system

Abstract

An object of the system according to the embodiment is to generate a reviewer specialized for a target group, automate a QA task, and acquire reviews at a high frequency.SOLUTION: A system includes a reviewer generation part, a review platform provision part, a QA automation part, and a high frequency review acquisition part. The reviewer generator generates a reviewer using the generation AI. The review platform providing unit provides a virtual review platform on which the reviewer generated by the reviewer generating unit performs a review. The QA automation unit automates a QA task by the reviewer generated by the reviewer generation unit. The high-frequency review acquisition unit acquires reviews at a high frequency by the reviewer generated by the reviewer generation unit.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] Conventional technology has faced challenges in that it is difficult to generate reviewers specialized for a target demographic, automate QA tasks, and obtain reviews frequently.

[0005] The system according to the embodiment aims to generate reviewers specialized for a target demographic, automate QA work, and obtain reviews frequently. [Means for solving the problem]

[0006] The system according to the embodiment includes a reviewer generation unit, a review platform providing unit, a QA automation unit, and a high-frequency review acquisition unit. The reviewer generation unit generates reviewers using a generation AI. The review platform providing unit provides a virtual review platform on which the reviewers generated by the reviewer generation unit perform reviews. The QA automation unit automates QA work using the reviewers generated by the reviewer generation unit. The high-frequency review acquisition unit allows the reviewers generated by the reviewer generation unit to acquire reviews at a high frequency. [Effects of the Invention]

[0007] The system according to the embodiment can generate reviewers specialized for a target demographic, automate QA work, and obtain reviews frequently. [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) The virtual review platform according to an embodiment of the present invention is a system that uses AI to generate reviewers with various attributes (personas) and provides a virtual review platform. As a result, the virtual review platform can provide services specialized for the target demographic, improve the efficiency of QA work, and obtain reviews more frequently.

[0029] A virtual review platform according to an embodiment includes a reviewer generation unit, a review platform providing unit, a QA automation unit, and a high-frequency review acquisition unit. The reviewer generation unit generates reviewers using a generation AI. For example, the generation AI uses a specific model, such as GPT-3 or BERT, to generate virtual reviewers with specific attributes based on a target demographic specified by a user. The review platform providing unit provides a virtual review platform on which the reviewers generated by the reviewer generation unit conduct reviews. For example, the virtual review platform includes a user interface and a backend system, and is intended for service providers and system developers to collect reviews of their apps and services. The QA automation unit automates QA tasks using the reviewers generated by the reviewer generation unit. For example, the virtual reviewers can detect bugs in apps and evaluate their usability, thereby improving the efficiency of QA tasks. The high-frequency review acquisition unit allows the reviewers generated by the reviewer generation unit to frequently acquire reviews. For example, the virtual reviewers can review each app update and provide immediate feedback on the results. As a result, the virtual review platform according to the embodiment can provide services specialized for the target demographic, improve the efficiency of QA work, and obtain reviews more frequently.

[0030] The reviewer generation unit can generate reviewers with attributes such as specific age groups, genders, occupations, hobbies, and preferences. The reviewer generation unit generates reviewers with attributes such as specific age groups, genders, occupations, hobbies, and preferences, for example, using a generation AI. For example, the generation AI generates virtual reviewers with specific attributes based on a target demographic specified by a user. This makes it possible to generate reviewers specialized for the target demographic.

[0031] The reviewer generation unit can generate highly reliable reviewers by taking into account the reviewer's past review history and ratings. In the reviewer generation unit, for example, the generation AI analyzes the reviewer's past review history to generate highly reliable reviewers. For example, a new reviewer is generated based on the attributes of reviewers who have received high ratings in the past. The unit also generates highly reliable reviewers by taking into account the reviewer's past rating data. For example, a new reviewer is generated based on the attributes of reviewers who have received a lot of positive feedback in the past. The generation AI also integrates the reviewer's past review history and ratings to generate highly reliable reviewers. For example, a highly reliable reviewer is generated based on the content of past reviews and rating scores. This makes it possible to generate highly reliable reviewers.

[0032] The reviewer generation unit can generate reviewers with specific cultural backgrounds and regional characteristics, and provide reviews from an international perspective. For example, the generation AI of the reviewer generation unit generates reviewers with specific cultural backgrounds and provides reviews based on that culture. For example, a reviewer who is knowledgeable about Japanese culture reviews products for the Japanese market. The unit also takes into account the reviewer's regional characteristics to generate reviews from an international perspective. For example, for products targeted at the Western market, it provides reviews from the perspective of Western consumers. The generation AI can also generate reviewers with specific cultural backgrounds and regional characteristics, and provide reviews that are appropriate for different markets. For example, for products targeted at the Asian market, it provides reviews from the perspective of Asian consumers. This allows the unit to provide reviews from an international perspective.

[0033] The reviewer generation unit can generate reviewers with specific expertise and skills to provide reviews from a specialized perspective. For example, the reviewer generation unit generates reviewers with specific expertise and provides specialized reviews based on that knowledge using a generation AI. For example, a reviewer with expertise in the medical field reviews medical devices. The review unit also generates reviews from a specialized perspective by taking into account the reviewer's skill set. For example, a reviewer with programming skills reviews software. The generation AI also generates reviewers with specific expertise and skills to provide reviews that include technical details. For example, a reviewer with expertise in engineering reviews technical products. This makes it possible to provide reviews from a specialized perspective.

