System

Abstract

An object of the system according to the embodiment is to automatically confirm and install or purchase a necessary plug-in based on a user's request.SOLUTION: A system according to an embodiment includes a request analysis unit, a plug-in confirmation unit, and an inquiry unit. The request analysis unit analyzes a user's request. The plug-in checking unit checks an installed plug-in based on the request analyzed by the request analyzing unit. When the necessary plug-in is not installed, the inquiry unit inquires of the user about installation or purchase of the plug-in.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 had the problem that the process of checking whether the appropriate plug-in was installed in response to a user request and prompting the user to install or purchase the plug-in as necessary was not automated, making it time-consuming.

[0005] The system according to the embodiment aims to automatically check, install, and purchase required plug-ins based on a user request. [Means for solving the problem]

[0006] A system according to an embodiment includes a request analysis unit, a plug-in confirmation unit, and an inquiry unit. The request analysis unit analyzes a user request. The plug-in confirmation unit checks installed plug-ins based on the request analyzed by the request analysis unit. If a required plug-in is not installed, the inquiry unit inquires of the user about installing or purchasing the plug-in. [Effects of the Invention]

[0007] The system according to the embodiment can automatically check and install or purchase required plug-ins based on a user request. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 plug-in management system according to an embodiment of the present invention is a system that understands requests and questions from users and executes processing using appropriate plug-ins based on those requests. This allows the plug-in management system to respond to user requests quickly and appropriately.

[0029] A plug-in management system according to an embodiment includes a request analysis unit, a plug-in confirmation unit, and an inquiry unit. The request analysis unit analyzes a user request. For example, the request analysis unit uses a generation AI to analyze the user request and understand its content. The request analysis unit can also analyze the request using natural language processing technology. The request analysis unit can also analyze the user request in text format. For example, the generation AI analyzes a request entered by the user and understands its content. The generation AI analyzes the request using a text generation AI (e.g., LLM). The generation AI determines an appropriate plug-in based on the content of the request. The plug-in confirmation unit checks installed plug-ins based on the request analyzed by the request analysis unit. For example, the plug-in confirmation unit references a list of plug-ins installed in the system and checks whether a plug-in corresponding to the request is installed. The plug-in confirmation unit can also check the version and compatibility of the plug-in. The plug-in confirmation unit can also reference the plug-in usage history and select a plug-in based on past success rates and error rates. For example, the plug-in confirmation unit obtains version information of plug-ins in the system and checks whether the latest version is installed. If a required plug-in is not installed, the inquiry unit inquires of the user about installing or purchasing the plug-in. For example, the inquiry unit may inquire in the form of, "An image editing plug-in is not installed. Would you like to install it or purchase it?" The inquiry unit may also refer to the user's past purchase history and installation history to suggest the most suitable plug-in. The inquiry unit may also make suggestions taking into consideration the user's budget and frequency of use. For example, the inquiry unit may suggest plug-ins that can be purchased within the user's budget. This allows the plug-in management system according to the embodiment to execute processing using an appropriate plug-in in response to a user request.For example, if a user inputs a request such as "I want to edit an image," a request analysis unit analyzes the request, a plug-in confirmation unit checks the installation status of the image editing plug-in, and an inquiry unit inquires about installing or purchasing the plug-in as necessary.

[0030] The request analysis unit can improve prediction accuracy by referencing the user's past request history and learning request patterns. For example, the request analysis unit stores the user's past request history in a database, and the generation AI analyzes that data. For example, for a user who has frequently requested "image editing" in the past, the request analysis unit predicts the likelihood that a similar request will be made next time. The request analysis unit can also use machine learning algorithms to learn request patterns. For example, the request analysis unit extracts request patterns based on past request data and builds a prediction model. The request analysis unit can also use clustering technology to learn request patterns. For example, the request analysis unit clusters past request data and identifies groups of similar requests. This improves the prediction accuracy of user requests.

[0031] The request analysis unit can analyze the user's voice tone or facial expression to determine the urgency or importance of a request. For example, the request analysis unit can analyze the voice tone used when the user inputs a request to determine the urgency or importance. For example, if the user's voice tone sounds tense or rushed, the request can be determined to be highly urgent. The request analysis unit can also analyze the user's facial expression to determine the urgency or importance of a request. For example, the user's facial expression when inputting a request can be captured with a camera and the emotion analyzed using a facial expression analysis algorithm. The request analysis unit can also analyze both the voice tone and facial expression to comprehensively determine the urgency or importance of a request. For example, the voice tone and facial expression changes can be analyzed in combination to evaluate the urgency or importance of a request. This allows for a prompt response by determining the urgency or importance of a request.

[0032] The request analysis unit can perform multilingual analysis of user requests so that they can be handled by users of different languages ​​or cultural backgrounds. The request analysis unit, for example, uses natural language processing technology to analyze user requests in multiple languages. For example, an analysis algorithm that supports multiple languages, such as English, Japanese, and French, is developed. The request analysis unit can also perform analysis that takes cultural background into account so that they can be handled by users of different cultural backgrounds. For example, the request analysis unit uses an analysis algorithm that takes cultural context into account to analyze requests from users of different cultural backgrounds. The request analysis unit can also use a translation algorithm to analyze user requests in multiple languages. For example, the request analysis unit automatically translates and analyzes user requests. This allows them to be handled by users of different languages ​​and cultural backgrounds.

[0033] The request analysis unit can analyze user requests not only from text but also from image or audio data. For example, the request analysis unit allows a user to upload not only text but also image or audio data when entering a request. For example, in the case of a request for image editing, the user uploads the image to be edited. The request analysis unit can also use image recognition technology or voice recognition technology to analyze the image or audio data. For example, the request analysis unit analyzes uploaded images and understands their content. The request analysis unit can also analyze uploaded audio data and understand its content. For example, the request analysis unit converts audio data into text using voice recognition technology and analyzes the text. The request analysis unit can also use multimodal generation AI to analyze image and audio data. For example, the request analysis unit uses multimodal generation AI to analyze image and audio data and understand its content. This allows requests to be analyzed not only from text but also from image and audio data.

