage unit. The reception unit receives requests from requesters. Requests from requesters include, but are not limited to, written requests, oral requests, and emails. For example, the reception unit can receive requests from requesters to check the content of output results of generated AI, specifying a range of parts that are suspected of being hallucinatory. The analysis unit analyzes the requests received by the reception unit. The analysis unit can analyze requests using methods such as text analysis, data mining, and statistical analysis. The analysis unit analyzes the requests and identifies the necessary areas of expertise and skill levels for checking. The request unit issues requests to the experts identified by the analysis unit. For example, the request unit can issue requests to all experts who match the case simultaneously. The request unit can issue requests using mass email or a notification system. The checking unit has the experts who have been requested by the request unit perform checks. The checking unit can perform checks using methods such as review, verification, and testing. The checking unit has experts confirm the request conditions, accept the request, and perform the check. The storage unit stores the results obtained by the checking unit. The storage unit can store the results, for example, by saving them to a database or in report format. The storage unit stores the results of the checker's verification that received high ratings from the requester in a search, extension, and generation database. As a result, the hallucination prevention system according to this embodiment can efficiently receive requests from clients, analyze them, request them from experts, perform checks, and store the results. Some or all of the above-described processes in the receiving unit, analysis unit, request unit, checking unit, and storage unit may be performed using AI, for example, or without using AI. For example, the receiving unit can input requests from clients into AI and have the AI ​​perform the request acceptance. The analysis unit can input requests into AI and have the AI ​​perform the analysis of requests. The request unit can input requests into AI and have the AI ​​perform requests to experts. The checking unit can input requests into AI and have the AI ​​perform checks.The data storage unit can input the check results into the AI ​​and have the AI ​​perform the task of storing the results.

[0071] The reception department receives requests from clients. These requests may include, but are not limited to, written documents, verbal requests, and emails. For example, a client can request a review of the output of the generated AI, specifying the portion suspected of being hallucinatory. Specifically, the reception department has interfaces for receiving information from clients in various formats. For instance, when receiving requests via a web portal, clients can enter the necessary information into a dedicated form and highlight the portions suspected of being hallucinatory. In the case of verbal requests, speech recognition technology can be used to transcribe the request into text and input it into the system. For email requests, there is a mechanism to automatically analyze emails sent to a dedicated email address and extract the request content. Furthermore, the reception department performs initial filtering of request content, automatically detecting clearly inappropriate requests or incomplete information and prompting the client to make corrections. This allows the reception department to efficiently and accurately receive requests and smoothly pass them on to the next processing step.

[0072] The analysis department analyzes requests received by the reception department. The analysis department can analyze requests using methods such as text analysis, data mining, and statistical analysis. Specifically, the analysis department utilizes natural language processing techniques to analyze the request in detail and identify areas suspected of hallucination. For example, text analysis can be used to understand the context of the request and extract suspicious sections using topic modeling and sentiment analysis. Data mining involves referencing past request data and similar cases to identify patterns and trends. Statistical analysis uses statistical methods to evaluate the reliability and consistency of the request. Furthermore, based on the request, the analysis department identifies the necessary expertise and skill levels for the check. For example, a request concerning hallucination in the medical field would require medical professionals or experts with skills in medical data analysis. This allows the analysis department to accurately understand the request and prepare to refer it to the appropriate experts.

[0073] The requesting department issues requests to experts identified by the analysis department. For example, the requesting department can issue requests to all experts who match the project simultaneously. Specifically, the requesting department refers to an expert database and selects the expert best suited to the request. The expert database contains detailed records of each expert's skill set, past performance, and evaluations, which are used to identify the most suitable expert. The requesting department can issue requests using mass email or a notification system. For example, after matching the request content with the experts' skills, it can send request emails to the selected experts simultaneously, requesting a prompt response. It is also possible to send real-time notifications to experts' smartphones or computers using a notification system. The requesting department also has functions to manage the progress of requests and track responses from experts. This allows the requesting department to efficiently issue requests to experts and encourage prompt responses.

[0074] The checking department employs experts who have been commissioned by the requesting department to perform checks. The checking department can perform checks using methods such as review, verification, and testing. Specifically, the checking department manages the process by which experts confirm the request conditions, accept the request, and perform the checks. Based on the request, experts thoroughly review the output results of the generative AI and check for hallucination. In the review, they refer to literature and databases to verify whether the output of the generative AI is accurate. In the verification, they use actual data and experiments to confirm whether the output of the generative AI matches reality. In the test, they reproduce the output of the generative AI and check whether similar results can be obtained. The checking department records the results of the checks performed by the experts and creates a report to report to the requesting department. Furthermore, the checking department can collect feedback from experts and use it to improve the system. This allows the checking department to perform accurate checks on the request and provide reliable results to the requesting department.