[0034] The review platform providing unit can simulate dialogue between reviewers and generate more multifaceted reviews. The review platform providing unit, for example, has multiple reviewers dialogue on a virtual review platform and generates multifaceted reviews based on the content of that dialogue. For example, it provides a review that integrates opinions from different perspectives. It can also simulate dialogue between reviewers and generate a detailed review based on the results. For example, reviewers ask each other questions and exchange opinions, and provide a review that reflects that content. It can also simulate discussion between reviewers on the virtual review platform and generate a comprehensive review based on the results. For example, reviewers with different expertise collaborate to review. In this way, it is possible to simulate dialogue between reviewers and generate multifaceted reviews.

[0035] The review platform providing unit can add a function to automatically analyze the content of reviews and extract specific topics or issues. The review platform providing unit, for example, adds a function to automatically analyze the content of reviews and extract specific topics or issues on a virtual review platform. For example, it analyzes text data of reviews and extracts frequently occurring keywords. It also adds a function to automatically analyze the content of reviews and identify specific issues. For example, it extracts parts with a lot of negative feedback and identifies those issues. It also adds a function to automatically analyze the content of reviews on the virtual review platform and aggregate opinions on specific topics. For example, it displays reviews related to a specific function together. This makes it possible to automatically analyze the content of reviews and extract specific topics or issues.

[0036] The review platform providing unit can introduce an algorithm that takes into account a reviewer's past performance and ratings in order to evaluate the reliability of a review. The review platform providing unit, for example, introduces an algorithm that analyzes a reviewer's past performance data on a virtual review platform and evaluates its reliability. For example, it calculates reliability based on the rating scores of past reviews. It also introduces an algorithm that takes into account a reviewer's past rating data and identifies highly reliable reviewers. For example, it preferentially displays reviews by reviewers who have received high ratings in the past. It also introduces an algorithm that integrates a reviewer's past performance and ratings on the virtual review platform and evaluates their reliability. For example, it calculates reliability based on the reviewer's past review content and rating scores. This makes it possible to introduce an algorithm for evaluating the reliability of reviews.

[0037] The review platform providing unit can add audio and video review functions to provide richer feedback. The review platform providing unit, for example, adds an audio review function to the virtual review platform to enable reviewers to provide feedback via audio. For example, the reviewer explains their experience using the product via audio. Also, a video review function can be added to the virtual review platform to enable reviewers to provide feedback via video. For example, the reviewer demonstrates how to use the product via video. Also, the audio and video review functions can be integrated into the virtual review platform to provide richer feedback. For example, the reviewer combines audio and video to provide a detailed review. This allows the addition of audio and video review functions to provide richer feedback.

[0038] The review platform providing unit can integrate reviews from different industries and fields to provide feedback from a cross-industry perspective. The review platform providing unit, for example, integrates reviews from different industries on a virtual review platform to provide feedback from a cross-industry perspective. For example, it integrates reviews from technology and design. It also adds a function that allows reviewers from different fields to collaborate on reviews and integrate the results. For example, it integrates reviews from marketing and engineering perspectives. It also integrates reviews from different industries and fields on the virtual review platform to provide comprehensive feedback. For example, it integrates reviews from the medical field and the consumer product field. This makes it possible to integrate reviews from different industries and fields to provide feedback from a cross-industry perspective.

[0039] The QA Automation Department can build a system that analyzes the results of automated QA work in real time and provides immediate feedback. The QA Automation Department can, for example, build a system that analyzes the results of automated QA work in real time and provides immediate feedback based on the results. For example, it can immediately propose a fix after a bug is detected. The department can also introduce a system that analyzes the results of QA work in real time and provides immediate feedback to developers. For example, it can immediately propose an improvement when a usability problem is detected. The department can also develop a system that analyzes the results of automated QA work in real time and provides rapid feedback based on the results. For example, it can display test results in real time and notify developers immediately. This makes it possible to analyze the results of automated QA work in real time and provide immediate feedback.

[0040] The QA Automation Department can add functionality to simultaneously test on different devices and platforms. For example, in automated QA work, the QA Automation Department adds functionality to simultaneously test on different devices and platforms. For example, tests can be performed simultaneously on smartphones, tablets, and PCs. In addition, by introducing functionality to simultaneously test on different platforms, the efficiency of QA work can be improved. For example, tests can be performed simultaneously on both iOS and Android. In addition, in automated QA work, a system can be built to simultaneously test on different devices and platforms. For example, tests can be performed simultaneously on multiple browsers. This allows the functionality to simultaneously test on different devices and platforms to be added.

[0041] The QA automation department automates QA tasks that correspond to different languages ​​and cultural spheres, enabling the provision of quality assurance from a global perspective. For example, the QA automation department uses generative AI to automate QA tasks that correspond to different languages ​​and cultural spheres, providing quality assurance from a global perspective. For example, it automates testing in multiple languages, such as English, Japanese, and Chinese. It also automates QA tasks that correspond to different cultural spheres, providing quality assurance that takes cultural differences into account. For example, it automates usability testing in each country. It also uses generative AI to automate QA tasks that correspond to different languages ​​and cultural spheres, providing quality assurance from an international perspective. For example, it automates testing based on each country's laws, regulations, and standards. This enables the automation of QA tasks that correspond to different languages ​​and cultural spheres, enabling the provision of quality assurance from a global perspective.

