system

Abstract

Provide a system. 【Solution means】 Means for collecting and formalizing evaluation information of a knowledge processing system to be generated; Evaluation means for quantifying the performance of a knowledge processing system to be generated based on the evaluation information; Means for receiving a user's work procedure and usage purpose and clarifying requirements; Means for selecting an optimal knowledge processing system to be generated using the requirements and the evaluation information; Means for automatically generating and notifying information on the selected knowledge processing system to be generated as a document; Means for collecting opinions from users and using them to improve the accuracy of evaluation means after the next time; Means for collecting data for optimizing the performance of various knowledge processing systems in an automatic control device and selecting an optimal knowledge processing system; A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] As the artificial intelligence to be generated diversifies, it is difficult for a user to select the artificial intelligence optimal for their own business. Due to the inconsistent criteria for comparing the performance and characteristics of artificial intelligence, it is difficult to make an optimal selection according to the user's requirements. In addition, there is a problem that there is a lack of a mechanism to efficiently utilize the feedback after selection and improve the selection accuracy for subsequent selections.

Means for Solving the Problems

[0005] This invention provides a system equipped with an evaluation means for quantifying the performance of generated artificial intelligence. This makes it possible to clarify the user's workflow and purpose of use and select the optimal artificial intelligence to generate. It also has a function to automatically generate a report on the selected artificial intelligence and notify the user. Furthermore, by collecting feedback from the user and utilizing this information in subsequent evaluations, it is possible to dynamically improve the artificial intelligence selection algorithm and enhance the selection accuracy.

[0006] "Generative artificial intelligence" refers to a computer program or system that has the ability to create new information based on data.

[0007] "Evaluation information" refers to data that quantifies or formalizes the performance and characteristics of the artificial intelligence being generated.

[0008] "Evaluation methods" refer to processes and methods for measuring and quantifying the performance of the artificial intelligence being generated.

[0009] A "business process flow" refers to the sequence of business processes and activities performed by a user.

[0010] "Requirements" refer to the conditions for the functions and performance that users expect from the artificial intelligence they generate.

[0011] The term "optimal" selection refers to choosing the artificial intelligence that is most suitable under specific conditions.

[0012] A "report" is a summary of documents and information provided to the user regarding the selection results and usage methods of the artificial intelligence that will be generated.

[0013] "Feedback" refers to information based on user evaluations, opinions, and experiences after using a product or service.

[0014] A "selection algorithm" is a set of steps and processes used to determine the optimal artificial intelligence to generate.

Brief Description of the Drawings

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0019] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that collects evaluation information on generated artificial intelligence and automates the process of users selecting the most suitable artificial intelligence for their business operations.

[0037] The following describes the specific operational aspects of this system.

[0038] The server collects data on artificial intelligence, generated periodically from external and internal data sources. This data includes performance metrics, user reviews, and feedback. The collected data is stored in a database and formatted.

[0039] Users input their workflow and requirements for the artificial intelligence they want to generate through a user interface. This allows the server to specifically understand the user's needs. For example, a graphic designer user who wants to generate images for advertising can request an AI with high-quality image generation capabilities.

[0040] The server analyzes the collected data and quantifies the performance of each generated artificial intelligence. Machine learning algorithms are used for the analysis, which evaluates metrics such as response time, accuracy, and user satisfaction for each model.

[0041] Next, the server selects the optimal artificial intelligence to generate based on the user's requirements and analysis results. In this selection process, it filters models that meet the specific requirements for the user's work and identifies the most appropriate model based on weighted scores.

[0042] Once the selection is complete, the server automatically generates a report on the selected artificial intelligence to be generated. This report details the characteristics, benefits, and recommended settings of the selected model. The server delivers this report to the user via email or in-app notification.

[0043] Furthermore, the terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the artificial intelligence they used and send them to the server. This feedback is used as important data to improve the accuracy of selections in the future.

[0044] This system allows users to more effectively utilize AI that generates results tailored to their specific tasks.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server collects performance data, user reviews, and feedback related to artificial intelligence generated from various data sources. This data is collected and stored via external APIs, web scraping, and internal databases.

[0048] Step 2:

[0049] The server cleans and preprocesses the collected data. This includes imputing missing values, formatting, and removing outliers. The formatted data is then stored in the database as an evaluation dataset.

[0050] Step 3:

[0051] The server evaluates each artificial intelligence model it generates using a pre-configured machine learning algorithm. The evaluation is performed by quantifying multiple performance indicators, such as response time, output accuracy, and user satisfaction score.

[0052] Step 4:

[0053] Users input workflow information and requirements for the artificial intelligence to be generated through a dedicated interface. For example, by specifying that they need high-resolution image generation for graphic design work, they can communicate their specific needs to the server.

[0054] Step 5:

[0055] The server combines user requirements with evaluated data, performs filtering and weighting, and selects the optimal artificial intelligence to generate. If multiple candidates exist, the model that best matches the conditions is selected.

[0056] Step 6:

[0057] The server automatically generates a report detailing the selected artificial intelligence to be generated. This report includes model characteristics, performance evaluations, and recommended configuration options, providing comprehensive information for the user.

[0058] Step 7:

[0059] The server delivers the generated reports to users via email or in-app notifications. This allows users to receive the selection results and quickly move on to the next step.

[0060] Step 8:

[0061] The device provides an interface for receiving user feedback. Users input their actual user experience and suggestions for improvement, and then send the feedback to the server.

[0062] Step 9:

[0063] The server analyzes the collected feedback and uses it as training data for the algorithm. Based on the analysis results, it adjusts the parameters of the selection algorithm to improve accuracy in the next selection process.

[0064] (Example 1)

[0065] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0066] The aim is to effectively automate the performance evaluation and optimal selection process of generated information processing systems, enabling the rapid and accurate selection of information processing systems suitable for the user's business processes. In conventional information system selection processes, the collection and formatting of evaluation data, requirements identification, and utilization of feedback were all done manually, resulting in a time-consuming and laborious process with limited selection accuracy.

[0067] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0068] In this invention, the server includes means for collecting evaluation data related to the information processing system to be generated and formatting it into a standardized format; evaluation means for quantifying the performance of the information processing system to be generated based on the evaluation data; and means for receiving the user's work process and objectives and identifying requirements suitable therefor. This enables the rapid and accurate selection of the optimal generation system.

[0069] A "generating information processing system" is a system designed to automatically process information using specific algorithms and processes to provide added value.

[0070] "Evaluation data" refers to data necessary to show the value of an information processing system in numerical terms and indicators, including its performance and quality, as well as user feedback.

[0071] A "standardized format" is a format that converts information collected from different data sources into a consistent and unified format, making subsequent processing and analysis easier.

[0072] "Evaluation means for quantifying performance" refers to a method or apparatus for quantitatively measuring and expressing the characteristics and performance of an information processing system as numerical values, based on collected evaluation data.

[0073] A "business process" refers to a series of steps and operations necessary to perform a specific task, and is a process for achieving a specific objective.

[0074] "Means for identifying requirements" refers to a method or apparatus for clarifying the specifications and conditions of the required system based on the user's needs and business objectives, and for selecting an information processing system that meets those requirements.

[0075] This invention automates the selection and optimization of information processing systems. A server plays a central role in this system, periodically collecting evaluation data on the generated information system from external and internal sources. This evaluation data includes system performance indicators and user feedback, which are then formatted into a standardized format. Specifically, the server uses a database system such as MySQL (registered trademark) to build an environment for managing and formatting the data.

[0076] Next, the server uses software frameworks such as TENSORFLOW® and PyTorch to analyze this evaluation data and quantify the performance of each system. Based on this quantified data, the value of the information processing system is evaluated. This data is used when receiving the user's business objectives and process requirements.

[0077] Users input their business objectives and system requirements via their terminal. This is done using input forms in a web application. These forms are built on modern frameworks such as React.js and Angular, providing a user-friendly interface. As a concrete example, when searching for a model to generate catchy ad copy in advertising, the following prompt might be entered:

[0078] Prompt example:

[0079] "We're looking for an AI that can generate catchy advertising copy that resonates with consumers, in order to highlight the appeal of our new product. Please suggest options that are expected to be more effective than those from past campaigns."

[0080] The server selects the optimal information processing system based on the user input and the analysis results of the quantified evaluation data. It uses weighted scores to filter out the most suitable system. A detailed report is automatically generated for the selected information system and notified to the user via the SMTP protocol, etc. The report includes the characteristics and recommended settings of the selected system.

[0081] These processes enable users to quickly implement information processing systems suited to their work, significantly improving efficiency and accuracy.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server collects evaluation data on the generated AI model from external and internal sources. It uses API calls to retrieve the latest performance metrics from external data providers and extracts historical user feedback from an internal database. This provides system performance metrics and user feedback as evaluation data. This data is initially retrieved in formats such as JSON and then formatted into a consistent format to facilitate subsequent processing.

[0085] Step 2:

[0086] The server formats the collected evaluation data into a standardized format and stores it in a database. Specifically, it uses a MySQL database to convert JSON data to CSV format, and checks for and corrects duplicates and missing data. The input is JSON data, and the output is formatted CSV data. This formatting and data cleansing process ensures data consistency and accuracy.

[0087] Step 3:

[0088] Users input their business objectives and requirements for the generated AI model through a user interface. The input forms used are built with front-end frameworks such as React.js and provide input completion features to help users enter accurate prompts. The input consists of business processes and requirements for expected output results, which are then sent to the server as requirement data.

[0089] Step 4:

[0090] The server analyzes requirements data and collected evaluation data, and uses a machine learning framework to quantify the performance of the generated AI model. Specifically, it uses TensorFlow to quantify the performance based on metrics such as AI model response time, accuracy, and user satisfaction. The input is formatted evaluation data and user requirements, and the output is quantified model performance data.

[0091] Step 5:

[0092] The server selects the optimal generative AI model based on quantified performance data and user requirements. Using a weighted scoring method, it filters the model that best fits the user requirements, identifying the optimal model. The input is quantified model performance data and user requirements, and the output is information about the selected AI model.

[0093] Step 6:

[0094] The server automatically generates a detailed report on the selected generative AI model and notifies the user. The report is generated using JasperReports and sent via email or in-application notification using the SMTP protocol. The input is information about the selected AI model, and the output is a detailed report.

[0095] Step 7:

[0096] The terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the AI ​​model they used and send them to the server. The input consists of the user's evaluation and improvement suggestions, and the output is feedback data used to improve the accuracy of future selections.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] In automated control systems, current knowledge processing systems present challenges in selecting the optimal artificial intelligence model due to the complexity of the selection process and limited information available for performance evaluation. Furthermore, insufficient adjustments to suit user work procedures can hinder efficient operation. Moreover, the evaluation and selection process lacks the ability to dynamically adapt, resulting in an inability to keep pace with rapidly changing technological requirements and environmental shifts.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for collecting and formalizing evaluation information of the knowledge processing system to be generated; evaluation means for quantifying the performance of the knowledge processing system to be generated based on the evaluation information; means for receiving the user's work procedures and purpose of use and clarifying the requirements; and means for collecting data for optimizing the performance of various knowledge processing systems in an automatic control device and selecting the optimal knowledge processing system. As a result, the user can quickly and appropriately select the optimal knowledge processing system and perform efficient and safe automatic control.

[0102] A "generating knowledge processing system" is a means of information processing newly constructed using machine learning or artificial intelligence algorithms for a specific task.

[0103] "Evaluation information" refers to a collection of data and feedback gathered to determine the performance and usefulness of the knowledge processing system that generates the information.

[0104] "Evaluation methods for quantifying performance" refer to methods and devices for quantitatively analyzing the diverse characteristics of a knowledge processing system and expressing them in specific numerical values.

[0105] "User procedures" refer to a series of steps or processes taken to perform a specific task or job.

[0106] "Means for clarifying requirements" refer to processes and devices that specifically define the needs and goals of users and clarify the conditions necessary for a knowledge processing system.

[0107] "Means for selecting the optimal knowledge processing system" refers to the criteria and methods for selecting the knowledge processing system that best suits the user's purpose, based on collected evaluation information and clarified requirements.

[0108] An "automatic control system" is a general term for a device that includes hardware and software for controlling the operation of machines and systems without human intervention.

[0109] This invention is implemented as a system that automates the process of selecting the optimal knowledge processing system in an automatic control device. In this system, a server is central and provides the following functions.

[0110] First, the server collects evaluation information for the knowledge processing system generated from external and internal databases, and uses this information to perform performance evaluations. The evaluation utilizes historical performance data and user feedback stored in a database management system running on Amazon Web Services (AWS®). This data is analyzed using a Python program, and performance is quantified using machine learning algorithms. Scikit-learn is the standard machine learning library used, and Pandas and NumPy are used for data preprocessing.

[0111] Next, the user's work procedures and purpose of use are entered through the user interface on the terminal. This input information is then condensed by the server into the necessary requirements and used as a criterion for selecting the optimal knowledge processing system. Detailed information about the selected system is included in an automatically generated report, through which the user can receive the reasons for the selection and configuration suggestions. This report is sent via in-app notification or email.

[0112] User feedback is entered directly on the device and sent to the server to improve the selection process for future use. This allows the evaluation algorithm to be continuously updated, enabling more accurate selections.

[0113] For example, in urban areas where traffic congestion is frequent, a knowledge processing system that selects the optimal route in real time and improves energy efficiency is chosen. To achieve this, a prompt in the form of "Please tell me how to select an AI model capable of precise urban environment interpretation in an autonomous vehicle" is used.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server collects evaluation information for the knowledge processing system generated from external and internal databases. Database queries are used as input, and historical performance data and user feedback obtained through these queries are output. Specifically, it accesses the Amazon Web Services (AWS) database and executes SQL queries based on a regular schedule.

[0117] Step 2:

[0118] The server preprocesses the collected information using a Python program. The input is the raw data obtained in step 1, and the output is data formatted into a parseable format. Specifically, it uses the Pandas library to clean the data (imputing missing values, normalizing data types).

[0119] Step 3:

[0120] The server analyzes the preprocessed data using the Scikit-learn library and quantifies the performance of the knowledge processing systems. The input is the data formatted in step 2, and the output is the quantified performance indicators for each system. Specifically, it builds a machine learning model, uses it to analyze the data, and generates an evaluation score for each knowledge processing system.