[0075] The storage unit stores the results obtained by the checking unit. The storage unit can store results, for example, by saving them to a database or in report format. Specifically, the storage unit centrally manages the results provided by the checking unit, making them available for future reference and analysis. The database stores detailed information for each request, check results, and expert feedback. This enables trend analysis and pattern recognition based on past request data. Furthermore, the storage unit stores the results of the checkers' evaluations that received high ratings from the requesters in a search-enhanced generation database. This allows the system to respond to future requests with greater accuracy based on past high-rated results. The storage unit also prioritizes data security and privacy protection; stored data is encrypted and protected from unauthorized access. This enables the storage unit to achieve highly reliable data management and improve the overall performance and reliability of the system.

[0076] The reception department can receive requests from clients to specify a range of parts of the output of the generated AI that are suspected of being hallucinatory and submit a request for content verification. For example, the reception department can receive requests from clients to specify a range of parts of the output of the generated AI that are suspected of being hallucinatory and submit a request for content verification. The reception department can also receive requests from clients to specify a maximum reward and a deadline for content verification. This allows clients to request content verification by specifying a range of parts that are suspected of being hallucinatory. Parts that are suspected of being hallucinatory include, but are not limited to, information that is contrary to the facts or erroneous inferences. Some or all of the above processing in the reception department may be performed using, for example, AI, or not using AI. For example, the reception department can input a request from a client into the AI ​​and have the AI ​​process the acceptance of the request.

[0077] The analysis department can analyze requests from clients and identify the necessary areas of expertise and skill levels for the checks. For example, the analysis department can analyze requests from clients using methods such as text analysis, data mining, and statistical analysis. The analysis department analyzes requests and identifies the necessary areas of expertise and skill levels for the checks. This allows the analysis department to analyze requests from clients and identify the necessary areas of expertise and skill levels for the checks. Required areas of expertise include, but are not limited to, medical, legal, and technical fields. Required skill levels include, but are not limited to, beginner, intermediate, and advanced levels. Some or all of the above processing in the analysis department may be performed using, for example, AI, or not. For example, the analysis department can input requests into an AI and have the AI ​​perform the analysis of the requests.

[0078] The requesting department can simultaneously issue requests to all experts who match the case. The requesting department can, for example, issue requests to all experts who match the case simultaneously. The requesting department can issue requests using mass email or notification systems. This allows requests to be issued simultaneously to all experts who match the case. Methods for issuing requests simultaneously include, but are not limited to, mass email or notification systems. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input the request into AI and have the AI ​​execute the request to experts.

[0079] The checking unit allows experts to review the request conditions, accept the request, and perform the check. For example, the checking unit can perform the check using methods such as review, verification, and testing. This allows experts to review the request conditions, accept the request, and perform the check. Request conditions include, but are not limited to, deadlines, quality standards, and compensation. Some or all of the processes described above in the checking unit may be performed using, for example, AI, or not using AI. For example, the checking unit can input the request into AI and have the AI ​​perform the check.

[0080] The storage unit can store the results of the checker's verification that received high ratings from the client in the search extension generation database. For example, the storage unit stores the results of the checker's verification that received high ratings from the client in the search extension generation database. This allows the storage unit to store the results that received high ratings from the client in the search extension generation database. Results that received high ratings include, but are not limited to, client feedback and evaluation scores. Some or all of the above processing in the storage unit may be performed using, for example, AI, or not using AI. For example, the storage unit can input the check results into AI and have AI perform the storage of the results.

[0081] The reception desk can estimate the client's emotions and adjust the priority of the request based on the estimated emotions. For example, if the client feels urgency, the reception desk can adjust the request to be processed with the highest priority. If the client is relaxed, the reception desk can also adjust the request to be processed with the normal priority. If the client is anxious, the reception desk can also raise the priority to respond quickly. This allows the priority of the request to be adjusted based on the client's emotions. The client's emotions include, but are not limited to, urgency, relaxation, and anxiety. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input client emotion data into an AI and have the AI ​​perform emotion estimation.

[0082] The reception department can analyze the client's past request history and select the most suitable reception method. For example, the reception department may prioritize suggesting reception methods that the client has frequently used in the past. The reception department can also select the most efficient reception method based on the client's past request history. Based on the client's past request history, the reception department can also suggest the most suitable reception method for a specific time slot. This allows the reception department to analyze the client's past request history and select the most suitable reception method. The most suitable reception method includes, but is not limited to, online forms and telephone reception. Some or all of the above processes in the reception department may be performed using AI, for example, or not. For example, the reception department can input the client's past request history into AI and have the AI ​​select the most suitable reception method.