[0034] The request analysis unit can add a process of feeding back the analysis results of the request to the user and checking whether the results match what the user intended. The request analysis unit, for example, adds a process of feeding back the analysis results of the request to the user and checking whether the results match what the user intended. For example, the analysis results may be displayed in text and the user may be asked to confirm. The request analysis unit can also use graphs or charts to visually display the analysis results. For example, the analysis results may be displayed in graphs or charts and the user may be asked to confirm. The request analysis unit can also feed back the analysis results aloud. For example, the analysis results may be read out aloud and the user may be asked to confirm. This improves the accuracy of request analysis by checking whether the results match what the user intended.

[0035] The request analysis unit can have experts from different industries or fields review the request analysis results and obtain feedback. For example, the request analysis unit can have experts from different industries or fields review the request analysis results and build a system that improves the analysis accuracy based on the feedback. For example, the request analysis unit can have experts in technical fields check the analysis results. The request analysis unit can also use an online platform to collect feedback from experts. For example, the analysis results can be uploaded to the online platform and feedback from the experts can be collected. The request analysis unit can also improve the analysis algorithm based on the expert feedback. For example, the parameters of the analysis algorithm can be adjusted based on the expert feedback. In this way, feedback from experts from different industries or fields can be obtained and the accuracy of the request analysis can be improved.

[0036] The request analysis unit can convert the analysis results of the request into visual notes or mind maps to make them easier to understand visually. The request analysis unit, for example, builds a system that converts the analysis results of the request into visual notes and displays them visually. For example, it shows the main points of the analysis results using diagrams or icons. The request analysis unit can also convert the analysis results into mind maps and display them visually. For example, it can show the structure of the analysis results in a mind map to make them easier to understand visually. The request analysis unit can also use a generation AI to automatically generate visual notes or mind maps. For example, the generation AI automatically generates visual notes or mind maps based on the analysis results. This makes the analysis results of the request easier to understand visually, thereby improving the user's understanding.

[0037] The plugin verification unit can check the version and compatibility of plugins and select the most suitable plugin. For example, when checking a plugin, the plugin verification unit obtains plugin version information and checks whether the latest version is installed. For example, if the version is old, it suggests updating. The plugin verification unit can also check plugin compatibility. For example, it checks whether the plugin is compatible with other software in the system. The plugin verification unit can also refer to the plugin usage history and select a plugin based on past success rates and error rates. For example, it can prioritize plugins with high success rates. In this way, by checking the plugin version and compatibility, the most suitable plugin can be selected.

[0038] The plugin confirmation unit can refer to the plugin usage history and select a plugin based on the past success rate and error rate. The plugin confirmation unit, for example, stores the plugin usage history in a database and analyzes the past success rate and error rate. For example, it prioritizes the selection of plugins with a high success rate. The plugin confirmation unit can also set plugin selection criteria based on the plugin usage history. For example, it can prioritize the selection of plugins with a low error rate. The plugin confirmation unit can also improve the plugin selection algorithm based on the plugin usage history. For example, it can adjust the parameters of the selection algorithm based on the success rate and error rate data. In this way, the optimal plugin can be selected by referring to the plugin usage history.

[0039] The plugin verification unit can make the plugin verification results available on different platforms and devices. The plugin verification unit, for example, builds a system that makes the plugin verification results available on different platforms and devices. For example, the plugin verification unit supports multiple operating systems such as Windows, macOS, and Linux. The plugin verification unit can also make the plugin verification results available on different devices. For example, the plugin verification unit supports multiple devices such as PCs, smartphones, and tablets. The plugin verification unit can also store the plugin verification results in the cloud so that they can be accessed from different platforms and devices. For example, the plugin verification results can be stored using cloud storage so that they can be accessed from different devices. This makes the plugin verification results available on different platforms and devices, thereby improving convenience.

[0040] The plug-in verification unit can share the plug-in verification results with other users and obtain feedback. For example, the plug-in verification unit builds a system for sharing the plug-in verification results with other users and obtaining feedback. For example, it provides an online platform for sharing the verification results. The plug-in verification unit can also use a survey function to collect feedback from other users. For example, it can collect feedback on the verification results in the form of a survey. The plug-in verification unit can also improve the plug-in selection algorithm based on feedback from other users. For example, it can adjust parameters of the selection algorithm based on the feedback data. In this way, by sharing the verification results with other users, it can obtain feedback and improve the plug-in selection process.

[0041] When installing or purchasing a plug-in, the inquiry unit can refer to the user's past purchase history and installation history to make the optimal suggestion. For example, the inquiry unit stores the user's past purchase history and installation history in a database and builds a system that suggests the optimal plug-in based on that data. For example, the inquiry unit can suggest plug-ins in the same category as plug-ins purchased in the past. The inquiry unit can also improve the plug-in suggestion algorithm based on the user's purchase history and installation history. For example, the inquiry unit can adjust the parameters of the suggestion algorithm based on the purchase history and installation history data. The inquiry unit can also set plug-in suggestion criteria based on the user's past purchase history and installation history. For example, the inquiry unit can preferentially suggest plug-ins that have been successful in the past. In this way, the optimal plug-in can be suggested by referring to the user's past history.

[0042] The inquiry unit can make suggestions taking into consideration the user's budget and frequency of use when installing or purchasing a plug-in. The inquiry unit, for example, builds a system that takes into consideration the user's budget and suggests optimal plug-ins. For example, it prioritizes suggesting plug-ins that can be purchased within the budget. The inquiry unit can also suggest optimal plug-ins taking into consideration the user's frequency of use. For example, it prioritizes suggesting frequently used plug-ins. The inquiry unit can also improve the plug-in suggestion algorithm based on the user's budget and frequency of use. For example, it adjusts parameters of the suggestion algorithm based on data on the budget and frequency of use. The inquiry unit can also set plug-in suggestion criteria based on the user's budget and frequency of use. For example, it suggests the most effective plug-in within the budget. In this way, it is possible to suggest optimal plug-ins by taking into consideration the user's budget and frequency of use.

[0043] The inquiry unit can make multilingual suggestions to install or purchase plug-ins so that the suggestions can be made to users of different languages ​​or cultural backgrounds. The inquiry unit, for example, builds a system that makes multilingual suggestions to install or purchase plug-ins. For example, it develops a suggestion algorithm that supports multiple languages, such as English, Japanese, and French. The inquiry unit can also make suggestions that take cultural backgrounds into account so that the system can also accommodate users of different cultural backgrounds. For example, the inquiry unit makes suggestions that take cultural contexts into account for users of different cultural backgrounds. The inquiry unit can also use a translation algorithm to make multilingual suggestions to install or purchase plug-ins. For example, the inquiry unit automatically translates the suggestions and presents them to the user. This allows the system to accommodate users of different languages ​​and cultural backgrounds.

