System

Abstract

An object of a system according to an embodiment is to fill a gap between training and an actual site and to facilitate provision of appropriate guidance and response to complaints.SOLUTION: A system includes a collection unit, a generation unit, a simulation unit, and a feedback unit. The collection unit collects attributes of the persona. The generation unit creates a persona based on the attributes collected by the collection unit. The simulation unit performs simulation on the persona created by the generation unit. The feedback unit analyzes a result of the simulation performed by the simulation unit and performs feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, there was a gap between training and actual on-site experience, making it difficult to provide appropriate guidance or respond to complaints.

[0005] The system according to the embodiment aims to bridge the gap between training and actual work, and to facilitate the provision of appropriate guidance and the handling of complaints. [Means for solving the problem]

[0006] A system according to an embodiment includes a collection unit, a generation unit, a simulation unit, and a feedback unit. The collection unit collects attributes of personas. The generation unit creates personas based on the attributes collected by the collection unit. The simulation unit performs a simulation on the persona created by the generation unit. The feedback unit analyzes the results of the simulation performed by the simulation unit and provides feedback. [Effects of the Invention]

[0007] The system according to the embodiment can bridge the gap between training and actual work, and can facilitate the provision of appropriate guidance and the handling of complaints. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A training support system according to an embodiment of the present invention is a system that performs simulations using personas created using a generative AI, allowing trainees to gain experience in actual workplaces in advance. In the training support system, the generative AI creates a variety of personas, allowing trainees to gain experience in responding to various situations. This system allows trainees to improve their ability to respond in actual workplaces. For example, in the training support system, the generative AI creates a variety of personas with attributes such as age, gender, occupation, and personality. Next, the training support system performs simulations using the created personas, allowing trainees to simulate tasks such as handling complaints and providing guidance. Furthermore, in the training support system, the generative AI analyzes the results of the simulations and provides feedback on areas for improvement to the trainees' responses. This allows trainees to specifically identify what went well and what needs improvement in their responses. This allows the training support system to provide trainees with actual workplace experience in advance, thereby bridging the gap between training and the actual workplace. For example, by performing simulations using a variety of personas during training, trainees can acquire skills for responding to various situations. Furthermore, the generative AI provides feedback, allowing trainees to specifically identify areas for improvement in their responses and improve their skills.

[0029] A training support system according to an embodiment includes a collection unit, a generation unit, a simulation unit, and a feedback unit. The collection unit collects persona attributes. Persona attributes include, but are not limited to, age, gender, occupation, and personality. The collection unit can collect data, for example, through questionnaires or interviews. The collection unit can also collect attributes from publicly available data on the Internet using data mining technology. The generation unit creates personas based on the attributes collected by the collection unit. The generation unit uses a generation AI to generate various personas based on the collected attributes. For example, the generation AI combines attributes such as age, gender, occupation, and personality to create realistic personas. The simulation unit performs simulations on the personas created by the generation unit. The simulation unit can perform simulations such as handling complaints and providing guidance. The simulation unit uses the generation AI to simulate interactions with personas, allowing trainees to gain experience in responding to various situations. The feedback unit analyzes the results of the simulation performed by the simulation unit and provides feedback on areas for improvement in the trainee's responses. The feedback unit uses the generation AI to analyze the results of the simulation and provide specific feedback on what went well in the trainee's response and what needs improvement. For example, the feedback unit may provide feedback on whether the trainee used appropriate language and attitude when handling a complaint, and whether there were any areas that needed improvement. This allows the training support system according to the embodiment to improve the trainee's ability to respond in actual situations.

[0030] The collection unit can collect data including age, gender, occupation, and personality as persona attributes. For example, the collection unit collects data such as age, gender, occupation, and personality through a questionnaire. The collection unit can also collect detailed attribute data through interviews. For example, the collection unit may interview trainees to collect information on persona attributes. The collection unit can also use data mining technology to collect attributes from publicly available data on the Internet. For example, the collection unit may extract attribute data from social media posts and public profiles. This allows for the collection of diverse data as persona attributes, thereby generating more realistic personas. Some or all of the above-described processing in the collection unit may be performed using or without the generation AI. For example, the collection unit may input questionnaire data into the generation AI and have the generation AI extract attribute data.

[0031] The generation unit can create various personas based on the collected attributes. The generation unit creates various personas based on collected attributes such as age, gender, occupation, and personality. The generation unit uses a generation AI to combine the collected attributes to generate realistic personas. For example, the generation AI combines attributes such as age, gender, occupation, and personality to create personas that can handle various scenarios, such as handling complaints from young customers or providing guidance to elderly people. The generation unit can also use the generation AI to generate scenarios based on the persona attributes. For example, the generation AI generates scenarios such as handling complaints and providing guidance based on the persona attributes. This allows trainees to gain experience in responding to various situations by creating various personas based on the collected attributes. Some or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can input collected attribute data into the generation AI and cause the generation AI to generate personas.

[0032] The simulation unit can perform a simulation of handling a complaint or providing guidance for the created persona. For example, the simulation unit performs a simulation of handling a complaint for the persona created by the generation unit. For example, the simulation unit sets up a scenario in which the persona files a complaint as a customer, and the trainee responds appropriately, thereby cultivating the ability to handle complaints in actual on-site situations. The simulation unit can also perform a simulation of providing guidance. For example, the simulation unit sets up a scenario in which the persona requests guidance as an elderly person, and the trainee provides appropriate guidance, thereby cultivating the ability to provide guidance in actual on-site situations. Furthermore, the simulation unit can simulate a dialogue with the persona using the generation AI. For example, the simulation unit has the generation AI interact with the trainee as the persona, and performs simulations such as handling a complaint or providing guidance. In this way, by performing simulations for the created persona, the trainee can improve their ability to respond in actual on-site situations. Some or all of the above-described processing in the simulation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the simulation unit can input a persona scenario into the generation AI and leave the execution of the simulation to the generation AI.

[0033] The feedback unit can analyze the results of the simulation and provide feedback on areas for improvement to the trainee's response. For example, the feedback unit analyzes the results of a simulation performed by the simulation unit and provides feedback on areas for improvement to the trainee's response. The feedback unit uses the generation AI to analyze the results of the simulation and provide specific feedback on what was good about the trainee's response and what areas need improvement. For example, the feedback unit can provide feedback on whether appropriate language and attitude were used when handling a complaint and whether there were areas for improvement. The feedback unit can also provide feedback on whether appropriate explanations were given when providing guidance and whether there were areas for improvement. In this way, by analyzing the results of the simulation and providing feedback on areas for improvement to the trainee's response, the trainee's skills can be improved. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the feedback unit can input simulation result data into the generation AI and cause the generation AI to generate feedback.

[0034] When collecting persona attributes, the collection unit can analyze the user's past behavioral history and select the optimal collection method. For example, the collection unit prioritizes the selection of collection methods (such as questionnaires and interviews) that the user has frequently used in the past. The collection unit can use data mining technology to analyze the user's past behavioral history. For example, the collection unit analyzes the user's website browsing history and purchase history to select the most efficient collection method. The collection unit can also customize the collection method based on the user's past behavioral history. For example, the collection unit prioritizes the selection of collection methods that the user has previously preferred, improving collection efficiency. This allows the optimal collection method to be selected by analyzing the user's past behavioral history. Some or all of the above-described processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's behavioral history data into the generation AI and have the generation AI select the optimal collection method.

[0035] When collecting persona attributes, the collection unit can filter them based on the user's current situation and areas of interest. For example, the collection unit prioritizes collecting attributes related to the user's current areas of interest. The collection unit can conduct surveys or interviews to understand the user's current situation and areas of interest. For example, the collection unit can ask the user questions about their current occupation and living environment and filter related attributes. The collection unit can also analyze social media posts and search history to analyze the user's current areas of interest. For example, the collection unit can filter related attributes based on keywords recently searched by the user or information shared on social media. This allows for filtering based on the user's current situation and areas of interest, thereby collecting more relevant attributes. Some or all of the above-mentioned processing in the collection unit can be performed using or without the generation AI. For example, the collection unit can input the user's area of ​​interest data into the generation AI and leave the filtering to the generation AI.

[0036] When collecting attributes of a persona, the collection unit can select the optimal collection method depending on the user's input method. For example, if the user prefers voice input, the collection unit selects a method for collecting attributes by voice. The collection unit can conduct surveys or interviews to understand the user's input method. For example, the collection unit can ask the user about their preference, such as voice input, text input, or image input, and select the optimal collection method. The collection unit can also analyze the user's past input history. For example, the collection unit can select the optimal collection method based on the input method the user has used in the past. This allows attributes to be collected efficiently by selecting the optimal collection method depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's input history data into the generation AI and have the generation AI select the optimal collection method.