[0121] Step 4:

[0122] Users input work procedures and usage purposes through a terminal. This input includes business workflows and desired performance requirements entered into the user interface, and this information is stored in a database. Specifically, users select options on the user interface and press input buttons to send the information to the server.

[0123] Step 5:

[0124] The server compares user input information with quantified performance metrics to select the optimal knowledge processing system. The input is the output from steps 3 and 4, and the output is the specifications of the system considered optimal. Specifically, it performs scoring using an algorithm and selects the one with the highest degree of fit.

[0125] Step 6:

[0126] The server automatically generates a report based on the selection results and notifies the user. The input is the output from step 5, and the output is the report document. Specifically, it uses a template engine to assemble the report and sends it via email or a terminal application.

[0127] Step 7:

[0128] Users provide feedback via their device after use. This feedback consists of evaluations and suggestions for improvement based on their experience, and is recorded in a database. Specifically, data is collected when users fill out a feedback form and press the submit button.

[0129] Step 8:

[0130] The server analyzes the collected feedback and uses it as data to improve the accuracy of future selection processes. The input is the feedback data from step 7, and the output is the improved evaluation algorithm. The specific operation includes a process of adjusting the model based on negative feedback to improve the algorithm's performance.

[0131] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0132] This invention is a system that enables the selection of more appropriate artificial intelligence by incorporating user emotional information into the selection and evaluation process of the artificial intelligence to be generated. A specific embodiment thereof is shown below.

[0133] The server first collects, formats, and compiles performance evaluation data and user reviews related to artificial intelligence generated using conventional methods. This data is stored in a database and used for evaluation. The server's role is to quantify the performance of each artificial intelligence model based on this data and conduct evaluations.

[0134] Next, the server is equipped with an emotion engine that recognizes user emotion data in real time through the terminal. This system detects emotions from webcam video analysis, the user's facial expressions in response to input, tone of voice, or writing patterns.

[0135] The user inputs the workflow and the functions and performance they require from the artificial intelligence into the terminal interface. During this process, the server uses an emotion engine to collect changes in the user's emotions as they input. This emotional information can be used to identify and record emotions, particularly those relevant to evaluation.

[0136] In the selection process, the server integrates pre-collected emotional information with other business requirements and uses it to determine the suitability of the artificial intelligence to be generated. For example, if a user shows interest in a model setting and expresses positive emotions, an artificial intelligence specifically tailored to that setting will be presented.

[0137] Once the selection is complete, the server generates a report containing selection results that reflect emotional information, as well as details about the artificial intelligence. This report includes customization options based on the user's emotional state and is provided to the user in a timely manner via email or in-app notifications.

[0138] Finally, the device receives emotional feedback from the user again and sends it to the server. The server analyzes the emotional data obtained along with the feedback and uses it to improve the selection algorithm and the functionality of the emotion engine. This further improves the accuracy of selections in subsequent attempts.

[0139] In this way, this invention, which combines an emotion engine, goes beyond conventional performance and requirements-centric model selection and enables more sophisticated AI generation selection that takes into account the user's psychological state.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server collects performance evaluation information about artificial intelligence generated from external data sources and past feedback. This may involve using API access or scraping techniques. The collected data is stored in a database and prepared for evaluation.

[0143] Step 2:

[0144] The emotion engine installed on the server collects real-time emotional data from users through their devices. It analyzes the user's facial expressions using a camera and analyzes their voice tone and patterns to determine their emotions. This data is processed within the emotion engine, and information about the user's psychological state is generated.

[0145] Step 3:

[0146] The user inputs their workflow and the functions and performance requirements they expect from the generated artificial intelligence into the terminal interface. During input, the emotion engine captures changes in the user's emotions and sends them to the server as emotion data.

[0147] Step 4:

[0148] The server integrates collected business requirements and sentiment data, along with pre-collected evaluation information for generating artificial intelligence, to select the most suitable AI. In particular, it focuses on AI that corresponds to settings and functions in which the user has expressed positive emotions.

[0149] Step 5:

[0150] After the selection is complete, the server automatically generates a detailed report on the artificial intelligence to be produced. This report includes the performance, benefits, and customization options of the selected AI. The report is provided to the user via email or in-app notification.

[0151] Step 6:

[0152] The device provides an interface for receiving emotionally charged feedback from users. Users input feedback, including their experience using the generated artificial intelligence and areas for improvement, and send it to the server along with emotional data.

[0153] Step 7:

[0154] The server analyzes feedback and sentiment data to improve the accuracy of the sentiment engine and selection algorithms. The analysis results are used in subsequent selection processes, continuously improving the overall system performance.

[0155] (Example 2)

[0156] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0157] Conventional AI selection systems only evaluate performance and specifications, which means they cannot consider user emotions or psychological aspects. This can lead to the selection of AI that lacks intuitive satisfaction or suitability from the user's perspective. It is necessary to address these challenges and achieve AI selection that is more optimized for the user.

[0158] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0159] In this invention, the server includes means for collecting evaluation information and emotional data of the artificial intelligence to be generated and formalizing them; evaluation means for quantifying the performance of the artificial intelligence to be generated based on the evaluation information and emotional data; and means for receiving the user's work procedures and purpose of use, clarifying the requirements, and associating emotional information. This makes it possible to select an artificial intelligence that takes into account the user's emotions and psychological aspects, resulting in a higher level of satisfaction.

[0160] "Generative artificial intelligence" refers to a program with human-like intelligence that has been newly modeled using technologies such as machine learning and deep learning.

[0161] "Evaluation information" refers to a collection of numerical and evaluative data regarding the performance and functionality of the artificial intelligence being generated, and is used as an indicator for selection and improvement.

[0162] "Emotional data" refers to psychological and emotional information collected through the user's facial expressions, tone of voice, input patterns, etc., and is data that reflects the user's inner state.

[0163] "Requirements" refer to specific functional and performance conditions that users desire from the artificial intelligence they generate, representing technical needs that take into account the intended use and workflow.

[0164] "Evaluation methods" refer to a system that quantifies and analyzes the performance of the artificial intelligence to be generated based on collected evaluation information and sentiment data, and then performs evaluations for selection purposes.

[0165] A "report" is a document that summarizes detailed information and analysis results regarding the selected artificial intelligence that will be generated, and is used as an information transmission medium as one of the means of notifying users.

[0166] "Feedback" refers to opinions, including evaluations, impressions, and sentiment data, provided by users after using artificial intelligence they have generated. This information is collected for the purpose of improving future development and selection processes.

[0167] This invention is a system that achieves more appropriate selection by incorporating user emotional information into the process of selecting the artificial intelligence to be generated. An embodiment thereof is shown below.

[0168] The server first collects performance evaluation data and user reviews of the generated AI models and stores them in a database. The hardware used here includes a high-performance database server, and the software used is a database management system. Subsequently, this data is formalized and evaluated numerically.

[0169] The device plays a role in collecting real-time emotional data from the user. It uses a webcam and microphone to perform facial expression analysis and voice tone analysis. The emotion engine is specialized software that analyzes the data collected from these devices and evaluates the user's emotional state.

[0170] The user inputs the desired workflow and performance requirements for the artificial intelligence model into the terminal interface. For example, the user might input "AI model that prioritizes emotion understanding" into the input field. An example of a prompt message used in this case would be, "Please select an AI model that understands emotions. Settings corresponding to specific emotions will be given priority."

[0171] The server combines user input and sentiment data to select the optimal generative AI model. This selection result is automatically generated as a report and sent to the user via email or in-app notifications.

[0172] Ultimately, the device receives user feedback and sends it to the server along with the collected sentiment data. The server analyzes this information and uses it to improve future selection algorithms and sentiment engines, further enhancing the accuracy of future selections.

[0173] This embodiment makes it possible to select artificial intelligence that takes into account the user's emotional state, thereby realizing a more user-friendly system.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The server collects evaluation information and user reviews related to the generated AI model. Input includes information from databases and online resources. This information is analyzed and stored in the database as formalized data. The output is a formatted dataset containing evaluation scores. Specifically, the server uses a data extraction algorithm to extract and format the necessary data from various sources.

[0177] Step 2:

[0178] The device collects user emotion data in real time. The primary inputs are webcam video and microphone audio data. The emotion engine analyzes this input data and represents the user's emotional state using numbers and tags. The final output is a dataset of emotion analysis results. In this process, facial recognition software and voice analysis programs work in conjunction with emotion detection algorithms.

[0179] Step 3:

[0180] The user inputs the desired functions and performance requirements for the artificial intelligence model into the terminal interface. This input data is presented as specific questions and options based on the business flow and specifications. From this input, the server clarifies the user's requirements and structures the necessary data. The output is a dataset serving as a requirements definition document. The operation includes a process of transferring the data input via the user interface to the server.

[0181] Step 4:

[0182] The server integrates collected evaluation information, sentiment data, and user requirements to select the optimal generative AI model. The input includes all datasets collected in the previous step. The server uses an evaluation algorithm to select candidate models and compiles the selection results. The output is the selected generative AI model and its evaluation results. Specific operations include data analysis and model comparison algorithms.

[0183] Step 5:

[0184] The server generates a report based on the selection results and notifies the user via the terminal. The input for this step is information about the selected AI model and its evaluation. The output is sent to the user as a detailed evaluation report. In terms of operation, document generation software is used to compile the selection results into a report and provide it to the user via email or in-app message.

[0185] Step 6:

[0186] The terminal collects user feedback and sentiment data again and sends it to the server. Feedback input includes user ratings, impressions, and post-use sentiment data. This is analyzed and saved as a dataset for improving the next selection algorithm. The output is elemental data for improving the next generation algorithm. The specific operation includes the process of aggregating user responses via the feedback form and returning them to the server.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0189] In the selection process for generative artificial intelligence that takes into account the individual emotional states of users, conventional performance evaluation and requirements-centric methods lack adaptability to individual needs. In particular, there is a need for technology that selects the optimal generative artificial intelligence according to the user's psychological state and provides services based on it.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes means for collecting and formalizing evaluation information of the artificial intelligence to be generated, evaluation means for quantifying performance based on the evaluation information, and means for receiving the user's workflow and purpose of use and clarifying the requirements. It also includes means for analyzing the emotional state and selecting the artificial intelligence to be generated based on the emotional information, and means for collecting feedback from the user to improve the accuracy of evaluations in the future. This makes it possible to select a personalized artificial intelligence to be generated based on the user's emotional state and to provide an optimized service.

[0192] "Generative artificial intelligence" is artificial intelligence that is dynamically generated in response to user requests and optimized to perform specific tasks.

[0193] "Evaluation information" refers to data collected based on the performance of the generated artificial intelligence and user feedback, and serves as the basis for judging the appropriateness of the artificial intelligence.

[0194] "Emotional information" refers to data acquired to analyze a user's psychological state, and it quantitatively represents the user's emotions.

[0195] The "selection process" is the procedure for choosing the optimal generative artificial intelligence based on evaluation information and emotional information.

[0196] Personalization refers to adjusting services and features to suit the individual user's characteristics, needs, and emotional state.

[0197] "Feedback" refers to the opinions and impressions provided by users after using the product, and is data used to evaluate and improve the AI ​​that generates future products.

[0198] This invention provides a system in which a server plays a central role in optimally selecting and customizing generated artificial intelligence using data from users and terminals.

[0199] The server first collects AI performance evaluation information and user feedback information, and stores this in a database. This evaluation information includes past AI model usage results, user reviews, and performance data, which are then formatted using data analysis tools such as Microsoft® Azure® and Google® Cloud.

[0200] Next, the server utilizes an emotion analysis engine to analyze the user's emotional data in real time through the terminal. This emotional data is obtained by analyzing the user's voice input and facial expression data, and existing emotion analysis APIs (for example, Microsoft Azure Emotion API) are used for this analysis.

[0201] When a user inputs their workflow and purpose of use through the terminal interface, the server clarifies the requirements based on this information and integrates it with emotional information. Emotional information is particularly used in the selection and recommendation process of a customized AI model that reflects the user's psychological state. For example, if the user is seeking relaxation, the system will recommend music or content appropriate for relaxation using AI.

[0202] Ultimately, a specific AI model desired by the user is selected, and this information is communicated to the user in a report. The report includes performance metrics for the selected AI and customization options tailored to the user's emotional state. Based on this information, the user can then utilize artificial intelligence in various digital services.

[0203] This process enables the use of personalized AI models that adapt to the user's emotions. An example of a specific prompt would be, "Please recommend the best music content for when the user is in a relaxed state."

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects performance evaluation information for generated artificial intelligence from various data sources and stores it in a database. Inputs include past usage data, user reviews, and performance metrics. Outputs are standardized evaluation data. During this process, data analysis tools are used to format the collected data, making it suitable for efficient searching and analysis.

[0207] Step 2:

[0208] The server uses an emotion analysis engine to process real-time user emotion data collected via the terminal. Inputs include user voice and facial expression data. Outputs include a report that quantifies the user's emotional state. Specifically, it uses voice tone analysis and image analysis techniques to identify the user's psychological state.

[0209] Step 3:

[0210] The terminal allows users to input their workflow and purpose of use through an interface, and sends this data to the server. The input includes text information related to the user's purpose. The server uses this information to clarify user requirements. The clarified requirements information is then provided to the system as output.

[0211] Step 4:

[0212] The server integrates clarified user requirements and sentiment information to initiate a process of selecting the optimal generative artificial intelligence. The input consists of user requirements and sentiment information. The output is the identification of the AI ​​model that best suits the user's needs. Machine learning algorithms are used to score the suitability of existing models in the AI ​​model selection process.

[0213] Step 5:

[0214] The server generates a report detailing the selected generative artificial intelligence and its associated customization options, and notifies the user. Inputs include information on the selected AI model and customization elements. Output is a detailed report for the user, which includes user-inspired suggestions and selection criteria.

[0215] Step 6:

[0216] Users input their emotions as feedback into the system based on the provided report and send it to the server via their terminal. The input consists of text data of the user's impressions and evaluations. The server receives this and updates the database to improve the accuracy of future evaluations. The output is improved evaluation information. The feedback is used to improve the evaluation algorithm.

[0217] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0233] This invention is a system that collects evaluation information on generated artificial intelligence and automates the process of users selecting the most suitable artificial intelligence for their business operations.

