system

Abstract

We provide the system. [Solution] A means of collecting agent performance information using generated data, A means for analyzing collected performance information and evaluating the performance metrics of each agent, A means of comparing agents based on evaluated performance metrics, A method for selecting the optimal agent based on the comparison results, A means of configuring the selected agent in the user environment, A system that includes this.

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] The selection and setting of agents using generated data have the problem that it is difficult for users to select the optimal one among various agents. Also, there is a need for a method to appropriately evaluate and analyze the performance and satisfaction of agents, but the conventional methods are inefficient and manual setting requires time and effort.

Means for Solving the Problems

[0005] This invention provides a means for collecting performance information of each agent using generated data. Furthermore, it includes means for analyzing the collected performance information and evaluating the performance indicators of each agent. Based on this, it provides means for automatically comparing agents to select the optimal agent that meets the user's specific needs. This invention also includes means for automatically configuring the selected agent in the user environment, thereby reducing the burden on the user and enabling rapid deployment.

[0006] "Generated data" refers to data constructed through processes utilizing artificial intelligence, and serves as foundational information for learning about and improving the performance of AI agents and user experience.

[0007] An "agent" is a software component designed to autonomously perform a specific task, and is a program that operates based on user input.

[0008] "Performance information" refers to data about the specific operational results provided by the agent, and includes information such as processing speed, accuracy, and user conversion rate, which are used to evaluate the effectiveness of each agent.

[0009] "Analysis" is the process of systematically analyzing collected data to derive indicators such as agent performance and satisfaction.

[0010] "Performance metrics" are numerical values ​​or categories that quantitatively indicate the efficiency and effectiveness of an agent's operation, and are used as evaluation criteria.

[0011] "Comparison" is the process of evaluating the performance metrics of multiple agents and determining their relative superiority or inferiority.

[0012] "Selection" refers to the act of choosing the most suitable agent from among the available options based on specific requirements and criteria.

[0013] "Configuration" refers to the process of setting various parameters and environments so that the agent can function optimally. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine.

Best Mode for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered 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.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered 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.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention provides a system for automatically selecting and configuring the optimal AI agent for a user. This system selects the agent that best suits the user's needs through a process of collecting, analyzing, and comparing information on the performance of different agents.

[0036] First, the server collects performance data from multiple AI agents. This includes data acquisition using APIs, scraping from user review sites, and incorporating user feedback. This allows for the collection of data such as agent response speed, success rate, and user satisfaction.

[0037] Next, the server analyzes the collected data. This analysis includes sentiment analysis of reviews using natural language processing and calculation of performance metrics using statistical methods. This generates an overall evaluation for each agent.

[0038] Next, the server compares agents based on the analyzed data. The comparison results are presented to the user as a visual ranking and evaluation metrics. This information serves as an important basis for selecting the optimal agent based on the user's workflow and purpose of use.

[0039] The server automatically installs and configures the selected agents. Since users do not need to perform any specific operations regarding agent configuration during this process, the efficiency of system usage is significantly improved.

[0040] As a concrete example, suppose a user is looking for the optimal agent for a text generation task. By using this system, the server analyzes data collected from relevant agents and automates the selection process. Ultimately, the most suitable agent is applied to the user's environment, and the user can immediately utilize its functions. In this way, the present invention reduces the effort and time required for selecting and configuring generation AI agents, thereby realizing efficient business support.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects performance data from each generated AI agent. This collection process includes sending periodic requests via APIs and applying scraping techniques from user review sites. This allows the server to obtain data on agent processing speed, success rate, and text information regarding user satisfaction.

[0044] Step 2:

[0045] The server stores the collected data in a database and prepares it for analysis. Data normalization and preprocessing are performed, and the data is organized into a format suitable for analysis.

[0046] Step 3:

[0047] The server uses natural language processing algorithms to perform sentiment analysis on user reviews. This analysis quantifies user satisfaction and dissatisfaction with the agent's use and is used as part of the evaluation metrics.

[0048] Step 4:

[0049] The server applies statistical methods to calculate performance metrics for the agents. Specifically, it uses quantitative data such as response time and processing accuracy to form an overall evaluation score for each agent.

[0050] Step 5:

[0051] The server generates visual comparison graphs and rankings based on these scores, making it easier for users to intuitively understand the comparison results of the agents.

[0052] Step 6:

[0053] The server automatically selects the optimal agent based on the user's business objectives and requirements. This selection is influenced by user-inputted conditions and past usage history.

[0054] Step 7:

[0055] The server installs the selected agent on the user's system and performs the initial setup automatically. This allows the user to immediately use the agent's functions without any additional configuration.

[0056] (Example 1)

[0057] 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."

[0058] There is a need to reduce the time and effort burden on users when selecting and configuring the optimal information processing system. However, conventional methods involve cumbersome data collection and analysis to choose the appropriate system from a large number of options, making it difficult for users to make such decisions. Furthermore, the configuration process after selection is also complex, posing a significant obstacle for users without specialized knowledge.

[0059] 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.

[0060] In this invention, the server includes means for collecting performance information from multiple information processing systems via data collection means, means for analyzing the collected performance information using natural language processing and statistical methods to calculate evaluation metrics for the information processing systems, and means for comparing the information processing systems based on the calculated evaluation metrics. As a result, users can visually select the most suitable information processing system, and the settings after selection are performed automatically, significantly reducing the burden of effort and time.

[0061] "Data acquisition means" refers to a method or device that plays the role of acquiring performance information from multiple information processing systems.

[0062] "Performance information" refers to data related to the operation and functionality of an information processing system, such as response speed, success rate, and user satisfaction.

[0063] "Natural language processing" is a technology that uses computers to analyze, understand, and utilize human language.

[0064] "Statistical methods" are mathematical techniques for collecting, analyzing, interpreting, and representing data.

[0065] "Evaluation indicators" are standards or benchmark values ​​that quantify and show the performance of an information processing system.

[0066] An "information processing system" is a system that includes hardware and software programmed to perform a specific task.

[0067] "Visual presentation" refers to displaying information visually in a way that is easy for users to understand.

[0068] "Automatically setting up" means that the setup is completed through mechanical or programmed actions without human intervention.

[0069] In this embodiment of the invention, the server primarily handles a series of processes, including collecting and analyzing performance information from multiple information processing systems and selecting the appropriate information processing system. The server achieves this using the following methods and techniques.

[0070] First, the server utilizes data collection methods, such as APIs and web scraping techniques, to gather a wide range of performance information from the information processing system. This allows the server to secure diverse data such as response speed, success rate, and user satisfaction.

[0071] Next, the server uses natural language processing technology to analyze the sentiment of the collected user reviews and quantifies the evaluation data. It also employs statistical methods to calculate evaluation metrics for each information processing system from the collected data. This allows for a comprehensive evaluation of different performance elements, resulting in comparable scores.

[0072] The server compares information processing systems based on calculated evaluation metrics and presents the results visually, allowing users to easily select the information processing system that best suits their needs.

[0073] For information processing systems selected by the user, the server automatically configures them. In this process, necessary installation and configuration are automated by the program, freeing the user from the hassle of manual adjustments.

[0074] For example, if a user is looking for an information processing system optimized for text generation, this system analyzes relevant performance information and automates the selection process. Ultimately, the selected information processing system is applied to the user's environment and becomes immediately available. In this way, users can perform their tasks efficiently.

[0075] As a concrete example of a prompt, the instruction "Based on user reviews, please select the most efficient AI agent" can be used. This allows the server to perform appropriate data analysis and select the appropriate information processing system.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server collects performance information from multiple information processing systems using APIs and web scraping techniques. It obtains access information from information processing systems and URLs of user review sites as input. Based on this input, the server collects performance data such as response speed, success rate, and user satisfaction, and structures and stores this data. The output is the collected structured data.

[0079] Step 2:

[0080] The server analyzes the collected performance information. It uses the structured data collected in step 1 as input. The server performs sentiment analysis of user reviews using natural language processing, quantifying positive, negative, and neutral ratings. Furthermore, it uses statistical methods to organize data on response speed and success rate, calculating an overall evaluation index for each information processing system. The output is analyzed data including the evaluation index.

[0081] Step 3:

[0082] The server compares information processing systems based on the analyzed data. It uses the evaluation metrics obtained in step 2 as input. Based on these metrics, the server generates a ranking of the information processing systems and organizes the data in a visually comparable format. Specifically, it creates graphs and charts and displays them clearly on the user interface. The output provides visualized comparative information.

[0083] Step 4:

[0084] The user selects a suitable information processing system based on visualized comparative information. The data visualized in step 3 is provided as input. Based on this input, the user selects the optimal information processing system according to their business needs. The selection is made using clicks and taps on the user interface. The output provides information about the selected information processing system.

[0085] Step 5:

[0086] The server automatically configures the information processing system selected by the user. It uses the information about the information processing system selected in step 4 as input. The server executes the system's installation script and automatically applies the necessary configurations. Specifically, the API key input and environment settings adjustments are performed programmatically. The configured information processing system is then provided to the user environment as output.

[0087] (Application Example 1)

[0088] 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."

[0089] Selecting and configuring the most suitable AI agent from a diverse range of agents to meet user needs requires advanced expertise and is time-consuming and labor-intensive. Furthermore, electronic payments constantly face security threats and the risk of fraudulent use, necessitating the rapid selection of the most appropriate security measures.

[0090] 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.