[0042] The QA automation department can link the results of automated QA work with other development tools and platforms to achieve integrated quality control. The QA automation department, for example, links the results of automated QA work with other development tools to achieve integrated quality control. For example, it links with a bug tracking system to automatically register bug reports. It also links with other development platforms to build a system that integrates the results of automated QA work. For example, it links with a CI / CD tool to automatically reflect test results. It also links the results of automated QA work with other development tools and platforms to develop a system that centralizes quality control. For example, it links with a project management tool to automatically update test results. In this way, it is possible to link the results of automated QA work with other development tools and platforms to achieve integrated quality control.

[0043] The high-frequency review acquisition unit can add a function to automatically aggregate the results of high-frequency reviews and analyze trends and patterns. The high-frequency review acquisition unit, for example, adds a function to automatically aggregate the results of high-frequency reviews and analyze trends and patterns based on that data. For example, it analyzes fluctuations in ratings for specific features. It also introduces a function to aggregate review results in real time and identify trends and patterns. For example, it identifies popular features based on user feedback. It also adds a function to automatically aggregate the results of high-frequency reviews and perform detailed analysis based on that data. For example, it identifies areas with a lot of negative feedback and analyzes the causes. This makes it possible to automatically aggregate the results of high-frequency reviews and analyze trends and patterns.

[0044] The high-frequency review acquisition unit can incorporate a function for generating reviews according to different time periods and situations. For example, the high-frequency review acquisition unit incorporates a function for generating reviews according to different time periods when acquiring high-frequency reviews. For example, reviews that reflect different reviewer perspectives are generated during the day and at night. In addition, a function for generating reviews according to different situations can be added to provide more multifaceted feedback. For example, reviews are generated according to specific events or campaigns. In addition, a system can be constructed that automatically generates reviews according to different time periods and situations when acquiring high-frequency reviews. For example, reviews that reflect different reviewer perspectives are generated on weekends and weekdays. This makes it possible to introduce a function for generating reviews according to different time periods and situations.

[0045] The high-frequency review acquisition unit can integrate high-frequency reviews from different devices and platforms and provide comprehensive feedback. For example, the high-frequency review acquisition unit uses a generation AI to integrate reviews from different devices and provide comprehensive feedback. For example, it integrates reviews from smartphones, tablets, and PCs. It also adds a function to integrate reviews from different platforms and provide comprehensive feedback. For example, it integrates reviews from both iOS and Android. It also uses a generation AI to build a system that integrates reviews from different devices and platforms and provides comprehensive feedback. For example, it integrates reviews from multiple browsers. This makes it possible to integrate high-frequency reviews from different devices and platforms and provide comprehensive feedback.

[0046] The high-frequency review acquisition unit can integrate the results of high-frequency reviews with other datasets (e.g., user behavior data and market data) to gain new insights. The high-frequency review acquisition unit, for example, builds a system that integrates the results of high-frequency reviews with user behavior data to gain new insights. For example, it associates user usage patterns with review content. It also adds a function that integrates market data and the results of high-frequency reviews to gain business insights. For example, it associates market trends with review content. It also develops a system that integrates the results of high-frequency reviews with other datasets to gain new insights. For example, it analyzes review content based on user behavior data and market data. This makes it possible to integrate the results of high-frequency reviews with other datasets to gain new insights.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The reviewer generation unit can also generate reviewers related to specific seasons or events, and provide reviews that correspond to the season or event. For example, during the Christmas season, reviewers who review Christmas-related products and services are generated. Also, reviewers related to specific events (e.g., the Olympics or the World Cup) can be generated, and reviews of products and services related to the event can be provided. Furthermore, reviewers can be generated according to seasonal trends and demands, and reviews of seasonal products and services can be provided. This makes it possible to provide reviews related to specific seasons and events.

[0049] The reviewer generation unit can also generate personalized reviewers based on a user's purchasing history and behavioral data, providing reviews tailored to the user's interests. For example, a reviewer who reviews related products and services can be generated based on products and services previously purchased. It can also analyze a user's website browsing history and search history and generate reviewers who provide reviews of products and services that may be of interest to the user based on that data. It can also analyze a user's social media activity and generate reviewers who provide personalized reviews based on that data. This allows the system to provide personalized reviews tailored to the user's interests.

[0050] The reviewer generation unit can also generate reviewers according to specific life stages (e.g., students, working adults, parents, retirees, etc.) and provide reviews of products and services related to those life stages. For example, it can generate reviewers who review learning tools and educational materials for students. It can also generate reviewers who provide reviews of business tools and career-related services for working adults. It can also generate reviewers who review childcare products and educational services for parents, and reviewers who provide reviews of hobby- and health-related products and services for retirees. This makes it possible to provide reviews according to specific life stages.

[0051] The reviewer generation unit can also generate reviewers according to specific health conditions or fitness levels and provide reviews of products or services related to health or fitness. For example, a reviewer can be generated according to a specific health condition (e.g., diabetes, heart disease, allergies, etc.) and provide reviews of products or services related to that health condition. A reviewer can also be generated according to a specific fitness level (e.g., beginner, intermediate, advanced) and provide reviews of training equipment or programs related to that fitness level. Furthermore, a reviewer can be generated that provides advice and information about health or fitness to support the user's health management. This allows reviews to be provided according to specific health conditions or fitness levels.