[0083] The reception department can filter requests based on the requester's current projects and areas of interest when receiving them. For example, the reception department can prioritize requests related to projects the requester is currently working on. The reception department can also filter requests based on the requester's areas of interest to ensure they are relevant. The reception department can also suggest the most suitable requests based on the progress of the requester's current projects. This allows for filtering based on the requester's current projects and areas of interest. Current projects and areas of interest include, but are not limited to, project management tools and survey results. Some or all of the above processing in the reception department may be performed using AI, for example, or not. For example, the reception department can input data on the requester's current projects and areas of interest into an AI and have the AI ​​perform the filtering.

[0084] The reception desk can estimate the client's emotions and determine the priority of the requests to be received based on the estimated emotions. For example, if the client is stressed, the reception desk will process the request with the highest priority. If the client is relaxed, the reception desk may process the request with the normal priority. If the client is in a hurry, the reception desk may also raise the priority to respond quickly. This allows the reception desk to determine the priority of requests to be received based on the client's emotions. Request priorities include, but are not limited to, urgency and importance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not using AI. For example, the reception desk can input client emotion data into an AI and have the AI ​​perform emotion estimation.

[0085] The reception department can prioritize requests based on their relevance, taking into account the requester's geographical location. For example, if a requester is in a specific region, the reception department will prioritize requests related to that region. The reception department can also suggest the most relevant requests based on the requester's current location. The reception department can also filter requests based on the requester's geographical location. This allows the reception department to prioritize requests based on their relevance, taking into account the requester's geographical location. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the reception department may be performed using AI, for example, or without AI. For example, the reception department can input the requester's geographical location information into AI and have the AI ​​perform the filtering.

[0086] The reception department can analyze the requester's social media activity upon receiving a request and accept relevant requests. For example, the reception department can prioritize requests related to the requester's areas of interest based on their social media activity. The reception department can also suggest the most suitable requests based on the requester's social media activity. The reception department can also analyze the requester's social media activity and filter out highly relevant requests. This allows the reception department to analyze the requester's social media activity and accept relevant requests. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the above processing in the reception department may be performed using, for example, AI, or not. For example, the reception department can input the requester's social media activity data into an AI and have the AI ​​perform the analysis.

[0087] The analysis unit can estimate the client's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the client is nervous, the analysis unit can provide a simple and visually clear presentation. If the client is relaxed, the analysis unit can also provide a presentation that includes detailed information. If the client is in a hurry, the analysis unit can also provide a presentation that gets straight to the point. This allows the presentation of the analysis to be adjusted based on the client's emotions. Presentation methods of the analysis include, but are not limited to, graphs and text reports. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0088] The analysis department can adjust the level of detail of the analysis based on the importance of the request. For example, the analysis department will perform a detailed analysis for high-priority requests. The analysis department can also perform a simplified analysis for low-priority requests. The analysis department can also dynamically adjust the level of detail of the analysis according to the importance of the request. This allows the level of detail of the analysis to be adjusted based on the importance of the request. The importance of the request includes, but is not limited to, business impact and urgency. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input request importance data into AI and have the AI ​​adjust the level of detail of the analysis.

[0089] The analysis department can apply different analysis algorithms depending on the category of the request during analysis. For example, the analysis department can apply a specialized analysis algorithm to a technical request. The analysis department can also apply a creative analysis algorithm to a creative request. The analysis department can also select the most suitable analysis algorithm depending on the category of the request. This allows for the application of different analysis algorithms depending on the category of the request. The categories of requests include, but are not limited to, technology, marketing, and legal. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input the category data of the request into an AI and have the AI ​​perform the application of the analysis algorithm.

[0090] The analysis unit can estimate the client's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the client is in a hurry, the analysis unit can provide a short, to-the-point analysis. If the client is relaxed, the analysis unit can also provide a longer analysis with detailed explanations. If the client is excited, the analysis unit can also provide an analysis with visually stimulating effects. This allows the length of the analysis to be adjusted based on the client's emotions. The length of the analysis includes, but is not limited to, the number of pages or time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0091] The analysis department can determine the priority of analyses based on the submission timing of the requests. For example, the analysis department can prioritize analyses for urgent requests. The analysis department can also prioritize analyses for requests with approaching deadlines. The analysis department can also dynamically adjust the priority of analyses according to the submission timing of the requests. This allows the analysis priority to be determined based on the submission timing of the requests. The submission timing of requests includes, but is not limited to, the submission date and deadline. Some or all of the above processes in the analysis department may be performed using AI, for example, or not. For example, the analysis department can input the submission timing data of the requests into an AI and have the AI ​​perform the priority determination.