[0091] In this invention, the server includes means for collecting characteristic information of artificial intelligence agents using generated information, means for analyzing the collected characteristic information and evaluating the characteristic indicators of each artificial intelligence agent, and means for analyzing payment history and patterns to select the safest and most appropriate artificial intelligence agent and enhance security. This enables the automatic selection of artificial intelligence agents that meet user needs and rapid security enhancement.

[0092] "Generated information" refers to the data necessary to evaluate the characteristics of an artificial intelligence agent. This data includes information about the agent's performance and user evaluations.

[0093] An "artificial intelligence agent" is a program that has the ability to autonomously perform specific tasks, and typically utilizes machine learning and natural language processing technologies.

[0094] "Characteristic information" refers to various pieces of information related to the performance and functions of an artificial intelligence agent, and is used as a standard for evaluation and comparison.

[0095] A "characteristic index" is an evaluation criterion that quantifies or scores the performance of an artificial intelligence agent, and is used for comparison and selection.

[0096] "Payment history and patterns" refers to a user's past transaction data and trends, which are important factors for enhancing security and selecting appropriate agents.

[0097] "Methods to enhance security" refer to measures and technologies used to protect systems from misuse and fraud, and are employed to ensure user safety.

[0098] To realize this invention, it is necessary to construct a data collection and analysis system using a server. The server will use the generated information to collect and analyze characteristic information of the artificial intelligence agent. This includes a process of collecting information from multiple data sources. Specifically, it will utilize data collection via APIs and scraping techniques from user review sites.

[0099] The server runs on a Python-based program and utilizes Flask as its backend framework. Machine learning libraries such as TENSORFLOW® and PyTorch are used for performance analysis. These tools are used to analyze characteristic information and generate characteristic metrics for each artificial intelligence agent.

[0100] The user terminal displays characteristic indicators based on analyzed data and provides a means for selecting an agent. The selected agent is automatically applied to the user terminal, ensuring safe and efficient operation. In particular, security is enhanced by analyzing payment history and patterns on the server and selecting the optimal agent.

[0101] As a concrete example, when a user makes an electronic payment while traveling abroad, the system automatically analyzes the payment pattern, selects the optimal AI agent, and enhances fraud detection capabilities. This allows users to make payments with peace of mind. The system generates a prompt message such as, "Please select the optimal AI agent for overseas use and instruct me on how to detect fraudulent activity."

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server receives a request from the user's terminal. This request contains information about the user's requests and needs. Based on this information, the server prepares to begin collecting appropriate data.

[0105] Step 2:

[0106] The server collects characteristic information from multiple artificial intelligence agents via APIs. Specifically, it obtains performance data, response speed, success rate, etc., for each agent. This data collection uses the API endpoint of the specified agent. The input is an API request, and the output is a collection of characteristic data.

[0107] Step 3:

[0108] The server analyzes the collected characteristic information. This analysis uses TensorFlow or PyTorch to calculate characteristic metrics for each agent and evaluate their performance. The input is the collected characteristic data, and the output is the characteristic metrics for each agent. The analysis results are generated after data processing through model training.

[0109] Step 4:

[0110] The server compares artificial intelligence agents based on the analyzed characteristic metrics. This comparison ranks the agents based on these metrics and selects the optimal agent. The input is a set of characteristic metrics, and the output is the selected optimal agent. Factors such as the degree of fit to user needs and safety are also considered.

[0111] Step 5:

[0112] The server configures the selected agent on the user terminal. In this step, a script is executed to quickly deploy the selected agent's functions to the user environment. The input is the selected agent information, and the output is the agent activated on the user terminal.

[0113] Step 6:

[0114] The server enhances security by analyzing the user's payment history and patterns, and then selecting the most suitable artificial intelligence agent. Here, a fraud detection model is applied based on past transaction data. The input is the payment history, and the output is the relevant agent with enhanced security settings.

[0115] Step 7:

[0116] The user uses an artificial intelligence agent configured by the server to perform actions such as electronic payments. This process is based on a previously configured prompt: "Select the optimal AI agent for overseas use and instruct on how to detect fraudulent activity." The input is the user action, and the output is the securely and quickly completed transaction.

[0117] 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.

[0118] This invention provides a system for effectively selecting and configuring AI agents by combining generated data and an emotion engine. This system automates the process of selecting the agent best suited to the user's needs by collecting, analyzing, and comparing agent performance information. Furthermore, it uses an emotion engine to recognize the user's emotional state and reflects the results in agent selection and configuration, thereby providing a more user-friendly solution.

[0119] First, the server collects performance data from multiple AI agents. This includes data acquisition via APIs and text collection from user review sites, encompassing agent response speed, success rate, and user feedback sentiment.

[0120] Next, the device analyzes the user's real-time emotional state via an emotion engine. This engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. The results of the emotion engine's analysis are then incorporated into the subsequent agent selection process.

[0121] Next, the server analyzes the generated data and calculates performance metrics for each agent using statistical methods. This analysis also takes into account collected user reviews and sentiment data, thereby quantifying the agent's satisfaction level and efficiency.

[0122] The server then compares agents based on the analysis results. It selects the optimal agent by comparing it with the user's emotional data and business objectives. In this selection process, the user's emotional state is directly reflected in the agent settings and selection results, resulting in a more personalized experience.

[0123] Finally, the server automatically installs the selected agent into the user's environment and performs the initial setup. Users can immediately use the customized agent from the first boot, and this invention achieves improved operational efficiency and user experience.

[0124] For example, if a user is looking for an AI agent suitable for call center work, this system will select the optimal agent after considering the stress level of the work. The selected agent will be configured based on the user's emotional state, thereby enhancing the support system in call center operations. Such automated processes support users' work and improve convenience.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server periodically retrieves relevant data using an API to collect performance data from each generated AI agent. This process includes information such as the success rate and response time of tasks handled by the agent. Furthermore, it performs scraping from user review sites to collect user feedback on the agents in text format.

[0128] Step 2:

[0129] The device activates an emotion engine to recognize the user's real-time emotional state. This engine analyzes the user's emotions, such as excitement and anxiety levels, through voice analysis and text sentiment analysis, and stores the results as emotion data. This information is obtained from the voice and text input when the user interacts with the system.

[0130] Step 3:

[0131] The server initiates the analysis process using the collected performance and sentiment data. It utilizes natural language processing techniques to analyze user reviews and quantify user satisfaction. Furthermore, statistical analysis tools are used to calculate performance metrics such as response time and accuracy, generating evaluation scores for each agent.

[0132] Step 4:

[0133] The server automatically compares agents by combining the generated evaluation scores with the user's emotional state. This process is carried out through a visual dashboard, taking emotional data into account to select agents that the user is more likely to consciously respond to.

[0134] Step 5:

[0135] The server selects the most suitable agent based on the user's business objectives and emotional state. The selected agent is displayed to the user as a suggestion, with detailed explanations of the agent's characteristics and past performance as the reason for the selection.

[0136] Step 6:

[0137] The server installs the selected agent on the user's terminal and applies a pre-configured profile. This process is fully automated, and the user does not need to change any settings. As a result, the user can immediately enjoy improved service provided by the selected agent.

[0138] (Example 2)

[0139] 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".

[0140] In user environments utilizing intelligent agents, the process of evaluating and selecting agent performance is not efficient, and selecting the optimal agent, particularly one that takes the user's emotional state into consideration, is a challenge. Furthermore, the complex agent configuration process impairs user convenience.

[0141] 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.

[0142] In this invention, the server includes means for collecting performance information of intelligent agents using generated data, means for analyzing the collected performance information and user evaluations to evaluate the performance indicators of each intelligent agent, and means for selecting the optimal intelligent agent based on the comparison results and the user's emotional state. This enables the automatic selection and setting of the optimal intelligent agent adapted to the user's emotional state, thereby realizing the construction of an efficient user environment.

[0143] "Generated data" refers to information and numerical data collected to evaluate the performance and operation of intelligent agents.

[0144] An "intelligent agent" refers to a software function that uses natural language processing and machine learning algorithms to automate specific tasks based on user instructions.

[0145] "Performance information" refers to indicators and data related to the capabilities and characteristics of an intelligent agent, specifically information on evaluation items such as response speed and success rate.

[0146] "User evaluation" refers to feedback and emotional ratings provided by users based on their experience using intelligent agents.

[0147] "Emotional state" refers to information that represents the emotions and psychological state a user is feeling at a specific point in time, such as stress levels or satisfaction levels.

[0148] "Performance metrics" refer to scores or metrics used to numerically evaluate the performance of intelligent agents.

[0149] "Automatically setting" means that the system will configure and adjust settings based on pre-programmed conditions without manual intervention.

[0150] This invention provides a system for effectively selecting and configuring intelligent agents by combining generated data and an emotion engine. The objective of this system is to improve the user experience by automatically selecting and configuring the optimal agent to meet the user's needs.

[0151] First, the server uses generated data to collect performance information about the intelligent agent. This collection includes data acquisition via APIs and text collection from user review sites. This information includes data on various performance metrics, such as the agent's response speed, success rate, and user feedback sentiment.

[0152] Next, the device uses an emotion engine to analyze the user's real-time emotional state. This emotion engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. For example, if the user enters keywords such as "tired" or "busy," the emotion engine analyzes this as emotional data. This information is used to consider the user's psychological state in the subsequent intelligent agent selection process.

[0153] As a concrete example, consider a user inputting a prompt into an AI model saying, "Please select the agent that can respond most calmly when I am feeling stressed." The system then automatically selects the most suitable intelligent agent based on the user's emotions, installs it in the user's environment, and performs initial setup. This allows the user to comfortably use the intelligent agent even in stressful situations.