[0044] The inquiry unit can make suggestions for installing or purchasing plug-ins not only from text but also from image or audio data. The inquiry unit, for example, builds a system that makes suggestions for installing or purchasing plug-ins not only from text but also from image or audio data. For example, the inquiry unit analyzes images and audio to suggest optimal plug-ins. The inquiry unit can also use image recognition technology or voice recognition technology to analyze image and audio data. For example, the inquiry unit can analyze uploaded images and suggest plug-ins based on their content. The inquiry unit can also analyze uploaded audio data and suggest plug-ins based on their content. For example, the inquiry unit can convert audio data into text using voice recognition technology, analyze the text, and suggest plug-ins. The inquiry unit can also use multimodal generation AI to analyze image and audio data. For example, the inquiry unit can analyze image and audio data and use multimodal generation AI to suggest plug-ins based on their content. This allows suggestions to be made based on not only text but also image and audio data, thereby meeting the user's needs.

[0045] The inquiry unit can automate the installation procedure or purchase procedure when installing or purchasing a plug-in, thereby minimizing the hassle for the user. The inquiry unit, for example, builds a system that automates the installation procedure of a plug-in. For example, when a user selects "Install," the plug-in is automatically downloaded and installed. The inquiry unit can also automate the purchase procedure of a plug-in. For example, when a user selects "Purchase," the purchase procedure is automatically performed and the plug-in is installed. The inquiry unit can also use a script or automation tool to automate the installation procedure or purchase procedure. For example, the inquiry unit uses a script to automate the installation procedure or purchase procedure. The inquiry unit can also use an API to automate the installation procedure or purchase procedure. For example, the inquiry unit uses an API to automate the installation procedure or purchase procedure. In this way, the installation procedure or purchase procedure can be automated, thereby minimizing the hassle for the user.

[0046] The inquiry unit can automatically check the operation of a plug-in after installation to check for any problems. The inquiry unit, for example, builds a system that automatically checks the operation of a plug-in after installation. For example, after installation is complete, the inquiry unit automatically runs an operation test of the plug-in. The inquiry unit can also provide feedback on the results of the operation check to the user. For example, the results of the operation check are displayed in text and notified to the user. The inquiry unit can also record the results of the operation check in a log so that they can be referenced later. For example, the results of the operation check are saved in a log file and referenced if a problem occurs. The inquiry unit can also improve the plug-in installation procedure based on the results of the operation check. For example, the parameters of the installation procedure are adjusted based on the results of the operation check. In this way, the operation check can be automatically performed after installation to check for any problems.

[0047] The inquiry unit can share the installation or purchase of a plug-in with other users and obtain feedback. The inquiry unit, for example, builds a system for sharing the installation or purchase of a plug-in with other users and obtaining feedback. For example, it provides an online platform for sharing the installation or purchase procedure. The inquiry unit can also use a survey function to collect feedback from other users. For example, it can collect feedback on the installation or purchase procedure in the form of a survey. The inquiry unit can also improve the installation or purchase procedure based on feedback from other users. For example, it can adjust procedure parameters based on the feedback data. By sharing the data with other users, it can obtain feedback and improve the execution process.

[0048] When a request is re-executed, the query unit can refer to the results of the previous execution and reflect improvements. For example, when a request is re-executed, the query unit stores the results of the previous execution in a database and builds a system that reflects improvements based on that data. For example, the query unit selects the optimal plug-in based on the results of the previous execution. The query unit can also improve the re-execution procedure based on the results of the previous execution. For example, the query unit analyzes the results of the previous execution and optimizes the re-execution procedure. The query unit can also improve the re-execution algorithm based on the results of the previous execution. For example, the query unit adjusts the parameters of the re-execution algorithm based on the data from the previous execution. In this way, improvements can be reflected when a request is re-executed by referring to the results of the previous execution.

[0049] The inquiry unit can collect user feedback when a request is re-executed and reflect it in the next execution. For example, the inquiry unit builds a system that collects user feedback when a request is re-executed and reflects the data in the next execution. For example, the inquiry unit adjusts the selection of plug-ins based on the feedback. The inquiry unit can also use a survey function to collect user feedback. For example, it collects feedback on the re-execution procedure in the form of a survey. The inquiry unit can also improve the re-execution procedure based on the user feedback. For example, it adjusts procedure parameters based on the feedback data. The inquiry unit can also improve the re-execution algorithm based on the user feedback. For example, it adjusts parameters of the re-execution algorithm based on the feedback data. In this way, user feedback can be collected and reflected in the next execution.

[0050] The inquiry unit can make the results of re-executing a request available on different platforms and devices. The inquiry unit, for example, builds a system that makes the results of re-executing a request available on different platforms and devices. For example, the inquiry unit supports multiple operating systems such as Windows, macOS, and Linux. The inquiry unit can also make the results of re-executing a request available on different devices. For example, the inquiry unit supports multiple devices such as PCs, smartphones, and tablets. The inquiry unit can also store the results of re-executing a request in the cloud so that they can be accessed from different platforms and devices. For example, cloud storage can be used to store the results of re-executing a request so that they can be accessed from different devices. This improves convenience by making the results of re-executing a request available on different platforms and devices.

[0051] The inquiry unit can share the results of the re-execution of the request with other users and obtain feedback. The inquiry unit, for example, builds a system for sharing the results of the re-execution of the request with other users and obtains feedback. For example, it provides an online platform for sharing the re-execution results. The inquiry unit can also use a survey function to collect feedback from other users. For example, it collects feedback on the re-execution results in the form of a survey. The inquiry unit can also improve the re-execution procedure based on the feedback from other users. For example, it can adjust the parameters of the procedure based on the feedback data. In this way, by sharing the results with other users, it can obtain feedback and improve the re-execution process.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0054] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0055] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0056] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0057] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The request analysis unit analyzes the user's request. For example, it can use generative AI to analyze the request and understand its content. It can also analyze the request using natural language processing technology. The request analysis unit analyzes the user's request in text format and determines the appropriate plugin. Step 2: The plugin verification unit checks the installed plugins based on the request analyzed by the request analysis unit. For example, it references the list of plugins installed in the system and checks whether the plugin corresponding to the request is installed. It also references the plugin version, compatibility, and usage history to select the most suitable plugin. Step 3: If a required plug-in is not installed, the inquiry unit asks the user about installing or purchasing the plug-in. For example, the inquiry may be in the form of "An image editing plug-in is not installed. Would you like to install it or purchase it?". The unit can also refer to the user's past purchase and installation history to suggest the most suitable plug-in. Furthermore, it makes suggestions taking into account the user's budget and frequency of use.