[0052] The review platform provider can also provide training programs to improve reviewer performance based on reviewer ratings and feedback. For example, it can analyze the content and ratings of reviewers' past reviews to identify areas for improvement. It can also provide training programs to improve reviewer skills and knowledge. It can also provide opportunities for reviewers to share feedback with each other and learn from each other. This can improve reviewer performance and enable them to provide higher quality reviews.

[0053] The review platform providing unit can also add a function to automatically translate the content of reviews and provide reviews in different languages. For example, reviews written in English can be translated into Japanese and provided to Japanese users. Reviews written in Japanese can also be translated into English and provided to English-speaking users. Furthermore, the content of reviews can be translated into multiple languages ​​to provide feedback from an international perspective. This makes it possible to provide reviews in different languages ​​and accommodate international users.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The reviewer generation unit generates reviewers using a generation AI. For example, the generation AI uses a specific model such as GPT-3 or BERT to generate virtual reviewers with specific attributes based on the target demographic specified by the user. Step 2: The review platform providing unit provides a virtual review platform where the reviewers generated by the reviewer generating unit perform reviews. For example, the virtual review platform includes a user interface and a back-end system, and is used by service providers and system developers to collect reviews of their apps and services. Step 3: The QA automation unit automates QA tasks using the reviewers generated by the reviewer generation unit. For example, the virtual reviewers can detect bugs in apps and evaluate their usability, improving the efficiency of QA tasks. Step 4: The high-frequency review acquisition unit uses the reviewers generated by the reviewer generation unit to acquire reviews frequently. For example, a virtual reviewer can review each update of an app and provide immediate feedback on the results.

[0056] (Example 2) The virtual review platform according to an embodiment of the present invention is a system that uses AI to generate reviewers with various attributes (personas) and provides a virtual review platform. As a result, the virtual review platform can provide services specialized for the target demographic, improve the efficiency of QA work, and obtain reviews more frequently.

[0057] A virtual review platform according to an embodiment includes a reviewer generation unit, a review platform providing unit, a QA automation unit, and a high-frequency review acquisition unit. The reviewer generation unit generates reviewers using a generation AI. For example, the generation AI uses a specific model, such as GPT-3 or BERT, to generate virtual reviewers with specific attributes based on a target demographic specified by a user. The review platform providing unit provides a virtual review platform on which the reviewers generated by the reviewer generation unit conduct reviews. For example, the virtual review platform includes a user interface and a backend system, and is intended for service providers and system developers to collect reviews of their apps and services. The QA automation unit automates QA tasks using the reviewers generated by the reviewer generation unit. For example, the virtual reviewers can detect bugs in apps and evaluate their usability, thereby improving the efficiency of QA tasks. The high-frequency review acquisition unit allows the reviewers generated by the reviewer generation unit to frequently acquire reviews. For example, the virtual reviewers can review each app update and provide immediate feedback on the results. As a result, the virtual review platform according to the embodiment can provide services specialized for the target demographic, improve the efficiency of QA work, and obtain reviews more frequently.

[0058] The reviewer generation unit can generate reviewers with attributes such as specific age groups, genders, occupations, hobbies, and preferences. The reviewer generation unit generates reviewers with attributes such as specific age groups, genders, occupations, hobbies, and preferences, for example, using a generation AI. For example, the generation AI generates virtual reviewers with specific attributes based on a target demographic specified by a user. This makes it possible to generate reviewers specialized for the target demographic.

[0059] The reviewer generation unit can estimate the emotional state of the reviewer and generate a review based on that emotional state. For example, the reviewer generation unit uses generation AI to estimate the emotional state of the reviewer in real time and generate a review based on that emotional state. For example, a reviewer in a positive emotional state generates a review that highlights the good points of a product. The reviewer's emotional state can also be estimated from past review history and a review can be generated based on that emotion. For example, a reviewer who has written many negative reviews in the past can generate a review that points out problems in detail. The generation AI can also estimate the reviewer's emotional state and provide feedback according to that emotion. For example, if the reviewer is dissatisfied, a review can be generated that includes specific suggestions to resolve the dissatisfaction. This makes it possible to generate reviews based on the reviewer's emotional state.

[0060] The reviewer generation unit can generate highly reliable reviewers by taking into account the reviewer's past review history and ratings. In the reviewer generation unit, for example, the generation AI analyzes the reviewer's past review history to generate highly reliable reviewers. For example, a new reviewer is generated based on the attributes of reviewers who have received high ratings in the past. The unit also generates highly reliable reviewers by taking into account the reviewer's past rating data. For example, a new reviewer is generated based on the attributes of reviewers who have received a lot of positive feedback in the past. The generation AI also integrates the reviewer's past review history and ratings to generate highly reliable reviewers. For example, a highly reliable reviewer is generated based on the content of past reviews and rating scores. This makes it possible to generate highly reliable reviewers.