[0037] When collecting persona attributes, the collection unit can prioritize collecting highly relevant attributes by taking into account the user's geographical location information. For example, if the user lives in a specific area, the collection unit prioritizes collecting attributes related to that area. The collection unit can collect GPS data and address information to determine the user's geographical location. For example, the collection unit obtains GPS data from the user's smartphone to determine their current location. The collection unit can also filter relevant attributes based on address information provided by the user. For example, the collection unit prioritizes collecting attributes related to the area based on the user's address information. This allows highly relevant attributes to be collected preferentially by taking into account the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's geographical location data into the generation AI and have the generation AI select highly relevant attributes.

[0038] When collecting persona attributes, the collection unit can analyze the user's social media activities and collect related attributes. For example, the collection unit collects related attributes based on information shared by the user on social media. The collection unit can use data mining technology to analyze the user's social media activities. For example, the collection unit analyzes the content of the user's social media posts, the number of likes, the number of followers, etc. to collect related attributes. The collection unit can also collect optimal attributes based on the user's social media activities. For example, the collection unit analyzes topics the user frequently posts on and themes of interest to collect related attributes. In this way, related attributes can be collected by analyzing the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's social media data into the generation AI and have the generation AI collect related attributes.

[0039] When collecting persona attributes, the collection unit can customize the collection method by reflecting the user's past feedback. The collection unit customizes the collection method, for example, based on feedback provided by the user in the past. The collection unit can use data mining technology to analyze the user's past feedback. For example, the collection unit analyzes survey results and comments provided by the user in the past and selects the optimal collection method. The collection unit can also adjust the collection means by reflecting the user's past feedback. For example, the collection unit prioritizes the collection method that the user has previously preferred to use, improving collection efficiency. This allows the optimal collection method to be selected by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's feedback data into the generation AI and have the generation AI customize the collection method.

[0040] When generating a persona, the generation unit can adjust the level of detail of the generation based on the importance of the collected attributes. For example, the generation unit generates a detailed persona based on important attributes. The generation unit can use data analysis techniques to evaluate the importance of the collected attributes. For example, the generation unit analyzes the collected attribute data and evaluates the importance of each attribute. The generation unit can also generate a concise persona based on less important attributes. For example, the generation unit generates a concise persona based on less important attributes. Furthermore, the generation unit can analyze the importance of attributes and generate a persona with an optimal level of detail. For example, the generation unit balances detailed personas and concise personas based on the importance of attributes. This allows the generation of an optimal persona by adjusting the level of detail of the generation based on the importance of the collected attributes. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the collected attribute data to a generation AI and cause the generation AI to generate a persona.

[0041] When generating a persona, the generation unit can apply different generation algorithms depending on the attribute category. For example, the generation unit applies a specific generation algorithm based on an age attribute. The generation unit can use data analysis techniques to evaluate the attribute categories. For example, the generation unit analyzes collected attribute data and evaluates each attribute category. The generation unit can also apply different generation algorithms based on a gender attribute. For example, the generation unit applies different generation algorithms based on the gender attribute. Furthermore, the generation unit can apply an optimal generation algorithm based on an occupation attribute. For example, the generation unit applies an optimal generation algorithm based on the occupation attribute. This allows for the generation of a more appropriate persona by applying different generation algorithms depending on the attribute category. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and cause the generation AI to generate a persona.

[0042] When generating a persona, the generation unit can improve the accuracy of the generation by referring to past generation results. The generation unit improves the accuracy, for example, based on personas generated in the past. The generation unit can use data analysis technology to evaluate past generation results. For example, the generation unit analyzes the evaluation results of personas generated in the past to improve the accuracy of the generation. The generation unit can also analyze past generation results and apply an optimal generation method. For example, the generation unit applies an optimal generation method based on past generation results. Furthermore, the generation unit can adjust the generation algorithm by referring to past generation results. For example, the generation unit adjusts parameters of the generation algorithm based on past generation results. In this way, the accuracy of the generation can be improved by referring to past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input past generation result data into the generation AI and cause the generation AI to improve the accuracy of the generation.

[0043] When generating a persona, the generation unit can determine a generation priority based on the time when the attributes were collected. For example, the generation unit generates a persona by prioritizing recently collected attributes. The generation unit can use data analysis technology to evaluate the time when the attributes were collected. For example, the generation unit analyzes the collection time of collected attribute data and prioritizes the most recent data. The generation unit can also generate a persona by deferring older attributes. For example, the generation unit generates a persona based on older attributes. Furthermore, the generation unit can determine an optimal generation order taking into account the time when the attributes were collected. For example, the generation unit determines an optimal generation order based on the time when the attributes were collected. In this way, by determining the generation priority based on the time when the attributes were collected, a persona that reflects the most recent information can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and cause the generation AI to generate a persona.

[0044] When generating personas, the generation unit can adjust the generation order based on the relevance of attributes. For example, the generation unit generates personas by prioritizing highly relevant attributes. The generation unit can use data analysis technology to evaluate the relevance of attributes. For example, the generation unit analyzes the relevance of collected attribute data and prioritizes highly relevant attributes. The generation unit can also generate personas by deferring less relevant attributes. For example, the generation unit generates personas based on less relevant attributes. Furthermore, the generation unit can analyze the relevance of attributes and determine an optimal generation order. For example, the generation unit determines an optimal generation order based on the relevance of attributes. As a result, by adjusting the generation order based on the relevance of attributes, more relevant personas can be generated. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and cause the generation AI to generate personas.

[0045] When generating a persona, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a persona that uses a lot of technical terminology. The generation unit can conduct a questionnaire or interview to evaluate the user's level of expertise. For example, the generation unit can ask the user questions about their expertise and evaluate their level of expertise. Furthermore, if the user does not have technical expertise, the generation unit can generate a persona using concise language. For example, the generation unit can evaluate that the user does not have technical expertise and generate a persona using concise language. Furthermore, the generation unit can analyze the user's level of expertise and generate a persona using optimal language. For example, the generation unit generates a persona using optimal language based on the user's level of expertise. This allows the generation of a persona that is easier to understand by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's technical expertise data into the generation AI and cause the generation AI to generate a persona.

[0046] During the simulation, the simulation unit can adjust the level of detail of the simulation based on the attributes of the persona. For example, the simulation unit performs a detailed simulation based on important attributes. The simulation unit can use data analysis techniques to evaluate the attributes of the persona. For example, the simulation unit analyzes the attribute data of the persona and evaluates the importance of each attribute. The simulation unit can also perform a concise simulation based on less important attributes. For example, the simulation unit performs a concise simulation based on less important attributes. Furthermore, the simulation unit can analyze the importance of the attributes and perform a simulation with an optimal level of detail. For example, the simulation unit balances detailed simulation and concise simulation based on the importance of the attributes. This allows for adjusting the level of detail of the simulation based on the attributes of the persona, thereby providing a more realistic simulation. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input the attribute data of the persona into the generation AI and cause the generation AI to adjust the level of detail of the simulation.

[0047] The simulation unit can apply different simulation algorithms depending on the persona category during the simulation. For example, the simulation unit applies a specific algorithm to a simulation of handling complaints. The simulation unit can use data analysis techniques to evaluate the persona category. For example, the simulation unit analyzes persona category data and selects an optimal simulation algorithm for each category. The simulation unit can also apply different algorithms to a simulation of providing guidance. For example, the simulation unit applies an optimal algorithm to a simulation of providing guidance. Furthermore, the simulation unit can apply an optimal simulation algorithm depending on the persona category. For example, the simulation unit applies an optimal simulation algorithm based on the persona category. This allows for a more appropriate simulation to be provided. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input persona category data into the generation AI and have the generation AI select a simulation algorithm.

[0048] During a simulation, the simulation unit can improve the accuracy of the simulation by referring to past simulation results. For example, the simulation unit improves the accuracy based on the past simulation results. The simulation unit can use data analysis techniques to evaluate past simulation results. For example, the simulation unit analyzes past simulation result data to improve the accuracy of the simulation. The simulation unit can also analyze past simulation results and apply an optimal simulation method. For example, the simulation unit applies an optimal simulation method based on the past simulation results. Furthermore, the simulation unit can adjust a simulation algorithm by referring to the past simulation results. For example, the simulation unit adjusts parameters of a simulation algorithm based on the past simulation results. In this way, the accuracy of the simulation can be improved by referring to the past simulation results. Some or all of the above-described processing in the simulation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the simulation unit can input past simulation result data into the generation AI and cause the generation AI to improve the accuracy of the simulation.