[0092] The analysis unit can adjust the order of analysis based on the relevance of the requests during the analysis process. For example, the analysis unit will prioritize analyzing requests that are related to other requests. The analysis unit can also determine the optimal order of analysis based on the relevance of the requests. The analysis unit can also dynamically adjust the order of analysis, taking into account the relevance of the requests. This allows the order of analysis to be adjusted based on the relevance of the requests. The relevance of the requests includes, but is not limited to, the degree of theme matching and past relevance. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the relevance data of the requests into AI and have the AI ​​perform the order adjustment.

[0093] The request unit can estimate the client's emotions and adjust the way the request is expressed based on the estimated emotions. For example, if the client is nervous, the request unit can provide a simple and easily understandable expression. If the client is relaxed, the request unit can also provide an expression that includes detailed information. If the client is in a hurry, the request unit can also provide an expression that gets straight to the point. This allows the request to be expressed based on the client's emotions. Examples of how the request is expressed include, but are not limited to, formal or casual writing styles. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the request unit may be performed using, for example, AI, or not using AI. For example, the request unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0094] The requesting department can adjust the level of detail of a request based on the importance of the expert at the time of the request. For example, the requesting department can provide detailed requests to highly important experts. The requesting department can also provide simplified requests to less important experts. The requesting department can also dynamically adjust the level of detail of a request according to the importance of the expert. This allows the level of detail of a request to be adjusted based on the importance of the expert. The importance of an expert includes, but is not limited to, years of experience and past performance. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input expert importance data into AI and have the AI ​​perform the adjustment of the level of detail.

[0095] The requesting unit can apply different requesting algorithms depending on the category of the expert when a request is made. For example, the requesting unit can apply a specialized requesting algorithm to a technical expert. The requesting unit can also apply a creative requesting algorithm to a creative expert. The requesting unit can also select the most suitable requesting algorithm depending on the category of the expert. This allows for the application of different requesting algorithms depending on the category of the expert. Examples of expert categories include, but are not limited to, medical, legal, and technical fields. Some or all of the above processing in the requesting unit may be performed using AI, for example, or not using AI. For example, the requesting unit can input expert category data into an AI and have the AI ​​perform the application of the requesting algorithm.

[0096] The request unit can estimate the requester's emotions and adjust the length of the request based on the estimated emotions. For example, if the requester is in a hurry, the request unit will provide a short, to-the-point request. If the requester is relaxed, the request unit may provide a longer request that includes detailed explanations. If the requester is excited, the request unit may provide a request with visually stimulating effects. This allows the length of the request to be adjusted based on the requester's emotions. The length of the request may include, but is not limited to, the number of pages or time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may include, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the request unit may be performed using AI or not using AI. For example, the request unit can input the requester's emotion data into an AI and have the AI ​​perform emotion estimation.

[0097] The requesting department can determine the priority of requests based on the submission timing of experts. For example, the requesting department will give the highest priority to urgent requests. The requesting department may also give priority to requests with approaching deadlines. The requesting department can also dynamically adjust the priority of requests according to the submission timing of experts. This allows the priority of requests to be determined based on the submission timing of experts. The submission timing of experts includes, but is not limited to, the submission date and deadline. Some or all of the above processing in the requesting department may be performed using, for example, AI, or not using AI. For example, the requesting department can input expert submission timing data into AI and have the AI ​​perform the priority determination.

[0098] The requesting unit can adjust the order of requests based on the relevance of experts when a request is made. For example, the requesting unit will prioritize requests if the expert is related to other requests. The requesting unit can also determine the optimal order of requests based on the relevance of experts. The requesting unit can also dynamically adjust the order of requests, taking into account the relevance of experts. This allows the order of requests to be adjusted based on the relevance of experts. Expert relevance includes, but is not limited to, the degree of theme matching and past relevance. Some or all of the above processing in the requesting unit may be performed using AI, for example, or not using AI. For example, the requesting unit can input expert relevance data into AI and have the AI ​​perform the order adjustment.