[0234] The following describes the specific operational aspects of this system.

[0235] The server collects data on artificial intelligence, generated periodically from external and internal data sources. This data includes performance metrics, user reviews, and feedback. The collected data is stored in a database and formatted.

[0236] Users input their workflow and requirements for the artificial intelligence they want to generate through a user interface. This allows the server to specifically understand the user's needs. For example, a graphic designer user who wants to generate images for advertising can request an AI with high-quality image generation capabilities.

[0237] The server analyzes the collected data and quantifies the performance of each generated artificial intelligence. Machine learning algorithms are used for the analysis, which evaluates metrics such as response time, accuracy, and user satisfaction for each model.

[0238] Next, the server selects the optimal artificial intelligence to generate based on the user's requirements and analysis results. In this selection process, it filters models that meet the specific requirements for the user's work and identifies the most appropriate model based on weighted scores.

[0239] Once the selection is complete, the server automatically generates a report on the selected artificial intelligence to be generated. This report details the characteristics, benefits, and recommended settings of the selected model. The server delivers this report to the user via email or in-app notification.

[0240] Furthermore, the terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the artificial intelligence they used and send them to the server. This feedback is used as important data to improve the accuracy of selections in the future.

[0241] This system allows users to more effectively utilize AI that generates results tailored to their specific tasks.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server collects performance data, user reviews, and feedback related to artificial intelligence generated from various data sources. This data is collected and stored via external APIs, web scraping, and internal databases.

[0245] Step 2:

[0246] The server cleans and preprocesses the collected data. This includes imputing missing values, formatting, and removing outliers. The formatted data is then stored in the database as an evaluation dataset.

[0247] Step 3:

[0248] The server evaluates each artificial intelligence model it generates using a pre-configured machine learning algorithm. The evaluation is performed by quantifying multiple performance indicators, such as response time, output accuracy, and user satisfaction score.

[0249] Step 4:

[0250] Users input workflow information and requirements for the artificial intelligence to be generated through a dedicated interface. For example, by specifying that they need high-resolution image generation for graphic design work, they can communicate their specific needs to the server.

[0251] Step 5:

[0252] The server combines user requirements with evaluated data, performs filtering and weighting, and selects the optimal artificial intelligence to generate. If multiple candidates exist, the model that best matches the conditions is selected.

[0253] Step 6:

[0254] The server automatically generates a report detailing the selected artificial intelligence to be generated. This report includes model characteristics, performance evaluations, and recommended configuration options, providing comprehensive information for the user.

[0255] Step 7:

[0256] The server delivers the generated reports to users via email or in-app notifications. This allows users to receive the selection results and quickly move on to the next step.

[0257] Step 8:

[0258] The device provides an interface for receiving user feedback. Users input their actual user experience and suggestions for improvement, and then send the feedback to the server.

[0259] Step 9:

[0260] The server analyzes the collected feedback and uses it as training data for the algorithm. Based on the analysis results, it adjusts the parameters of the selection algorithm to improve accuracy in the next selection process.

[0261] (Example 1)

[0262] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] The aim is to effectively automate the performance evaluation and optimal selection process of generated information processing systems, enabling the rapid and accurate selection of information processing systems suitable for the user's business processes. In conventional information system selection processes, the collection and formatting of evaluation data, requirements identification, and utilization of feedback were all done manually, resulting in a time-consuming and laborious process with limited selection accuracy.

[0264] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0265] In this invention, the server includes means for collecting evaluation data related to the information processing system to be generated and formatting it into a standardized format; evaluation means for quantifying the performance of the information processing system to be generated based on the evaluation data; and means for receiving the user's work process and objectives and identifying requirements suitable therefor. This enables the rapid and accurate selection of the optimal generation system.

[0266] A "generating information processing system" is a system designed to automatically process information using specific algorithms and processes to provide added value.

[0267] "Evaluation data" refers to data necessary to show the value of an information processing system in numerical terms and indicators, including its performance and quality, as well as user feedback.

[0268] A "standardized format" is a format that converts information collected from different data sources into a consistent and unified format, making subsequent processing and analysis easier.

[0269] "Evaluation means for quantifying performance" refers to a method or apparatus for quantitatively measuring and expressing the characteristics and performance of an information processing system as numerical values, based on collected evaluation data.

[0270] A "business process" refers to a series of steps and operations necessary to perform a specific task, and is a process for achieving a specific objective.

[0271] "Means for identifying requirements" refers to a method or apparatus for clarifying the specifications and conditions of the required system based on the user's needs and business objectives, and for selecting an information processing system that meets those requirements.

[0272] This invention automates the selection and optimization of information processing systems. A server plays a central role in this system, periodically collecting evaluation data on the generated information system from external and internal sources. This evaluation data includes system performance indicators and user feedback, which are then formatted into a standardized format. Specifically, the server uses a database system such as MySQL to build an environment for managing and formatting the data.

[0273] Next, the server uses software frameworks such as TensorFlow and PyTorch to analyze this evaluation data and quantify the performance of each system. Based on this quantified data, the value of the information processing system is evaluated. This data is used when receiving the user's business objectives and process requirements.

[0274] Users input their business objectives and system requirements via their terminal. This is done using input forms in a web application. These forms are built on modern frameworks such as React.js and Angular, providing a user-friendly interface. As a concrete example, when searching for a model to generate catchy ad copy in advertising, the following prompt might be entered:

[0275] Prompt example:

[0276] "We're looking for an AI that can generate catchy advertising copy that resonates with consumers, in order to highlight the appeal of our new product. Please suggest options that are expected to be more effective than those from past campaigns."

[0277] Based on the input from this user and the analysis results of the quantified evaluation data, the server selects the optimal information processing system. It performs a process of filtering the most appropriate system using weighted scores. For the selected information system, a detailed report is automatically generated and notified to the user through protocols such as the SMTP protocol. The report includes the features of the selected system and recommended settings.

[0278] Through these steps, the user can introduce an information processing system suitable for their business in a short period and significantly improve the efficiency and accuracy of their business.

[0279] The flow of the specific process in Example 1 will be described using FIG. 11.

[0280] Step 1:

[0281] The server collects evaluation data regarding the AI model from external and internal information sources. It uses API calls as input to obtain the latest performance metrics from external data providers and extracts past user feedback from the internal database. Thereby, system performance metrics and user feedback are obtained as evaluation data. These data are first obtained in a format such as JSON and are formatted into a consistent format to facilitate subsequent processing.

[0282] Step 2:

[0283] The server formats the collected evaluation data into a standardized format and stores it in the database. As a specific example, a MySQL database is used, JSON-formatted data is converted to CSV format, and duplicates and missing values are checked and corrected. The input is JSON-formatted data, and the output is CSV-formatted and cleaned data. In this process of formatting and data cleansing, the consistency and accuracy of the data are ensured.

[0284] Step 3:

[0285] The user inputs the requirements for business purposes and the generative AI model through the user interface. The input form used is constructed with a front-end framework such as React.js and provides an input completion function to assist the user in entering an accurate prompt sentence. What is input are the business processes and requirements for the expected output results, which are sent to the server as requirement data.

[0286] Step 4:

[0287] The server analyzes the requirement data and the collected evaluation data and uses a machine learning framework to quantify the performance of the generative AI model. Specifically, TensorFlow is used to quantify the performance based on metrics such as the response time, accuracy, and user satisfaction of the AI model. The input is the formatted evaluation data and user requirements, and the output is the quantified model performance data.

[0288] Step 5:

[0289] The server selects the optimal generative AI model based on the quantified performance data and the user's requirements. Using a weighted scoring method, the model that best matches the user requirements is filtered to identify the optimal model. The input is the quantified model performance data and user requirements, and the output is the information of the selected AI model.

[0290] Step 6:

[0291] The server automatically generates a detailed report on the selected generative AI model and notifies the user. JasperReports is used to generate the report, which is sent as an email or in-application notification using the SMTP protocol. The input is the information of the selected AI model, and the output is the detailed report.

[0292] Step 7:

[0293] The terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the AI ​​model they used and send them to the server. The input consists of the user's evaluation and improvement suggestions, and the output is feedback data used to improve the accuracy of future selections.

[0294] (Application Example 1)

[0295] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0296] In automated control systems, current knowledge processing systems present challenges in selecting the optimal artificial intelligence model due to the complexity of the selection process and limited information available for performance evaluation. Furthermore, insufficient adjustments to suit user work procedures can hinder efficient operation. Moreover, the evaluation and selection process lacks the ability to dynamically adapt, resulting in an inability to keep pace with rapidly changing technological requirements and environmental shifts.

[0297] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0298] In this invention, the server includes means for collecting and formalizing evaluation information of the knowledge processing system to be generated; evaluation means for quantifying the performance of the knowledge processing system to be generated based on the evaluation information; means for receiving the user's work procedures and purpose of use and clarifying the requirements; and means for collecting data for optimizing the performance of various knowledge processing systems in an automatic control device and selecting the optimal knowledge processing system. As a result, the user can quickly and appropriately select the optimal knowledge processing system and perform efficient and safe automatic control.

[0299] A "generating knowledge processing system" is a means of information processing newly constructed using machine learning or artificial intelligence algorithms for a specific task.

[0300] "Evaluation information" refers to a collection of data and feedback gathered to determine the performance and usefulness of the knowledge processing system that generates the information.

[0301] "Evaluation methods for quantifying performance" refer to methods and devices for quantitatively analyzing the diverse characteristics of a knowledge processing system and expressing them in specific numerical values.

[0302] "User procedures" refer to a series of steps or processes taken to perform a specific task or job.

[0303] "Means for clarifying requirements" refer to processes and devices that specifically define the needs and goals of users and clarify the conditions necessary for a knowledge processing system.

[0304] "Means for selecting the optimal knowledge processing system" refers to the criteria and methods for selecting the knowledge processing system that best suits the user's purpose, based on collected evaluation information and clarified requirements.

[0305] An "automatic control system" is a general term for a device that includes hardware and software for controlling the operation of machines and systems without human intervention.

[0306] This invention is implemented as a system that automates the process of selecting the optimal knowledge processing system in an automatic control device. In this system, a server is central and provides the following functions.

[0307] First, the server collects evaluation information of the knowledge processing system generated from external and internal databases and uses this to perform performance evaluation. For the evaluation, past performance data stored in a database management system operating on Amazon Web Services (AWS) and feedback from users are utilized. This data is analyzed by a program using Python, and the performance is quantified by a machine learning algorithm. It is standard to use Scikit-learn for the machine learning library to be used and Pandas and NumPy for data preprocessing.

[0308] Next, through the user interface from the terminal, the user's work procedures and purposes of use are input. This input information is concretized into necessary requirements by the server and utilized as a criterion for selecting the optimal knowledge processing system. Detailed information about the selected system is included in an automatically generated report, and the user can receive reasons for selection and setting proposals through this report. This report is sent through in-application notifications or emails.

[0309] Feedback from the user is input directly on the terminal and sent to the server to improve the selection process for subsequent times. As a result, the evaluation algorithm is continuously updated, enabling more accurate selection.

[0310] For example, in an urban area where traffic congestion frequently occurs, a knowledge processing system that selects the optimal route in real time and improves energy efficiency is selected. As a prompt sentence for realizing this, a format such as "Please teach me how to select an AI model capable of precise urban environment interpretation in an autonomous vehicle." is used.

[0311] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0312] Step 1:

[0313] The server collects evaluation information for the knowledge processing system generated from external and internal databases. Database queries are used as input, and historical performance data and user feedback obtained through these queries are output. Specifically, it accesses the Amazon Web Services (AWS) database and executes SQL queries based on a regular schedule.

[0314] Step 2:

[0315] The server preprocesses the collected information using a Python program. The input is the raw data obtained in step 1, and the output is data formatted into a parseable format. Specifically, it uses the Pandas library to clean the data (imputing missing values, normalizing data types).

[0316] Step 3:

[0317] The server analyzes the preprocessed data using the Scikit-learn library and quantifies the performance of the knowledge processing systems. The input is the data formatted in step 2, and the output is the quantified performance indicators for each system. Specifically, it builds a machine learning model, uses it to analyze the data, and generates an evaluation score for each knowledge processing system.

[0318] Step 4:

[0319] Users input work procedures and usage purposes through a terminal. This input includes business workflows and desired performance requirements entered into the user interface, and this information is stored in a database. Specifically, users select options on the user interface and press input buttons to send the information to the server.

[0320] Step 5:

[0321] The server compares user input information with quantified performance metrics to select the optimal knowledge processing system. The input is the output from steps 3 and 4, and the output is the specifications of the system considered optimal. Specifically, it performs scoring using an algorithm and selects the one with the highest degree of fit.

[0322] Step 6:

[0323] The server automatically generates a report based on the selection results and notifies the user. The input is the output from step 5, and the output is the report document. Specifically, it uses a template engine to assemble the report and sends it via email or a terminal application.

[0324] Step 7:

[0325] Users provide feedback via their device after use. This feedback consists of evaluations and suggestions for improvement based on their experience, and is recorded in a database. Specifically, data is collected when users fill out a feedback form and press the submit button.

[0326] Step 8:

[0327] The server analyzes the collected feedback and uses it as data to improve the accuracy of future selection processes. The input is the feedback data from step 7, and the output is the improved evaluation algorithm. The specific operation includes a process of adjusting the model based on negative feedback to improve the algorithm's performance.

[0328] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0329] This invention is a system that enables the selection of more appropriate artificial intelligence by incorporating user emotional information into the selection and evaluation process of the artificial intelligence to be generated. A specific embodiment thereof is shown below.

[0330] The server first collects, formats, and compiles performance evaluation data and user reviews related to artificial intelligence generated using conventional methods. This data is stored in a database and used for evaluation. The server's role is to quantify the performance of each artificial intelligence model based on this data and conduct evaluations.

[0331] Next, the server is equipped with an emotion engine that recognizes user emotion data in real time through the terminal. This system detects emotions from webcam video analysis, the user's facial expressions in response to input, tone of voice, or writing patterns.

[0332] The user inputs the workflow and the functions and performance they require from the artificial intelligence into the terminal interface. During this process, the server uses an emotion engine to collect changes in the user's emotions as they input. This emotional information can be used to identify and record emotions, particularly those relevant to evaluation.