[0061] The reviewer generation unit can generate reviewers with specific cultural backgrounds and regional characteristics, and provide reviews from an international perspective. For example, the generation AI of the reviewer generation unit generates reviewers with specific cultural backgrounds and provides reviews based on that culture. For example, a reviewer who is knowledgeable about Japanese culture reviews products for the Japanese market. The unit also takes into account the reviewer's regional characteristics to generate reviews from an international perspective. For example, for products targeted at the Western market, it provides reviews from the perspective of Western consumers. The generation AI can also generate reviewers with specific cultural backgrounds and regional characteristics, and provide reviews that are appropriate for different markets. For example, for products targeted at the Asian market, it provides reviews from the perspective of Asian consumers. This allows the unit to provide reviews from an international perspective.

[0062] The reviewer generation unit can generate reviewers with specific expertise and skills to provide reviews from a specialized perspective. For example, the reviewer generation unit generates reviewers with specific expertise and provides specialized reviews based on that knowledge using a generation AI. For example, a reviewer with expertise in the medical field reviews medical devices. The review unit also generates reviews from a specialized perspective by taking into account the reviewer's skill set. For example, a reviewer with programming skills reviews software. The generation AI also generates reviewers with specific expertise and skills to provide reviews that include technical details. For example, a reviewer with expertise in engineering reviews technical products. This makes it possible to provide reviews from a specialized perspective.

[0063] The reviewer generation unit uses the emotion estimation function to generate a reviewer according to the user's emotions, and can provide a review that elicits positive emotions. The reviewer generation unit, for example, uses the emotion estimation function to analyze the user's emotional state and generate a reviewer according to that emotion. For example, if the user has positive emotions, a reviewer that emphasizes those emotions is generated. Also, a reviewer that elicits positive emotions is generated based on the user's emotion data. For example, if the user is excited, a reviewer that shares that excitement is generated. Also, the emotion estimation function is used to generate a reviewer that provides feedback according to the user's emotions. For example, if the user is feeling anxious, a reviewer that alleviates that anxiety is generated. In this way, a reviewer according to the user's emotions can be generated and a review that elicits positive emotions can be provided.

[0064] The review platform providing unit can simulate dialogue between reviewers and generate more multifaceted reviews. The review platform providing unit, for example, has multiple reviewers dialogue on a virtual review platform and generates multifaceted reviews based on the content of that dialogue. For example, it provides a review that integrates opinions from different perspectives. It can also simulate dialogue between reviewers and generate a detailed review based on the results. For example, reviewers ask each other questions and exchange opinions, and provide a review that reflects that content. It can also simulate discussion between reviewers on the virtual review platform and generate a comprehensive review based on the results. For example, reviewers with different expertise collaborate to review. In this way, it is possible to simulate dialogue between reviewers and generate multifaceted reviews.

[0065] The review platform providing unit can add a function to automatically analyze the content of reviews and extract specific topics or issues. The review platform providing unit, for example, adds a function to automatically analyze the content of reviews and extract specific topics or issues on a virtual review platform. For example, it analyzes text data of reviews and extracts frequently occurring keywords. It also adds a function to automatically analyze the content of reviews and identify specific issues. For example, it extracts parts with a lot of negative feedback and identifies those issues. It also adds a function to automatically analyze the content of reviews on the virtual review platform and aggregate opinions on specific topics. For example, it displays reviews related to a specific function together. This makes it possible to automatically analyze the content of reviews and extract specific topics or issues.

[0066] The review platform providing unit can introduce an algorithm that takes into account a reviewer's past performance and ratings in order to evaluate the reliability of a review. The review platform providing unit, for example, introduces an algorithm that analyzes a reviewer's past performance data on a virtual review platform and evaluates its reliability. For example, it calculates reliability based on the rating scores of past reviews. It also introduces an algorithm that takes into account a reviewer's past rating data and identifies highly reliable reviewers. For example, it preferentially displays reviews by reviewers who have received high ratings in the past. It also introduces an algorithm that integrates a reviewer's past performance and ratings on the virtual review platform and evaluates their reliability. For example, it calculates reliability based on the reviewer's past review content and rating scores. This makes it possible to introduce an algorithm for evaluating the reliability of reviews.

[0067] The review platform providing unit can add audio and video review functions to provide richer feedback. The review platform providing unit, for example, adds an audio review function to the virtual review platform to enable reviewers to provide feedback via audio. For example, the reviewer explains their experience using the product via audio. Also, a video review function can be added to the virtual review platform to enable reviewers to provide feedback via video. For example, the reviewer demonstrates how to use the product via video. Also, the audio and video review functions can be integrated into the virtual review platform to provide richer feedback. For example, the reviewer combines audio and video to provide a detailed review. This allows the addition of audio and video review functions to provide richer feedback.

[0068] The review platform providing unit can integrate reviews from different industries and fields to provide feedback from a cross-industry perspective. The review platform providing unit, for example, integrates reviews from different industries on a virtual review platform to provide feedback from a cross-industry perspective. For example, it integrates reviews from technology and design. It also adds a function that allows reviewers from different fields to collaborate on reviews and integrate the results. For example, it integrates reviews from marketing and engineering perspectives. It also integrates reviews from different industries and fields on the virtual review platform to provide comprehensive feedback. For example, it integrates reviews from the medical field and the consumer product field. This makes it possible to integrate reviews from different industries and fields to provide feedback from a cross-industry perspective.