[0060] (Example 2) The plug-in management system according to an embodiment of the present invention is a system that understands requests and questions from users and executes processing using appropriate plug-ins based on those requests. This allows the plug-in management system to respond to user requests quickly and appropriately.

[0061] A plug-in management system according to an embodiment includes a request analysis unit, a plug-in confirmation unit, and an inquiry unit. The request analysis unit analyzes a user request. For example, the request analysis unit uses a generation AI to analyze the user request and understand its content. The request analysis unit can also analyze the request using natural language processing technology. The request analysis unit can also analyze the user request in text format. For example, the generation AI analyzes a request entered by the user and understands its content. The generation AI analyzes the request using a text generation AI (e.g., LLM). The generation AI determines an appropriate plug-in based on the content of the request. The plug-in confirmation unit checks installed plug-ins based on the request analyzed by the request analysis unit. For example, the plug-in confirmation unit references a list of plug-ins installed in the system and checks whether a plug-in corresponding to the request is installed. The plug-in confirmation unit can also check the version and compatibility of the plug-in. The plug-in confirmation unit can also reference the plug-in usage history and select a plug-in based on past success rates and error rates. For example, the plug-in confirmation unit obtains version information of plug-ins in the system and checks whether the latest version is installed. If a required plug-in is not installed, the inquiry unit inquires of the user about installing or purchasing the plug-in. For example, the inquiry unit may inquire in the form of, "An image editing plug-in is not installed. Would you like to install it or purchase it?" The inquiry unit may also refer to the user's past purchase history and installation history to suggest the most suitable plug-in. The inquiry unit may also make suggestions taking into consideration the user's budget and frequency of use. For example, the inquiry unit may suggest plug-ins that can be purchased within the user's budget. This allows the plug-in management system according to the embodiment to execute processing using an appropriate plug-in in response to a user request.For example, if a user inputs a request such as "I want to edit an image," a request analysis unit analyzes the request, a plug-in confirmation unit checks the installation status of the image editing plug-in, and an inquiry unit inquires about installing or purchasing the plug-in as necessary.

[0062] The request analysis unit can improve prediction accuracy by referencing the user's past request history and learning request patterns. For example, the request analysis unit stores the user's past request history in a database, and the generation AI analyzes that data. For example, for a user who has frequently requested "image editing" in the past, the request analysis unit predicts the likelihood that a similar request will be made next time. The request analysis unit can also use machine learning algorithms to learn request patterns. For example, the request analysis unit extracts request patterns based on past request data and builds a prediction model. The request analysis unit can also use clustering technology to learn request patterns. For example, the request analysis unit clusters past request data and identifies groups of similar requests. This improves the prediction accuracy of user requests.

[0063] The request analysis unit can analyze the user's voice tone or facial expression to determine the urgency or importance of a request. For example, the request analysis unit can analyze the voice tone used when the user inputs a request to determine the urgency or importance. For example, if the user's voice tone sounds tense or rushed, the request can be determined to be highly urgent. The request analysis unit can also analyze the user's facial expression to determine the urgency or importance of a request. For example, the user's facial expression when inputting a request can be captured with a camera and the emotion analyzed using a facial expression analysis algorithm. The request analysis unit can also analyze both the voice tone and facial expression to comprehensively determine the urgency or importance of a request. For example, the voice tone and facial expression changes can be analyzed in combination to evaluate the urgency or importance of a request. This allows for a prompt response by determining the urgency or importance of a request.

[0064] The request analysis unit uses the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. The request analysis unit, for example, employs an emotion estimation algorithm to analyze the user's emotional state. For example, the request analysis unit analyzes the user's facial expression and voice when inputting a request and calculates an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state in real time. For example, the request analysis unit can analyze the user's facial expression and voice in real time using a camera or microphone and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit analyzes the user's emotional state when inputting a request and infers the intention of the request based on the emotion. In this way, by analyzing the user's emotional state, the intention behind the request can be more deeply understood.

[0065] The request analysis unit can perform multilingual analysis of user requests so that they can be handled by users of different languages ​​or cultural backgrounds. The request analysis unit, for example, uses natural language processing technology to analyze user requests in multiple languages. For example, an analysis algorithm that supports multiple languages, such as English, Japanese, and French, is developed. The request analysis unit can also perform analysis that takes cultural background into account so that they can be handled by users of different cultural backgrounds. For example, the request analysis unit uses an analysis algorithm that takes cultural context into account to analyze requests from users of different cultural backgrounds. The request analysis unit can also use a translation algorithm to analyze user requests in multiple languages. For example, the request analysis unit automatically translates and analyzes user requests. This allows them to be handled by users of different languages ​​and cultural backgrounds.

[0066] The request analysis unit can analyze user requests not only from text but also from image or audio data. For example, the request analysis unit allows a user to upload not only text but also image or audio data when entering a request. For example, in the case of a request for image editing, the user uploads the image to be edited. The request analysis unit can also use image recognition technology or voice recognition technology to analyze the image or audio data. For example, the request analysis unit analyzes uploaded images and understands their content. The request analysis unit can also analyze uploaded audio data and understand its content. For example, the request analysis unit converts audio data into text using voice recognition technology and analyzes the text. The request analysis unit can also use multimodal generation AI to analyze image and audio data. For example, the request analysis unit uses multimodal generation AI to analyze image and audio data and understand its content. This allows requests to be analyzed not only from text but also from image and audio data.