[0333] In the selection process, the server integrates pre-collected emotional information with other business requirements and uses it to determine the suitability of the artificial intelligence to be generated. For example, if a user shows interest in a model setting and expresses positive emotions, an artificial intelligence specifically tailored to that setting will be presented.

[0334] Once the selection is complete, the server generates a report containing selection results that reflect emotional information, as well as details about the artificial intelligence. This report includes customization options based on the user's emotional state and is provided to the user in a timely manner via email or in-app notifications.

[0335] Finally, the device receives emotional feedback from the user again and sends it to the server. The server analyzes the emotional data obtained along with the feedback and uses it to improve the selection algorithm and the functionality of the emotion engine. This further improves the accuracy of selections in subsequent attempts.

[0336] In this way, this invention, which combines an emotion engine, goes beyond conventional performance and requirements-centric model selection and enables more sophisticated AI generation selection that takes into account the user's psychological state.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The server collects performance evaluation information about artificial intelligence generated from external data sources and past feedback. This may involve using API access or scraping techniques. The collected data is stored in a database and prepared for evaluation.

[0340] Step 2:

[0341] The emotion engine installed on the server collects real-time emotional data from users through their devices. It analyzes the user's facial expressions using a camera and analyzes their voice tone and patterns to determine their emotions. This data is processed within the emotion engine, and information about the user's psychological state is generated.

[0342] Step 3:

[0343] The user inputs their workflow and the functions and performance requirements they expect from the generated artificial intelligence into the terminal interface. During input, the emotion engine captures changes in the user's emotions and sends them to the server as emotion data.

[0344] Step 4:

[0345] The server integrates collected business requirements and sentiment data, along with pre-collected evaluation information for generating artificial intelligence, to select the most suitable AI. In particular, it focuses on AI that corresponds to settings and functions in which the user has expressed positive emotions.

[0346] Step 5:

[0347] After the selection is complete, the server automatically generates a detailed report on the artificial intelligence to be produced. This report includes the performance, benefits, and customization options of the selected AI. The report is provided to the user via email or in-app notification.

[0348] Step 6:

[0349] The device provides an interface for receiving emotionally charged feedback from users. Users input feedback, including their experience using the generated artificial intelligence and areas for improvement, and send it to the server along with emotional data.

[0350] Step 7:

[0351] The server analyzes feedback and sentiment data to improve the accuracy of the sentiment engine and selection algorithms. The analysis results are used in subsequent selection processes, continuously improving the overall system performance.

[0352] (Example 2)

[0353] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0354] Conventional AI selection systems only evaluate performance and specifications, which means they cannot consider user emotions or psychological aspects. This can lead to the selection of AI that lacks intuitive satisfaction or suitability from the user's perspective. It is necessary to address these challenges and achieve AI selection that is more optimized for the user.

[0355] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0356] In this invention, the server includes means for collecting evaluation information and emotional data of the artificial intelligence to be generated and formalizing them; evaluation means for quantifying the performance of the artificial intelligence to be generated based on the evaluation information and emotional data; and means for receiving the user's work procedures and purpose of use, clarifying the requirements, and associating emotional information. This makes it possible to select an artificial intelligence that takes into account the user's emotions and psychological aspects, resulting in a higher level of satisfaction.

[0357] "Generative artificial intelligence" refers to a program with human-like intelligence that has been newly modeled using technologies such as machine learning and deep learning.

[0358] "Evaluation information" refers to a collection of numerical and evaluative data regarding the performance and functionality of the artificial intelligence being generated, and is used as an indicator for selection and improvement.

[0359] "Emotional data" refers to psychological and emotional information collected through the user's facial expressions, tone of voice, input patterns, etc., and is data that reflects the user's inner state.

[0360] "Requirements" refer to specific functional and performance conditions that users desire from the artificial intelligence they generate, representing technical needs that take into account the intended use and workflow.

[0361] "Evaluation methods" refer to a system that quantifies and analyzes the performance of the artificial intelligence to be generated based on collected evaluation information and sentiment data, and then performs evaluations for selection purposes.

[0362] A "report" is a document that summarizes detailed information and analysis results regarding the selected artificial intelligence that will be generated, and is used as an information transmission medium as one of the means of notifying users.

[0363] "Feedback" refers to opinions, including evaluations, impressions, and sentiment data, provided by users after using artificial intelligence they have generated. This information is collected for the purpose of improving future development and selection processes.

[0364] This invention is a system that achieves more appropriate selection by incorporating user emotional information into the process of selecting the artificial intelligence to be generated. An embodiment thereof is shown below.

[0365] The server first collects performance evaluation data and user reviews of the generated AI models and stores them in a database. The hardware used here includes a high-performance database server, and the software used is a database management system. Subsequently, this data is formalized and evaluated numerically.

[0366] The device plays a role in collecting real-time emotional data from the user. It uses a webcam and microphone to perform facial expression analysis and voice tone analysis. The emotion engine is specialized software that analyzes the data collected from these devices and evaluates the user's emotional state.

[0367] The user inputs the desired workflow and performance requirements for the artificial intelligence model into the terminal interface. For example, the user might input "AI model that prioritizes emotion understanding" into the input field. An example of a prompt message used in this case would be, "Please select an AI model that understands emotions. Settings corresponding to specific emotions will be given priority."

[0368] The server combines user input and sentiment data to select the optimal generative AI model. This selection result is automatically generated as a report and sent to the user via email or in-app notifications.

[0369] Ultimately, the device receives user feedback and sends it to the server along with the collected sentiment data. The server analyzes this information and uses it to improve future selection algorithms and sentiment engines, further enhancing the accuracy of future selections.

[0370] This embodiment makes it possible to select artificial intelligence that takes into account the user's emotional state, thereby realizing a more user-friendly system.

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1:

[0373] The server collects evaluation information and user reviews related to the generated AI model. Input includes information from databases and online resources. This information is analyzed and stored in the database as formalized data. The output is a formatted dataset containing evaluation scores. Specifically, the server uses a data extraction algorithm to extract and format the necessary data from various sources.

[0374] Step 2:

[0375] The device collects user emotion data in real time. The primary inputs are webcam video and microphone audio data. The emotion engine analyzes this input data and represents the user's emotional state using numbers and tags. The final output is a dataset of emotion analysis results. In this process, facial recognition software and voice analysis programs work in conjunction with emotion detection algorithms.

[0376] Step 3:

[0377] The user inputs the desired functions and performance requirements for the artificial intelligence model into the terminal interface. This input data is presented as specific questions and options based on the business flow and specifications. From this input, the server clarifies the user's requirements and structures the necessary data. The output is a dataset serving as a requirements definition document. The operation includes a process of transferring the data input via the user interface to the server.

[0378] Step 4:

[0379] The server integrates collected evaluation information, sentiment data, and user requirements to select the optimal generative AI model. The input includes all datasets collected in the previous step. The server uses an evaluation algorithm to select candidate models and compiles the selection results. The output is the selected generative AI model and its evaluation results. Specific operations include data analysis and model comparison algorithms.

[0380] Step 5:

[0381] The server generates a report based on the selection results and notifies the user via the terminal. The input for this step is information about the selected AI model and its evaluation. The output is sent to the user as a detailed evaluation report. In terms of operation, document generation software is used to compile the selection results into a report and provide it to the user via email or in-app message.

[0382] Step 6:

[0383] The terminal collects user feedback and sentiment data again and sends it to the server. Feedback input includes user ratings, impressions, and post-use sentiment data. This is analyzed and saved as a dataset for improving the next selection algorithm. The output is elemental data for improving the next generation algorithm. The specific operation includes the process of aggregating user responses via the feedback form and returning them to the server.

[0384] (Application Example 2)

[0385] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0386] In the selection process for generative artificial intelligence that takes into account the individual emotional states of users, conventional performance evaluation and requirements-centric methods lack adaptability to individual needs. In particular, there is a need for technology that selects the optimal generative artificial intelligence according to the user's psychological state and provides services based on it.

[0387] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0388] In this invention, the server includes means for collecting and formalizing evaluation information of the artificial intelligence to be generated, evaluation means for quantifying performance based on the evaluation information, and means for receiving the user's workflow and purpose of use and clarifying the requirements. It also includes means for analyzing the emotional state and selecting the artificial intelligence to be generated based on the emotional information, and means for collecting feedback from the user to improve the accuracy of evaluations in the future. This makes it possible to select a personalized artificial intelligence to be generated based on the user's emotional state and to provide an optimized service.

[0389] "Generative artificial intelligence" is artificial intelligence that is dynamically generated in response to user requests and optimized to perform specific tasks.

[0390] "Evaluation information" refers to data collected based on the performance of the generated artificial intelligence and user feedback, and serves as the basis for judging the appropriateness of the artificial intelligence.

[0391] "Emotional information" refers to data acquired to analyze a user's psychological state, and it quantitatively represents the user's emotions.

[0392] The "selection process" is the procedure for choosing the optimal generative artificial intelligence based on evaluation information and emotional information.

[0393] Personalization refers to adjusting services and features to suit the individual user's characteristics, needs, and emotional state.

[0394] "Feedback" refers to the opinions and impressions provided by users after using the product, and is data used to evaluate and improve the AI ​​that generates future products.

[0395] This invention provides a system in which a server plays a central role in optimally selecting and customizing generated artificial intelligence using data from users and terminals.

[0396] The server first collects AI performance evaluation information and user feedback information, and stores this in a database. This database includes evaluation information such as past AI model usage results, user reviews, and performance data, which are then formatted using data analysis tools such as Microsoft Azure and Google Cloud.

[0397] Next, the server utilizes an emotion analysis engine to analyze the user's emotional data in real time through the terminal. This emotional data is obtained by analyzing the user's voice input and facial expression data, and existing emotion analysis APIs (for example, Microsoft Azure Emotion API) are used for this analysis.

[0398] When a user inputs their workflow and purpose of use through the terminal interface, the server clarifies the requirements based on this information and integrates it with emotional information. Emotional information is particularly used in the selection and recommendation process of a customized AI model that reflects the user's psychological state. For example, if the user is seeking relaxation, the system will recommend music or content appropriate for relaxation using AI.

[0399] Ultimately, a specific AI model desired by the user is selected, and this information is communicated to the user in a report. The report includes performance metrics for the selected AI and customization options tailored to the user's emotional state. Based on this information, the user can then utilize artificial intelligence in various digital services.

[0400] This process enables the use of personalized AI models that adapt to the user's emotions. An example of a specific prompt would be, "Please recommend the best music content for when the user is in a relaxed state."

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The server collects performance evaluation information for generated artificial intelligence from various data sources and stores it in a database. Inputs include past usage data, user reviews, and performance metrics. Outputs are standardized evaluation data. During this process, data analysis tools are used to format the collected data, making it suitable for efficient searching and analysis.

[0404] Step 2:

[0405] The server uses an emotion analysis engine to process real-time user emotion data collected via the terminal. Inputs include user voice and facial expression data. Outputs include a report that quantifies the user's emotional state. Specifically, it uses voice tone analysis and image analysis techniques to identify the user's psychological state.

[0406] Step 3:

[0407] The terminal allows users to input their workflow and purpose of use through an interface, and sends this data to the server. The input includes text information related to the user's purpose. The server uses this information to clarify user requirements. The clarified requirements information is then provided to the system as output.

[0408] Step 4:

[0409] The server integrates clarified user requirements and sentiment information to initiate a process of selecting the optimal generative artificial intelligence. The input consists of user requirements and sentiment information. The output is the identification of the AI ​​model that best suits the user's needs. Machine learning algorithms are used to score the suitability of existing models in the AI ​​model selection process.

[0410] Step 5:

[0411] The server generates a report detailing the selected generative artificial intelligence and its associated customization options, and notifies the user. Inputs include information on the selected AI model and customization elements. Output is a detailed report for the user, which includes user-inspired suggestions and selection criteria.

[0412] Step 6:

[0413] Users input their emotions as feedback into the system based on the provided report and send it to the server via their terminal. The input consists of text data of the user's impressions and evaluations. The server receives this and updates the database to improve the accuracy of future evaluations. The output is improved evaluation information. The feedback is used to improve the evaluation algorithm.

[0414] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0415] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0416] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0417] [Third Embodiment]

[0418] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0419] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0420] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0421] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0422] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0423] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0424] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0425] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0426] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0427] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0428] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0429] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0430] This invention is a system that collects evaluation information on generated artificial intelligence and automates the process of users selecting the most suitable artificial intelligence for their business operations.

[0431] The following describes the specific operational aspects of this system.

[0432] The server collects data on artificial intelligence, generated periodically from external and internal data sources. This data includes performance metrics, user reviews, and feedback. The collected data is stored in a database and formatted.

[0433] Users input their workflow and requirements for the artificial intelligence they want to generate through a user interface. This allows the server to specifically understand the user's needs. For example, a graphic designer user who wants to generate images for advertising can request an AI with high-quality image generation capabilities.

[0434] The server analyzes the collected data and quantifies the performance of each generated artificial intelligence. Machine learning algorithms are used for the analysis, which evaluates metrics such as response time, accuracy, and user satisfaction for each model.

[0435] Next, the server selects the optimal artificial intelligence to generate based on the user's requirements and analysis results. In this selection process, it filters models that meet the specific requirements for the user's work and identifies the most appropriate model based on weighted scores.

[0436] Once the selection is complete, the server automatically generates a report on the selected artificial intelligence to be generated. This report details the characteristics, benefits, and recommended settings of the selected model. The server delivers this report to the user via email or in-app notification.

[0437] Furthermore, the terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the artificial intelligence they used and send them to the server. This feedback is used as important data to improve the accuracy of selections in the future.

[0438] This system allows users to more effectively utilize AI that generates results tailored to their specific tasks.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The server collects performance data, user reviews, and feedback related to artificial intelligence generated from various data sources. This data is collected and stored via external APIs, web scraping, and internal databases.

[0442] Step 2:

[0443] The server cleans and preprocesses the collected data. This includes imputing missing values, formatting, and removing outliers. The formatted data is then stored in the database as an evaluation dataset.

[0444] Step 3:

[0445] The server evaluates each artificial intelligence model it generates using a pre-configured machine learning algorithm. The evaluation is performed by quantifying multiple performance indicators, such as response time, output accuracy, and user satisfaction score.