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] The server uses generated data to collect performance information from intelligent agents. Input at this stage includes API responses from agent providers and text data from user review sites. The server receives this input, analyzes information such as response speed, success rate, and user feedback sentiment, and outputs performance metric data. This process involves data format conversion and extraction of key information to compile a comprehensive evaluation of the agent's performance.

[0157] Step 2:

[0158] The device uses an emotion engine to analyze the user's real-time emotional state. Input here consists of text and voice data from the user. The device receives this data and, utilizing natural language processing and speech analysis technologies, outputs emotional information such as positive or negative. Specifically, an emotion analysis algorithm scans the user's words and voice tone, and provides the results as numerical emotional data.

[0159] Step 3:

[0160] The server analyzes the collected performance metric data and sentiment data, and evaluates the performance metrics of each intelligent agent using statistical methods. The input consists of performance metric data from Step 1 and sentiment data from Step 2. The server integrates this data, evaluates agent responsiveness and user adaptability, and outputs candidates for the optimal agent. This analysis process uses regression analysis and clustering methods to perform a multifaceted evaluation.

[0161] Step 4:

[0162] The server compares intelligent agents based on the analysis results and selects the agent that best matches the user's emotional state and business objectives. The input is a list of optimal agent candidates obtained from step 3. The server evaluates this list and selects the most suitable agent as the final output. This process involves ranking agents based on evaluation scores and checking their suitability to the user's business objectives.

[0163] Step 5:

[0164] The server automatically configures the selected agent in the user's environment. The input is the agent information selected in step 4. Based on this information, the server performs the necessary installation and customization, and the output is an agent optimized for the user's environment. In this step, an environment configuration script is used to complete the setup so that the user can use it immediately.

[0165] (Application Example 2)

[0166] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0167] Conventional intelligent entity selection systems fail to adequately address the diverse emotional states of users, making it difficult to provide optimal intelligent entities tailored to individual needs. Furthermore, they lack mechanisms to directly reflect user evaluations, resulting in insufficient adaptability and satisfaction levels with selected intelligent entities. This leads to a challenge in that improvements in user convenience are limited.

[0168] 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.

[0169] In this invention, the server includes means for acquiring performance information of intelligent entities using generated data, means for analyzing the acquired performance information and evaluating the performance indicators of each intelligent entity, means for comparing intelligent entities based on the evaluated performance indicators, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the intelligent entities based on the user's emotional state. This makes it possible to automatically select and set individually optimized intelligent entities that take into account the diverse emotional states of the user.

[0170] "Generated data" refers to information used to evaluate the performance of intelligent entities, and includes user feedback and reaction data.

[0171] An "intelligent entity" is an artificial intelligence-based agent or system that operates according to user needs and is a program that has the function of performing a specific task.

[0172] "Performance information" refers to data about the actions performed by an intelligent entity and their results, including metrics such as response speed, success rate, and user satisfaction.

[0173] An "emotion analysis engine" is software or a system that analyzes a user's emotional state in real time, and utilizes speech recognition and natural language processing technologies.

[0174] A "user" is an individual or organization that uses intelligent entities and is subject to service customization based on their needs and responses.

[0175] "Evaluation metrics" are standards or parameters used to quantify and evaluate the performance of intelligent entities, and they play a crucial role in improving the user experience.

[0176] The system that realizes this invention consists of a server, a terminal, and an interface with the user. The server uses generated data to acquire performance information of intelligent entities, analyzes the performance information, and calculates evaluation metrics. Based on the evaluated performance metrics, it selects the optimal intelligent entity and transmits the result to the terminal.

[0177] The device is equipped with an emotion analysis engine that analyzes the user's emotional state from their input and voice. Specifically, it uses natural language processing and speech recognition technologies to acquire the user's emotional information in real time. This emotional information is sent to a server and used to select an intelligent entity. Based on this information, the server selects and configures an intelligent entity that is appropriate for the user's emotional state.

[0178] Users can receive personalized services using pre-configured intelligent entities. For example, a user analyzed as being tired might be offered services such as playing relaxing music or adjusting the lighting environment.

[0179] This system can quickly select the most suitable intelligent entity for the user and make emotion-based adjustments, thereby significantly improving user convenience and satisfaction.

[0180] An example of a prompt would be, "Please suggest which AI agent is best suited to my emotional state today." This allows the system to receive the user's emotional state and use it as data to select the appropriate intelligent entity.

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The server acquires generated data. It collects performance information from intelligent entities and user feedback as input. It automatically retrieves data from external sources via an API, obtaining performance metrics such as response speed and success rate. The output is performance information data for analysis.

[0184] Step 2:

[0185] The device analyzes the user's emotional state. It collects user voice input and text as input and performs natural language processing using an emotion analysis engine. This identifies the user's emotional state, and the emotional data is sent to the server as output.

[0186] Step 3:

[0187] The server calculates evaluation metrics for intelligent entities based on the acquired performance information. It receives performance data for each intelligent entity as input and uses statistical methods to quantify the evaluation metrics for each entity. The output is a list of the evaluated intelligent entities.

[0188] Step 4:

[0189] The server acquires user emotion data and selects the optimal intelligent entity by comparing it with evaluation metrics. The input consists of emotion data and evaluated entity information. This identifies the optimal entity considering the emotional state. The output is information about the selected intelligent entity.

[0190] Step 5:

[0191] The server configures the selected intelligent entity on the terminal. Using the information of the selected entity as input, it performs customized settings according to the user's environment. As a result, the user can immediately use an individually optimized intelligent entity. The output is the configured intelligent entity.

[0192] Step 6:

[0193] Users utilize intelligent entities to streamline their daily tasks. Input consists of user instructions and requests sent to the intelligent entities. The intelligent entities then act upon this input, performing specific tasks. As a result, the user's quality of life improves, and their satisfaction increases. Output includes task completion status and user feedback.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] [Second Embodiment]

[0198] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0199] 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.

[0200] 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).

[0201] 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.

[0202] 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.

[0203] 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).

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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".

[0210] This invention provides a system for automatically selecting and configuring the optimal AI agent for a user. This system selects the agent that best suits the user's needs through a process of collecting, analyzing, and comparing information on the performance of different agents.

[0211] First, the server collects performance data from multiple AI agents. This includes data acquisition using APIs, scraping from user review sites, and incorporating user feedback. This allows for the collection of data such as agent response speed, success rate, and user satisfaction.

[0212] Next, the server analyzes the collected data. This analysis includes sentiment analysis of reviews using natural language processing and calculation of performance metrics using statistical methods. This generates an overall evaluation for each agent.

[0213] Next, the server compares agents based on the analyzed data. The comparison results are presented to the user as a visual ranking and evaluation metrics. This information serves as an important basis for selecting the optimal agent based on the user's workflow and purpose of use.

[0214] The server automatically installs and configures the selected agents. Since users do not need to perform any specific operations regarding agent configuration during this process, the efficiency of system usage is significantly improved.

[0215] As a concrete example, suppose a user is looking for the optimal agent for a text generation task. By using this system, the server analyzes data collected from relevant agents and automates the selection process. Ultimately, the most suitable agent is applied to the user's environment, and the user can immediately utilize its functions. In this way, the present invention reduces the effort and time required for selecting and configuring generation AI agents, thereby realizing efficient business support.

[0216] The following describes the processing flow.

[0217] Step 1:

[0218] The server collects performance data from each generated AI agent. This collection process includes sending periodic requests via APIs and applying scraping techniques from user review sites. This allows the server to obtain data on agent processing speed, success rate, and text information regarding user satisfaction.

[0219] Step 2:

[0220] The server stores the collected data in a database and prepares it for analysis. Data normalization and preprocessing are performed, and the data is organized into a format suitable for analysis.

[0221] Step 3:

[0222] The server uses natural language processing algorithms to perform sentiment analysis on user reviews. This analysis quantifies user satisfaction and dissatisfaction with the agent's use and is used as part of the evaluation metrics.

[0223] Step 4:

[0224] The server applies statistical methods to calculate performance metrics for the agents. Specifically, it uses quantitative data such as response time and processing accuracy to form an overall evaluation score for each agent.

[0225] Step 5:

[0226] The server generates visual comparison graphs and rankings based on these scores, making it easier for users to intuitively understand the comparison results of the agents.

[0227] Step 6:

[0228] The server automatically selects the optimal agent based on the user's business objectives and requirements. This selection is influenced by user-inputted conditions and past usage history.

[0229] Step 7:

[0230] The server installs the selected agent on the user's system and performs the initial setup automatically. This allows the user to immediately use the agent's functions without any additional configuration.

[0231] (Example 1)

[0232] 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."

[0233] There is a need to reduce the time and effort burden on users when selecting and configuring the optimal information processing system. However, conventional methods involve cumbersome data collection and analysis to choose the appropriate system from a large number of options, making it difficult for users to make such decisions. Furthermore, the configuration process after selection is also complex, posing a significant obstacle for users without specialized knowledge.

[0234] 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.

[0235] In this invention, the server includes means for collecting performance information from multiple information processing systems via data collection means, means for analyzing the collected performance information using natural language processing and statistical methods to calculate evaluation metrics for the information processing systems, and means for comparing the information processing systems based on the calculated evaluation metrics. As a result, users can visually select the most suitable information processing system, and the settings after selection are performed automatically, significantly reducing the burden of effort and time.

[0236] "Data acquisition means" refers to a method or device that plays the role of acquiring performance information from multiple information processing systems.

[0237] "Performance information" refers to data related to the operation and functionality of an information processing system, such as response speed, success rate, and user satisfaction.

[0238] "Natural language processing" is a technology that uses computers to analyze, understand, and utilize human language.