[0067] The request analysis unit can use the emotion estimation function to analyze the emotion of a user when inputting a request in real time and make suggestions to elicit positive emotions. The request analysis unit, for example, uses the emotion estimation function to analyze the emotion of a user when inputting a request. For example, the request analysis unit can use a camera or microphone to analyze the user's facial expression and voice and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotion in real time and make suggestions based on the emotion. For example, the emotion estimation function can be used to analyze the emotion of a user when inputting a request and make suggestions to elicit positive emotions. The request analysis unit can also use the emotion estimation function to analyze the user's emotion in real time and make suggestions to reduce negative emotions. For example, the emotion estimation function can be used to analyze the emotion of a user when inputting a request and make suggestions to reduce negative emotions. In this way, the user's emotion can be analyzed in real time and suggestions to elicit positive emotions can be made.

[0068] The request analysis unit can add a process of feeding back the analysis results of the request to the user and checking whether the results match what the user intended. The request analysis unit, for example, adds a process of feeding back the analysis results of the request to the user and checking whether the results match what the user intended. For example, the analysis results may be displayed in text and the user may be asked to confirm. The request analysis unit can also use graphs or charts to visually display the analysis results. For example, the analysis results may be displayed in graphs or charts and the user may be asked to confirm. The request analysis unit can also feed back the analysis results aloud. For example, the analysis results may be read out aloud and the user may be asked to confirm. This improves the accuracy of request analysis by checking whether the results match what the user intended.

[0069] The request analysis unit can use the emotion estimation function to collect the user's emotional reactions to the request analysis results and improve the analysis accuracy. The request analysis unit, for example, collects the user's emotional reactions to the request analysis results and builds a system that improves the analysis accuracy based on the data. For example, if there are many positive reactions to the analysis results, that analysis method is used preferentially. The request analysis unit can also use the emotion estimation function to collect the user's emotional reactions in real time. For example, it can use a camera or microphone to analyze the user's facial expressions and voice in real time and calculate an emotion score. The request analysis unit can also use the emotion estimation function to collect the user's emotional reactions and improve the analysis algorithm based on the data. For example, it can adjust the parameters of the analysis algorithm based on the emotional reaction data. In this way, collecting the user's emotional reactions improves the analysis accuracy of the request.

[0070] The request analysis unit can have experts from different industries or fields review the request analysis results and obtain feedback. For example, the request analysis unit can have experts from different industries or fields review the request analysis results and build a system that improves the analysis accuracy based on the feedback. For example, the request analysis unit can have experts in technical fields check the analysis results. The request analysis unit can also use an online platform to collect feedback from experts. For example, the analysis results can be uploaded to the online platform and feedback from the experts can be collected. The request analysis unit can also improve the analysis algorithm based on the expert feedback. For example, the parameters of the analysis algorithm can be adjusted based on the expert feedback. In this way, feedback from experts from different industries or fields can be obtained and the accuracy of the request analysis can be improved.

[0071] The request analysis unit can convert the analysis results of the request into visual notes or mind maps to make them easier to understand visually. The request analysis unit, for example, builds a system that converts the analysis results of the request into visual notes and displays them visually. For example, it shows the main points of the analysis results using diagrams or icons. The request analysis unit can also convert the analysis results into mind maps and display them visually. For example, it can show the structure of the analysis results in a mind map to make them easier to understand visually. The request analysis unit can also use a generation AI to automatically generate visual notes or mind maps. For example, the generation AI automatically generates visual notes or mind maps based on the analysis results. This makes the analysis results of the request easier to understand visually, thereby improving the user's understanding.

[0072] The request analysis unit can use the emotion estimation function to monitor the user's emotional reactions to the analysis results in real time and optimize the analysis process. The request analysis unit, for example, monitors the user's emotional reactions to the analysis results in real time and builds a system that optimizes the analysis process based on that data. For example, it prioritizes the use of analysis methods that generate a high number of positive reactions. The request analysis unit can also use the emotion estimation function to collect the user's emotional reactions in real time. For example, it can use a camera or microphone to analyze the user's facial expressions and voice in real time and calculate an emotion score. The request analysis unit can also use the emotion estimation function to collect the user's emotional reactions and improve the analysis algorithm based on that data. For example, it can adjust the parameters of the analysis algorithm based on the emotional reaction data. In this way, the analysis process can be optimized by monitoring the user's emotional reactions in real time.

[0073] The plugin verification unit can check the version and compatibility of plugins and select the most suitable plugin. For example, when checking a plugin, the plugin verification unit obtains plugin version information and checks whether the latest version is installed. For example, if the version is old, it suggests updating. The plugin verification unit can also check plugin compatibility. For example, it checks whether the plugin is compatible with other software in the system. The plugin verification unit can also refer to the plugin usage history and select a plugin based on past success rates and error rates. For example, it can prioritize plugins with high success rates. In this way, by checking the plugin version and compatibility, the most suitable plugin can be selected.

[0074] The plugin confirmation unit can refer to the plugin usage history and select a plugin based on the past success rate and error rate. The plugin confirmation unit, for example, stores the plugin usage history in a database and analyzes the past success rate and error rate. For example, it prioritizes the selection of plugins with a high success rate. The plugin confirmation unit can also set plugin selection criteria based on the plugin usage history. For example, it can prioritize the selection of plugins with a low error rate. The plugin confirmation unit can also improve the plugin selection algorithm based on the plugin usage history. For example, it can adjust the parameters of the selection algorithm based on the success rate and error rate data. In this way, the optimal plugin can be selected by referring to the plugin usage history.

[0075] The plugin verification unit can use the emotion estimation function to collect users' emotional reactions to plugin selection and improve the selection process. The plugin verification unit, for example, collects users' emotional reactions to plugin selection and builds a system to improve the selection process based on the data. For example, it prioritizes the selection of plugins with a large number of positive reactions. The plugin verification unit can also use the emotion estimation function to collect users' emotional reactions in real time. For example, it can use a camera or microphone to analyze the user's facial expressions and voice in real time and calculate an emotion score. The plugin verification unit can also use the emotion estimation function to collect users' emotional reactions and improve the selection algorithm based on the data. For example, it can adjust the parameters of the selection algorithm based on the emotional reaction data. In this way, the plugin selection process can be improved by collecting users' emotional reactions.

[0076] The plugin verification unit can make the plugin verification results available on different platforms and devices. The plugin verification unit, for example, builds a system that makes the plugin verification results available on different platforms and devices. For example, the plugin verification unit supports multiple operating systems such as Windows, macOS, and Linux. The plugin verification unit can also make the plugin verification results available on different devices. For example, the plugin verification unit supports multiple devices such as PCs, smartphones, and tablets. The plugin verification unit can also store the plugin verification results in the cloud so that they can be accessed from different platforms and devices. For example, the plugin verification results can be stored using cloud storage so that they can be accessed from different devices. This makes the plugin verification results available on different platforms and devices, thereby improving convenience.