[0049] During a simulation, the simulation unit can determine the priority of the simulation based on the generation time of the persona. For example, the simulation unit prioritizes the most recently generated persona during the simulation. The simulation unit can use data analysis techniques to evaluate the generation time of the persona. For example, the simulation unit analyzes the generation time of the generated persona and prioritizes the most recent persona. The simulation unit can also postpone the simulation of older personas. For example, the simulation unit postpones the simulation based on older personas. Furthermore, the simulation unit can determine the optimal simulation order taking into account the generation time of the persona. For example, the simulation unit determines the optimal simulation order based on the generation time of the persona. This allows for simulations that reflect the latest information to be provided by prioritizing the simulations based on the generation time of the persona. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input data on the generation time of the persona into the generation AI and have the generation AI determine the priority of the simulations.

[0050] During a simulation, the simulation unit can adjust the order of simulations based on the relevance of personas. For example, the simulation unit prioritizes highly relevant personas during simulation. The simulation unit can use data analysis techniques to evaluate the relevance of personas. For example, the simulation unit analyzes persona attribute data and evaluates the relevance of each persona. The simulation unit can also postpone simulations for less relevant personas. For example, the simulation unit postpones simulations based on less relevant personas. Furthermore, the simulation unit can analyze the relevance of personas and determine an optimal simulation order. For example, the simulation unit determines an optimal simulation order based on the relevance of personas. This allows for adjusting the order of simulations based on the relevance of personas to provide a more relevant simulation. Some or all of the above-described processing in the simulation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the simulation unit can input persona relevance data into the generation AI and cause the generation AI to adjust the order of simulations.

[0051] During the simulation, the simulation unit can adjust the use of technical terminology in the simulation according to the user's level of expertise. For example, if the user has technical expertise, the simulation unit provides a simulation that uses a lot of technical terminology. The simulation unit can conduct a questionnaire or interview to evaluate the user's level of expertise. For example, the simulation unit can ask the user questions about their technical expertise and evaluate their level of expertise. Furthermore, if the user does not have technical expertise, the simulation unit can provide a simulation in simple language. For example, the simulation unit can determine that the user does not have technical expertise and provide a simulation in simple language. Furthermore, the simulation unit can analyze the user's level of expertise and provide a simulation using optimal language. For example, the simulation unit can provide a simulation using optimal language based on the user's level of expertise. This allows for a simulation that is easier to understand by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-described processing in the simulation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the simulation unit can input the user's technical expertise data into the generation AI and have the generation AI control the use of technical terminology in the simulation.

[0052] The feedback unit can adjust the level of detail of the feedback based on the results of the simulation when providing feedback. For example, the feedback unit provides detailed feedback based on important simulation results. The feedback unit can use data analysis techniques to evaluate the results of the simulation. For example, the feedback unit can analyze simulation result data and evaluate the importance of each result. The feedback unit can also provide brief feedback based on simulation results with low importance. For example, the feedback unit can provide brief feedback based on simulation results with low importance. Furthermore, the feedback unit can analyze the importance of the simulation results and provide feedback with an optimal level of detail. For example, the feedback unit balances detailed feedback and brief feedback based on the importance of the simulation results. This allows for more appropriate feedback to be provided by adjusting the level of detail of the feedback based on the results of the simulation. Some or all of the above-described processing in the feedback unit can be performed using or without the generation AI. For example, the feedback unit can input simulation result data to the generation AI and cause the generation AI to adjust the level of detail of the feedback.

[0053] The feedback unit can apply different feedback algorithms depending on the category of the simulation when providing feedback. For example, the feedback unit applies a specific algorithm to feedback on complaint handling. The feedback unit can use data analysis techniques to evaluate the category of the simulation. For example, the feedback unit analyzes simulation category data and selects an optimal feedback algorithm for each category. The feedback unit can also apply different algorithms to feedback on providing guidance. For example, the feedback unit applies an optimal algorithm to feedback on providing guidance. The feedback unit can also apply an optimal feedback algorithm depending on the category of the simulation. For example, the feedback unit applies an optimal feedback algorithm based on the category of the simulation. This allows for more appropriate feedback to be provided by applying different feedback algorithms depending on the category of the simulation. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input simulation category data to the generation AI and have the generation AI select a feedback algorithm.

[0054] The feedback unit can improve the accuracy of feedback by referring to past feedback results when providing feedback. For example, the feedback unit improves the accuracy based on past feedback results. The feedback unit can use data analysis technology to evaluate past feedback results. For example, the feedback unit analyzes past feedback result data to improve the accuracy of feedback. The feedback unit can also analyze past feedback results and apply an optimal feedback method. For example, the feedback unit applies an optimal feedback method based on past feedback results. Furthermore, the feedback unit can adjust the feedback algorithm by referring to past feedback results. For example, the feedback unit adjusts parameters of the feedback algorithm based on past feedback results. In this way, the accuracy of feedback can be improved by referring to past feedback results. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input past feedback result data into the generation AI and cause the generation AI to improve the accuracy of feedback.

[0055] The feedback unit can determine the priority of feedback based on the time when the simulation was performed when providing feedback. For example, the feedback unit prioritizes providing feedback for the most recently performed simulation. The feedback unit can use data analysis techniques to evaluate the time when the simulation was performed. For example, the feedback unit analyzes data on the time when the simulation was performed and prioritizes the most recent simulation. The feedback unit can also provide feedback for older simulations at a later date. For example, the feedback unit provides feedback based on older simulations at a later date. Furthermore, the feedback unit can determine an optimal feedback order taking into account the time when the simulation was performed. For example, the feedback unit determines an optimal feedback order based on the time when the simulation was performed. In this way, feedback reflecting the latest information can be provided by determining the priority of feedback based on the time when the simulation was performed. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input data on the time when the simulation was performed to the generation AI and cause the generation AI to determine the priority of feedback.

[0056] The feedback unit can adjust the order of feedback based on the relevance of the simulations when providing feedback. For example, the feedback unit prioritizes providing feedback for highly relevant simulations. The feedback unit can use data analysis techniques to evaluate the relevance of the simulations. For example, the feedback unit analyzes relevance data of the simulations and evaluates the relevance of each simulation. The feedback unit can also provide feedback for less relevant simulations at a later date. For example, the feedback unit provides feedback based on less relevant simulations at a later date. Furthermore, the feedback unit can analyze the relevance of the simulations and determine an optimal feedback order. For example, the feedback unit determines an optimal feedback order based on the relevance of the simulations. As a result, more relevant feedback can be provided by adjusting the feedback order based on the relevance of the simulations. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input relevance data of the simulations to the generation AI and cause the generation AI to adjust the feedback order.

[0057] When providing feedback, the feedback unit can adjust the use of technical terms in the feedback depending on the user's level of expertise. For example, if the user has technical expertise, the feedback unit provides feedback that uses a lot of technical terms. The feedback unit can conduct a questionnaire or interview to evaluate the user's level of expertise. For example, the feedback unit can ask the user questions about their expertise and evaluate their level of expertise. Furthermore, if the user does not have technical expertise, the feedback unit can provide feedback in concise language. For example, the feedback unit can evaluate that the user does not have technical expertise and provide feedback in concise language. Furthermore, the feedback unit can analyze the user's level of expertise and provide feedback in optimal language. For example, the feedback unit can provide feedback in optimal language based on the user's level of expertise. This allows for providing feedback that is easier to understand by adjusting the use of technical terms depending on the user's level of expertise. Some or all of the above-described processing in the feedback unit may be performed using a generation AI or without a generation AI. For example, the feedback unit can input the user's technical expertise data into the generation AI and cause the generation AI to use technical terms in the feedback.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The collection unit can analyze the user's past feedback and customize the collection method. For example, the collection unit can adjust the content of survey questions and the interview progress method based on the user's past feedback. The collection unit can also optimize the timing and frequency of collection based on the user's past feedback. This enables more effective attribute collection by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the user's feedback data into the generation AI and have the generation AI customize the collection method.

[0060] When generating a persona, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit can generate a persona that uses a lot of technical terminology. Alternatively, if the user does not have technical expertise, the generation unit can generate a persona using concise language. Furthermore, the generation unit can analyze the user's level of expertise and generate a persona using optimal language. This allows for the generation of a persona that is easier to understand by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's technical expertise data into the generation AI and cause the generation AI to generate a persona.