[0239] "Statistical methods" are mathematical techniques for collecting, analyzing, interpreting, and representing data.

[0240] "Evaluation indicators" are standards or benchmark values ​​that quantify and show the performance of an information processing system.

[0241] An "information processing system" is a system that includes hardware and software programmed to perform a specific task.

[0242] "Visual presentation" refers to displaying information visually in a way that is easy for users to understand.

[0243] "Automatically setting up" means that the setup is completed through mechanical or programmed actions without human intervention.

[0244] In this embodiment of the invention, the server primarily handles a series of processes, including collecting and analyzing performance information from multiple information processing systems and selecting the appropriate information processing system. The server achieves this using the following methods and techniques.

[0245] First, the server utilizes data collection methods, such as APIs and web scraping techniques, to gather a wide range of performance information from the information processing system. This allows the server to secure diverse data such as response speed, success rate, and user satisfaction.

[0246] Next, the server uses natural language processing technology to analyze the sentiment of the collected user reviews and quantifies the evaluation data. It also employs statistical methods to calculate evaluation metrics for each information processing system from the collected data. This allows for a comprehensive evaluation of different performance elements, resulting in comparable scores.

[0247] The server compares information processing systems based on calculated evaluation metrics and presents the results visually, allowing users to easily select the information processing system that best suits their needs.

[0248] For information processing systems selected by the user, the server automatically configures them. In this process, necessary installation and configuration are automated by the program, freeing the user from the hassle of manual adjustments.

[0249] For example, if a user is looking for an information processing system optimized for text generation, this system analyzes relevant performance information and automates the selection process. Ultimately, the selected information processing system is applied to the user's environment and becomes immediately available. In this way, users can perform their tasks efficiently.

[0250] As a concrete example of a prompt, the instruction "Based on user reviews, please select the most efficient AI agent" can be used. This allows the server to perform appropriate data analysis and select the appropriate information processing system.

[0251] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0252] Step 1:

[0253] The server collects performance information from multiple information processing systems using APIs and web scraping techniques. It obtains access information from information processing systems and URLs of user review sites as input. Based on this input, the server collects performance data such as response speed, success rate, and user satisfaction, and structures and stores this data. The output is the collected structured data.

[0254] Step 2:

[0255] The server analyzes the collected performance information. It uses the structured data collected in step 1 as input. The server performs sentiment analysis of user reviews using natural language processing, quantifying positive, negative, and neutral ratings. Furthermore, it uses statistical methods to organize data on response speed and success rate, calculating an overall evaluation index for each information processing system. The output is analyzed data including the evaluation index.

[0256] Step 3:

[0257] The server compares information processing systems based on the analyzed data. It uses the evaluation metrics obtained in step 2 as input. Based on these metrics, the server generates a ranking of the information processing systems and organizes the data in a visually comparable format. Specifically, it creates graphs and charts and displays them clearly on the user interface. The output provides visualized comparative information.

[0258] Step 4:

[0259] The user selects a suitable information processing system based on visualized comparative information. The data visualized in step 3 is provided as input. Based on this input, the user selects the optimal information processing system according to their business needs. The selection is made using clicks and taps on the user interface. The output provides information about the selected information processing system.

[0260] Step 5:

[0261] The server automatically configures the information processing system selected by the user. It uses the information about the information processing system selected in step 4 as input. The server executes the system's installation script and automatically applies the necessary configurations. Specifically, the API key input and environment settings adjustments are performed programmatically. The configured information processing system is then provided to the user environment as output.

[0262] (Application Example 1)

[0263] 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."

[0264] Selecting and configuring the most suitable AI agent from a diverse range of agents to meet user needs requires advanced expertise and is time-consuming and labor-intensive. Furthermore, electronic payments constantly face security threats and the risk of fraudulent use, necessitating the rapid selection of the most appropriate security measures.

[0265] 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.

[0266] In this invention, the server includes means for collecting characteristic information of artificial intelligence agents using generated information, means for analyzing the collected characteristic information and evaluating the characteristic indicators of each artificial intelligence agent, and means for analyzing payment history and patterns to select the safest and most appropriate artificial intelligence agent and enhance security. This enables the automatic selection of artificial intelligence agents that meet user needs and rapid security enhancement.

[0267] "Generated information" refers to the data necessary to evaluate the characteristics of an artificial intelligence agent. This data includes information about the agent's performance and user evaluations.

[0268] An "artificial intelligence agent" is a program that has the ability to autonomously perform specific tasks, and typically utilizes machine learning and natural language processing technologies.

[0269] "Characteristic information" refers to various pieces of information related to the performance and functions of an artificial intelligence agent, and is used as a standard for evaluation and comparison.

[0270] A "characteristic index" is an evaluation criterion that quantifies or scores the performance of an artificial intelligence agent, and is used for comparison and selection.

[0271] "Payment history and patterns" refers to a user's past transaction data and trends, which are important factors for enhancing security and selecting appropriate agents.

[0272] "Methods to enhance security" refer to measures and technologies used to protect systems from misuse and fraud, and are employed to ensure user safety.

[0273] To realize this invention, it is necessary to construct a data collection and analysis system using a server. The server will use the generated information to collect and analyze characteristic information of the artificial intelligence agent. This includes a process of collecting information from multiple data sources. Specifically, it will utilize data collection via APIs and scraping techniques from user review sites.

[0274] The server runs on a Python-based program and utilizes Flask as its backend framework. Machine learning libraries such as TensorFlow and PyTorch are used for performance analysis. These tools are used to analyze characteristic information and generate characteristic metrics for each artificial intelligence agent.

[0275] The user terminal displays characteristic indicators based on analyzed data and provides a means for selecting an agent. The selected agent is automatically applied to the user terminal, ensuring safe and efficient operation. In particular, security is enhanced by analyzing payment history and patterns on the server and selecting the optimal agent.

[0276] As a specific example, when a user makes an electronic payment during an overseas trip, the system automatically analyzes the payment pattern, selects the optimal AI agent, and enhances the fraud detection function. As a result, the user can make payments with confidence. The system generates a prompt such as "Please instruct me on how to select the optimal AI agent for overseas use and detect unauthorized use."

[0277] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0278] Step 1:

[0279] The server receives a request from the user terminal. This request contains information regarding the user's requests and needs. Based on this information, the server prepares to start appropriate data collection.

[0280] Step 2:

[0281] The server collects characteristic information from multiple artificial intelligence agents through the API. Specifically, it obtains performance data, response speed, success rate, etc. of each agent. For this data collection, the API endpoints of the specified agents are used. The input is an API request, and the output is a collection of characteristic data.

[0282] Step 3:

[0283] The server analyzes the collected characteristic information. In this analysis, TensorFlow or PyTorch is used to calculate the characteristic indicators of each agent and perform a performance evaluation. The input is the collected characteristic data, and the output is the characteristic indicators of each agent. The analysis results are generated through data processing by training the model.

[0284] Step 4:

[0285] The server compares artificial intelligence agents based on the analyzed characteristic indicators. In this comparison, ranking is performed based on the characteristic indicators to select the optimal agent. The input is a set of characteristic indicators, and the output is the selected optimal agent. Here, factors such as the degree of fit with user needs and safety are also considered.

[0286] Step 5:

[0287] The server sets the selected agent to the user terminal. In this step, a script for quickly introducing the functions of the selected agent into the user environment is executed. The input is the selected agent information, and the output is the agent activated on the user terminal.

[0288] Step 6:

[0289] The server analyzes the user's payment history and patterns and strengthens security by selecting the optimal artificial intelligence agent again. Here, an anti-fraud detection model is applied based on past transaction data. The input is the payment history, and the output is the related agent with enhanced security settings.

[0290] Step 7:

[0291] The user uses the artificial intelligence agent set by the server to perform actions such as electronic payment. At this time, the previously set prompt sentence "Please indicate how to select the optimal AI agent for overseas use and detect unauthorized use" functions as a basis. The input is the user action, and the output is a safe and quickly completed transaction.

[0292] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0293] This invention provides a system for effectively selecting and configuring AI agents by combining generated data and an emotion engine. This system automates the process of selecting the agent best suited to the user's needs by collecting, analyzing, and comparing agent performance information. Furthermore, it uses an emotion engine to recognize the user's emotional state and reflects the results in agent selection and configuration, thereby providing a more user-friendly solution.

[0294] First, the server collects performance data from multiple AI agents. This includes data acquisition via APIs and text collection from user review sites, encompassing agent response speed, success rate, and user feedback sentiment.

[0295] Next, the device analyzes the user's real-time emotional state via an emotion engine. This engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. The results of the emotion engine's analysis are then incorporated into the subsequent agent selection process.

[0296] Next, the server analyzes the generated data and calculates performance metrics for each agent using statistical methods. This analysis also takes into account collected user reviews and sentiment data, thereby quantifying the agent's satisfaction level and efficiency.

[0297] The server then compares agents based on the analysis results. It selects the optimal agent by comparing it with the user's emotional data and business objectives. In this selection process, the user's emotional state is directly reflected in the agent settings and selection results, resulting in a more personalized experience.

[0298] Finally, the server automatically installs the selected agent into the user's environment and performs the initial setup. Users can immediately use the customized agent from the first boot, and this invention achieves improved operational efficiency and user experience.

[0299] For example, if a user is looking for an AI agent suitable for call center work, this system will select the optimal agent after considering the stress level of the work. The selected agent will be configured based on the user's emotional state, thereby enhancing the support system in call center operations. Such automated processes support users' work and improve convenience.

[0300] The following describes the processing flow.