[0077] The plug-in verification unit can share the plug-in verification results with other users and obtain feedback. For example, the plug-in verification unit builds a system for sharing the plug-in verification results with other users and obtaining feedback. For example, it provides an online platform for sharing the verification results. The plug-in verification unit can also use a survey function to collect feedback from other users. For example, it can collect feedback on the verification results in the form of a survey. The plug-in verification unit can also improve the plug-in selection algorithm based on feedback from other users. For example, it can adjust parameters of the selection algorithm based on the feedback data. In this way, by sharing the verification results with other users, it can obtain feedback and improve the plug-in selection process.

[0078] When installing or purchasing a plug-in, the inquiry unit can refer to the user's past purchase history and installation history to make the optimal suggestion. For example, the inquiry unit stores the user's past purchase history and installation history in a database and builds a system that suggests the optimal plug-in based on that data. For example, the inquiry unit can suggest plug-ins in the same category as plug-ins purchased in the past. The inquiry unit can also improve the plug-in suggestion algorithm based on the user's purchase history and installation history. For example, the inquiry unit can adjust the parameters of the suggestion algorithm based on the purchase history and installation history data. The inquiry unit can also set plug-in suggestion criteria based on the user's past purchase history and installation history. For example, the inquiry unit can preferentially suggest plug-ins that have been successful in the past. In this way, the optimal plug-in can be suggested by referring to the user's past history.

[0079] The inquiry unit can make suggestions taking into consideration the user's budget and frequency of use when installing or purchasing a plug-in. The inquiry unit, for example, builds a system that takes into consideration the user's budget and suggests optimal plug-ins. For example, it prioritizes suggesting plug-ins that can be purchased within the budget. The inquiry unit can also suggest optimal plug-ins taking into consideration the user's frequency of use. For example, it prioritizes suggesting frequently used plug-ins. The inquiry unit can also improve the plug-in suggestion algorithm based on the user's budget and frequency of use. For example, it adjusts parameters of the suggestion algorithm based on data on the budget and frequency of use. The inquiry unit can also set plug-in suggestion criteria based on the user's budget and frequency of use. For example, it suggests the most effective plug-in within the budget. In this way, it is possible to suggest optimal plug-ins by taking into consideration the user's budget and frequency of use.

[0080] The inquiry unit can use the emotion estimation function to collect users' emotional reactions to installing or purchasing a plug-in and improve the recommendation process. For example, the inquiry unit collects users' emotional reactions to installing or purchasing a plug-in and builds a system to improve the recommendation process based on the data. For example, the inquiry unit can prioritize suggesting plug-ins with a high number of positive reactions. The inquiry unit can also use the emotion estimation function to collect users' emotional reactions in real time. For example, the inquiry unit can use a camera or microphone to analyze the user's facial expressions and voice in real time and calculate an emotion score. The inquiry unit can also use the emotion estimation function to collect users' emotional reactions and improve the recommendation algorithm based on the data. For example, the inquiry unit can adjust the parameters of the recommendation algorithm based on the emotional reaction data. In this way, the recommendation process can be improved by collecting users' emotional reactions.

[0081] The inquiry unit can make multilingual suggestions to install or purchase plug-ins so that the suggestions can be made to users of different languages ​​or cultural backgrounds. The inquiry unit, for example, builds a system that makes multilingual suggestions to install or purchase plug-ins. For example, it develops a suggestion algorithm that supports multiple languages, such as English, Japanese, and French. The inquiry unit can also make suggestions that take cultural backgrounds into account so that the system can also accommodate users of different cultural backgrounds. For example, the inquiry unit makes suggestions that take cultural contexts into account for users of different cultural backgrounds. The inquiry unit can also use a translation algorithm to make multilingual suggestions to install or purchase plug-ins. For example, the inquiry unit automatically translates the suggestions and presents them to the user. This allows the system to accommodate users of different languages ​​and cultural backgrounds.

[0082] The inquiry unit can make suggestions for installing or purchasing plug-ins not only from text but also from image or audio data. The inquiry unit, for example, builds a system that makes suggestions for installing or purchasing plug-ins not only from text but also from image or audio data. For example, the inquiry unit analyzes images and audio to suggest optimal plug-ins. The inquiry unit can also use image recognition technology or voice recognition technology to analyze image and audio data. For example, the inquiry unit can analyze uploaded images and suggest plug-ins based on their content. The inquiry unit can also analyze uploaded audio data and suggest plug-ins based on their content. For example, the inquiry unit can convert audio data into text using voice recognition technology, analyze the text, and suggest plug-ins. The inquiry unit can also use multimodal generation AI to analyze image and audio data. For example, the inquiry unit can analyze image and audio data and use multimodal generation AI to suggest plug-ins based on their content. This allows suggestions to be made based on not only text but also image and audio data, thereby meeting the user's needs.

[0083] The inquiry unit can use the emotion estimation function to analyze the user's emotional response to the installation or purchase of the plug-in in real time and make suggestions to elicit positive emotions. The inquiry unit, for example, uses the emotion estimation function to build a system that analyzes the user's emotional response to the installation or purchase of the plug-in in real time. For example, the inquiry unit can analyze the user's facial expressions and voice using a camera or microphone and calculate an emotion score. The inquiry unit can also use the emotion estimation function to analyze the user's emotions in real time and make suggestions based on the emotions. For example, if the user is showing positive emotions, the inquiry unit can make suggestions to elicit those emotions. The inquiry unit can also use the emotion estimation function to analyze the user's emotions in real time and make suggestions to alleviate negative emotions. For example, if the user is showing negative emotions, the inquiry unit can make suggestions to alleviate those emotions. In this way, by analyzing the user's emotional responses in real time, suggestions to elicit positive emotions can be made.