[0069] The review platform providing unit can use the emotion estimation function to analyze the emotional tone of a review and make suggestions to convert a negative review into a positive one. The review platform providing unit, for example, uses the emotion estimation function to analyze the emotional tone of a review and make suggestions to convert a negative review into a positive one. For example, it makes suggestions to replace negative expressions with positive expressions. Furthermore, based on the results of the emotion analysis of the review, it makes specific suggestions to improve negative elements. For example, it generates a review that includes suggestions to solve problems. Furthermore, it uses the emotion estimation function to analyze the emotional tone of a review in real time and provides feedback to convert a negative review into a positive one. For example, it recommends positive expressions to the reviewer. This makes it possible to analyze the emotional tone of a review and make suggestions to convert a negative review into a positive one.

[0070] The QA automation unit can use the emotion estimation function to generate bug reports based on the user's emotions. For example, the generation AI in the QA automation unit analyzes the user's emotional state and generates a bug report based on that emotion. For example, if the user is feeling dissatisfied, a detailed bug report reflecting that dissatisfaction is generated. The emotion estimation function is also used to automatically generate bug reports based on the user's emotions. For example, if the user is feeling surprised, a bug report that identifies the cause of that surprise is generated. The generation AI also generates emotion-based bug reports based on the user's emotion data. For example, if the user is confused, a bug report including specific suggestions for resolving the confusion is generated. In this way, bug reports based on the user's emotions can be generated.

[0071] The QA Automation Department can build a system that analyzes the results of automated QA work in real time and provides immediate feedback. The QA Automation Department can, for example, build a system that analyzes the results of automated QA work in real time and provides immediate feedback based on the results. For example, it can immediately propose a fix after a bug is detected. The department can also introduce a system that analyzes the results of QA work in real time and provides immediate feedback to developers. For example, it can immediately propose an improvement when a usability problem is detected. The department can also develop a system that analyzes the results of automated QA work in real time and provides rapid feedback based on the results. For example, it can display test results in real time and notify developers immediately. This makes it possible to analyze the results of automated QA work in real time and provide immediate feedback.

[0072] The QA Automation Department can add functionality to simultaneously test on different devices and platforms. For example, in automated QA work, the QA Automation Department adds functionality to simultaneously test on different devices and platforms. For example, tests can be performed simultaneously on smartphones, tablets, and PCs. In addition, by introducing functionality to simultaneously test on different platforms, the efficiency of QA work can be improved. For example, tests can be performed simultaneously on both iOS and Android. In addition, in automated QA work, a system can be built to simultaneously test on different devices and platforms. For example, tests can be performed simultaneously on multiple browsers. This allows the functionality to simultaneously test on different devices and platforms to be added.

[0073] The QA automation department automates QA tasks that correspond to different languages ​​and cultural spheres, enabling the provision of quality assurance from a global perspective. For example, the QA automation department uses generative AI to automate QA tasks that correspond to different languages ​​and cultural spheres, providing quality assurance from a global perspective. For example, it automates testing in multiple languages, such as English, Japanese, and Chinese. It also automates QA tasks that correspond to different cultural spheres, providing quality assurance that takes cultural differences into account. For example, it automates usability testing in each country. It also uses generative AI to automate QA tasks that correspond to different languages ​​and cultural spheres, providing quality assurance from an international perspective. For example, it automates testing based on each country's laws, regulations, and standards. This enables the automation of QA tasks that correspond to different languages ​​and cultural spheres, enabling the provision of quality assurance from a global perspective.

[0074] The QA automation department can link the results of automated QA work with other development tools and platforms to achieve integrated quality control. The QA automation department, for example, links the results of automated QA work with other development tools to achieve integrated quality control. For example, it links with a bug tracking system to automatically register bug reports. It also links with other development platforms to build a system that integrates the results of automated QA work. For example, it links with a CI / CD tool to automatically reflect test results. It also links the results of automated QA work with other development tools and platforms to develop a system that centralizes quality control. For example, it links with a project management tool to automatically update test results. In this way, it is possible to link the results of automated QA work with other development tools and platforms to achieve integrated quality control.

[0075] The QA automation unit can use the emotion estimation function to analyze the user's emotional response to the results of the QA work and identify areas for improvement. For example, the QA automation unit uses the emotion estimation function to analyze the user's emotional response to the results of the QA work in real time and identify areas for improvement. For example, it identifies areas where the user felt dissatisfied and proposes areas for improvement. It also analyzes user emotion data regarding the results of the QA work and identifies areas where there are many negative reactions. For example, it identifies areas where users felt confused and proposes areas for improvement. It also uses the emotion estimation function to analyze the user's emotional response to the results of the QA work and identifies areas where there are few positive reactions. For example, it identifies areas where functions that the user expected are lacking and proposes areas for improvement. In this way, it is possible to analyze the user's emotional response to the results of the QA work and identify areas for improvement.

[0076] The high-frequency review acquisition unit can utilize the emotion estimation function to generate high-frequency reviews based on the user's emotions. For example, the high-frequency review acquisition unit uses a generation AI to analyze the user's emotional state and generate high-frequency reviews based on those emotions. For example, if the user has positive emotions, it generates a review that reflects those emotions. It also uses the emotion estimation function to automatically generate high-frequency reviews based on the user's emotions. For example, if the user is dissatisfied, it generates a review that describes that dissatisfaction in detail. It also generates high-frequency reviews based on the user's emotion data. For example, if the user is excited, it generates a review that shares that excitement. This makes it possible to generate high-frequency reviews based on the user's emotions.