[0301] Step 1:

[0302] The server periodically retrieves relevant data using an API to collect performance data from each generated AI agent. This process includes information such as the success rate and response time of tasks handled by the agent. Furthermore, it performs scraping from user review sites to collect user feedback on the agents in text format.

[0303] Step 2:

[0304] The device activates an emotion engine to recognize the user's real-time emotional state. This engine analyzes the user's emotions, such as excitement and anxiety levels, through voice analysis and text sentiment analysis, and stores the results as emotion data. This information is obtained from the voice and text input when the user interacts with the system.

[0305] Step 3:

[0306] The server starts the analysis process using the collected performance data and sentiment data. It performs sentiment analysis on user reviews using natural language processing technology to quantify user satisfaction. Also, it uses statistical analysis tools to calculate performance metrics such as response time and accuracy, and generates an evaluation score for each agent.

[0307] Step 4:

[0308] The server automatically compares agents by combining the generated evaluation scores and the user's sentiment state. This process is carried out through a visual dashboard, taking into account sentiment data so that agents that are easier for users to consciously respond to are selected.

[0309] Step 5:

[0310] The server selects the optimal agent based on the user's business purpose and sentiment state. The selected agent is displayed as a proposal to the user, and the characteristics and past performance of the agent are detailed as the reasons.

[0311] Step 6:

[0312] The server installs the selected agent on the user's terminal and applies a pre-set profile. This operation proceeds fully automatically, and the user does not need to make any particular settings changes. As a result, the user can immediately utilize the improved service provided by the selected agent. [[ID=D26]]

[0313] (Example 2)

[0314] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] In user environments utilizing intelligent agents, the process of evaluating and selecting agent performance is not efficient, and selecting the optimal agent, particularly one that takes the user's emotional state into consideration, is a challenge. Furthermore, the complex agent configuration process impairs user convenience.

[0316] 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.

[0317] In this invention, the server includes means for collecting performance information of intelligent agents using generated data, means for analyzing the collected performance information and user evaluations to evaluate the performance indicators of each intelligent agent, and means for selecting the optimal intelligent agent based on the comparison results and the user's emotional state. This enables the automatic selection and setting of the optimal intelligent agent adapted to the user's emotional state, thereby realizing the construction of an efficient user environment.

[0318] "Generated data" refers to information and numerical data collected to evaluate the performance and operation of intelligent agents.

[0319] An "intelligent agent" refers to a software function that uses natural language processing and machine learning algorithms to automate specific tasks based on user instructions.

[0320] "Performance information" refers to indicators and data related to the capabilities and characteristics of an intelligent agent, specifically information on evaluation items such as response speed and success rate.

[0321] "User evaluation" refers to feedback and emotional ratings provided by users based on their experience using intelligent agents.

[0322] "Emotional state" refers to information that represents the emotions and psychological state a user is feeling at a specific point in time, such as stress levels or satisfaction levels.

[0323] "Performance metrics" refer to scores or metrics used to numerically evaluate the performance of intelligent agents.

[0324] "Automatically setting" means that the system will configure and adjust settings based on pre-programmed conditions without manual intervention.

[0325] This invention provides a system for effectively selecting and configuring intelligent agents by combining generated data and an emotion engine. The objective of this system is to improve the user experience by automatically selecting and configuring the optimal agent to meet the user's needs.

[0326] First, the server uses generated data to collect performance information about the intelligent agent. This collection includes data acquisition via APIs and text collection from user review sites. This information includes data on various performance metrics, such as the agent's response speed, success rate, and user feedback sentiment.

[0327] Next, the device uses an emotion engine to analyze the user's real-time emotional state. This emotion engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. For example, if the user enters keywords such as "tired" or "busy," the emotion engine analyzes this as emotional data. This information is used to consider the user's psychological state in the subsequent intelligent agent selection process.

[0328] As a concrete example, consider a user inputting a prompt into an AI model saying, "Please select the agent that can respond most calmly when I am feeling stressed." The system then automatically selects the most suitable intelligent agent based on the user's emotions, installs it in the user's environment, and performs initial setup. This allows the user to comfortably use the intelligent agent even in stressful situations.

[0329] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0330] Step 1:

[0331] The server uses generated data to collect performance information from intelligent agents. Input at this stage includes API responses from agent providers and text data from user review sites. The server receives this input, analyzes information such as response speed, success rate, and user feedback sentiment, and outputs performance metric data. This process involves data format conversion and extraction of key information to compile a comprehensive evaluation of the agent's performance.

[0332] Step 2:

[0333] The device uses an emotion engine to analyze the user's real-time emotional state. Input here consists of text and voice data from the user. The device receives this data and, utilizing natural language processing and speech analysis technologies, outputs emotional information such as positive or negative. Specifically, an emotion analysis algorithm scans the user's words and voice tone, and provides the results as numerical emotional data.

[0334] Step 3:

[0335] The server analyzes the collected performance metric data and sentiment data, and evaluates the performance metrics of each intelligent agent using statistical methods. The input consists of performance metric data from Step 1 and sentiment data from Step 2. The server integrates this data, evaluates agent responsiveness and user adaptability, and outputs candidates for the optimal agent. This analysis process uses regression analysis and clustering methods to perform a multifaceted evaluation.

[0336] Step 4:

[0337] The server compares intelligent agents based on the analysis results and selects the agent that best matches the user's emotional state and business objectives. The input is a list of optimal agent candidates obtained from step 3. The server evaluates this list and selects the most suitable agent as the final output. This process involves ranking agents based on evaluation scores and checking their suitability to the user's business objectives.

[0338] Step 5:

[0339] The server automatically configures the selected agent in the user's environment. The input is the agent information selected in step 4. Based on this information, the server performs the necessary installation and customization, and the output is an agent optimized for the user's environment. In this step, an environment configuration script is used to complete the setup so that the user can use it immediately.

[0340] (Application Example 2)

[0341] 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."

[0342] Conventional intelligent entity selection systems fail to adequately address the diverse emotional states of users, making it difficult to provide optimal intelligent entities tailored to individual needs. Furthermore, they lack mechanisms to directly reflect user evaluations, resulting in insufficient adaptability and satisfaction levels with selected intelligent entities. This leads to a challenge in that improvements in user convenience are limited.

[0343] 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.

[0344] In this invention, the server includes means for acquiring performance information of intelligent entities using generated data, means for analyzing the acquired performance information and evaluating the performance indicators of each intelligent entity, means for comparing intelligent entities based on the evaluated performance indicators, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the intelligent entities based on the user's emotional state. This makes it possible to automatically select and set individually optimized intelligent entities that take into account the diverse emotional states of the user.

[0345] "Generated data" refers to information used to evaluate the performance of intelligent entities, and includes user feedback and reaction data.

[0346] An "intelligent entity" is an artificial intelligence-based agent or system that operates according to user needs and is a program that has the function of performing a specific task.

[0347] "Performance information" refers to data about the actions performed by an intelligent entity and their results, including metrics such as response speed, success rate, and user satisfaction.

[0348] An "emotion analysis engine" is software or a system that analyzes a user's emotional state in real time, and utilizes speech recognition and natural language processing technologies.

[0349] A "user" is an individual or organization that uses intelligent entities and is subject to service customization based on their needs and responses.

[0350] "Evaluation metrics" are standards or parameters used to quantify and evaluate the performance of intelligent entities, and they play a crucial role in improving the user experience.

[0351] The system that realizes this invention consists of a server, a terminal, and an interface with the user. The server uses generated data to acquire performance information of intelligent entities, analyzes the performance information, and calculates evaluation metrics. Based on the evaluated performance metrics, it selects the optimal intelligent entity and transmits the result to the terminal.

[0352] The device is equipped with an emotion analysis engine that analyzes the user's emotional state from their input and voice. Specifically, it uses natural language processing and speech recognition technologies to acquire the user's emotional information in real time. This emotional information is sent to a server and used to select an intelligent entity. Based on this information, the server selects and configures an intelligent entity that is appropriate for the user's emotional state.

[0353] Users can receive personalized services using pre-configured intelligent entities. For example, a user analyzed as being tired might be offered services such as playing relaxing music or adjusting the lighting environment.

[0354] This system can quickly select the most suitable intelligent entity for the user and make emotion-based adjustments, thereby significantly improving user convenience and satisfaction.

[0355] An example of a prompt would be, "Please suggest which AI agent is best suited to my emotional state today." This allows the system to receive the user's emotional state and use it as data to select the appropriate intelligent entity.

[0356] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0357] Step 1:

[0358] The server acquires generated data. It collects performance information from intelligent entities and user feedback as input. It automatically retrieves data from external sources via an API, obtaining performance metrics such as response speed and success rate. The output is performance information data for analysis.

[0359] Step 2:

[0360] The device analyzes the user's emotional state. It collects user voice input and text as input and performs natural language processing using an emotion analysis engine. This identifies the user's emotional state, and the emotional data is sent to the server as output.

[0361] Step 3:

[0362] The server calculates evaluation metrics for intelligent entities based on the acquired performance information. It receives performance data for each intelligent entity as input and uses statistical methods to quantify the evaluation metrics for each entity. The output is a list of the evaluated intelligent entities.

[0363] Step 4:

[0364] The server acquires user emotion data and selects the optimal intelligent entity by comparing it with evaluation metrics. The input consists of emotion data and evaluated entity information. This identifies the optimal entity considering the emotional state. The output is information about the selected intelligent entity.

[0365] Step 5:

[0366] The server configures the selected intelligent entity on the terminal. Using the information of the selected entity as input, it performs customized settings according to the user's environment. As a result, the user can immediately use an individually optimized intelligent entity. The output is the configured intelligent entity.