[0084] The inquiry unit can automate the installation procedure or purchase procedure when installing or purchasing a plug-in, thereby minimizing the hassle for the user. The inquiry unit, for example, builds a system that automates the installation procedure of a plug-in. For example, when a user selects "Install," the plug-in is automatically downloaded and installed. The inquiry unit can also automate the purchase procedure of a plug-in. For example, when a user selects "Purchase," the purchase procedure is automatically performed and the plug-in is installed. The inquiry unit can also use a script or automation tool to automate the installation procedure or purchase procedure. For example, the inquiry unit uses a script to automate the installation procedure or purchase procedure. The inquiry unit can also use an API to automate the installation procedure or purchase procedure. For example, the inquiry unit uses an API to automate the installation procedure or purchase procedure. In this way, the installation procedure or purchase procedure can be automated, thereby minimizing the hassle for the user.

[0085] The inquiry unit can automatically check the operation of a plug-in after installation to check for any problems. The inquiry unit, for example, builds a system that automatically checks the operation of a plug-in after installation. For example, after installation is complete, the inquiry unit automatically runs an operation test of the plug-in. The inquiry unit can also provide feedback on the results of the operation check to the user. For example, the results of the operation check are displayed in text and notified to the user. The inquiry unit can also record the results of the operation check in a log so that they can be referenced later. For example, the results of the operation check are saved in a log file and referenced if a problem occurs. The inquiry unit can also improve the plug-in installation procedure based on the results of the operation check. For example, the parameters of the installation procedure are adjusted based on the results of the operation check. In this way, the operation check can be automatically performed after installation to check for any problems.

[0086] The inquiry unit can use the emotion estimation function to collect the user's emotional reactions to the installation or purchase of the plug-in and improve the execution process. For example, the inquiry unit collects the user's emotional reactions to the installation or purchase of the plug-in and builds a system to improve the execution process based on the data. For example, the inquiry unit can prioritize the use of procedures with a high number of positive reactions. The inquiry unit can also use the emotion estimation function to collect the user's emotional reactions in real time. For example, the inquiry unit can use a camera or microphone to analyze the user's facial expressions and voice in real time and calculate an emotion score. The inquiry unit can also use the emotion estimation function to collect the user's emotional reactions and improve the execution algorithm based on the data. For example, the inquiry unit can adjust the parameters of the execution algorithm based on the emotional reaction data. In this way, the execution process can be improved by collecting the user's emotional reactions.

[0087] The inquiry unit can share the installation or purchase of a plug-in with other users and obtain feedback. The inquiry unit, for example, builds a system for sharing the installation or purchase of a plug-in with other users and obtaining feedback. For example, it provides an online platform for sharing the installation or purchase procedure. The inquiry unit can also use a survey function to collect feedback from other users. For example, it can collect feedback on the installation or purchase procedure in the form of a survey. The inquiry unit can also improve the installation or purchase procedure based on feedback from other users. For example, it can adjust procedure parameters based on the feedback data. By sharing the data with other users, it can obtain feedback and improve the execution process.

[0088] The inquiry unit can use the emotion estimation function to monitor the user's emotional reactions to the installation or purchase of the plug-in in real time and optimize the execution process. For example, the inquiry unit can monitor the user's emotional reactions to the installation or purchase of the plug-in in real time and build a system to optimize the execution process based on the data. For example, the inquiry unit can prioritize the use of procedures with a high number of positive reactions. The inquiry unit can also use the emotion estimation function to collect the user's emotional reactions in real time. For example, the inquiry unit can analyze the user's facial expressions and voice in real time using a camera or microphone and calculate an emotion score. The inquiry unit can also use the emotion estimation function to collect the user's emotional reactions and improve the execution algorithm based on the data. For example, the inquiry unit can adjust the parameters of the execution algorithm based on the emotional reaction data. In this way, the execution process can be optimized by monitoring the user's emotional reactions in real time.

[0089] When a request is re-executed, the query unit can refer to the results of the previous execution and reflect improvements. For example, when a request is re-executed, the query unit stores the results of the previous execution in a database and builds a system that reflects improvements based on that data. For example, the query unit selects the optimal plug-in based on the results of the previous execution. The query unit can also improve the re-execution procedure based on the results of the previous execution. For example, the query unit analyzes the results of the previous execution and optimizes the re-execution procedure. The query unit can also improve the re-execution algorithm based on the results of the previous execution. For example, the query unit adjusts the parameters of the re-execution algorithm based on the data from the previous execution. In this way, improvements can be reflected when a request is re-executed by referring to the results of the previous execution.

[0090] The inquiry unit can collect user feedback when a request is re-executed and reflect it in the next execution. For example, the inquiry unit builds a system that collects user feedback when a request is re-executed and reflects the data in the next execution. For example, the inquiry unit adjusts the selection of plug-ins based on the feedback. The inquiry unit can also use a survey function to collect user feedback. For example, it collects feedback on the re-execution procedure in the form of a survey. The inquiry unit can also improve the re-execution procedure based on the user feedback. For example, it adjusts procedure parameters based on the feedback data. The inquiry unit can also improve the re-execution algorithm based on the user feedback. For example, it adjusts parameters of the re-execution algorithm based on the feedback data. In this way, user feedback can be collected and reflected in the next execution.

[0091] The query unit can use the emotion estimation function to collect the user's emotional reactions to the retry of the request and improve the retry process. For example, the query unit collects the user's emotional reactions to the retry of the request and builds a system to improve the retry process based on the data. For example, the query unit prioritizes the use of procedures with a high number of positive reactions. The query unit can also use the emotion estimation function to collect the user's emotional reactions in real time. For example, the query unit can analyze the user's facial expressions and voice in real time using a camera or microphone and calculate an emotion score. The query unit can also use the emotion estimation function to collect the user's emotional reactions and improve the retry algorithm based on the data. For example, the query unit can adjust the parameters of the retry algorithm based on the emotional reaction data. In this way, the retry process can be improved by collecting the user's emotional reactions.

[0092] The inquiry unit can make the results of re-executing a request available on different platforms and devices. The inquiry unit, for example, builds a system that makes the results of re-executing a request available on different platforms and devices. For example, the inquiry unit supports multiple operating systems such as Windows, macOS, and Linux. The inquiry unit can also make the results of re-executing a request available on different devices. For example, the inquiry unit supports multiple devices such as PCs, smartphones, and tablets. The inquiry unit can also store the results of re-executing a request in the cloud so that they can be accessed from different platforms and devices. For example, cloud storage can be used to store the results of re-executing a request so that they can be accessed from different devices. This improves convenience by making the results of re-executing a request available on different platforms and devices.