[0446] Step 4:

[0447] Users input workflow information and requirements for the artificial intelligence to be generated through a dedicated interface. For example, by specifying that they need high-resolution image generation for graphic design work, they can communicate their specific needs to the server.

[0448] Step 5:

[0449] The server combines user requirements with evaluated data, performs filtering and weighting, and selects the optimal artificial intelligence to generate. If multiple candidates exist, the model that best matches the conditions is selected.

[0450] Step 6:

[0451] The server automatically generates a report detailing the selected artificial intelligence to be generated. This report includes model characteristics, performance evaluations, and recommended configuration options, providing comprehensive information for the user.

[0452] Step 7:

[0453] The server delivers the generated reports to users via email or in-app notifications. This allows users to receive the selection results and quickly move on to the next step.

[0454] Step 8:

[0455] The device provides an interface for receiving user feedback. Users input their actual user experience and suggestions for improvement, and then send the feedback to the server.

[0456] Step 9:

[0457] The server analyzes the collected feedback and uses it as training data for the algorithm. Based on the analysis results, it adjusts the parameters of the selection algorithm to improve accuracy in the next selection process.

[0458] (Example 1)

[0459] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0460] The aim is to effectively automate the performance evaluation and optimal selection process of generated information processing systems, enabling the rapid and accurate selection of information processing systems suitable for the user's business processes. In conventional information system selection processes, the collection and formatting of evaluation data, requirements identification, and utilization of feedback were all done manually, resulting in a time-consuming and laborious process with limited selection accuracy.

[0461] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0462] In this invention, the server includes means for collecting evaluation data related to the information processing system to be generated and formatting it into a standardized format; evaluation means for quantifying the performance of the information processing system to be generated based on the evaluation data; and means for receiving the user's work process and objectives and identifying requirements suitable therefor. This enables the rapid and accurate selection of the optimal generation system.

[0463] A "generating information processing system" is a system designed to automatically process information using specific algorithms and processes to provide added value.

[0464] "Evaluation data" refers to data necessary to show the value of an information processing system in numerical terms and indicators, including its performance and quality, as well as user feedback.

[0465] A "standardized format" is a format that converts information collected from different data sources into a consistent and unified format, making subsequent processing and analysis easier.

[0466] "Evaluation means for quantifying performance" refers to a method or apparatus for quantitatively measuring and expressing the characteristics and performance of an information processing system as numerical values, based on collected evaluation data.

[0467] A "business process" refers to a series of steps and operations necessary to perform a specific task, and is a process for achieving a specific objective.

[0468] "Means for identifying requirements" refers to a method or apparatus for clarifying the specifications and conditions of the required system based on the user's needs and business objectives, and for selecting an information processing system that meets those requirements.

[0469] This invention automates the selection and optimization of information processing systems. A server plays a central role in this system, periodically collecting evaluation data on the generated information system from external and internal sources. This evaluation data includes system performance indicators and user feedback, which are then formatted into a standardized format. Specifically, the server uses a database system such as MySQL to build an environment for managing and formatting the data.

[0470] Next, the server uses software frameworks such as TensorFlow and PyTorch to analyze this evaluation data and quantify the performance of each system. Based on this quantified data, the value of the information processing system is evaluated. This data is used when receiving the user's business objectives and process requirements.

[0471] Users input their business objectives and system requirements via their terminal. This is done using input forms in a web application. These forms are built on modern frameworks such as React.js and Angular, providing a user-friendly interface. As a concrete example, when searching for a model to generate catchy ad copy in advertising, the following prompt might be entered:

[0472] Prompt example:

[0473] "We're looking for an AI that can generate catchy advertising copy that resonates with consumers, in order to highlight the appeal of our new product. Please suggest options that are expected to be more effective than those from past campaigns."

[0474] The server selects the optimal information processing system based on the user input and the analysis results of the quantified evaluation data. It uses weighted scores to filter out the most suitable system. A detailed report is automatically generated for the selected information system and notified to the user via the SMTP protocol, etc. The report includes the characteristics and recommended settings of the selected system.

[0475] These processes enable users to quickly implement information processing systems suited to their work, significantly improving efficiency and accuracy.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The server collects evaluation data on the generated AI model from external and internal sources. It uses API calls to retrieve the latest performance metrics from external data providers and extracts historical user feedback from an internal database. This provides system performance metrics and user feedback as evaluation data. This data is initially retrieved in formats such as JSON and then formatted into a consistent format to facilitate subsequent processing.

[0479] Step 2:

[0480] The server formats the collected evaluation data into a standardized format and stores it in a database. Specifically, it uses a MySQL database to convert JSON data to CSV format, and checks for and corrects duplicates and missing data. The input is JSON data, and the output is formatted CSV data. This formatting and data cleansing process ensures data consistency and accuracy.

[0481] Step 3:

[0482] Users input their business objectives and requirements for the generated AI model through a user interface. The input forms used are built with front-end frameworks such as React.js and provide input completion features to help users enter accurate prompts. The input consists of business processes and requirements for expected output results, which are then sent to the server as requirement data.

[0483] Step 4:

[0484] The server analyzes requirements data and collected evaluation data, and uses a machine learning framework to quantify the performance of the generated AI model. Specifically, it uses TensorFlow to quantify the performance based on metrics such as AI model response time, accuracy, and user satisfaction. The input is formatted evaluation data and user requirements, and the output is quantified model performance data.

[0485] Step 5:

[0486] The server selects the optimal generative AI model based on quantified performance data and user requirements. Using a weighted scoring method, it filters the model that best fits the user requirements, identifying the optimal model. The input is quantified model performance data and user requirements, and the output is information about the selected AI model.

[0487] Step 6:

[0488] The server automatically generates a detailed report on the selected generative AI model and notifies the user. The report is generated using JasperReports and sent via email or in-application notification using the SMTP protocol. The input is information about the selected AI model, and the output is a detailed report.

[0489] Step 7:

[0490] The terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the AI ​​model they used and send them to the server. The input consists of the user's evaluation and improvement suggestions, and the output is feedback data used to improve the accuracy of future selections.

[0491] (Application Example 1)

[0492] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0493] In automated control systems, current knowledge processing systems present challenges in selecting the optimal artificial intelligence model due to the complexity of the selection process and limited information available for performance evaluation. Furthermore, insufficient adjustments to suit user work procedures can hinder efficient operation. Moreover, the evaluation and selection process lacks the ability to dynamically adapt, resulting in an inability to keep pace with rapidly changing technological requirements and environmental shifts.

[0494] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0495] In this invention, the server includes means for collecting and formalizing evaluation information of the knowledge processing system to be generated; evaluation means for quantifying the performance of the knowledge processing system to be generated based on the evaluation information; means for receiving the user's work procedures and purpose of use and clarifying the requirements; and means for collecting data for optimizing the performance of various knowledge processing systems in an automatic control device and selecting the optimal knowledge processing system. As a result, the user can quickly and appropriately select the optimal knowledge processing system and perform efficient and safe automatic control.

[0496] A "generating knowledge processing system" is a means of information processing newly constructed using machine learning or artificial intelligence algorithms for a specific task.

[0497] "Evaluation information" refers to a collection of data and feedback gathered to determine the performance and usefulness of the knowledge processing system that generates the information.

[0498] "Evaluation methods for quantifying performance" refer to methods and devices for quantitatively analyzing the diverse characteristics of a knowledge processing system and expressing them in specific numerical values.

[0499] "User procedures" refer to a series of steps or processes taken to perform a specific task or job.

[0500] "Means for clarifying requirements" refer to processes and devices that specifically define the needs and goals of users and clarify the conditions necessary for a knowledge processing system.

[0501] "Means for selecting the optimal knowledge processing system" refers to the criteria and methods for selecting the knowledge processing system that best suits the user's purpose, based on collected evaluation information and clarified requirements.

[0502] An "automatic control system" is a general term for a device that includes hardware and software for controlling the operation of machines and systems without human intervention.

[0503] This invention is implemented as a system that automates the process of selecting the optimal knowledge processing system in an automatic control device. In this system, a server is central and provides the following functions.

[0504] First, the server collects evaluation information for the knowledge processing system generated from external and internal databases, and uses this information to perform performance evaluations. The evaluation utilizes historical performance data and user feedback stored in a database management system running on Amazon Web Services (AWS). This data is analyzed using a Python program, and performance is quantified using machine learning algorithms. Scikit-learn is the standard machine learning library used, and Pandas and NumPy are typically used for data preprocessing.

[0505] Next, the user's work procedures and purpose of use are entered through the user interface on the terminal. This input information is then condensed by the server into the necessary requirements and used as a criterion for selecting the optimal knowledge processing system. Detailed information about the selected system is included in an automatically generated report, through which the user can receive the reasons for the selection and configuration suggestions. This report is sent via in-app notification or email.

[0506] User feedback is entered directly on the device and sent to the server to improve the selection process for future use. This allows the evaluation algorithm to be continuously updated, enabling more accurate selections.

[0507] For example, in urban areas where traffic congestion is frequent, a knowledge processing system that selects the optimal route in real time and improves energy efficiency is chosen. To achieve this, a prompt in the form of "Please tell me how to select an AI model capable of precise urban environment interpretation in an autonomous vehicle" is used.

[0508] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0509] Step 1:

[0510] The server collects evaluation information for the knowledge processing system generated from external and internal databases. Database queries are used as input, and historical performance data and user feedback obtained through these queries are output. Specifically, it accesses the Amazon Web Services (AWS) database and executes SQL queries based on a regular schedule.

[0511] Step 2:

[0512] The server preprocesses the collected information using a Python program. The input is the raw data obtained in step 1, and the output is data formatted into a parseable format. Specifically, it uses the Pandas library to clean the data (imputing missing values, normalizing data types).

[0513] Step 3:

[0514] The server analyzes the preprocessed data using the Scikit-learn library and quantifies the performance of the knowledge processing systems. The input is the data formatted in step 2, and the output is the quantified performance indicators for each system. Specifically, it builds a machine learning model, uses it to analyze the data, and generates an evaluation score for each knowledge processing system.

[0515] Step 4:

[0516] Users input work procedures and usage purposes through a terminal. This input includes business workflows and desired performance requirements entered into the user interface, and this information is stored in a database. Specifically, users select options on the user interface and press input buttons to send the information to the server.

[0517] Step 5:

[0518] The server compares user input information with quantified performance metrics to select the optimal knowledge processing system. The input is the output from steps 3 and 4, and the output is the specifications of the system considered optimal. Specifically, it performs scoring using an algorithm and selects the one with the highest degree of fit.

[0519] Step 6:

[0520] The server automatically generates a report based on the selection results and notifies the user. The input is the output from step 5, and the output is the report document. Specifically, it uses a template engine to assemble the report and sends it via email or a terminal application.

[0521] Step 7:

[0522] Users provide feedback via their device after use. This feedback consists of evaluations and suggestions for improvement based on their experience, and is recorded in a database. Specifically, data is collected when users fill out a feedback form and press the submit button.

[0523] Step 8:

[0524] The server analyzes the collected feedback and uses it as data to improve the accuracy of future selection processes. The input is the feedback data from step 7, and the output is the improved evaluation algorithm. The specific operation includes a process of adjusting the model based on negative feedback to improve the algorithm's performance.

[0525] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0526] This invention is a system that enables the selection of more appropriate artificial intelligence by incorporating user emotional information into the selection and evaluation process of the artificial intelligence to be generated. A specific embodiment thereof is shown below.

[0527] The server first collects, formats, and compiles performance evaluation data and user reviews related to artificial intelligence generated using conventional methods. This data is stored in a database and used for evaluation. The server's role is to quantify the performance of each artificial intelligence model based on this data and conduct evaluations.

[0528] Next, the server is equipped with an emotion engine that recognizes user emotion data in real time through the terminal. This system detects emotions from webcam video analysis, the user's facial expressions in response to input, tone of voice, or writing patterns.

[0529] The user inputs the workflow and the functions and performance they require from the artificial intelligence into the terminal interface. During this process, the server uses an emotion engine to collect changes in the user's emotions as they input. This emotional information can be used to identify and record emotions, particularly those relevant to evaluation.

[0530] In the selection process, the server integrates pre-collected emotional information with other business requirements and uses it to determine the suitability of the artificial intelligence to be generated. For example, if a user shows interest in a model setting and expresses positive emotions, an artificial intelligence specifically tailored to that setting will be presented.

[0531] Once the selection is complete, the server generates a report containing selection results that reflect emotional information, as well as details about the artificial intelligence. This report includes customization options based on the user's emotional state and is provided to the user in a timely manner via email or in-app notifications.

[0532] Finally, the device receives emotional feedback from the user again and sends it to the server. The server analyzes the emotional data obtained along with the feedback and uses it to improve the selection algorithm and the functionality of the emotion engine. This further improves the accuracy of selections in subsequent attempts.

[0533] In this way, this invention, which combines an emotion engine, goes beyond conventional performance and requirements-centric model selection and enables more sophisticated AI generation selection that takes into account the user's psychological state.

[0534] The following describes the processing flow.

[0535] Step 1:

[0536] The server collects performance evaluation information about artificial intelligence generated from external data sources and past feedback. This may involve using API access or scraping techniques. The collected data is stored in a database and prepared for evaluation.

[0537] Step 2:

[0538] The emotion engine installed on the server collects real-time emotional data from users through their devices. It analyzes the user's facial expressions using a camera and analyzes their voice tone and patterns to determine their emotions. This data is processed within the emotion engine, and information about the user's psychological state is generated.

[0539] Step 3:

[0540] The user inputs their workflow and the functions and performance requirements they expect from the generated artificial intelligence into the terminal interface. During input, the emotion engine captures changes in the user's emotions and sends them to the server as emotion data.

[0541] Step 4:

[0542] The server integrates collected business requirements and sentiment data, along with pre-collected evaluation information for generating artificial intelligence, to select the most suitable AI. In particular, it focuses on AI that corresponds to settings and functions in which the user has expressed positive emotions.

[0543] Step 5:

[0544] After the selection is complete, the server automatically generates a detailed report on the artificial intelligence to be produced. This report includes the performance, benefits, and customization options of the selected AI. The report is provided to the user via email or in-app notification.