[0099] The checking unit can estimate the client's emotions and adjust the checking method based on the estimated emotions. For example, if the client is nervous, the checking unit can provide a simple and highly visible checking method. If the client is relaxed, the checking unit can also provide a checking method that includes detailed information. If the client is in a hurry, the checking unit can also provide a check method that gets straight to the point. This allows the checking method to be adjusted based on the client's emotions. Checking methods include, but are not limited to, reviews, verifications, and tests. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI, for example, or not using AI. For example, the checking unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0100] The checking unit can analyze the past history of the request content during the checking process to select the optimal checking method. For example, the checking unit can select the most efficient checking method from the past history of the request content. The checking unit can also propose the optimal checking method for a specific time period based on the past history of the request content. The checking unit can also analyze the past history of the request content and dynamically adjust the optimal checking method. This allows the checking unit to analyze the past history of the request content and select the optimal checking method. The optimal checking method includes, but is not limited to, past history analysis and algorithm selection. Some or all of the above processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input past history data of the request content into AI and have the AI ​​perform the selection of the checking method.

[0101] The checking unit can customize the checking methods based on the current status of the request during the checking process. For example, the checking unit can select the optimal checking method according to the current status of the request. The checking unit can also propose a specific checking method based on the current status of the request. The checking unit can also dynamically customize the checking methods considering the current status of the request. This allows the checking methods to be customized based on the current status of the request. The current status of the request includes, but is not limited to, progress status and resource status. Some or all of the above-described processes in the checking unit may be performed using, for example, AI, or not using AI. For example, the checking unit can input data on the current status of the request into the AI ​​and have the AI ​​perform the customization of the methods.

[0102] The checking unit can estimate the client's emotions and determine the priority of the checks based on the estimated emotions. For example, if the client is stressed, the checking unit will process the checks with the highest priority. If the client is relaxed, the checking unit can process them with the normal priority. If the client is in a hurry, the checking unit can also raise the priority to respond quickly. This allows the checking unit to determine the priority of the checks based on the client's emotions. Prioritization of checks includes, but is not limited to, urgency and importance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI, or not using AI. For example, the checking unit can input client emotion data into an AI and have the AI ​​perform emotion estimation.

[0103] The checking unit can select the optimal checking method while considering the geographical location information of the request. For example, if the requester is in a specific region, the checking unit will prioritize processing checks related to that region. The checking unit can also suggest the optimal checking method based on the requester's current location. The checking unit can also filter highly relevant checks based on the requester's geographical location information. This allows the checking unit to select the optimal checking method while considering the geographical location information of the request. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the geographical location information of the request into AI and have the AI ​​select the checking method.

[0104] The checking unit can analyze the social media activity of the request and propose checking methods during the checking process. For example, the checking unit can prioritize processing checking items related to the client's areas of interest from the client's social media activity. The checking unit can also propose the most suitable checking method based on the client's social media activity. The checking unit can also analyze the client's social media activity and filter out highly relevant checking items. This allows the checking unit to analyze the social media activity of the request and propose checking methods. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the processing described above in the checking unit may be performed using AI, for example, or not. For example, the checking unit can input the social media activity data of the request into AI and have the AI ​​propose methods.

[0105] The storage unit can estimate the client's emotions and select storage data based on the estimated emotions. For example, if the client is nervous, the storage unit will prioritize storing important data. If the client is relaxed, the storage unit can also store normal data. If the client is in a hurry, the storage unit can also prioritize storing important data to respond quickly. This allows for the selection of storage data based on the client's emotions. The selection of storage data includes, but is not limited to, data importance and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI, or not using AI. For example, the storage unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0106] The storage unit can optimize the storage algorithm by referring to past stored data during storage. For example, the storage unit can select the optimal storage algorithm based on past stored data. The storage unit can also propose the optimal storage algorithm for a specific time period by referring to past stored data. The storage unit can also analyze past stored data and dynamically adjust the optimal storage algorithm. This allows the storage algorithm to be optimized by referring to past stored data. The storage algorithm includes, but is not limited to, referring to past data and adjusting the algorithm. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input past stored data into AI and have the AI ​​perform algorithm optimization.

[0107] The storage unit can select storage data based on the current status of the request during storage. For example, the storage unit can select the optimal storage data according to the current status of the request. The storage unit can also suggest specific storage data based on the current status of the request. The storage unit can also dynamically select storage data considering the current status of the request. This allows for the selection of storage data based on the current status of the request. The current status of the request includes, but is not limited to, progress status and resource status. Some or all of the above processing in the storage unit may be performed using, for example, AI, or not using AI. For example, the storage unit can input the current status data of the request into AI and have AI perform the data selection.