[0061] During a simulation, the simulation unit can determine the priority of the simulation based on the generation time of the persona. For example, the simulation unit can prioritize the most recently generated persona. The simulation unit can also prioritize the simulation of older personas. Furthermore, the simulation unit can determine the optimal simulation order taking into account the generation time of the persona. This makes it possible to provide a simulation that reflects the latest information by determining the priority of the simulation based on the generation time of the persona. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input data on the generation time of the persona into the generation AI and have the generation AI determine the priority of the simulation.

[0062] The feedback unit can determine the priority of feedback based on the time when the simulation was performed when providing feedback. For example, the feedback unit can provide feedback of the most recently performed simulation with priority. The feedback unit can also provide feedback of older simulations later. Furthermore, the feedback unit can determine the optimal feedback order taking into account the time when the simulation was performed. In this way, by determining the priority of feedback based on the time when the simulation was performed, it is possible to provide feedback that reflects the latest information. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the feedback unit can input data on the time when the simulation was performed to the generation AI and have the generation AI determine the priority of feedback.

[0063] When collecting persona attributes, the collection unit can prioritize collecting highly relevant attributes by taking into account the user's geographical location information. For example, if the user lives in a specific area, attributes related to that area are prioritized for collection. The collection unit can also collect GPS data and address information to understand the user's geographical location information. Furthermore, the collection unit can also filter relevant attributes based on the address information provided by the user. This allows highly relevant attributes to be prioritized for collection by taking into account the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's geographical location data into the generation AI and have the generation AI select highly relevant attributes.

[0064] When generating a persona, the generation unit can apply different generation algorithms depending on the attribute category. For example, a specific generation algorithm can be applied based on the age attribute. The generation unit can also apply a different generation algorithm based on the gender attribute. Furthermore, the generation unit can apply an optimal generation algorithm based on the occupation attribute. This allows for the generation of a more appropriate persona by applying different generation algorithms depending on the attribute category. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and have the generation AI generate a persona.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The collection unit collects persona attributes. Persona attributes include, for example, age, gender, occupation, and personality. The collection unit can collect data through questionnaires or interviews. Attributes can also be collected from publicly available data on the Internet using data mining techniques. Step 2: The generation unit creates personas based on the attributes collected by the collection unit. The generation unit uses generative AI to generate various personas based on the collected attributes. For example, realistic personas are created by combining attributes such as age, gender, occupation, and personality. Step 3: The simulation department performs simulations on the personas created by the generation department. The simulation department can perform simulations such as handling complaints and providing guidance. By using the generation AI to simulate interactions with personas, trainees can gain experience in dealing with various situations. Step 4: The Feedback Department analyzes the results of the simulation conducted by the Simulation Department and provides feedback on areas for improvement to the trainee's response. The results of the simulation are analyzed using generative AI, and specific feedback is provided on what went well in the trainee's response and what needs improvement. For example, feedback is provided on whether the trainee used appropriate language and attitude when handling a complaint, and whether there were any areas that needed improvement.

[0067] (Example 2) A training support system according to an embodiment of the present invention is a system that performs simulations using personas created using a generative AI, allowing trainees to gain experience in actual workplaces in advance. In the training support system, the generative AI creates a variety of personas, allowing trainees to gain experience in responding to various situations. This system allows trainees to improve their ability to respond in actual workplaces. For example, in the training support system, the generative AI creates a variety of personas with attributes such as age, gender, occupation, and personality. Next, the training support system performs simulations using the created personas, allowing trainees to simulate tasks such as handling complaints and providing guidance. Furthermore, in the training support system, the generative AI analyzes the results of the simulations and provides feedback on areas for improvement to the trainees' responses. This allows trainees to specifically identify what went well and what needs improvement in their responses. This allows the training support system to provide trainees with actual workplace experience in advance, thereby bridging the gap between training and the actual workplace. For example, by performing simulations using a variety of personas during training, trainees can acquire skills for responding to various situations. Furthermore, the generative AI provides feedback, allowing trainees to specifically identify areas for improvement in their responses and improve their skills.

[0068] A training support system according to an embodiment includes a collection unit, a generation unit, a simulation unit, and a feedback unit. The collection unit collects persona attributes. Persona attributes include, but are not limited to, age, gender, occupation, and personality. The collection unit can collect data, for example, through questionnaires or interviews. The collection unit can also collect attributes from publicly available data on the Internet using data mining technology. The generation unit creates personas based on the attributes collected by the collection unit. The generation unit uses a generation AI to generate various personas based on the collected attributes. For example, the generation AI combines attributes such as age, gender, occupation, and personality to create realistic personas. The simulation unit performs simulations on the personas created by the generation unit. The simulation unit can perform simulations such as handling complaints and providing guidance. The simulation unit uses the generation AI to simulate interactions with personas, allowing trainees to gain experience in responding to various situations. The feedback unit analyzes the results of the simulation performed by the simulation unit and provides feedback on areas for improvement in the trainee's responses. The feedback unit uses the generation AI to analyze the results of the simulation and provide specific feedback on what went well in the trainee's response and what needs improvement. For example, the feedback unit may provide feedback on whether the trainee used appropriate language and attitude when handling a complaint, and whether there were any areas that needed improvement. This allows the training support system according to the embodiment to improve the trainee's ability to respond in actual situations.

[0069] The collection unit can collect data including age, gender, occupation, and personality as persona attributes. For example, the collection unit collects data such as age, gender, occupation, and personality through a questionnaire. The collection unit can also collect detailed attribute data through interviews. For example, the collection unit may interview trainees to collect information on persona attributes. The collection unit can also use data mining technology to collect attributes from publicly available data on the Internet. For example, the collection unit may extract attribute data from social media posts and public profiles. This allows for the collection of diverse data as persona attributes, thereby generating more realistic personas. Some or all of the above-described processing in the collection unit may be performed using or without the generation AI. For example, the collection unit may input questionnaire data into the generation AI and have the generation AI extract attribute data.

[0070] The generation unit can create various personas based on the collected attributes. The generation unit creates various personas based on collected attributes such as age, gender, occupation, and personality. The generation unit uses a generation AI to combine the collected attributes to generate realistic personas. For example, the generation AI combines attributes such as age, gender, occupation, and personality to create personas that can handle various scenarios, such as handling complaints from young customers or providing guidance to elderly people. The generation unit can also use the generation AI to generate scenarios based on the persona attributes. For example, the generation AI generates scenarios such as handling complaints and providing guidance based on the persona attributes. This allows trainees to gain experience in responding to various situations by creating various personas based on the collected attributes. Some or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can input collected attribute data into the generation AI and cause the generation AI to generate personas.

[0071] The simulation unit can perform a simulation of handling a complaint or providing guidance for the created persona. For example, the simulation unit performs a simulation of handling a complaint for the persona created by the generation unit. For example, the simulation unit sets up a scenario in which the persona files a complaint as a customer, and the trainee responds appropriately, thereby cultivating the ability to handle complaints in actual on-site situations. The simulation unit can also perform a simulation of providing guidance. For example, the simulation unit sets up a scenario in which the persona requests guidance as an elderly person, and the trainee provides appropriate guidance, thereby cultivating the ability to provide guidance in actual on-site situations. Furthermore, the simulation unit can simulate a dialogue with the persona using the generation AI. For example, the simulation unit has the generation AI interact with the trainee as the persona, and performs simulations such as handling a complaint or providing guidance. In this way, by performing simulations for the created persona, the trainee can improve their ability to respond in actual on-site situations. Some or all of the above-described processing in the simulation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the simulation unit can input a persona scenario into the generation AI and leave the execution of the simulation to the generation AI.

[0072] The feedback unit can analyze the results of the simulation and provide feedback on areas for improvement to the trainee's response. For example, the feedback unit analyzes the results of a simulation performed by the simulation unit and provides feedback on areas for improvement to the trainee's response. The feedback unit uses the generation AI to analyze the results of the simulation and provide specific feedback on what was good about the trainee's response and what areas need improvement. For example, the feedback unit can provide feedback on whether appropriate language and attitude were used when handling a complaint and whether there were areas for improvement. The feedback unit can also provide feedback on whether appropriate explanations were given when providing guidance and whether there were areas for improvement. In this way, by analyzing the results of the simulation and providing feedback on areas for improvement to the trainee's response, the trainee's skills can be improved. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the feedback unit can input simulation result data into the generation AI and cause the generation AI to generate feedback.