[0545] Step 6:

[0546] The device provides an interface for receiving emotionally charged feedback from users. Users input feedback, including their experience using the generated artificial intelligence and areas for improvement, and send it to the server along with emotional data.

[0547] Step 7:

[0548] The server analyzes feedback and sentiment data to improve the accuracy of the sentiment engine and selection algorithms. The analysis results are used in subsequent selection processes, continuously improving the overall system performance.

[0549] (Example 2)

[0550] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] Conventional AI selection systems only evaluate performance and specifications, which means they cannot consider user emotions or psychological aspects. This can lead to the selection of AI that lacks intuitive satisfaction or suitability from the user's perspective. It is necessary to address these challenges and achieve AI selection that is more optimized for the user.

[0552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0553] In this invention, the server includes means for collecting evaluation information and emotional data of the artificial intelligence to be generated and formalizing them; evaluation means for quantifying the performance of the artificial intelligence to be generated based on the evaluation information and emotional data; and means for receiving the user's work procedures and purpose of use, clarifying the requirements, and associating emotional information. This makes it possible to select an artificial intelligence that takes into account the user's emotions and psychological aspects, resulting in a higher level of satisfaction.

[0554] "Generative artificial intelligence" refers to a program with human-like intelligence that has been newly modeled using technologies such as machine learning and deep learning.

[0555] "Evaluation information" refers to a collection of numerical and evaluative data regarding the performance and functionality of the artificial intelligence being generated, and is used as an indicator for selection and improvement.

[0556] "Emotional data" refers to psychological and emotional information collected through the user's facial expressions, tone of voice, input patterns, etc., and is data that reflects the user's inner state.

[0557] "Requirements" refer to specific functional and performance conditions that users desire from the artificial intelligence they generate, representing technical needs that take into account the intended use and workflow.

[0558] "Evaluation methods" refer to a system that quantifies and analyzes the performance of the artificial intelligence to be generated based on collected evaluation information and sentiment data, and then performs evaluations for selection purposes.

[0559] A "report" is a document that summarizes detailed information and analysis results regarding the selected artificial intelligence that will be generated, and is used as an information transmission medium as one of the means of notifying users.

[0560] "Feedback" refers to opinions, including evaluations, impressions, and sentiment data, provided by users after using artificial intelligence they have generated. This information is collected for the purpose of improving future development and selection processes.

[0561] This invention is a system that achieves more appropriate selection by incorporating user emotional information into the process of selecting the artificial intelligence to be generated. An embodiment thereof is shown below.

[0562] The server first collects performance evaluation data and user reviews of the generated AI models and stores them in a database. The hardware used here includes a high-performance database server, and the software used is a database management system. Subsequently, this data is formalized and evaluated numerically.

[0563] The device plays a role in collecting real-time emotional data from the user. It uses a webcam and microphone to perform facial expression analysis and voice tone analysis. The emotion engine is specialized software that analyzes the data collected from these devices and evaluates the user's emotional state.

[0564] The user inputs the desired workflow and performance requirements for the artificial intelligence model into the terminal interface. For example, the user might input "AI model that prioritizes emotion understanding" into the input field. An example of a prompt message used in this case would be, "Please select an AI model that understands emotions. Settings corresponding to specific emotions will be given priority."

[0565] The server combines user input and sentiment data to select the optimal generative AI model. This selection result is automatically generated as a report and sent to the user via email or in-app notifications.

[0566] Ultimately, the device receives user feedback and sends it to the server along with the collected sentiment data. The server analyzes this information and uses it to improve future selection algorithms and sentiment engines, further enhancing the accuracy of future selections.

[0567] This embodiment makes it possible to select artificial intelligence that takes into account the user's emotional state, thereby realizing a more user-friendly system.

[0568] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0569] Step 1:

[0570] The server collects evaluation information and user reviews related to the generated AI model. Input includes information from databases and online resources. This information is analyzed and stored in the database as formalized data. The output is a formatted dataset containing evaluation scores. Specifically, the server uses a data extraction algorithm to extract and format the necessary data from various sources.

[0571] Step 2:

[0572] The device collects user emotion data in real time. The primary inputs are webcam video and microphone audio data. The emotion engine analyzes this input data and represents the user's emotional state using numbers and tags. The final output is a dataset of emotion analysis results. In this process, facial recognition software and voice analysis programs work in conjunction with emotion detection algorithms.

[0573] Step 3:

[0574] The user inputs the desired functions and performance requirements for the artificial intelligence model into the terminal interface. This input data is presented as specific questions and options based on the business flow and specifications. From this input, the server clarifies the user's requirements and structures the necessary data. The output is a dataset serving as a requirements definition document. The operation includes a process of transferring the data input via the user interface to the server.

[0575] Step 4:

[0576] The server integrates collected evaluation information, sentiment data, and user requirements to select the optimal generative AI model. The input includes all datasets collected in the previous step. The server uses an evaluation algorithm to select candidate models and compiles the selection results. The output is the selected generative AI model and its evaluation results. Specific operations include data analysis and model comparison algorithms.

[0577] Step 5:

[0578] The server generates a report based on the selection results and notifies the user via the terminal. The input for this step is information about the selected AI model and its evaluation. The output is sent to the user as a detailed evaluation report. In terms of operation, document generation software is used to compile the selection results into a report and provide it to the user via email or in-app message.

[0579] Step 6:

[0580] The terminal collects user feedback and sentiment data again and sends it to the server. Feedback input includes user ratings, impressions, and post-use sentiment data. This is analyzed and saved as a dataset for improving the next selection algorithm. The output is elemental data for improving the next generation algorithm. The specific operation includes the process of aggregating user responses via the feedback form and returning them to the server.

[0581] (Application Example 2)

[0582] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0583] In the selection process for generative artificial intelligence that takes into account the individual emotional states of users, conventional performance evaluation and requirements-centric methods lack adaptability to individual needs. In particular, there is a need for technology that selects the optimal generative artificial intelligence according to the user's psychological state and provides services based on it.

[0584] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0585] In this invention, the server includes means for collecting and formalizing evaluation information of the artificial intelligence to be generated, evaluation means for quantifying performance based on the evaluation information, and means for receiving the user's workflow and purpose of use and clarifying the requirements. It also includes means for analyzing the emotional state and selecting the artificial intelligence to be generated based on the emotional information, and means for collecting feedback from the user to improve the accuracy of evaluations in the future. This makes it possible to select a personalized artificial intelligence to be generated based on the user's emotional state and to provide an optimized service.

[0586] "Generative artificial intelligence" is artificial intelligence that is dynamically generated in response to user requests and optimized to perform specific tasks.

[0587] "Evaluation information" refers to data collected based on the performance of the generated artificial intelligence and user feedback, and serves as the basis for judging the appropriateness of the artificial intelligence.

[0588] "Emotional information" refers to data acquired to analyze a user's psychological state, and it quantitatively represents the user's emotions.

[0589] The "selection process" is the procedure for choosing the optimal generative artificial intelligence based on evaluation information and emotional information.

[0590] Personalization refers to adjusting services and features to suit the individual user's characteristics, needs, and emotional state.

[0591] "Feedback" refers to the opinions and impressions provided by users after using the product, and is data used to evaluate and improve the AI ​​that generates future products.

[0592] This invention provides a system in which a server plays a central role in optimally selecting and customizing generated artificial intelligence using data from users and terminals.

[0593] The server first collects AI performance evaluation information and user feedback information, and stores this in a database. This database includes evaluation information such as past AI model usage results, user reviews, and performance data, which are then formatted using data analysis tools such as Microsoft Azure and Google Cloud.

[0594] Next, the server utilizes an emotion analysis engine to analyze the user's emotional data in real time through the terminal. This emotional data is obtained by analyzing the user's voice input and facial expression data, and existing emotion analysis APIs (for example, Microsoft Azure Emotion API) are used for this analysis.

[0595] When a user inputs their workflow and purpose of use through the terminal interface, the server clarifies the requirements based on this information and integrates it with emotional information. Emotional information is particularly used in the selection and recommendation process of a customized AI model that reflects the user's psychological state. For example, if the user is seeking relaxation, the system will recommend music or content appropriate for relaxation using AI.

[0596] Ultimately, a specific AI model desired by the user is selected, and this information is communicated to the user in a report. The report includes performance metrics for the selected AI and customization options tailored to the user's emotional state. Based on this information, the user can then utilize artificial intelligence in various digital services.

[0597] This process enables the use of personalized AI models that adapt to the user's emotions. An example of a specific prompt would be, "Please recommend the best music content for when the user is in a relaxed state."

[0598] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0599] Step 1:

[0600] The server collects performance evaluation information for generated artificial intelligence from various data sources and stores it in a database. Inputs include past usage data, user reviews, and performance metrics. Outputs are standardized evaluation data. During this process, data analysis tools are used to format the collected data, making it suitable for efficient searching and analysis.

[0601] Step 2:

[0602] The server uses an emotion analysis engine to process real-time user emotion data collected via the terminal. Inputs include user voice and facial expression data. Outputs include a report that quantifies the user's emotional state. Specifically, it uses voice tone analysis and image analysis techniques to identify the user's psychological state.

[0603] Step 3:

[0604] The terminal allows users to input their workflow and purpose of use through an interface, and sends this data to the server. The input includes text information related to the user's purpose. The server uses this information to clarify user requirements. The clarified requirements information is then provided to the system as output.

[0605] Step 4:

[0606] The server integrates clarified user requirements and sentiment information to initiate a process of selecting the optimal generative artificial intelligence. The input consists of user requirements and sentiment information. The output is the identification of the AI ​​model that best suits the user's needs. Machine learning algorithms are used to score the suitability of existing models in the AI ​​model selection process.

[0607] Step 5:

[0608] The server generates a report detailing the selected generative artificial intelligence and its associated customization options, and notifies the user. Inputs include information on the selected AI model and customization elements. Output is a detailed report for the user, which includes user-inspired suggestions and selection criteria.

[0609] Step 6:

[0610] Users input their emotions as feedback into the system based on the provided report and send it to the server via their terminal. The input consists of text data of the user's impressions and evaluations. The server receives this and updates the database to improve the accuracy of future evaluations. The output is improved evaluation information. The feedback is used to improve the evaluation algorithm.

[0611] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0612] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0613] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0614] [Fourth Embodiment]

[0615] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0616] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0617] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0618] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0619] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0620] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0621] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0622] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0623] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0624] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0625] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0626] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0627] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0628] This invention is a system that collects evaluation information on generated artificial intelligence and automates the process of users selecting the most suitable artificial intelligence for their business operations.

[0629] The following describes the specific operational aspects of this system.

[0630] The server collects data on artificial intelligence, generated periodically from external and internal data sources. This data includes performance metrics, user reviews, and feedback. The collected data is stored in a database and formatted.

[0631] Users input their workflow and requirements for the artificial intelligence they want to generate through a user interface. This allows the server to specifically understand the user's needs. For example, a graphic designer user who wants to generate images for advertising can request an AI with high-quality image generation capabilities.

[0632] The server analyzes the collected data and quantifies the performance of each generated artificial intelligence. Machine learning algorithms are used for the analysis, which evaluates metrics such as response time, accuracy, and user satisfaction for each model.

[0633] Next, the server selects the optimal artificial intelligence to generate based on the user's requirements and analysis results. In this selection process, it filters models that meet the specific requirements for the user's work and identifies the most appropriate model based on weighted scores.

[0634] Once the selection is complete, the server automatically generates a report on the selected artificial intelligence to be generated. This report details the characteristics, benefits, and recommended settings of the selected model. The server delivers this report to the user via email or in-app notification.

[0635] Furthermore, the terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the artificial intelligence they used and send them to the server. This feedback is used as important data to improve the accuracy of selections in the future.

[0636] This system allows users to more effectively utilize AI that generates results tailored to their specific tasks.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] The server collects performance data, user reviews, and feedback related to artificial intelligence generated from various data sources. This data is collected and stored via external APIs, web scraping, and internal databases.

[0640] Step 2:

[0641] The server cleans and preprocesses the collected data. This includes imputing missing values, formatting, and removing outliers. The formatted data is then stored in the database as an evaluation dataset.

[0642] Step 3:

[0643] The server evaluates each artificial intelligence model it generates using a pre-configured machine learning algorithm. The evaluation is performed by quantifying multiple performance indicators, such as response time, output accuracy, and user satisfaction score.

[0644] Step 4:

[0645] Users input workflow information and requirements for the artificial intelligence to be generated through a dedicated interface. For example, by specifying that they need high-resolution image generation for graphic design work, they can communicate their specific needs to the server.

[0646] Step 5:

[0647] The server combines the requirements received from the user with evaluated data, performs filtering and weighting, and selects the optimal artificial intelligence to generate. If multiple candidates exist, the model that best matches the conditions is selected.

[0648] Step 6:

[0649] The server automatically generates a report detailing the selected artificial intelligence to be generated. This report includes model characteristics, performance evaluations, and recommended configuration options, providing comprehensive information for the user.

[0650] Step 7:

[0651] The server delivers the generated reports to users via email or in-app notifications. This allows users to receive the selection results and quickly move on to the next step.

[0652] Step 8:

[0653] The device provides an interface for receiving user feedback. Users input their actual user experience and suggestions for improvement, and then send the feedback to the server.

[0654] Step 9:

[0655] The server analyzes the collected feedback and uses it as training data for the algorithm. Based on the analysis results, it adjusts the parameters of the selection algorithm to improve accuracy in the next selection process.

[0656] (Example 1)

[0657] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] The aim is to effectively automate the performance evaluation and optimal selection process of generated information processing systems, enabling the rapid and accurate selection of information processing systems suitable for the user's business processes. In conventional information system selection processes, the collection and formatting of evaluation data, requirements identification, and utilization of feedback were all done manually, resulting in a time-consuming and laborious process with limited selection accuracy.

[0659] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0660] In this invention, the server includes means for collecting evaluation data related to the information processing system to be generated and formatting it into a standardized format; evaluation means for quantifying the performance of the information processing system to be generated based on the evaluation data; and means for receiving the user's work process and objectives and identifying requirements suitable therefor. This enables the rapid and accurate selection of the optimal generation system.