[0108] The storage unit can estimate the client's emotions and adjust the storage frequency based on the estimated emotions. For example, if the client is nervous, the storage unit will store data frequently. If the client is relaxed, the storage unit can store data at a normal frequency. If the client is in a hurry, the storage unit can store data frequently to respond quickly. This allows the storage frequency to be adjusted based on the client's emotions. Storage frequency includes, but is not limited to, periodic storage or event-driven storage. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the storage unit may be performed using or without AI. For example, the storage unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0109] The storage unit can weight the stored data based on the submission timing of the requests during storage. For example, the storage unit will store requests with approaching deadlines with higher weighting. The storage unit can also store requests with distant deadlines with normal weighting. The storage unit can also dynamically adjust the weighting of the stored data according to the submission timing of the requests. This allows the storage unit to weight the stored data based on the submission timing of the requests. The submission timing includes, but is not limited to, the submission date and deadline. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the request submission timing data into AI and have AI perform the weighting.

[0110] The storage unit can select data to store based on the relevance of the requests during storage. For example, the storage unit will prioritize storing requests that are related to other requests. The storage unit can also select the most suitable data to store based on the relevance of the requests. The storage unit can also dynamically select data to store, taking into account the relevance of the requests. This allows for the selection of data to be stored based on the relevance of the requests. The relevance of the requests includes, but is not limited to, the degree of theme matching and past relevance. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input request relevance data into AI and have AI perform data selection.

[0111] The storage unit can select data to store based on the importance of the request during storage. For example, the storage unit will prioritize storing requests with high importance. The storage unit can also perform normal storage for requests with low importance. The storage unit can also dynamically adjust the selection of data to store according to the importance of the request. This allows for the selection of data to be stored based on the importance of the request. The importance of a request includes, but is not limited to, business impact and urgency. Some or all of the above processing in the storage unit may be performed using, for example, AI, or not using AI. For example, the storage unit can input request importance data into AI and have the AI ​​perform the data selection.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The reception desk can estimate the client's emotions and adjust the priority of the request based on the estimated emotions. For example, if the client feels urgency, the request can be prioritized. If the client is relaxed, it can be processed with the normal priority. If the client is anxious, the priority can be increased to ensure a quick response. This allows for the adjustment of the priority of requests based on the client's emotions. The client's emotions include, but are not limited to, urgency, relaxation, and anxiety. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input client emotion data into an AI and have the AI ​​perform emotion estimation.

[0114] The reception department can analyze a client's past request history and select the most suitable reception method. For example, it can prioritize suggesting reception methods that the client has frequently used in the past. It can also select the most efficient reception method based on the client's past request history. Based on the client's past request history, it can also suggest the most suitable reception method for a specific time slot. This allows the reception department to analyze the client's past request history and select the most suitable reception method. The most suitable reception method includes, but is not limited to, online forms and telephone reception. Some or all of the above processes in the reception department may be performed using AI, for example, or not. For example, the reception department can input the client's past request history into AI and have the AI ​​select the most suitable reception method.

[0115] The analysis unit can estimate the client's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the client is nervous, a simple and highly visual presentation can be provided. If the client is relaxed, a presentation containing detailed information can be provided. If the client is in a hurry, a presentation that gets straight to the point can be provided. This allows the presentation of the analysis to be adjusted based on the client's emotions. Presentation methods of the analysis include, but are not limited to, graphs and text reports. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0116] The requesting department can adjust the level of detail of a request based on the importance of the expert at the time of the request. For example, it can provide detailed request information to highly important experts and simplified request information to less important experts. It can also dynamically adjust the level of detail of a request according to the importance of the expert. This allows for adjustment of the level of detail of a request based on the importance of the expert. The importance of an expert includes, but is not limited to, years of experience and past performance. Some or all of the above processing in the requesting department may be performed using AI, for example, or not using AI. For example, the requesting department can input expert importance data into AI and have the AI ​​perform the adjustment of the level of detail.

[0117] The checking unit can estimate the client's emotions and adjust the checking method based on the estimated emotions. For example, if the client is nervous, it can provide a simple and highly visible checking method. If the client is relaxed, it can also provide a checking method that includes detailed information. If the client is in a hurry, it can provide a checking method that gets straight to the point. This allows the checking method to be adjusted based on the client's emotions. Checking methods include, but are not limited to, reviews, verifications, and tests. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI, for example, or not using AI. For example, the checking unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0118] The checking unit can analyze the past history of the request content during the checking process to select the optimal checking method. For example, it can select the most efficient checking method from the past history of the request content. It can also propose the optimal checking method for a specific time period based on the past history of the request content. It can also dynamically adjust the optimal checking method by analyzing the past history of the request content. This allows for the selection of the optimal checking method by analyzing the past history of the request content. The optimal checking method includes, but is not limited to, past history analysis and algorithm selection. Some or all of the above-described processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input past history data of the request content into AI and have the AI ​​perform the selection of the checking method.