[0093] The inquiry unit can share the results of the re-execution of the request with other users and obtain feedback. The inquiry unit, for example, builds a system for sharing the results of the re-execution of the request with other users and obtains feedback. For example, it provides an online platform for sharing the re-execution results. The inquiry unit can also use a survey function to collect feedback from other users. For example, it collects feedback on the re-execution results in the form of a survey. The inquiry unit can also improve the re-execution procedure based on the feedback from other users. For example, it can adjust the parameters of the procedure based on the feedback data. In this way, by sharing the results with other users, it can obtain feedback and improve the re-execution process.

[0094] The query unit can use the emotion estimation function to monitor the user's emotional response to the replay of the request in real time and optimize the replay process. The query unit, for example, uses the emotion estimation function to build a system that monitors the user's emotional response to the replay of the request in real time. For example, the query unit analyzes the user's facial expression and voice and calculates an emotion score. The query unit can also use the emotion estimation function to collect the user's emotional response in real time. For example, the query unit can use a camera or microphone to analyze the user's facial expression and voice in real time and calculate an emotion score. The query unit can also use the emotion estimation function to collect the user's emotional response and improve the replay algorithm based on the data. For example, the query unit adjusts parameters of the replay algorithm based on the emotional response data. In this way, the replay process can be optimized by monitoring the user's emotional response in real time.

[0095] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0096] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0097] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0098] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0099] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0100] When analyzing a user's request, the request analysis unit can obtain additional information from related external databases or APIs based on the content of the request. For example, if a user inputs a request such as "I want to know the latest weather information," the request analysis unit accesses a weather information API to obtain the latest weather data. Alternatively, if a user inputs a request such as "I want to check the price of a specific product," the request analysis unit can access the API of a price comparison site to obtain price information from multiple online stores. Furthermore, if a user inputs a request such as "I want to read a specific news article," the request analysis unit can access a news API to obtain the latest news articles. This allows the request analysis unit to provide richer information in response to the user's request.

[0101] The request analysis unit can use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's facial expression and voice when the user inputs a request and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state in real time. For example, the request analysis unit can analyze the user's facial expression and voice in real time using a camera or microphone and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's emotional state when the user inputs a request and infer the intention of the request based on the emotion. In this way, by analyzing the user's emotional state, the intention behind the request can be more deeply understood.

[0102] The request analysis unit can use the emotion estimation function to analyze the emotion of a user when inputting a request in real time and make suggestions to elicit positive emotions. For example, when a user inputs a request, the emotion estimation function is used to analyze the emotion. For example, a camera or microphone is used to analyze the user's facial expression and voice and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotion in real time and make suggestions based on the emotion. For example, when a user inputs a request, the emotion estimation function is used to analyze the emotion and make suggestions to elicit positive emotions. The request analysis unit can also use the emotion estimation function to analyze the user's emotion in real time and make suggestions to reduce negative emotions. For example, when a user inputs a request, the emotion estimation function is used to analyze the emotion and make suggestions to reduce negative emotions. In this way, the user's emotion can be analyzed in real time and suggestions to elicit positive emotions can be made.

[0103] The request analysis unit can use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's facial expression and voice when the user inputs a request and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state in real time. For example, the request analysis unit can analyze the user's facial expression and voice in real time using a camera or microphone and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's emotional state when the user inputs a request and infer the intention of the request based on the emotion. In this way, by analyzing the user's emotional state, the intention behind the request can be more deeply understood.

[0104] The request analysis unit can use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's facial expression and voice when the user inputs a request and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state in real time. For example, the request analysis unit can analyze the user's facial expression and voice in real time using a camera or microphone and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's emotional state when the user inputs a request and infer the intention of the request based on the emotion. In this way, by analyzing the user's emotional state, the intention behind the request can be more deeply understood.

[0105] The request analysis unit can use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's facial expression and voice when the user inputs a request and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state in real time. For example, the request analysis unit can analyze the user's facial expression and voice in real time using a camera or microphone and calculate an emotion score. The request analysis unit can also use the emotion estimation function to analyze the user's emotional state and gain a deeper understanding of the intention behind the request. For example, the request analysis unit can analyze the user's emotional state when the user inputs a request and infer the intention of the request based on the emotion. In this way, by analyzing the user's emotional state, the intention behind the request can be more deeply understood.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The request analysis unit analyzes the user's request. For example, it can use generative AI to analyze the request and understand its content. It can also analyze the request using natural language processing technology. The request analysis unit analyzes the user's request in text format and determines the appropriate plugin. Step 2: The plugin verification unit checks the installed plugins based on the request analyzed by the request analysis unit. For example, it references the list of plugins installed in the system and checks whether the plugin corresponding to the request is installed. It also references the plugin version, compatibility, and usage history to select the most suitable plugin. Step 3: If a required plug-in is not installed, the inquiry unit asks the user about installing or purchasing the plug-in. For example, the inquiry may be in the form of "An image editing plug-in is not installed. Would you like to install it or purchase it?". The unit can also refer to the user's past purchase and installation history to suggest the most suitable plug-in. Furthermore, it makes suggestions taking into account the user's budget and frequency of use.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0121] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0134] 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.

[0135] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0152] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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."

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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]

[0175] 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 request analysis unit that analyzes a user request; a plug-in checking unit that checks installed plug-ins based on the request analyzed by the request analyzing unit; and an inquiry unit that inquires of the user about installing or purchasing a plug-in if the required plug-in is not installed. A system characterized by:

2. The request analysis unit Emotion estimation capabilities allow us to analyze the user's emotional state and gain a deeper understanding of the intent behind their requests.

2. The system of claim 1.

3. The request analysis unit Multilingual analysis of user requests to accommodate users of different languages ​​or cultures 2. The system of claim 1.

4. The request analysis unit Refer to relevant external databases to perform highly accurate analysis 2. The system of claim 1.

5. The plug-in confirmation unit Check plugin versions and compatibility and select the best plugins 2. The system of claim 1.

6. The inquiry unit When installing or purchasing a plugin, the system refers to the user's past purchase and installation history to provide optimal suggestions.

2. The system of claim 1.

7. The inquiry unit Automate the installation and purchase process to minimize user effort when installing or purchasing plugins 2. The system of claim 1.

8. The inquiry unit Using emotion estimation, we collect users' emotional responses to replay requests and improve the replay process.

2. The system of claim 1.

Images