[0077] The high-frequency review acquisition unit can add a function to automatically aggregate the results of high-frequency reviews and analyze trends and patterns. The high-frequency review acquisition unit, for example, adds a function to automatically aggregate the results of high-frequency reviews and analyze trends and patterns based on that data. For example, it analyzes fluctuations in ratings for specific features. It also introduces a function to aggregate review results in real time and identify trends and patterns. For example, it identifies popular features based on user feedback. It also adds a function to automatically aggregate the results of high-frequency reviews and perform detailed analysis based on that data. For example, it identifies areas with a lot of negative feedback and analyzes the causes. This makes it possible to automatically aggregate the results of high-frequency reviews and analyze trends and patterns.

[0078] The high-frequency review acquisition unit can incorporate a function for generating reviews according to different time periods and situations. For example, the high-frequency review acquisition unit incorporates a function for generating reviews according to different time periods when acquiring high-frequency reviews. For example, reviews that reflect different reviewer perspectives are generated during the day and at night. In addition, a function for generating reviews according to different situations can be added to provide more multifaceted feedback. For example, reviews are generated according to specific events or campaigns. In addition, a system can be constructed that automatically generates reviews according to different time periods and situations when acquiring high-frequency reviews. For example, reviews that reflect different reviewer perspectives are generated on weekends and weekdays. This makes it possible to introduce a function for generating reviews according to different time periods and situations.

[0079] The high-frequency review acquisition unit can integrate high-frequency reviews from different devices and platforms and provide comprehensive feedback. For example, the high-frequency review acquisition unit uses a generation AI to integrate reviews from different devices and provide comprehensive feedback. For example, it integrates reviews from smartphones, tablets, and PCs. It also adds a function to integrate reviews from different platforms and provide comprehensive feedback. For example, it integrates reviews from both iOS and Android. It also uses a generation AI to build a system that integrates reviews from different devices and platforms and provides comprehensive feedback. For example, it integrates reviews from multiple browsers. This makes it possible to integrate high-frequency reviews from different devices and platforms and provide comprehensive feedback.

[0080] The high-frequency review acquisition unit can integrate the results of high-frequency reviews with other datasets (e.g., user behavior data and market data) to gain new insights. The high-frequency review acquisition unit, for example, builds a system that integrates the results of high-frequency reviews with user behavior data to gain new insights. For example, it associates user usage patterns with review content. It also adds a function that integrates market data and the results of high-frequency reviews to gain business insights. For example, it associates market trends with review content. It also develops a system that integrates the results of high-frequency reviews with other datasets to gain new insights. For example, it analyzes review content based on user behavior data and market data. This makes it possible to integrate the results of high-frequency reviews with other datasets to gain new insights.

[0081] The high-frequency review acquisition unit uses an emotion estimation function to monitor users' emotional reactions to high-frequency reviews in real time and propose optimal improvement measures. The high-frequency review acquisition unit, for example, uses the emotion estimation function to build a system that monitors users' emotional reactions to high-frequency reviews in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. It also identifies areas of high-frequency reviews to improve and proposes optimal improvement measures based on the user's emotional reaction data. For example, it identifies areas with a high number of negative emotional reactions and proposes improvement measures for those areas. It also develops a system that collects emotion estimation data in real time and uses it to improve high-frequency reviews. For example, it dynamically adjusts the review content according to changes in the user's emotions. This makes it possible to monitor users' emotional reactions to high-frequency reviews in real time and propose optimal improvement measures.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The reviewer generation unit can also generate reviewers related to specific seasons or events, and provide reviews that correspond to the season or event. For example, during the Christmas season, reviewers who review Christmas-related products and services are generated. Also, reviewers related to specific events (e.g., the Olympics or the World Cup) can be generated, and reviews of products and services related to the event can be provided. Furthermore, reviewers can be generated according to seasonal trends and demands, and reviews of seasonal products and services can be provided. This makes it possible to provide reviews related to specific seasons and events.

[0084] The reviewer generation unit can also generate personalized reviewers based on a user's purchasing history and behavioral data, providing reviews tailored to the user's interests. For example, a reviewer who reviews related products and services can be generated based on products and services previously purchased. It can also analyze a user's website browsing history and search history and generate reviewers who provide reviews of products and services that may be of interest to the user based on that data. It can also analyze a user's social media activity and generate reviewers who provide personalized reviews based on that data. This allows the system to provide personalized reviews tailored to the user's interests.

[0085] The reviewer generation unit can also use the emotion estimation function to generate a reviewer based on the user's emotions and provide a review that empathizes with the user's emotions. For example, if the user is sad, a reviewer that empathizes with the user's emotions can be generated and provide a review that includes words of comfort and encouragement. Also, if the user is happy, a reviewer that shares the user's joy can be generated and provide positive feedback. Furthermore, if the user is stressed, a reviewer that provides a review that includes advice on how to alleviate the stress can be generated. This makes it possible to provide a review that empathizes with the user's emotions.