[0367] Step 6:

[0368] Users utilize intelligent entities to streamline their daily tasks. Input consists of user instructions and requests sent to the intelligent entities. The intelligent entities then act upon this input, performing specific tasks. As a result, the user's quality of life improves, and their satisfaction increases. Output includes task completion status and user feedback.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] [Third Embodiment]

[0373] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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".

[0385] This invention provides a system for automatically selecting and configuring the optimal AI agent for a user. This system selects the agent that best suits the user's needs through a process of collecting, analyzing, and comparing information on the performance of different agents.

[0386] First, the server collects performance data from multiple AI agents. This includes data acquisition using APIs, scraping from user review sites, and incorporating user feedback. This allows for the collection of data such as agent response speed, success rate, and user satisfaction.

[0387] Next, the server analyzes the collected data. This analysis includes sentiment analysis of reviews using natural language processing and calculation of performance metrics using statistical methods. This generates an overall evaluation for each agent.

[0388] Next, the server compares agents based on the analyzed data. The comparison results are presented to the user as a visual ranking and evaluation metrics. This information serves as an important basis for selecting the optimal agent based on the user's workflow and purpose of use.

[0389] The server automatically installs and configures the selected agents. Since users do not need to perform any specific operations regarding agent configuration during this process, the efficiency of system usage is significantly improved.

[0390] As a concrete example, suppose a user is looking for the optimal agent for a text generation task. By using this system, the server analyzes data collected from relevant agents and automates the selection process. Ultimately, the most suitable agent is applied to the user's environment, and the user can immediately utilize its functions. In this way, the present invention reduces the effort and time required for selecting and configuring generation AI agents, thereby realizing efficient business support.

[0391] The following describes the processing flow.

[0392] Step 1:

[0393] The server collects performance data from each generated AI agent. This collection process includes sending periodic requests via APIs and applying scraping techniques from user review sites. This allows the server to obtain data on agent processing speed, success rate, and text information regarding user satisfaction.

[0394] Step 2:

[0395] The server stores the collected data in a database and prepares it for analysis. Data normalization and preprocessing are performed, and the data is organized into a format suitable for analysis.

[0396] Step 3:

[0397] The server uses natural language processing algorithms to perform sentiment analysis on user reviews. This analysis quantifies user satisfaction and dissatisfaction with the agent's use and is used as part of the evaluation metrics.

[0398] Step 4:

[0399] The server applies statistical methods to calculate performance metrics for the agents. Specifically, it uses quantitative data such as response time and processing accuracy to form an overall evaluation score for each agent.

[0400] Step 5:

[0401] The server generates visual comparison graphs and rankings based on these scores, making it easier for users to intuitively understand the comparison results of the agents.

[0402] Step 6:

[0403] The server automatically selects the optimal agent based on the user's business objectives and requirements. This selection is influenced by user-inputted conditions and past usage history.

[0404] Step 7:

[0405] The server installs the selected agent on the user's system and performs the initial setup automatically. This allows the user to immediately use the agent's functions without any additional configuration.

[0406] (Example 1)

[0407] 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."

[0408] There is a need to reduce the time and effort burden on users when selecting and configuring the optimal information processing system. However, conventional methods involve cumbersome data collection and analysis to choose the appropriate system from a large number of options, making it difficult for users to make such decisions. Furthermore, the configuration process after selection is also complex, posing a significant obstacle for users without specialized knowledge.

[0409] 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.

[0410] In this invention, the server includes means for collecting performance information from multiple information processing systems via data collection means, means for analyzing the collected performance information using natural language processing and statistical methods to calculate evaluation metrics for the information processing systems, and means for comparing the information processing systems based on the calculated evaluation metrics. As a result, users can visually select the most suitable information processing system, and the settings after selection are performed automatically, significantly reducing the burden of effort and time.

[0411] "Data acquisition means" refers to a method or device that plays the role of acquiring performance information from multiple information processing systems.

[0412] "Performance information" refers to data related to the operation and functionality of an information processing system, such as response speed, success rate, and user satisfaction.

[0413] "Natural language processing" is a technology that uses computers to analyze, understand, and utilize human language.

[0414] "Statistical methods" are mathematical techniques for collecting, analyzing, interpreting, and representing data.

[0415] "Evaluation indicators" are standards or benchmark values ​​that quantify and show the performance of an information processing system.

[0416] An "information processing system" is a system that includes hardware and software programmed to perform a specific task.

[0417] "Visual presentation" refers to displaying information visually in a way that is easy for users to understand.

[0418] "Automatically setting up" means that the setup is completed through mechanical or programmed actions without human intervention.

[0419] In this embodiment of the invention, the server primarily handles a series of processes, including collecting and analyzing performance information from multiple information processing systems and selecting the appropriate information processing system. The server achieves this using the following methods and techniques.

[0420] First, the server utilizes data collection methods, such as APIs and web scraping techniques, to gather a wide range of performance information from the information processing system. This allows the server to secure diverse data such as response speed, success rate, and user satisfaction.

[0421] Next, the server uses natural language processing technology to analyze the sentiment of the collected user reviews and quantifies the evaluation data. It also employs statistical methods to calculate evaluation metrics for each information processing system from the collected data. This allows for a comprehensive evaluation of different performance elements, resulting in comparable scores.

[0422] The server compares information processing systems based on calculated evaluation metrics and presents the results visually, allowing users to easily select the information processing system that best suits their needs.

[0423] For information processing systems selected by the user, the server automatically configures them. In this process, necessary installation and configuration are automated by the program, freeing the user from the hassle of manual adjustments.

[0424] For example, if a user is looking for an information processing system optimized for text generation, this system analyzes relevant performance information and automates the selection process. Ultimately, the selected information processing system is applied to the user's environment and becomes immediately available. In this way, users can perform their tasks efficiently.

[0425] As a concrete example of a prompt, the instruction "Based on user reviews, please select the most efficient AI agent" can be used. This allows the server to perform appropriate data analysis and select the appropriate information processing system.

[0426] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0427] Step 1:

[0428] The server collects performance information from multiple information processing systems using APIs and web scraping techniques. It obtains access information from information processing systems and URLs of user review sites as input. Based on this input, the server collects performance data such as response speed, success rate, and user satisfaction, and structures and stores this data. The output is the collected structured data.

[0429] Step 2:

[0430] The server analyzes the collected performance information. It uses the structured data collected in step 1 as input. The server performs sentiment analysis of user reviews using natural language processing, quantifying positive, negative, and neutral ratings. Furthermore, it uses statistical methods to organize data on response speed and success rate, calculating an overall evaluation index for each information processing system. The output is analyzed data including the evaluation index.

[0431] Step 3:

[0432] The server compares information processing systems based on the analyzed data. It uses the evaluation metrics obtained in step 2 as input. Based on these metrics, the server generates a ranking of the information processing systems and organizes the data in a visually comparable format. Specifically, it creates graphs and charts and displays them clearly on the user interface. The output provides visualized comparative information.

[0433] Step 4:

[0434] The user selects a suitable information processing system based on visualized comparative information. The data visualized in step 3 is provided as input. Based on this input, the user selects the optimal information processing system according to their business needs. The selection is made using clicks and taps on the user interface. The output provides information about the selected information processing system.

[0435] Step 5:

[0436] The server automatically configures the information processing system selected by the user. It uses the information about the information processing system selected in step 4 as input. The server executes the system's installation script and automatically applies the necessary configurations. Specifically, the API key input and environment settings adjustments are performed programmatically. The configured information processing system is then provided to the user environment as output.

[0437] (Application Example 1)

[0438] 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."

[0439] Selecting and configuring the most suitable AI agent from a diverse range of agents to meet user needs requires advanced expertise and is time-consuming and labor-intensive. Furthermore, electronic payments constantly face security threats and the risk of fraudulent use, necessitating the rapid selection of the most appropriate security measures.

[0440] 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.

[0441] In this invention, the server includes means for collecting characteristic information of artificial intelligence agents using generated information, means for analyzing the collected characteristic information and evaluating the characteristic indicators of each artificial intelligence agent, and means for analyzing payment history and patterns to select the safest and most appropriate artificial intelligence agent and enhance security. This enables the automatic selection of artificial intelligence agents that meet user needs and rapid security enhancement.

[0442] "Generated information" refers to the data necessary to evaluate the characteristics of an artificial intelligence agent. This data includes information about the agent's performance and user evaluations.

[0443] An "artificial intelligence agent" is a program that has the ability to autonomously perform specific tasks, and typically utilizes machine learning and natural language processing technologies.

[0444] "Characteristic information" refers to various pieces of information related to the performance and functions of an artificial intelligence agent, and is used as a standard for evaluation and comparison.

[0445] A "characteristic index" is an evaluation criterion that quantifies or scores the performance of an artificial intelligence agent, and is used for comparison and selection.

[0446] "Payment history and patterns" refers to a user's past transaction data and trends, which are important factors for enhancing security and selecting appropriate agents.

[0447] "Methods to enhance security" refer to measures and technologies used to protect systems from misuse and fraud, and are employed to ensure user safety.

[0448] To realize this invention, it is necessary to construct a data collection and analysis system using a server. The server will use the generated information to collect and analyze characteristic information of the artificial intelligence agent. This includes a process of collecting information from multiple data sources. Specifically, it will utilize data collection via APIs and scraping techniques from user review sites.

[0449] The server runs on a Python-based program and utilizes Flask as its backend framework. Machine learning libraries such as TensorFlow and PyTorch are used for performance analysis. These tools are used to analyze characteristic information and generate characteristic metrics for each artificial intelligence agent.