[0119] The storage unit can estimate the client's emotions and select storage data based on the estimated emotions. For example, if the client is nervous, important data can be prioritized for storage. If the client is relaxed, normal data can also be stored. If the client is in a hurry, important data can also be prioritized for storage to enable a quick response. This allows for the selection of storage data based on the client's emotions. The selection of storage data includes, but is not limited to, data importance and relevance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI, or not using AI. For example, the storage unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0120] The storage unit can optimize the storage algorithm by referring to past stored data during storage. For example, it can select the optimal storage algorithm based on past stored data. It can also propose the optimal storage algorithm for a specific time period by referring to past stored data. It can also dynamically adjust the optimal storage algorithm by analyzing past stored data. This allows the storage algorithm to be optimized by referring to past stored data. The storage algorithm includes, but is not limited to, referring to past data and adjusting the algorithm. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input past stored data into AI and have the AI ​​perform algorithm optimization.

[0121] The storage unit can estimate the client's emotions and adjust the storage frequency based on the estimated emotions. For example, if the client is nervous, data may be stored frequently. If the client is relaxed, data may be stored at a normal frequency. If the client is in a hurry, data may be stored frequently to respond quickly. This allows the storage frequency to be adjusted based on the client's emotions. Storage frequencies include, but are not limited to, periodic storage and event-driven storage. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not using AI. For example, the storage unit can input the client's emotion data into an AI and have the AI ​​perform emotion estimation.

[0122] The storage unit can weight the stored data based on the submission timing of the requests during storage. For example, requests with approaching deadlines can be stored with a higher weight. Requests with distant deadlines can be stored with the normal weighting. The weighting of the stored data can also be dynamically adjusted according to the submission timing of the requests. This allows the stored data to be weighted based on the submission timing of the requests. The submission timing includes, but is not limited to, the submission date and deadline. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the submission timing data of the requests into the AI ​​and have the AI ​​perform the weighting.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The reception department receives requests from clients. Requests from clients can be in written form, verbally, or via email. For example, a client can request a review of the output of the generated AI, specifying a range of parts that they suspect may contain hallucinations. Step 2: The Analysis Department analyzes the requests received by the Reception Department. The Analysis Department analyzes the requests using methods such as text analysis, data mining, and statistical analysis to identify the areas of expertise and skill levels required for the checks. Step 3: The requesting department issues a request to the experts identified by the analysis department. The requesting department can issue a request to all experts who match the case simultaneously, and can do so via mass email or a notification system. Step 4: The checking department employs experts who have been commissioned by the requesting department to perform the checks. The checking department uses methods such as review, verification, and testing to perform the checks, and the experts confirm the request conditions and accept the commission to perform the checks. Step 5: The storage unit stores the results obtained by the checking unit. The storage unit stores the results in a database or in report format, and stores the results that received high ratings from the client among the checker's verification results in the search and extension generation database.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the reception unit, analysis unit, request unit, checking unit, and storage unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives requests from clients. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the received requests. The request unit is implemented by the specific processing unit 290 of the data processing device 12 and sends requests to experts. The checking unit is implemented by the control unit 46A of the smart device 14 and experts perform checks. The storage unit is implemented by the specific processing unit 290 of the data processing device 12 and stores the check results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the reception unit, analysis unit, request unit, checking unit, and storage unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives requests from clients. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the received requests. The request unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and sends requests to experts. The checking unit is implemented, for example, by the control unit 46A of the smart glasses 214 and has experts perform checks. The storage unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and stores the check results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the reception unit, analysis unit, request unit, checking unit, and storage unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives requests from the requester. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing device 12 and analyzes the received requests. The request unit is implemented by, for example, the specific processing unit 290 of the data processing device 12 and issues requests to experts. The checking unit is implemented by, for example, the control unit 46A of the headset terminal 314 and experts perform checks. The storage unit is implemented by, for example, the specific processing unit 290 of the data processing device 12 and stores the check results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the reception unit, analysis unit, request unit, checking unit, and storage unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives requests from clients. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the received requests. The request unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and issues requests to experts. The checking unit is implemented by, for example, the control unit 46A of the robot 414 and experts perform checks. The storage unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and stores the check results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0178] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] 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.