[0661] A "generating information processing system" is a system designed to automatically process information using specific algorithms and processes to provide added value.

[0662] "Evaluation data" refers to data necessary to show the value of an information processing system in numerical terms and indicators, including its performance and quality, as well as user feedback.

[0663] A "standardized format" is a format that converts information collected from different data sources into a consistent and unified format, making subsequent processing and analysis easier.

[0664] "Evaluation means for quantifying performance" refers to a method or apparatus for quantitatively measuring and expressing the characteristics and performance of an information processing system as numerical values, based on collected evaluation data.

[0665] A "business process" refers to a series of steps and operations necessary to perform a specific task, and is a process for achieving a specific objective.

[0666] "Means for identifying requirements" refers to a method or apparatus for clarifying the specifications and conditions of the required system based on the user's needs and business objectives, and for selecting an information processing system that meets those requirements.

[0667] This invention automates the selection and optimization of information processing systems. A server plays a central role in this system, periodically collecting evaluation data on the generated information system from external and internal sources. This evaluation data includes system performance indicators and user feedback, which are then formatted into a standardized format. Specifically, the server uses a database system such as MySQL to build an environment for managing and formatting the data.

[0668] Next, the server uses software frameworks such as TensorFlow and PyTorch to analyze this evaluation data and quantify the performance of each system. Based on this quantified data, the value of the information processing system is evaluated. This data is used when receiving the user's business objectives and process requirements.

[0669] Users input their business objectives and system requirements via their terminal. This is done using input forms in a web application. These forms are built on modern frameworks such as React.js and Angular, providing a user-friendly interface. As a concrete example, when searching for a model to generate catchy ad copy in advertising, the following prompt might be entered:

[0670] Prompt example:

[0671] "We're looking for an AI that can generate catchy advertising copy that resonates with consumers, in order to highlight the appeal of our new product. Please suggest options that are expected to be more effective than those from past campaigns."

[0672] The server selects the optimal information processing system based on the user input and the analysis results of the quantified evaluation data. It uses weighted scores to filter out the most suitable system. A detailed report is automatically generated for the selected information system and notified to the user via the SMTP protocol, etc. The report includes the characteristics and recommended settings of the selected system.

[0673] These processes enable users to quickly implement information processing systems suited to their work, significantly improving efficiency and accuracy.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The server collects evaluation data on the generated AI model from external and internal sources. It uses API calls to retrieve the latest performance metrics from external data providers and extracts historical user feedback from an internal database. This provides system performance metrics and user feedback as evaluation data. This data is initially retrieved in formats such as JSON and then formatted into a consistent format to facilitate subsequent processing.

[0677] Step 2:

[0678] The server formats the collected evaluation data into a standardized format and stores it in a database. Specifically, it uses a MySQL database to convert JSON data to CSV format, and checks for and corrects duplicates and missing data. The input is JSON data, and the output is formatted CSV data. This formatting and data cleansing process ensures data consistency and accuracy.

[0679] Step 3:

[0680] Users input their business objectives and requirements for the generated AI model through a user interface. The input forms used are built with front-end frameworks such as React.js and provide input completion features to help users enter accurate prompts. The input consists of business processes and requirements for expected output results, which are then sent to the server as requirement data.

[0681] Step 4:

[0682] The server analyzes requirements data and collected evaluation data, and uses a machine learning framework to quantify the performance of the generated AI model. Specifically, it uses TensorFlow to quantify the performance based on metrics such as AI model response time, accuracy, and user satisfaction. The input is formatted evaluation data and user requirements, and the output is quantified model performance data.

[0683] Step 5:

[0684] The server selects the optimal generative AI model based on quantified performance data and user requirements. Using a weighted scoring method, it filters the model that best fits the user requirements, identifying the optimal model. The input is quantified model performance data and user requirements, and the output is information about the selected AI model.

[0685] Step 6:

[0686] The server automatically generates a detailed report on the selected generative AI model and notifies the user. The report is generated using JasperReports and sent via email or in-application notification using the SMTP protocol. The input is information about the selected AI model, and the output is a detailed report.

[0687] Step 7:

[0688] The terminal provides an interface for collecting user feedback. Users input their evaluations and suggestions for improvement regarding the AI ​​model they used and send them to the server. The input consists of the user's evaluation and improvement suggestions, and the output is feedback data used to improve the accuracy of future selections.

[0689] (Application Example 1)

[0690] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] In automated control systems, current knowledge processing systems present challenges in selecting the optimal artificial intelligence model due to the complexity of the selection process and limited information available for performance evaluation. Furthermore, insufficient adjustments to suit user work procedures can hinder efficient operation. Moreover, the evaluation and selection process lacks the ability to dynamically adapt, resulting in an inability to keep pace with rapidly changing technological requirements and environmental shifts.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0693] In this invention, the server includes means for collecting and formalizing evaluation information of the knowledge processing system to be generated; evaluation means for quantifying the performance of the knowledge processing system to be generated based on the evaluation information; means for receiving the user's work procedures and purpose of use and clarifying the requirements; and means for collecting data for optimizing the performance of various knowledge processing systems in an automatic control device and selecting the optimal knowledge processing system. As a result, the user can quickly and appropriately select the optimal knowledge processing system and perform efficient and safe automatic control.

[0694] A "generating knowledge processing system" is a means of information processing newly constructed using machine learning or artificial intelligence algorithms for a specific task.

[0695] "Evaluation information" refers to a collection of data and feedback gathered to determine the performance and usefulness of the knowledge processing system that generates the information.

[0696] "Evaluation methods for quantifying performance" refer to methods and devices for quantitatively analyzing the diverse characteristics of a knowledge processing system and expressing them in specific numerical values.

[0697] "User procedures" refer to a series of steps or processes taken to perform a specific task or job.

[0698] "Means for clarifying requirements" refer to processes and devices that specifically define the needs and goals of users and clarify the conditions necessary for a knowledge processing system.

[0699] "Means for selecting the optimal knowledge processing system" refers to the criteria and methods for selecting the knowledge processing system that best suits the user's purpose, based on collected evaluation information and clarified requirements.

[0700] An "automatic control system" is a general term for a device that includes hardware and software for controlling the operation of machines and systems without human intervention.

[0701] This invention is implemented as a system that automates the process of selecting the optimal knowledge processing system in an automatic control device. In this system, a server is central and provides the following functions.

[0702] First, the server collects evaluation information for the knowledge processing system generated from external and internal databases, and uses this information to perform performance evaluations. The evaluation utilizes historical performance data and user feedback stored in a database management system running on Amazon Web Services (AWS). This data is analyzed using a Python program, and performance is quantified using machine learning algorithms. Scikit-learn is the standard machine learning library used, and Pandas and NumPy are typically used for data preprocessing.

[0703] Next, the user's work procedures and purpose of use are entered through the user interface on the terminal. This input information is then condensed by the server into the necessary requirements and used as a criterion for selecting the optimal knowledge processing system. Detailed information about the selected system is included in an automatically generated report, through which the user can receive the reasons for the selection and configuration suggestions. This report is sent via in-app notification or email.

[0704] User feedback is entered directly on the device and sent to the server to improve the selection process for future use. This allows the evaluation algorithm to be continuously updated, enabling more accurate selections.

[0705] For example, in urban areas where traffic congestion is frequent, a knowledge processing system that selects the optimal route in real time and improves energy efficiency is chosen. To achieve this, a prompt in the form of "Please tell me how to select an AI model capable of precise urban environment interpretation in an autonomous vehicle" is used.

[0706] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0707] Step 1:

[0708] The server collects evaluation information for the knowledge processing system generated from external and internal databases. Database queries are used as input, and historical performance data and user feedback obtained through these queries are output. Specifically, it accesses the Amazon Web Services (AWS) database and executes SQL queries based on a regular schedule.

[0709] Step 2:

[0710] The server preprocesses the collected information using a Python program. The input is the raw data obtained in step 1, and the output is data formatted into a parseable format. Specifically, it uses the Pandas library to clean the data (imputing missing values, normalizing data types).

[0711] Step 3:

[0712] The server analyzes the preprocessed data using the Scikit-learn library and quantifies the performance of the knowledge processing systems. The input is the data formatted in step 2, and the output is the quantified performance indicators for each system. Specifically, it builds a machine learning model, uses it to analyze the data, and generates an evaluation score for each knowledge processing system.

[0713] Step 4:

[0714] Users input work procedures and usage purposes through a terminal. This input includes business workflows and desired performance requirements entered into the user interface, and this information is stored in a database. Specifically, users select options on the user interface and press input buttons to send the information to the server.

[0715] Step 5:

[0716] The server compares user input information with quantified performance metrics to select the optimal knowledge processing system. The input is the output from steps 3 and 4, and the output is the specifications of the system considered optimal. Specifically, it performs scoring using an algorithm and selects the one with the highest degree of fit.

[0717] Step 6:

[0718] The server automatically generates a report based on the selection results and notifies the user. The input is the output from step 5, and the output is the report document. Specifically, it uses a template engine to assemble the report and sends it via email or a terminal application.

[0719] Step 7:

[0720] Users provide feedback via their device after use. This feedback consists of evaluations and suggestions for improvement based on their experience, and is recorded in a database. Specifically, data is collected when users fill out a feedback form and press the submit button.

[0721] Step 8:

[0722] The server analyzes the collected feedback and uses it as data to improve the accuracy of future selection processes. The input is the feedback data from step 7, and the output is the improved evaluation algorithm. The specific operation includes a process of adjusting the model based on negative feedback to improve the algorithm's performance.

[0723] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0724] This invention is a system that enables the selection of more appropriate artificial intelligence by incorporating user emotional information into the selection and evaluation process of the artificial intelligence to be generated. A specific embodiment thereof is shown below.

[0725] The server first collects, formats, and compiles performance evaluation data and user reviews related to artificial intelligence generated using conventional methods. This data is stored in a database and used for evaluation. The server's role is to quantify the performance of each artificial intelligence model based on this data and conduct evaluations.

[0726] Next, the server is equipped with an emotion engine that recognizes user emotion data in real time through the terminal. This system detects emotions from webcam video analysis, the user's facial expressions in response to input, tone of voice, or writing patterns.

[0727] The user inputs the workflow and the functions and performance they require from the artificial intelligence into the terminal interface. During this process, the server uses an emotion engine to collect changes in the user's emotions as they input. This emotional information can be used to identify and record emotions, particularly those relevant to evaluation.

[0728] In the selection process, the server integrates pre-collected emotional information with other business requirements and uses it to determine the suitability of the artificial intelligence to be generated. For example, if a user shows interest in a model setting and expresses positive emotions, an artificial intelligence specifically tailored to that setting will be presented.

[0729] Once the selection is complete, the server generates a report containing selection results that reflect emotional information, as well as details about the artificial intelligence. This report includes customization options based on the user's emotional state and is provided to the user in a timely manner via email or in-app notifications.

[0730] Finally, the device receives emotional feedback from the user again and sends it to the server. The server analyzes the emotional data obtained along with the feedback and uses it to improve the selection algorithm and the functionality of the emotion engine. This further improves the accuracy of selections in subsequent attempts.

[0731] In this way, this invention, which combines an emotion engine, goes beyond conventional performance and requirements-centric model selection and enables more sophisticated AI generation selection that takes into account the user's psychological state.

[0732] The following describes the processing flow.

[0733] Step 1:

[0734] The server collects performance evaluation information about artificial intelligence generated from external data sources and past feedback. This may involve using API access or scraping techniques. The collected data is stored in a database and prepared for evaluation.

[0735] Step 2:

[0736] The emotion engine installed on the server collects real-time emotional data from users through their devices. It analyzes the user's facial expressions using a camera and analyzes their voice tone and patterns to determine their emotions. This data is processed within the emotion engine, and information about the user's psychological state is generated.

[0737] Step 3:

[0738] The user inputs their workflow and the functions and performance requirements they expect from the generated artificial intelligence into the terminal interface. During input, the emotion engine captures changes in the user's emotions and sends them to the server as emotion data.

[0739] Step 4:

[0740] The server integrates collected business requirements and sentiment data, along with pre-collected evaluation information for generating artificial intelligence, to select the most suitable AI. In particular, it focuses on AI that corresponds to settings and functions in which the user has expressed positive emotions.

[0741] Step 5:

[0742] After the selection is complete, the server automatically generates a detailed report on the artificial intelligence to be produced. This report includes the performance, benefits, and customization options of the selected AI. The report is provided to the user via email or in-app notification.

[0743] Step 6:

[0744] The device provides an interface for receiving emotionally charged feedback from users. Users input feedback, including their experience using the generated artificial intelligence and areas for improvement, and send it to the server along with emotional data.

[0745] Step 7:

[0746] The server analyzes feedback and sentiment data to improve the accuracy of the sentiment engine and selection algorithms. The analysis results are used in subsequent selection processes, continuously improving the overall system performance.

[0747] (Example 2)

[0748] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0749] Conventional AI selection systems only evaluate performance and specifications, which means they cannot consider user emotions or psychological aspects. This can lead to the selection of AI that lacks intuitive satisfaction or suitability from the user's perspective. It is necessary to address these challenges and achieve AI selection that is more optimized for the user.

[0750] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0751] In this invention, the server includes means for collecting evaluation information and emotional data of the artificial intelligence to be generated and formalizing them; evaluation means for quantifying the performance of the artificial intelligence to be generated based on the evaluation information and emotional data; and means for receiving the user's work procedures and purpose of use, clarifying the requirements, and associating emotional information. This makes it possible to select an artificial intelligence that takes into account the user's emotions and psychological aspects, resulting in a higher level of satisfaction.

[0752] "Generative artificial intelligence" refers to a program with human-like intelligence that has been newly modeled using technologies such as machine learning and deep learning.

[0753] "Evaluation information" refers to a collection of numerical and evaluative data regarding the performance and functionality of the artificial intelligence being generated, and is used as an indicator for selection and improvement.

[0754] "Emotional data" refers to psychological and emotional information collected through the user's facial expressions, tone of voice, input patterns, etc., and is data that reflects the user's inner state.

[0755] "Requirements" refer to specific functional and performance conditions that users desire from the artificial intelligence they generate, representing technical needs that take into account the intended use and workflow.