[0450] The user terminal displays characteristic indicators based on analyzed data and provides a means for selecting an agent. The selected agent is automatically applied to the user terminal, ensuring safe and efficient operation. In particular, security is enhanced by analyzing payment history and patterns on the server and selecting the optimal agent.

[0451] As a concrete example, when a user makes an electronic payment while traveling abroad, the system automatically analyzes the payment pattern, selects the optimal AI agent, and enhances fraud detection capabilities. This allows users to make payments with peace of mind. The system generates a prompt message such as, "Please select the optimal AI agent for overseas use and instruct me on how to detect fraudulent activity."

[0452] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0453] Step 1:

[0454] The server receives a request from the user's terminal. This request contains information about the user's requests and needs. Based on this information, the server prepares to begin collecting appropriate data.

[0455] Step 2:

[0456] The server collects characteristic information from multiple artificial intelligence agents via APIs. Specifically, it obtains performance data, response speed, success rate, etc., for each agent. This data collection uses the API endpoint of the specified agent. The input is an API request, and the output is a collection of characteristic data.

[0457] Step 3:

[0458] The server analyzes the collected characteristic information. This analysis uses TensorFlow or PyTorch to calculate characteristic metrics for each agent and evaluate their performance. The input is the collected characteristic data, and the output is the characteristic metrics for each agent. The analysis results are generated after data processing through model training.

[0459] Step 4:

[0460] The server compares artificial intelligence agents based on the analyzed characteristic metrics. This comparison ranks the agents based on these metrics and selects the optimal agent. The input is a set of characteristic metrics, and the output is the selected optimal agent. Factors such as the degree of fit to user needs and safety are also considered.

[0461] Step 5:

[0462] The server configures the selected agent on the user terminal. In this step, a script is executed to quickly deploy the selected agent's functions to the user environment. The input is the selected agent information, and the output is the agent activated on the user terminal.

[0463] Step 6:

[0464] The server enhances security by analyzing the user's payment history and patterns, and then selecting the most suitable artificial intelligence agent. Here, a fraud detection model is applied based on past transaction data. The input is the payment history, and the output is the relevant agent with enhanced security settings.

[0465] Step 7:

[0466] The user uses an artificial intelligence agent configured by the server to perform actions such as electronic payments. This process is based on a previously configured prompt: "Select the optimal AI agent for overseas use and instruct on how to detect fraudulent activity." The input is the user action, and the output is the securely and quickly completed transaction.

[0467] 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.

[0468] This invention provides a system for effectively selecting and configuring AI agents by combining generated data and an emotion engine. This system automates the process of selecting the agent best suited to the user's needs by collecting, analyzing, and comparing agent performance information. Furthermore, it uses an emotion engine to recognize the user's emotional state and reflects the results in agent selection and configuration, thereby providing a more user-friendly solution.

[0469] First, the server collects performance data from multiple AI agents. This includes data acquisition via APIs and text collection from user review sites, encompassing agent response speed, success rate, and user feedback sentiment.

[0470] Next, the device analyzes the user's real-time emotional state via an emotion engine. This engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. The results of the emotion engine's analysis are then incorporated into the subsequent agent selection process.

[0471] Next, the server analyzes the generated data and calculates performance metrics for each agent using statistical methods. This analysis also takes into account collected user reviews and sentiment data, thereby quantifying the agent's satisfaction level and efficiency.

[0472] The server then compares agents based on the analysis results. It selects the optimal agent by comparing it with the user's emotional data and business objectives. In this selection process, the user's emotional state is directly reflected in the agent settings and selection results, resulting in a more personalized experience.

[0473] Finally, the server automatically installs the selected agent into the user's environment and performs the initial setup. Users can immediately use the customized agent from the first boot, and this invention achieves improved operational efficiency and user experience.

[0474] For example, if a user is looking for an AI agent suitable for call center work, this system will select the optimal agent after considering the stress level of the work. The selected agent will be configured based on the user's emotional state, thereby enhancing the support system in call center operations. Such automated processes support users' work and improve convenience.

[0475] The following describes the processing flow.

[0476] Step 1:

[0477] The server periodically retrieves relevant data using an API to collect performance data from each generated AI agent. This process includes information such as the success rate and response time of tasks handled by the agent. Furthermore, it performs scraping from user review sites to collect user feedback on the agents in text format.

[0478] Step 2:

[0479] The device activates an emotion engine to recognize the user's real-time emotional state. This engine analyzes the user's emotions, such as excitement and anxiety levels, through voice analysis and text sentiment analysis, and stores the results as emotion data. This information is obtained from the voice and text input when the user interacts with the system.

[0480] Step 3:

[0481] The server initiates the analysis process using the collected performance and sentiment data. It utilizes natural language processing techniques to analyze user reviews and quantify user satisfaction. Furthermore, statistical analysis tools are used to calculate performance metrics such as response time and accuracy, generating evaluation scores for each agent.

[0482] Step 4:

[0483] The server automatically compares agents by combining the generated evaluation scores with the user's emotional state. This process is carried out through a visual dashboard, taking emotional data into account to select agents that the user is more likely to consciously respond to.

[0484] Step 5:

[0485] The server selects the most suitable agent based on the user's business objectives and emotional state. The selected agent is displayed to the user as a suggestion, with detailed explanations of the agent's characteristics and past performance as the reason for the selection.

[0486] Step 6:

[0487] The server installs the selected agent on the user's terminal and applies a pre-configured profile. This process is fully automated, and the user does not need to change any settings. As a result, the user can immediately enjoy improved service provided by the selected agent.

[0488] (Example 2)

[0489] 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."

[0490] In user environments utilizing intelligent agents, the process of evaluating and selecting agent performance is not efficient, and selecting the optimal agent, particularly one that takes the user's emotional state into consideration, is a challenge. Furthermore, the complex agent configuration process impairs user convenience.

[0491] 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.

[0492] In this invention, the server includes means for collecting performance information of intelligent agents using generated data, means for analyzing the collected performance information and user evaluations to evaluate the performance indicators of each intelligent agent, and means for selecting the optimal intelligent agent based on the comparison results and the user's emotional state. This enables the automatic selection and setting of the optimal intelligent agent adapted to the user's emotional state, thereby realizing the construction of an efficient user environment.

[0493] "Generated data" refers to information and numerical data collected to evaluate the performance and operation of intelligent agents.

[0494] An "intelligent agent" refers to a software function that uses natural language processing and machine learning algorithms to automate specific tasks based on user instructions.

[0495] "Performance information" refers to indicators and data related to the capabilities and characteristics of an intelligent agent, specifically information on evaluation items such as response speed and success rate.

[0496] "User evaluation" refers to feedback and emotional ratings provided by users based on their experience using intelligent agents.

[0497] "Emotional state" refers to information that represents the emotions and psychological state a user is feeling at a specific point in time, such as stress levels or satisfaction levels.

[0498] "Performance metrics" refer to scores or metrics used to numerically evaluate the performance of intelligent agents.

[0499] "Automatically setting" means that the system will configure and adjust settings based on pre-programmed conditions without manual intervention.

[0500] This invention provides a system for effectively selecting and configuring intelligent agents by combining generated data and an emotion engine. The objective of this system is to improve the user experience by automatically selecting and configuring the optimal agent to meet the user's needs.

[0501] First, the server uses generated data to collect performance information about the intelligent agent. This collection includes data acquisition via APIs and text collection from user review sites. This information includes data on various performance metrics, such as the agent's response speed, success rate, and user feedback sentiment.

[0502] Next, the device uses an emotion engine to analyze the user's real-time emotional state. This emotion engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. For example, if the user enters keywords such as "tired" or "busy," the emotion engine analyzes this as emotional data. This information is used to consider the user's psychological state in the subsequent intelligent agent selection process.

[0503] As a concrete example, consider a user inputting a prompt into an AI model saying, "Please select the agent that can respond most calmly when I am feeling stressed." The system then automatically selects the most suitable intelligent agent based on the user's emotions, installs it in the user's environment, and performs initial setup. This allows the user to comfortably use the intelligent agent even in stressful situations.

[0504] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0505] Step 1:

[0506] The server uses generated data to collect performance information from intelligent agents. Input at this stage includes API responses from agent providers and text data from user review sites. The server receives this input, analyzes information such as response speed, success rate, and user feedback sentiment, and outputs performance metric data. This process involves data format conversion and extraction of key information to compile a comprehensive evaluation of the agent's performance.

[0507] Step 2:

[0508] The device uses an emotion engine to analyze the user's real-time emotional state. Input here consists of text and voice data from the user. The device receives this data and, utilizing natural language processing and speech analysis technologies, outputs emotional information such as positive or negative. Specifically, an emotion analysis algorithm scans the user's words and voice tone, and provides the results as numerical emotional data.

[0509] Step 3:

[0510] The server analyzes the collected performance metric data and sentiment data, and evaluates the performance metrics of each intelligent agent using statistical methods. The input consists of performance metric data from Step 1 and sentiment data from Step 2. The server integrates this data, evaluates agent responsiveness and user adaptability, and outputs candidates for the optimal agent. This analysis process uses regression analysis and clustering methods to perform a multifaceted evaluation.

[0511] Step 4:

[0512] The server compares intelligent agents based on the analysis results and selects the agent that best matches the user's emotional state and business objectives. The input is a list of optimal agent candidates obtained from step 3. The server evaluates this list and selects the most suitable agent as the final output. This process involves ranking agents based on evaluation scores and checking their suitability to the user's business objectives.