[0188] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] (Note 1) The reception department receives requests from clients, An analysis department analyzes requests received by the aforementioned reception department, The requesting department will issue a request to the specialists identified by the aforementioned analysis department, The aforementioned requesting department has a checking department where experts who have been requested by the requesting department perform checks, The system includes a storage unit that stores the results obtained by the checking unit. A system characterized by the following features. (Note 2) The aforementioned reception unit is The client selects a range of the AI ​​output that they suspect contains hallucination and submits a request for content verification. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit is We analyze the client's request and identify the specialized fields and skill levels required for the check. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned request unit is, We will simultaneously send a request to all experts who match the requirements of the project. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned checking unit is Experts review the request requirements, accept the request, and then perform the checks. The system described in Appendix 1, characterized by the features described herein. (Note 6) The storage unit is The results of the checker's verification, specifically those that received high ratings from the client, will be stored in the search extension generation database. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is We estimate the client's emotions and adjust the priority of the request based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We analyze the client's past request history and select the most suitable method of receiving their request. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving a request, we filter it based on the requester's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the client's emotions and determines the priority of the requests to be accepted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving a request, we prioritize requests that are highly relevant, taking into account the requester's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving a request, we analyze the requester's social media activity and accept related requests. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is We estimate the client's emotions and adjust the way the analysis is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is During the analysis, adjust the level of detail based on the importance of the request. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is During analysis, different analytical algorithms are applied depending on the category of the request. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is The analysis length is adjusted based on the estimated client's emotions and the client's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is During the analysis, we prioritize the analysis based on when the request was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is During the analysis, the order of analysis will be adjusted based on the relevance of the requested information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned request unit is, We estimate the client's emotions and adjust the way the request is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned request unit is, When making a request, adjust the level of detail based on the importance of the expert's expertise. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned request unit is, When making a request, a different request algorithm is applied depending on the expert's category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned request unit is, We estimate the client's emotions and adjust the length of the request based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned request unit is, When making a request, we prioritize the requests based on the submission timing of the experts. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned request unit is, When making a request, we will adjust the order of requests based on the relevance of the experts involved. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned checking unit is We estimate the client's emotions and adjust the checking method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned checking unit is During the check, we analyze the past history of the request to select the most suitable checking method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned checking unit is During the check, customize the checking method based on the current status of the request. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned checking unit is We estimate the client's emotions and determine the priority of the checks based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned checking unit is During the check, the most suitable checking method will be selected, taking into account the geographical location information of the request. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned checking unit is During the review process, we will analyze the social media activity related to the request and propose methods for verification. The system described in Appendix 1, characterized by the features described herein. (Note 31) The storage unit is The system estimates the client's emotions and selects accumulated data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The storage unit is During data storage, the storage algorithm is optimized by referring to past stored data. The system described in Appendix 1, characterized by the features described herein. (Note 33) The storage unit is During data storage, the data to be stored is selected based on the current status of the request. The system described in Appendix 1, characterized by the features described herein. (Note 34) The storage unit is The system estimates the client's emotions and adjusts the frequency of data accumulation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The storage unit is During data accumulation, the accumulated data is weighted based on the submission date of the request. The system described in Appendix 1, characterized by the features described herein. (Note 36) The storage unit is During data storage, the data to be stored is selected based on the relevance of the request. The system described in Appendix 1, characterized by the features described herein. (Note 37) The storage unit is During data storage, the data to be stored is selected based on the importance of the request. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The reception department receives requests from clients, An analysis department analyzes requests received by the aforementioned reception department, The requesting department will issue a request to the specialists identified by the aforementioned analysis department, The aforementioned requesting department has a checking department where experts who have been requested by the requesting department perform checks, The system includes a storage unit that stores the results obtained by the checking unit. A system characterized by the following features.

2. The aforementioned reception unit is The client selects a range of the output from the generated AI that they suspect contains hallucination and submits a request for content verification. The system according to feature 1.

3. The aforementioned analysis unit is We analyze the client's request and identify the specialized fields and skill levels required for the check. The system according to feature 1.

4. The aforementioned request unit is, We will simultaneously send a request to all experts who match the requirements of the project. The system according to feature 1.

5. The aforementioned checking unit is Experts review the request requirements, accept the request, and then perform the checks. The system according to feature 1.

6. The storage unit is The results of the checker's verification, specifically those that received high ratings from the client, will be stored in the search extension generation database. The system according to feature 1.

7. The aforementioned reception unit is We estimate the client's emotions and adjust the priority of the request based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is We analyze the client's past request history and select the most suitable method of receiving their request. The system according to feature 1.

9. The aforementioned reception unit is When receiving a request, we filter it based on the requester's current projects and areas of interest. The system according to feature 1.

10. The aforementioned reception unit is The system estimates the client's emotions and determines the priority of the requests to be accepted based on those estimated emotions. The system according to feature 1.

Images