[0073] The collection unit can estimate the user's emotions and adjust the timing of persona attribute collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit delays the timing of collection and collects data when the user is relaxed. The collection unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the collection unit can capture the user's facial expressions with a camera and estimate the emotion using a facial expression recognition algorithm. The collection unit can also record the user's voice with a microphone and estimate the emotion using a voice analysis algorithm. Furthermore, if the user is relaxed, the collection unit can immediately start attribute collection and collect data efficiently. For example, the collection unit can detect that the user is relaxed using an emotion estimation algorithm and collect attribute data through questionnaires or interviews. Furthermore, if the user is in a hurry, the collection unit can shorten the timing of collection and quickly collect necessary attributes. For example, the collection unit can detect that the user is in a hurry using an emotion estimation algorithm and conduct a questionnaire that can be completed in a short time. In this way, by adjusting the collection timing based on the user's emotions, attributes can be collected at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0074] When collecting persona attributes, the collection unit can analyze the user's past behavioral history and select the optimal collection method. For example, the collection unit prioritizes the selection of collection methods (such as questionnaires and interviews) that the user has frequently used in the past. The collection unit can use data mining technology to analyze the user's past behavioral history. For example, the collection unit analyzes the user's website browsing history and purchase history to select the most efficient collection method. The collection unit can also customize the collection method based on the user's past behavioral history. For example, the collection unit prioritizes the selection of collection methods that the user has previously preferred, improving collection efficiency. This allows the optimal collection method to be selected by analyzing the user's past behavioral history. Some or all of the above-described processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's behavioral history data into the generation AI and have the generation AI select the optimal collection method.

[0075] When collecting persona attributes, the collection unit can filter them based on the user's current situation and areas of interest. For example, the collection unit prioritizes collecting attributes related to the user's current areas of interest. The collection unit can conduct surveys or interviews to understand the user's current situation and areas of interest. For example, the collection unit can ask the user questions about their current occupation and living environment and filter related attributes. The collection unit can also analyze social media posts and search history to analyze the user's current areas of interest. For example, the collection unit can filter related attributes based on keywords recently searched by the user or information shared on social media. This allows for filtering based on the user's current situation and areas of interest, thereby collecting more relevant attributes. Some or all of the above-mentioned processing in the collection unit can be performed using or without the generation AI. For example, the collection unit can input the user's area of ​​interest data into the generation AI and leave the filtering to the generation AI.

[0076] When collecting attributes of a persona, the collection unit can select the optimal collection method depending on the user's input method. For example, if the user prefers voice input, the collection unit selects a method for collecting attributes by voice. The collection unit can conduct surveys or interviews to understand the user's input method. For example, the collection unit can ask the user about their preference, such as voice input, text input, or image input, and select the optimal collection method. The collection unit can also analyze the user's past input history. For example, the collection unit can select the optimal collection method based on the input method the user has used in the past. This allows attributes to be collected efficiently by selecting the optimal collection method depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's input history data into the generation AI and have the generation AI select the optimal collection method.

[0077] The collection unit can estimate the user's emotions and determine the priority of persona attributes to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit prioritizes collecting important attributes, thereby shortening the collection time. The collection unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the collection unit can capture the user's facial expressions with a camera and estimate the emotion using a facial expression recognition algorithm. The collection unit can also record the user's voice with a microphone and estimate the emotion using a voice analysis algorithm. Furthermore, when the user is relaxed, the collection unit collects detailed attributes to improve the accuracy of the persona. For example, the collection unit can detect that the user is relaxed using an emotion estimation algorithm and collect attribute data through a detailed questionnaire or interview. Furthermore, when the user is in a hurry, the collection unit can collect only the most important attributes and quickly create a persona. For example, the collection unit can detect that the user is in a hurry using an emotion estimation algorithm and conduct a questionnaire that can be completed in a short time. In this way, by determining the priority of attributes based on the user's emotions, important attributes can be preferentially collected. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0078] When collecting persona attributes, the collection unit can prioritize collecting highly relevant attributes by taking into account the user's geographical location information. For example, if the user lives in a specific area, the collection unit prioritizes collecting attributes related to that area. The collection unit can collect GPS data and address information to determine the user's geographical location. For example, the collection unit obtains GPS data from the user's smartphone to determine their current location. The collection unit can also filter relevant attributes based on address information provided by the user. For example, the collection unit prioritizes collecting attributes related to the area based on the user's address information. This allows highly relevant attributes to be collected preferentially by taking into account the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's geographical location data into the generation AI and have the generation AI select highly relevant attributes.

[0079] When collecting persona attributes, the collection unit can analyze the user's social media activities and collect related attributes. For example, the collection unit collects related attributes based on information shared by the user on social media. The collection unit can use data mining technology to analyze the user's social media activities. For example, the collection unit analyzes the content of the user's social media posts, the number of likes, the number of followers, etc. to collect related attributes. The collection unit can also collect optimal attributes based on the user's social media activities. For example, the collection unit analyzes topics the user frequently posts on and themes of interest to collect related attributes. In this way, related attributes can be collected by analyzing the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's social media data into the generation AI and have the generation AI collect related attributes.

[0080] When collecting persona attributes, the collection unit can customize the collection method by reflecting the user's past feedback. The collection unit customizes the collection method, for example, based on feedback provided by the user in the past. The collection unit can use data mining technology to analyze the user's past feedback. For example, the collection unit analyzes survey results and comments provided by the user in the past and selects the optimal collection method. The collection unit can also adjust the collection means by reflecting the user's past feedback. For example, the collection unit prioritizes the collection method that the user has previously preferred to use, improving collection efficiency. This allows the optimal collection method to be selected by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's feedback data into the generation AI and have the generation AI customize the collection method.

[0081] The generation unit can estimate the user's emotions and adjust the persona generation method based on the estimated user emotions. For example, if the user is relaxed, the generation unit generates a detailed persona. The generation unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the generation unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The generation unit can also record the user's voice with a microphone and estimate the emotions using a voice analysis algorithm. Furthermore, if the user is in a hurry, the generation unit generates a concise persona. For example, the generation unit can detect that the user is in a hurry using an emotion estimation algorithm and generate a concise persona. Furthermore, if the user is excited, the generation unit can generate a visually appealing persona. For example, the generation unit can detect that the user is excited using an emotion estimation algorithm and generate a visually appealing persona. This allows for the generation of a more appropriate persona by adjusting the generation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0082] When generating a persona, the generation unit can adjust the level of detail of the generation based on the importance of the collected attributes. For example, the generation unit generates a detailed persona based on important attributes. The generation unit can use data analysis techniques to evaluate the importance of the collected attributes. For example, the generation unit analyzes the collected attribute data and evaluates the importance of each attribute. The generation unit can also generate a concise persona based on less important attributes. For example, the generation unit generates a concise persona based on less important attributes. Furthermore, the generation unit can analyze the importance of attributes and generate a persona with an optimal level of detail. For example, the generation unit balances detailed personas and concise personas based on the importance of attributes. This allows the generation of an optimal persona by adjusting the level of detail of the generation based on the importance of the collected attributes. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the collected attribute data to a generation AI and cause the generation AI to generate a persona.

[0083] When generating a persona, the generation unit can apply different generation algorithms depending on the attribute category. For example, the generation unit applies a specific generation algorithm based on an age attribute. The generation unit can use data analysis techniques to evaluate the attribute categories. For example, the generation unit analyzes collected attribute data and evaluates each attribute category. The generation unit can also apply different generation algorithms based on a gender attribute. For example, the generation unit applies different generation algorithms based on the gender attribute. Furthermore, the generation unit can apply an optimal generation algorithm based on an occupation attribute. For example, the generation unit applies an optimal generation algorithm based on the occupation attribute. This allows for the generation of a more appropriate persona by applying different generation algorithms depending on the attribute category. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and cause the generation AI to generate a persona.

[0084] When generating a persona, the generation unit can improve the accuracy of the generation by referring to past generation results. The generation unit improves the accuracy, for example, based on personas generated in the past. The generation unit can use data analysis technology to evaluate past generation results. For example, the generation unit analyzes the evaluation results of personas generated in the past to improve the accuracy of the generation. The generation unit can also analyze past generation results and apply an optimal generation method. For example, the generation unit applies an optimal generation method based on past generation results. Furthermore, the generation unit can adjust the generation algorithm by referring to past generation results. For example, the generation unit adjusts parameters of the generation algorithm based on past generation results. In this way, the accuracy of the generation can be improved by referring to past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input past generation result data into the generation AI and cause the generation AI to improve the accuracy of the generation.