[0086] The reviewer generation unit can also generate reviewers according to specific life stages (e.g., students, working adults, parents, retirees, etc.) and provide reviews of products and services related to those life stages. For example, it can generate reviewers who review learning tools and educational materials for students. It can also generate reviewers who provide reviews of business tools and career-related services for working adults. It can also generate reviewers who review childcare products and educational services for parents, and reviewers who provide reviews of hobby- and health-related products and services for retirees. This makes it possible to provide reviews according to specific life stages.

[0087] The reviewer generation unit can also use the emotion estimation function to generate a reviewer based on the user's emotions and provide a review that changes the user's emotions to a positive one. For example, if the user has negative emotions, a reviewer can be generated that provides a review including advice and encouraging words to change those emotions to a positive one. Also, if the user is feeling anxious, a reviewer can be generated that provides a review including specific suggestions to ease the anxiety. Furthermore, if the user is feeling angry, a reviewer can be generated that provides a review including calm advice to calm the anger. In this way, a review that changes the user's emotions to a positive one can be provided.

[0088] The reviewer generation unit can also generate reviewers according to specific health conditions or fitness levels and provide reviews of products or services related to health or fitness. For example, a reviewer can be generated according to a specific health condition (e.g., diabetes, heart disease, allergies, etc.) and provide reviews of products or services related to that health condition. A reviewer can also be generated according to a specific fitness level (e.g., beginner, intermediate, advanced) and provide reviews of training equipment or programs related to that fitness level. Furthermore, a reviewer can be generated that provides advice and information about health or fitness to support the user's health management. This allows reviews to be provided according to specific health conditions or fitness levels.

[0089] The reviewer generation unit can also use the emotion estimation function to generate a reviewer based on the user's emotions and provide customized feedback according to the user's emotions. For example, if the user is excited, a reviewer who shares that excitement can be generated and provide positive feedback. If the user is feeling down, a reviewer who empathizes with the user's emotions can be generated and provide feedback including encouraging words. Furthermore, if the user has doubts or anxieties, a reviewer who provides feedback including specific advice to resolve those doubts or anxieties can be generated. This makes it possible to provide customized feedback according to the user's emotions.

[0090] The review platform provider can also provide training programs to improve reviewer performance based on reviewer ratings and feedback. For example, it can analyze the content and ratings of reviewers' past reviews to identify areas for improvement. It can also provide training programs to improve reviewer skills and knowledge. It can also provide opportunities for reviewers to share feedback with each other and learn from each other. This can improve reviewer performance and enable them to provide higher quality reviews.

[0091] The review platform providing unit can also add a function to automatically translate the content of reviews and provide reviews in different languages. For example, reviews written in English can be translated into Japanese and provided to Japanese users. Reviews written in Japanese can also be translated into English and provided to English-speaking users. Furthermore, the content of reviews can be translated into multiple languages ​​to provide feedback from an international perspective. This makes it possible to provide reviews in different languages ​​and accommodate international users.

[0092] The review platform provider can also use the emotion estimation function to analyze the emotional tone of the review and provide feedback to the reviewer. For example, if the reviewer has negative emotions, it can provide advice to alleviate those emotions. Alternatively, if the reviewer has positive emotions, it can provide feedback to further reinforce those emotions. Furthermore, it can make specific suggestions to adjust the content of the review based on the reviewer's emotional state. This makes it possible to provide feedback according to the reviewer's emotions and improve the quality of reviews.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The reviewer generation unit generates reviewers using a generation AI. For example, the generation AI uses a specific model such as GPT-3 or BERT to generate virtual reviewers with specific attributes based on the target demographic specified by the user. Step 2: The review platform providing unit provides a virtual review platform where the reviewers generated by the reviewer generating unit perform reviews. For example, the virtual review platform includes a user interface and a back-end system, and is used by service providers and system developers to collect reviews of their apps and services. Step 3: The QA automation unit automates QA tasks using the reviewers generated by the reviewer generation unit. For example, the virtual reviewers can detect bugs in apps and evaluate their usability, improving the efficiency of QA tasks. Step 4: The high-frequency review acquisition unit uses the reviewers generated by the reviewer generation unit to acquire reviews frequently. For example, a virtual reviewer can review each update of an app and provide immediate feedback on the results.

[0095] 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.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0097] 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.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0112] 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.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0124] 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.

[0125] 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.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] 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.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] In the robot 414, 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 robot 414 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.

[0140] 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.

[0141] 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.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0149] 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."

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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. [Explanation of symbols]

[0162] 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 reviewer generation unit that generates a reviewer using a generation AI; a review platform providing unit that provides a virtual review platform on which the reviewers generated by the reviewer generating unit can review; a QA automation unit that automates QA work using the reviewers generated by the reviewer generation unit; a high-frequency review acquisition unit in which the reviewers generated by the reviewer generation unit acquire reviews at a high frequency; A system characterized by:

2. The reviewer generation unit Generate reviewers with specific attributes such as age, gender, occupation, hobbies, etc.

2. The system of claim 1.

3. The reviewer generation unit Inferring the reviewer's emotional state and generating the review based on the emotional state 2. The system of claim 1.

4. The reviewer generation unit Generate highly reliable reviewers by taking into account their past review history and ratings.

2. The system of claim 1.

5. The reviewer generation unit Generate reviewers with specific cultural backgrounds and regional characteristics to provide reviews from an international perspective 2. The system of claim 1.

Images