[0756] "Evaluation methods" refer to a system that quantifies and analyzes the performance of the artificial intelligence to be generated based on collected evaluation information and sentiment data, and then performs evaluations for selection purposes.

[0757] A "report" is a document that summarizes detailed information and analysis results regarding the selected artificial intelligence that will be generated, and is used as an information transmission medium as one of the means of notifying users.

[0758] "Feedback" refers to opinions, including evaluations, impressions, and sentiment data, provided by users after using artificial intelligence they have generated. This information is collected for the purpose of improving future development and selection processes.

[0759] This invention is a system that achieves more appropriate selection by incorporating user emotional information into the process of selecting the artificial intelligence to be generated. An embodiment thereof is shown below.

[0760] The server first collects performance evaluation data and user reviews of the generated AI models and stores them in a database. The hardware used here includes a high-performance database server, and the software used is a database management system. Subsequently, this data is formalized and evaluated numerically.

[0761] The device plays a role in collecting real-time emotional data from the user. It uses a webcam and microphone to perform facial expression analysis and voice tone analysis. The emotion engine is specialized software that analyzes the data collected from these devices and evaluates the user's emotional state.

[0762] The user inputs the desired workflow and performance requirements for the artificial intelligence model into the terminal interface. For example, the user might input "AI model that prioritizes emotion understanding" into the input field. An example of a prompt message used in this case would be, "Please select an AI model that understands emotions. Settings corresponding to specific emotions will be given priority."

[0763] The server combines user input and sentiment data to select the optimal generative AI model. This selection result is automatically generated as a report and sent to the user via email or in-app notifications.

[0764] Ultimately, the device receives user feedback and sends it to the server along with the collected sentiment data. The server analyzes this information and uses it to improve future selection algorithms and sentiment engines, further enhancing the accuracy of future selections.

[0765] This embodiment makes it possible to select artificial intelligence that takes into account the user's emotional state, thereby realizing a more user-friendly system.

[0766] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0767] Step 1:

[0768] The server collects evaluation information and user reviews related to the generated AI model. Input includes information from databases and online resources. This information is analyzed and stored in the database as formalized data. The output is a formatted dataset containing evaluation scores. Specifically, the server uses a data extraction algorithm to extract and format the necessary data from various sources.

[0769] Step 2:

[0770] The device collects user emotion data in real time. The primary inputs are webcam video and microphone audio data. The emotion engine analyzes this input data and represents the user's emotional state using numbers and tags. The final output is a dataset of emotion analysis results. In this process, facial recognition software and voice analysis programs work in conjunction with emotion detection algorithms.

[0771] Step 3:

[0772] The user inputs the desired functions and performance requirements for the artificial intelligence model into the terminal interface. This input data is presented as specific questions and options based on the business flow and specifications. From this input, the server clarifies the user's requirements and structures the necessary data. The output is a dataset serving as a requirements definition document. The operation includes a process of transferring the data input via the user interface to the server.

[0773] Step 4:

[0774] The server integrates collected evaluation information, sentiment data, and user requirements to select the optimal generative AI model. The input includes all datasets collected in the previous step. The server uses an evaluation algorithm to select candidate models and compiles the selection results. The output is the selected generative AI model and its evaluation results. Specific operations include data analysis and model comparison algorithms.

[0775] Step 5:

[0776] The server generates a report based on the selection results and notifies the user via the terminal. The input for this step is information about the selected AI model and its evaluation. The output is sent to the user as a detailed evaluation report. In terms of operation, document generation software is used to compile the selection results into a report and provide it to the user via email or in-app message.

[0777] Step 6:

[0778] The terminal collects user feedback and sentiment data again and sends it to the server. Feedback input includes user ratings, impressions, and post-use sentiment data. This is analyzed and saved as a dataset for improving the next selection algorithm. The output is elemental data for improving the next generation algorithm. The specific operation includes the process of aggregating user responses via the feedback form and returning them to the server.

[0779] (Application Example 2)

[0780] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0781] In the selection process for generative artificial intelligence that takes into account the individual emotional states of users, conventional performance evaluation and requirements-centric methods lack adaptability to individual needs. In particular, there is a need for technology that selects the optimal generative artificial intelligence according to the user's psychological state and provides services based on it.

[0782] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0783] In this invention, the server includes means for collecting and formalizing evaluation information of the artificial intelligence to be generated, evaluation means for quantifying performance based on the evaluation information, and means for receiving the user's workflow and purpose of use and clarifying the requirements. It also includes means for analyzing the emotional state and selecting the artificial intelligence to be generated based on the emotional information, and means for collecting feedback from the user to improve the accuracy of evaluations in the future. This makes it possible to select a personalized artificial intelligence to be generated based on the user's emotional state and to provide an optimized service.

[0784] "Generative artificial intelligence" is artificial intelligence that is dynamically generated in response to user requests and optimized to perform specific tasks.

[0785] "Evaluation information" refers to data collected based on the performance of the generated artificial intelligence and user feedback, and serves as the basis for judging the appropriateness of the artificial intelligence.

[0786] "Emotional information" refers to data acquired to analyze a user's psychological state, and it quantitatively represents the user's emotions.

[0787] The "selection process" is the procedure for choosing the optimal generative artificial intelligence based on evaluation information and emotional information.

[0788] Personalization refers to adjusting services and features to suit the individual user's characteristics, needs, and emotional state.

[0789] "Feedback" refers to the opinions and impressions provided by users after using the product, and is data used to evaluate and improve the AI ​​that generates future products.

[0790] This invention provides a system in which a server plays a central role in optimally selecting and customizing generated artificial intelligence using data from users and terminals.

[0791] The server first collects AI performance evaluation information and user feedback information, and stores this in a database. This database includes evaluation information such as past AI model usage results, user reviews, and performance data, which are then formatted using data analysis tools such as Microsoft Azure and Google Cloud.

[0792] Next, the server utilizes an emotion analysis engine to analyze the user's emotional data in real time through the terminal. This emotional data is obtained by analyzing the user's voice input and facial expression data, and existing emotion analysis APIs (for example, Microsoft Azure Emotion API) are used for this analysis.

[0793] When a user inputs their workflow and purpose of use through the terminal interface, the server clarifies the requirements based on this information and integrates it with emotional information. Emotional information is particularly used in the selection and recommendation process of a customized AI model that reflects the user's psychological state. For example, if the user is seeking relaxation, the system will recommend music or content appropriate for relaxation using AI.

[0794] Ultimately, a specific AI model desired by the user is selected, and this information is communicated to the user in a report. The report includes performance metrics for the selected AI and customization options tailored to the user's emotional state. Based on this information, the user can then utilize artificial intelligence in various digital services.

[0795] This process enables the use of personalized AI models that adapt to the user's emotions. An example of a specific prompt would be, "Please recommend the best music content for when the user is in a relaxed state."

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The server collects performance evaluation information for generated artificial intelligence from various data sources and stores it in a database. Inputs include past usage data, user reviews, and performance metrics. Outputs are standardized evaluation data. During this process, data analysis tools are used to format the collected data, making it suitable for efficient searching and analysis.

[0799] Step 2:

[0800] The server uses an emotion analysis engine to process real-time user emotion data collected via the terminal. Inputs include user voice and facial expression data. Outputs include a report that quantifies the user's emotional state. Specifically, it uses voice tone analysis and image analysis techniques to identify the user's psychological state.

[0801] Step 3:

[0802] The terminal allows users to input their workflow and purpose of use through an interface, and sends this data to the server. The input includes text information related to the user's purpose. The server uses this information to clarify user requirements. The clarified requirements information is then provided to the system as output.

[0803] Step 4:

[0804] The server integrates clarified user requirements and sentiment information to initiate a process of selecting the optimal generative artificial intelligence. The input consists of user requirements and sentiment information. The output is the identification of the AI ​​model that best suits the user's needs. Machine learning algorithms are used to score the suitability of existing models in the AI ​​model selection process.

[0805] Step 5:

[0806] The server generates a report detailing the selected generative artificial intelligence and its associated customization options, and notifies the user. Inputs include information on the selected AI model and customization elements. Output is a detailed report for the user, which includes user-inspired suggestions and selection criteria.

[0807] Step 6:

[0808] Users input their emotions as feedback into the system based on the provided report and send it to the server via their terminal. The input consists of text data of the user's impressions and evaluations. The server receives this and updates the database to improve the accuracy of future evaluations. The output is improved evaluation information. The feedback is used to improve the evaluation algorithm.

[0809] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0810] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0811] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0812] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0813] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0814] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0815] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0816] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0817] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0818] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0819] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0820] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0821] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0822] 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.

[0823] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0824] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0825] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0826] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0827] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0828] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0829] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0830] The following is further disclosed regarding the embodiments described above.

[0831] (Claim 1)

[0832] A means of collecting and formalizing evaluation information on the artificial intelligence being generated,

[0833] Based on the aforementioned evaluation information, an evaluation means for quantifying the performance of the artificial intelligence to be generated,

[0834] A means of receiving the user's workflow and purpose of use, and clarifying the requirements,

[0835] A means for selecting the optimal artificial intelligence to generate using the aforementioned requirements and the aforementioned evaluation information,

[0836] A means of automatically generating and notifying information about the selected artificial intelligence to be generated as a report,

[0837] A means of collecting user feedback and using it to improve the accuracy of future evaluation methods,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, which recommends customization options for the artificial intelligence to be generated according to the user's workflow.

[0841] (Claim 3)

[0842] The system according to claim 1, which dynamically updates the selection algorithm for the artificial intelligence to be generated based on the results of feedback analysis.

[0843] "Example 1"

[0844] (Claim 1)

[0845] A means for collecting evaluation data related to the information processing system to be generated and formatting it into a standardized format,

[0846] An evaluation means for quantifying the performance of the generated information processing system based on the aforementioned evaluation data,

[0847] A means of receiving the user's work process and objectives, and identifying the requirements that are suitable for them,

[0848] A means for selecting the optimal information processing system to generate using the aforementioned requirements and the aforementioned evaluation data,

[0849] A means for automatically generating and notifying information about the selected information processing system,

[0850] A means of collecting opinions and evaluations from users and using them to improve the accuracy of future evaluation methods,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, which proposes individualized options for the information processing system to be generated according to the user's work process.

[0854] (Claim 3)

[0855] The system according to claim 1, which dynamically updates the method for selecting the information processing system to be generated based on the analysis results of opinions and evaluations.

[0856] "Application Example 1"

[0857] (Claim 1)

[0858] A means for collecting and formalizing evaluation information of a knowledge processing system that generates knowledge,

[0859] An evaluation means for quantifying the performance of the knowledge processing system to be generated based on the aforementioned evaluation information,

[0860] A means of receiving the user's work procedures and purpose of use, and clarifying the requirements,

[0861] A means for selecting the optimal knowledge processing system using the aforementioned requirements and the aforementioned evaluation information,

[0862] A means for automatically generating and notifying information about the selected knowledge processing system to generate, as a document,

[0863] A means of collecting feedback from users and using it to improve the accuracy of future evaluation methods,

[0864] A means for collecting data to optimize the performance of various knowledge processing systems in an automatic control device and for selecting the optimal knowledge processing system,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, which recommends adjustment options for the knowledge processing system to be generated according to the user's work procedure.

[0868] (Claim 3)

[0869] The system according to claim 1, which dynamically updates the selection calculation method for the knowledge processing system to be generated based on the results of opinion analysis.

[0870] "Example 2 of combining an emotion engine"

[0871] (Claim 1)

[0872] A means of collecting evaluation information and sentiment data for the artificial intelligence being generated, and formalizing these,

[0873] An evaluation means for quantifying the performance of the artificial intelligence to be generated based on the aforementioned evaluation information and emotion data,

[0874] A means of receiving user work procedures and intended use, clarifying requirements, and associating emotional information,

[0875] A means for selecting the optimal generating artificial intelligence using the aforementioned requirements and evaluation information, as well as emotional information,

[0876] A means of automatically generating and notifying information about the selected artificial intelligence to be generated as a report,

[0877] A means of collecting user feedback and sentiment data and using it to improve the accuracy of future evaluation methods,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, which recommends setting options for the artificial intelligence to be generated, taking into account emotional information, according to the user's work procedure.

[0881] (Claim 3)

[0882] The system according to claim 1, which dynamically updates the selection algorithm for generating artificial intelligence based on the results of feedback analysis and emotion data.

[0883] "Application example 2 when combining with an emotional engine"

[0884] (Claim 1)

[0885] A means of collecting and formalizing evaluation information on the artificial intelligence being generated,

[0886] Based on the aforementioned evaluation information, an evaluation means for quantifying the performance of the artificial intelligence to be generated,

[0887] A means of receiving the user's workflow and purpose of use, and clarifying the requirements,

[0888] A means for selecting the optimal artificial intelligence to generate using the aforementioned requirements and the aforementioned evaluation information,

[0889] A means of automatically generating and notifying information about the selected artificial intelligence to be generated as a report,

[0890] A means for analyzing the user's emotional state and selecting artificial intelligence to generate based on emotional information,

[0891] A means of collecting user feedback and using it to improve the accuracy of future evaluation methods,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, which recommends customization options for the artificial intelligence to be generated according to the user's workflow and provides content based on emotional state.

[0895] (Claim 3)

[0896] The system according to claim 1, which dynamically updates the selection algorithm for the artificial intelligence to be generated based on the results of feedback analysis and improves the selection accuracy using emotional information. [Explanation of Symbols]

[0897] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting and formalizing evaluation information of a knowledge processing system that generates knowledge, An evaluation means for quantifying the performance of the knowledge processing system to be generated based on the aforementioned evaluation information, A means of receiving the user's work procedures and purpose of use, and clarifying the requirements, A means for selecting the optimal knowledge processing system using the aforementioned requirements and the aforementioned evaluation information, A means for automatically generating and notifying information about the selected knowledge processing system to generate, as a document, A means of collecting feedback from users and using it to improve the accuracy of future evaluation methods, A means for collecting data to optimize the performance of various knowledge processing systems in an automatic control device and for selecting the optimal knowledge processing system, A system that includes this.

2. The system according to claim 1, which recommends adjustment options for the knowledge processing system to be generated according to the user's work procedure.

3. The system according to claim 1, which dynamically updates the selection calculation method for the knowledge processing system to be generated based on the results of opinion analysis.

Images