[0085] The generation unit can estimate the user's emotions and adjust the balance of attributes of the persona to be generated based on the estimated user's emotions. For example, when the user is relaxed, the generation unit generates a balanced persona. The generation unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the generation unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The generation unit can also record the user's voice with a microphone and estimate the emotions using a voice analysis algorithm. Furthermore, when the user is in a hurry, the generation unit generates a persona that emphasizes important attributes. For example, the generation unit can detect that the user is in a hurry using an emotion estimation algorithm and generate a persona that emphasizes important attributes. Furthermore, when the user is excited, the generation unit can generate a persona that emphasizes visually appealing attributes. For example, the generation unit can detect that the user is excited using an emotion estimation algorithm and generate a persona that emphasizes visually appealing attributes. In this way, a more balanced persona can be generated by adjusting the balance of attributes based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0086] When generating a persona, the generation unit can determine a generation priority based on the time when the attributes were collected. For example, the generation unit generates a persona by prioritizing recently collected attributes. The generation unit can use data analysis technology to evaluate the time when the attributes were collected. For example, the generation unit analyzes the collection time of collected attribute data and prioritizes the most recent data. The generation unit can also generate a persona by deferring older attributes. For example, the generation unit generates a persona based on older attributes. Furthermore, the generation unit can determine an optimal generation order taking into account the time when the attributes were collected. For example, the generation unit determines an optimal generation order based on the time when the attributes were collected. In this way, by determining the generation priority based on the time when the attributes were collected, a persona that reflects the most recent information can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and cause the generation AI to generate a persona.

[0087] When generating personas, the generation unit can adjust the generation order based on the relevance of attributes. For example, the generation unit generates personas by prioritizing highly relevant attributes. The generation unit can use data analysis technology to evaluate the relevance of attributes. For example, the generation unit analyzes the relevance of collected attribute data and prioritizes highly relevant attributes. The generation unit can also generate personas by deferring less relevant attributes. For example, the generation unit generates personas based on less relevant attributes. Furthermore, the generation unit can analyze the relevance of attributes and determine an optimal generation order. For example, the generation unit determines an optimal generation order based on the relevance of attributes. As a result, by adjusting the generation order based on the relevance of attributes, more relevant personas can be generated. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and cause the generation AI to generate personas.

[0088] When generating a persona, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a persona that uses a lot of technical terminology. The generation unit can conduct a questionnaire or interview to evaluate the user's level of expertise. For example, the generation unit can ask the user questions about their expertise and evaluate their level of expertise. Furthermore, if the user does not have technical expertise, the generation unit can generate a persona using concise language. For example, the generation unit can evaluate that the user does not have technical expertise and generate a persona using concise language. Furthermore, the generation unit can analyze the user's level of expertise and generate a persona using optimal language. For example, the generation unit generates a persona using optimal language based on the user's level of expertise. This allows the generation of a persona that is easier to understand by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's technical expertise data into the generation AI and cause the generation AI to generate a persona.

[0089] The simulation unit can estimate the user's emotions and adjust the simulation scenario based on the estimated user emotions. For example, if the user is relaxed, the simulation unit provides a detailed scenario. The simulation unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the simulation unit can capture the user's facial expressions with a camera and estimate the emotions using a facial expression recognition algorithm. The simulation unit can also record the user's voice with a microphone and estimate the emotions using a voice analysis algorithm. Furthermore, if the user is in a hurry, the simulation unit can provide a concise scenario. For example, the simulation unit can detect that the user is in a hurry using an emotion estimation algorithm and provide a concise scenario. Furthermore, the simulation unit can provide a visually appealing scenario if the user is excited. For example, the simulation unit can detect that the user is excited using an emotion estimation algorithm and provide a visually appealing scenario. This allows the simulation scenario to be adjusted based on the user's emotions, thereby providing a more appropriate simulation. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the simulation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the simulation unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0090] During the simulation, the simulation unit can adjust the level of detail of the simulation based on the attributes of the persona. For example, the simulation unit performs a detailed simulation based on important attributes. The simulation unit can use data analysis techniques to evaluate the attributes of the persona. For example, the simulation unit analyzes the attribute data of the persona and evaluates the importance of each attribute. The simulation unit can also perform a concise simulation based on less important attributes. For example, the simulation unit performs a concise simulation based on less important attributes. Furthermore, the simulation unit can analyze the importance of the attributes and perform a simulation with an optimal level of detail. For example, the simulation unit balances detailed simulation and concise simulation based on the importance of the attributes. This allows for adjusting the level of detail of the simulation based on the attributes of the persona, thereby providing a more realistic simulation. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input the attribute data of the persona into the generation AI and cause the generation AI to adjust the level of detail of the simulation.

[0091] The simulation unit can apply different simulation algorithms depending on the persona category during the simulation. For example, the simulation unit applies a specific algorithm to a simulation of handling complaints. The simulation unit can use data analysis techniques to evaluate the persona category. For example, the simulation unit analyzes persona category data and selects an optimal simulation algorithm for each category. The simulation unit can also apply different algorithms to a simulation of providing guidance. For example, the simulation unit applies an optimal algorithm to a simulation of providing guidance. Furthermore, the simulation unit can apply an optimal simulation algorithm depending on the persona category. For example, the simulation unit applies an optimal simulation algorithm based on the persona category. This allows for a more appropriate simulation to be provided. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input persona category data into the generation AI and have the generation AI select a simulation algorithm.

[0092] During a simulation, the simulation unit can improve the accuracy of the simulation by referring to past simulation results. For example, the simulation unit improves the accuracy based on the past simulation results. The simulation unit can use data analysis techniques to evaluate past simulation results. For example, the simulation unit analyzes past simulation result data to improve the accuracy of the simulation. The simulation unit can also analyze past simulation results and apply an optimal simulation method. For example, the simulation unit applies an optimal simulation method based on the past simulation results. Furthermore, the simulation unit can adjust a simulation algorithm by referring to the past simulation results. For example, the simulation unit adjusts parameters of a simulation algorithm based on the past simulation results. In this way, the accuracy of the simulation can be improved by referring to the past simulation results. Some or all of the above-described processing in the simulation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the simulation unit can input past simulation result data into the generation AI and cause the generation AI to improve the accuracy of the simulation.

[0093] The simulation unit can estimate the user's emotions and adjust the length of the simulation based on the estimated user emotions. For example, if the user is relaxed, the simulation unit provides a longer simulation. The simulation unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the simulation unit can capture the user's facial expressions with a camera and estimate the emotion using a facial expression recognition algorithm. The simulation unit can also record the user's voice with a microphone and estimate the emotion using a voice analysis algorithm. Furthermore, if the user is in a hurry, the simulation unit can provide a shorter simulation. For example, the simulation unit can detect that the user is in a hurry using an emotion estimation algorithm and provide a shorter simulation. Furthermore, the simulation unit can provide a visually appealing simulation if the user is excited. For example, the simulation unit can detect that the user is excited using an emotion estimation algorithm and provide a visually appealing simulation. This allows the length of the simulation to be adjusted based on the user's emotions, thereby providing a more appropriate simulation. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the simulation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the simulation unit may input user facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0094] During a simulation, the simulation unit can determine the priority of the simulation based on the generation time of the persona. For example, the simulation unit prioritizes the most recently generated persona during the simulation. The simulation unit can use data analysis techniques to evaluate the generation time of the persona. For example, the simulation unit analyzes the generation time of the generated persona and prioritizes the most recent persona. The simulation unit can also postpone the simulation of older personas. For example, the simulation unit postpones the simulation based on older personas. Furthermore, the simulation unit can determine the optimal simulation order taking into account the generation time of the persona. For example, the simulation unit determines the optimal simulation order based on the generation time of the persona. This allows for simulations that reflect the latest information to be provided by prioritizing the simulations based on the generation time of the persona. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input data on the generation time of the persona into the generation AI and have the generation AI determine the priority of the simulations.

[0095] During a simulation, the simulation unit can adjust the order of simulations based on the relevance of personas. For example, the simulation unit prioritizes highly relevant personas during simulation. The simulation unit can use data analysis techniques to evaluate the relevance of personas. For example, the simulation unit analyzes persona attribute data and evaluates the relevance of each persona. The simulation unit can also postpone simulations for less relevant personas. For example, the simulation unit postpones simulations based on less relevant personas. Furthermore, the simulation unit can analyze the relevance of personas and determine an optimal simulation order. For example, the simulation unit determines an optimal simulation order based on the relevance of personas. This allows for adjusting the order of simulations based on the relevance of personas to provide a more relevant simulation. Some or all of the above-described processing in the simulation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the simulation unit can input persona relevance data into the generation AI and cause the generation AI to adjust the order of simulations.

[0096] During the simulation, the simulation unit can adjust the use of technical terminology in the simulation according to the user's level of expertise. For example, if the user has technical expertise, the simulation unit provides a simulation that uses a lot of technical terminology. The simulation unit can conduct a questionnaire or interview to evaluate the user's level of expertise. For example, the simulation unit can ask the user questions about their technical expertise and evaluate their level of expertise. Furthermore, if the user does not have technical expertise, the simulation unit can provide a simulation in simple language. For example, the simulation unit can determine that the user does not have technical expertise and provide a simulation in simple language. Furthermore, the simulation unit can analyze the user's level of expertise and provide a simulation using optimal language. For example, the simulation unit can provide a simulation using optimal language based on the user's level of expertise. This allows for a simulation that is easier to understand by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-described processing in the simulation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the simulation unit can input the user's technical expertise data into the generation AI and have the generation AI control the use of technical terminology in the simulation.

[0097] The feedback unit can estimate the user's emotions and adjust the feedback method based on the estimated user's emotions. For example, if the user is relaxed, the feedback unit provides detailed feedback. The feedback unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the feedback unit can capture the user's facial expressions with a camera and estimate the emotion using a facial expression recognition algorithm. The feedback unit can also record the user's voice with a microphone and estimate the emotion using a voice analysis algorithm. Furthermore, if the user is in a hurry, the feedback unit can provide concise feedback. For example, the feedback unit can detect that the user is in a hurry using an emotion estimation algorithm and provide concise feedback. Furthermore, the feedback unit can provide visually appealing feedback if the user is excited. For example, the feedback unit can detect that the user is excited using an emotion estimation algorithm and provide visually appealing feedback. This allows the system to provide more appropriate feedback by adjusting the feedback method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the feedback unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0098] The feedback unit can adjust the level of detail of the feedback based on the results of the simulation when providing feedback. For example, the feedback unit provides detailed feedback based on important simulation results. The feedback unit can use data analysis techniques to evaluate the results of the simulation. For example, the feedback unit can analyze simulation result data and evaluate the importance of each result. The feedback unit can also provide brief feedback based on simulation results with low importance. For example, the feedback unit can provide brief feedback based on simulation results with low importance. Furthermore, the feedback unit can analyze the importance of the simulation results and provide feedback with an optimal level of detail. For example, the feedback unit balances detailed feedback and brief feedback based on the importance of the simulation results. This allows for more appropriate feedback to be provided by adjusting the level of detail of the feedback based on the results of the simulation. Some or all of the above-described processing in the feedback unit can be performed using or without the generation AI. For example, the feedback unit can input simulation result data to the generation AI and cause the generation AI to adjust the level of detail of the feedback.

[0099] The feedback unit can apply different feedback algorithms depending on the category of the simulation when providing feedback. For example, the feedback unit applies a specific algorithm to feedback on complaint handling. The feedback unit can use data analysis techniques to evaluate the category of the simulation. For example, the feedback unit analyzes simulation category data and selects an optimal feedback algorithm for each category. The feedback unit can also apply different algorithms to feedback on providing guidance. For example, the feedback unit applies an optimal algorithm to feedback on providing guidance. The feedback unit can also apply an optimal feedback algorithm depending on the category of the simulation. For example, the feedback unit applies an optimal feedback algorithm based on the category of the simulation. This allows for more appropriate feedback to be provided by applying different feedback algorithms depending on the category of the simulation. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input simulation category data to the generation AI and have the generation AI select a feedback algorithm.

[0100] The feedback unit can improve the accuracy of feedback by referring to past feedback results when providing feedback. For example, the feedback unit improves the accuracy based on past feedback results. The feedback unit can use data analysis technology to evaluate past feedback results. For example, the feedback unit analyzes past feedback result data to improve the accuracy of feedback. The feedback unit can also analyze past feedback results and apply an optimal feedback method. For example, the feedback unit applies an optimal feedback method based on past feedback results. Furthermore, the feedback unit can adjust the feedback algorithm by referring to past feedback results. For example, the feedback unit adjusts parameters of the feedback algorithm based on past feedback results. In this way, the accuracy of feedback can be improved by referring to past feedback results. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input past feedback result data into the generation AI and cause the generation AI to improve the accuracy of feedback.

[0101] The feedback unit can estimate the user's emotions and prioritize feedback based on the estimated user emotions. For example, if the user is relaxed, the feedback unit can prioritize providing detailed feedback. The feedback unit can use facial expression recognition technology or voice analysis technology to estimate the user's emotions. For example, the feedback unit can capture the user's facial expressions with a camera and estimate the emotion using a facial expression recognition algorithm. The feedback unit can also record the user's voice with a microphone and estimate the emotion using a voice analysis algorithm. Furthermore, if the user is in a hurry, the feedback unit can prioritize providing concise feedback. For example, the feedback unit can detect that the user is in a hurry using an emotion estimation algorithm and prioritize providing concise feedback. Furthermore, if the user is excited, the feedback unit can prioritize providing visually appealing feedback. For example, the feedback unit can detect that the user is excited using an emotion estimation algorithm and prioritize providing visually appealing feedback. This allows for providing more appropriate feedback by prioritizing feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the feedback unit may input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0102] The feedback unit can determine the priority of feedback based on the time when the simulation was performed when providing feedback. For example, the feedback unit prioritizes providing feedback for the most recently performed simulation. The feedback unit can use data analysis techniques to evaluate the time when the simulation was performed. For example, the feedback unit analyzes data on the time when the simulation was performed and prioritizes the most recent simulation. The feedback unit can also provide feedback for older simulations at a later date. For example, the feedback unit provides feedback based on older simulations at a later date. Furthermore, the feedback unit can determine an optimal feedback order taking into account the time when the simulation was performed. For example, the feedback unit determines an optimal feedback order based on the time when the simulation was performed. In this way, feedback reflecting the latest information can be provided by determining the priority of feedback based on the time when the simulation was performed. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input data on the time when the simulation was performed to the generation AI and cause the generation AI to determine the priority of feedback.

[0103] The feedback unit can adjust the order of feedback based on the relevance of the simulations when providing feedback. For example, the feedback unit prioritizes providing feedback for highly relevant simulations. The feedback unit can use data analysis techniques to evaluate the relevance of the simulations. For example, the feedback unit analyzes relevance data of the simulations and evaluates the relevance of each simulation. The feedback unit can also provide feedback for less relevant simulations at a later date. For example, the feedback unit provides feedback based on less relevant simulations at a later date. Furthermore, the feedback unit can analyze the relevance of the simulations and determine an optimal feedback order. For example, the feedback unit determines an optimal feedback order based on the relevance of the simulations. As a result, more relevant feedback can be provided by adjusting the feedback order based on the relevance of the simulations. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input relevance data of the simulations to the generation AI and cause the generation AI to adjust the feedback order.

[0104] When providing feedback, the feedback unit can adjust the use of technical terms in the feedback depending on the user's level of expertise. For example, if the user has technical expertise, the feedback unit provides feedback that uses a lot of technical terms. The feedback unit can conduct a questionnaire or interview to evaluate the user's level of expertise. For example, the feedback unit can ask the user questions about their expertise and evaluate their level of expertise. Furthermore, if the user does not have technical expertise, the feedback unit can provide feedback in concise language. For example, the feedback unit can evaluate that the user does not have technical expertise and provide feedback in concise language. Furthermore, the feedback unit can analyze the user's level of expertise and provide feedback in optimal language. For example, the feedback unit can provide feedback in optimal language based on the user's level of expertise. This allows for providing feedback that is easier to understand by adjusting the use of technical terms depending on the user's level of expertise. Some or all of the above-described processing in the feedback unit can be performed using a generation AI or without a generation AI. For example, the feedback unit can input the user's technical expertise data into the generation AI and cause the generation AI to use technical terms in the feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, generation unit, simulation unit, and feedback unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect attributes of the persona using the camera 42 or microphone 38B of the smart device 14. For example, the generation unit creates a persona based on the attributes collected by the specific processing unit 290 of the data processing device 12. For example, the simulation unit can simulate interactions with the persona using the control unit 46A of the smart device 14, allowing the trainee to gain experience in responding to various situations. For example, the feedback unit can analyze the results of the simulation using the specific processing unit 290 of the data processing device 12 and provide feedback on areas for improvement to the trainee's response. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, generation unit, simulation unit, and feedback unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect attributes of the persona using the camera 42 or microphone 238 of the smart glasses 214. For example, the generation unit creates a persona based on the attributes collected by the specific processing unit 290 of the data processing device 12. For example, the simulation unit can simulate interactions with the persona using the control unit 46A of the smart glasses 214, allowing the trainee to gain experience in responding to various situations. For example, the feedback unit can analyze the results of the simulation using the specific processing unit 290 of the data processing device 12 and provide feedback on improvements to the trainee's response. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, generation unit, simulation unit, and feedback unit, described above, is realized, for example, in at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit can collect attributes of the persona using the camera 42 or microphone 238 of the headset terminal 314. For example, the generation unit creates a persona based on the attributes collected by the specific processing unit 290 of the data processing device 12. For example, the simulation unit can simulate an interaction with the persona using the control unit 46A of the headset terminal 314, allowing the trainee to gain experience in responding to various situations. For example, the feedback unit can analyze the results of the simulation using the specific processing unit 290 of the data processing device 12 and provide feedback on areas for improvement to the trainee's response. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, generation unit, simulation unit, and feedback unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect attributes of the persona using the camera 42 or microphone 238 of the robot 414. For example, the generation unit creates a persona based on the attributes collected by the specific processing unit 290 of the data processing device 12. For example, the simulation unit can simulate an interaction with the persona using the control unit 46A of the robot 414, allowing the trainee to gain experience in responding to various situations. For example, the feedback unit can analyze the results of the simulation using the specific processing unit 290 of the data processing device 12 and provide feedback on areas for improvement to the trainee's response.

[0105] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0106] The collection unit can analyze the user's past feedback and customize the collection method. For example, the collection unit can adjust the content of survey questions and the interview progress method based on the user's past feedback. The collection unit can also optimize the timing and frequency of collection based on the user's past feedback. This enables more effective attribute collection by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can input the user's feedback data into the generation AI and have the generation AI customize the collection method.

[0107] When generating a persona, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit can generate a persona that uses a lot of technical terminology. Alternatively, if the user does not have technical expertise, the generation unit can generate a persona using concise language. Furthermore, the generation unit can analyze the user's level of expertise and generate a persona using optimal language. This allows for the generation of a persona that is easier to understand by adjusting the use of technical terminology according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's technical expertise data into the generation AI and cause the generation AI to generate a persona.

[0108] During a simulation, the simulation unit can determine the priority of the simulation based on the generation time of the persona. For example, the simulation unit can prioritize the most recently generated persona. The simulation unit can also prioritize the simulation of older personas. Furthermore, the simulation unit can determine the optimal simulation order taking into account the generation time of the persona. This makes it possible to provide a simulation that reflects the latest information by determining the priority of the simulation based on the generation time of the persona. Some or all of the above-described processing in the simulation unit may be performed using or without the generation AI. For example, the simulation unit can input data on the generation time of the persona into the generation AI and have the generation AI determine the priority of the simulation.

[0109] The feedback unit can determine the priority of feedback based on the time when the simulation was performed when providing feedback. For example, the feedback unit can provide feedback of the most recently performed simulation with priority. The feedback unit can also provide feedback of older simulations later. Furthermore, the feedback unit can determine the optimal feedback order taking into account the time when the simulation was performed. In this way, by determining the priority of feedback based on the time when the simulation was performed, it is possible to provide feedback that reflects the latest information. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the feedback unit can input data on the time when the simulation was performed to the generation AI and have the generation AI determine the priority of feedback.

[0110] The collection unit can estimate the user's emotions and adjust the timing of persona attribute collection based on the estimated user emotions. For example, if the user is stressed, the collection unit can delay the timing of collection and collect data in a relaxed state. Furthermore, if the user is relaxed, the collection unit can immediately start attribute collection and efficiently collect data. Furthermore, if the user is in a hurry, the collection unit can shorten the timing of collection and quickly collect necessary attributes. This allows attributes to be collected at a more appropriate time by adjusting the collection timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using the generation AI, or without the generation AI. For example, the collection unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0111] The generation unit can estimate the user's emotions and adjust the persona generation method based on the estimated user emotions. For example, if the user is relaxed, the generation unit can generate a detailed persona. If the user is in a hurry, the generation unit can also generate a concise persona. Furthermore, if the user is excited, the generation unit can generate a visually appealing persona. This allows for a more appropriate persona to be generated by adjusting the generation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the generation unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0112] The simulation unit can estimate the user's emotions and adjust the simulation scenario based on the estimated user emotions. For example, if the user is relaxed, the simulation unit can provide a detailed scenario. If the user is in a hurry, the simulation unit can provide a concise scenario. Furthermore, if the user is excited, the simulation unit can provide a visually appealing scenario. This allows for adjusting the simulation scenario based on the user's emotions to provide a more appropriate simulation. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the simulation unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the simulation unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0113] The feedback unit can estimate the user's emotions and adjust the feedback method based on the estimated user's emotions. For example, if the user is relaxed, the feedback unit can provide detailed feedback. If the user is in a hurry, the feedback unit can also provide concise feedback. Furthermore, if the user is excited, the feedback unit can also provide visually appealing feedback. This allows for more appropriate feedback by adjusting the feedback method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the feedback unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0114] When collecting persona attributes, the collection unit can prioritize collecting highly relevant attributes by taking into account the user's geographical location information. For example, if the user lives in a specific area, attributes related to that area are prioritized for collection. The collection unit can also collect GPS data and address information to understand the user's geographical location information. Furthermore, the collection unit can also filter relevant attributes based on the address information provided by the user. This allows highly relevant attributes to be prioritized for collection by taking into account the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using or without the generation AI. For example, the collection unit can input the user's geographical location data into the generation AI and have the generation AI select highly relevant attributes.

[0115] When generating a persona, the generation unit can apply different generation algorithms depending on the attribute category. For example, a specific generation algorithm can be applied based on the age attribute. The generation unit can also apply a different generation algorithm based on the gender attribute. Furthermore, the generation unit can apply an optimal generation algorithm based on the occupation attribute. This allows for the generation of a more appropriate persona by applying different generation algorithms depending on the attribute category. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input collected attribute data into a generation AI and have the generation AI generate a persona.

[0116] The processing flow of the second embodiment will be briefly explained below.

[0117] Step 1: The collection unit collects persona attributes. Persona attributes include, for example, age, gender, occupation, and personality. The collection unit can collect data through questionnaires or interviews. Attributes can also be collected from publicly available data on the Internet using data mining techniques. Step 2: The generation unit creates personas based on the attributes collected by the collection unit. The generation unit uses generative AI to generate various personas based on the collected attributes. For example, realistic personas are created by combining attributes such as age, gender, occupation, and personality. Step 3: The simulation department performs simulations on the personas created by the generation department. The simulation department can perform simulations such as handling complaints and providing guidance. By using the generation AI to simulate interactions with personas, trainees can gain experience in dealing with various situations. Step 4: The Feedback Department analyzes the results of the simulation conducted by the Simulation Department and provides feedback on areas for improvement to the trainee's response. The results of the simulation are analyzed using generative AI, and specific feedback is provided on what went well in the trainee's response and what needs improvement. For example, feedback is provided on whether the trainee used appropriate language and attitude when handling a complaint, and whether there were any areas that needed improvement.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0123] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0139] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0155] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0157] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0161] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0162] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0163] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0166] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0169] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0172] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0173] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0174] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0175] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0176] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0177] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0178] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0179] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0180] 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.

[0181] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0182] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0183] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0184] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0185] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0186] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0187] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0188] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0189] [Explanation of symbols]

[0190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects persona attributes; a generation unit that generates a persona based on the attributes collected by the collection unit; a simulation unit that performs a simulation on the persona created by the generation unit; a feedback unit that analyzes the results of the simulation performed by the simulation unit and provides feedback. A system characterized by:

2. The collecting unit Collect data on persona attributes, including age, gender, occupation, and personality 2. The system of claim 1.

3. The generation unit Create various personas based on collected attributes 2. The system of claim 1.

4. The simulation unit Simulate handling a complaint or providing guidance to the persona created 2. The system of claim 1.

5. The feedback unit Analyze the results of the simulation and provide feedback on how the trainees can improve their responses.

2. The system of claim 1.

6. The collecting unit Estimate user emotions and adjust the timing of persona attribute collection based on the estimated user emotions 2. The system of claim 1.

7. The collecting unit When collecting persona attributes, analyze the user's past behavioral history and select the optimal collection method.

2. The system of claim 1.

8. The collecting unit When collecting persona attributes, filter based on the user's current situation and areas of interest.

2. The system of claim 1.

Images