[0513] Step 5:

[0514] The server automatically configures the selected agent in the user's environment. The input is the agent information selected in step 4. Based on this information, the server performs the necessary installation and customization, and the output is an agent optimized for the user's environment. In this step, an environment configuration script is used to complete the setup so that the user can use it immediately.

[0515] (Application Example 2)

[0516] 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."

[0517] Conventional intelligent entity selection systems fail to adequately address the diverse emotional states of users, making it difficult to provide optimal intelligent entities tailored to individual needs. Furthermore, they lack mechanisms to directly reflect user evaluations, resulting in insufficient adaptability and satisfaction levels with selected intelligent entities. This leads to a challenge in that improvements in user convenience are limited.

[0518] 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.

[0519] In this invention, the server includes means for acquiring performance information of intelligent entities using generated data, means for analyzing the acquired performance information and evaluating the performance indicators of each intelligent entity, means for comparing intelligent entities based on the evaluated performance indicators, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the intelligent entities based on the user's emotional state. This makes it possible to automatically select and set individually optimized intelligent entities that take into account the diverse emotional states of the user.

[0520] "Generated data" refers to information used to evaluate the performance of intelligent entities, and includes user feedback and reaction data.

[0521] An "intelligent entity" is an artificial intelligence-based agent or system that operates according to user needs and is a program that has the function of performing a specific task.

[0522] "Performance information" refers to data about the actions performed by an intelligent entity and their results, including metrics such as response speed, success rate, and user satisfaction.

[0523] An "emotion analysis engine" is software or a system that analyzes a user's emotional state in real time, and utilizes speech recognition and natural language processing technologies.

[0524] A "user" is an individual or organization that uses intelligent entities and is subject to service customization based on their needs and responses.

[0525] "Evaluation metrics" are standards or parameters used to quantify and evaluate the performance of intelligent entities, and they play a crucial role in improving the user experience.

[0526] The system that realizes this invention consists of a server, a terminal, and an interface with the user. The server uses generated data to acquire performance information of intelligent entities, analyzes the performance information, and calculates evaluation metrics. Based on the evaluated performance metrics, it selects the optimal intelligent entity and transmits the result to the terminal.

[0527] The device is equipped with an emotion analysis engine that analyzes the user's emotional state from their input and voice. Specifically, it uses natural language processing and speech recognition technologies to acquire the user's emotional information in real time. This emotional information is sent to a server and used to select an intelligent entity. Based on this information, the server selects and configures an intelligent entity that is appropriate for the user's emotional state.

[0528] Users can receive personalized services using pre-configured intelligent entities. For example, a user analyzed as being tired might be offered services such as playing relaxing music or adjusting the lighting environment.

[0529] This system can quickly select the most suitable intelligent entity for the user and make emotion-based adjustments, thereby significantly improving user convenience and satisfaction.

[0530] An example of a prompt would be, "Please suggest which AI agent is best suited to my emotional state today." This allows the system to receive the user's emotional state and use it as data to select the appropriate intelligent entity.

[0531] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0532] Step 1:

[0533] The server acquires generated data. It collects performance information from intelligent entities and user feedback as input. It automatically retrieves data from external sources via an API, obtaining performance metrics such as response speed and success rate. The output is performance information data for analysis.

[0534] Step 2:

[0535] The device analyzes the user's emotional state. It collects user voice input and text as input and performs natural language processing using an emotion analysis engine. This identifies the user's emotional state, and the emotional data is sent to the server as output.

[0536] Step 3:

[0537] The server calculates evaluation metrics for intelligent entities based on the acquired performance information. It receives performance data for each intelligent entity as input and uses statistical methods to quantify the evaluation metrics for each entity. The output is a list of the evaluated intelligent entities.

[0538] Step 4:

[0539] The server acquires user emotion data and selects the optimal intelligent entity by comparing it with evaluation metrics. The input consists of emotion data and evaluated entity information. This identifies the optimal entity considering the emotional state. The output is information about the selected intelligent entity.

[0540] Step 5:

[0541] The server configures the selected intelligent entity on the terminal. Using the information of the selected entity as input, it performs customized settings according to the user's environment. As a result, the user can immediately use an individually optimized intelligent entity. The output is the configured intelligent entity.

[0542] Step 6:

[0543] Users utilize intelligent entities to streamline their daily tasks. Input consists of user instructions and requests sent to the intelligent entities. The intelligent entities then act upon this input, performing specific tasks. As a result, the user's quality of life improves, and their satisfaction increases. Output includes task completion status and user feedback.

[0544] 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.

[0545] 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.

[0546] 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.

[0547] [Fourth Embodiment]

[0548] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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).

[0554] 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.

[0555] 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.

[0556] 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.

[0557] 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.

[0558] 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.

[0559] 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.

[0560] 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".

[0561] This invention provides a system for automatically selecting and configuring the optimal AI agent for a user. This system selects the agent that best suits the user's needs through a process of collecting, analyzing, and comparing information on the performance of different agents.

[0562] First, the server collects performance data from multiple AI agents. This includes data acquisition using APIs, scraping from user review sites, and incorporating user feedback. This allows for the collection of data such as agent response speed, success rate, and user satisfaction.

[0563] Next, the server analyzes the collected data. This analysis includes sentiment analysis of reviews using natural language processing and calculation of performance metrics using statistical methods. This generates an overall evaluation for each agent.

[0564] Next, the server compares agents based on the analyzed data. The comparison results are presented to the user as a visual ranking and evaluation metrics. This information serves as an important basis for selecting the optimal agent based on the user's workflow and purpose of use.

[0565] The server automatically installs and configures the selected agents. Since users do not need to perform any specific operations regarding agent configuration during this process, the efficiency of system usage is significantly improved.

[0566] As a concrete example, suppose a user is looking for the optimal agent for a text generation task. By using this system, the server analyzes data collected from relevant agents and automates the selection process. Ultimately, the most suitable agent is applied to the user's environment, and the user can immediately utilize its functions. In this way, the present invention reduces the effort and time required for selecting and configuring generation AI agents, thereby realizing efficient business support.

[0567] The following describes the processing flow.

[0568] Step 1:

[0569] The server collects performance data from each generated AI agent. This collection process includes sending periodic requests via APIs and applying scraping techniques from user review sites. This allows the server to obtain data on agent processing speed, success rate, and text information regarding user satisfaction.

[0570] Step 2:

[0571] The server stores the collected data in a database and prepares it for analysis. Data normalization and preprocessing are performed, and the data is organized into a format suitable for analysis.

[0572] Step 3:

[0573] The server uses natural language processing algorithms to perform sentiment analysis on user reviews. This analysis quantifies user satisfaction and dissatisfaction with the agent's use and is used as part of the evaluation metrics.

[0574] Step 4:

[0575] The server applies statistical methods to calculate performance metrics for the agents. Specifically, it uses quantitative data such as response time and processing accuracy to form an overall evaluation score for each agent.

[0576] Step 5:

[0577] The server generates visual comparison graphs and rankings based on these scores, making it easier for users to intuitively understand the comparison results of the agents.

[0578] Step 6:

[0579] The server automatically selects the optimal agent based on the user's business objectives and requirements. This selection is influenced by user-inputted conditions and past usage history.

[0580] Step 7:

[0581] The server installs the selected agent on the user's system and performs the initial setup automatically. This allows the user to immediately use the agent's functions without any additional configuration.

[0582] (Example 1)

[0583] 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".

[0584] There is a need to reduce the time and effort burden on users when selecting and configuring the optimal information processing system. However, conventional methods involve cumbersome data collection and analysis to choose the appropriate system from a large number of options, making it difficult for users to make such decisions. Furthermore, the configuration process after selection is also complex, posing a significant obstacle for users without specialized knowledge.

[0585] 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.

[0586] In this invention, the server includes means for collecting performance information from multiple information processing systems via data collection means, means for analyzing the collected performance information using natural language processing and statistical methods to calculate evaluation metrics for the information processing systems, and means for comparing the information processing systems based on the calculated evaluation metrics. As a result, users can visually select the most suitable information processing system, and the settings after selection are performed automatically, significantly reducing the burden of effort and time.

[0587] "Data acquisition means" refers to a method or device that plays the role of acquiring performance information from multiple information processing systems.

[0588] "Performance information" refers to data related to the operation and functionality of an information processing system, such as response speed, success rate, and user satisfaction.

[0589] "Natural language processing" is a technology that uses computers to analyze, understand, and utilize human language.

[0590] "Statistical methods" are mathematical techniques for collecting, analyzing, interpreting, and representing data.

[0591] "Evaluation indicators" are standards or benchmark values ​​that quantify and show the performance of an information processing system.

[0592] An "information processing system" is a system that includes hardware and software programmed to perform a specific task.

[0593] "Visual presentation" refers to displaying information visually in a way that is easy for users to understand.

[0594] "Automatically setting up" means that the setup is completed through mechanical or programmed actions without human intervention.

[0595] In this embodiment of the invention, the server primarily handles a series of processes, including collecting and analyzing performance information from multiple information processing systems and selecting the appropriate information processing system. The server achieves this using the following methods and techniques.

[0596] First, the server utilizes data collection methods, such as APIs and web scraping techniques, to gather a wide range of performance information from the information processing system. This allows the server to secure diverse data such as response speed, success rate, and user satisfaction.

[0597] Next, the server uses natural language processing technology to analyze the sentiment of the collected user reviews and quantifies the evaluation data. It also employs statistical methods to calculate evaluation metrics for each information processing system from the collected data. This allows for a comprehensive evaluation of different performance elements, resulting in comparable scores.

[0598] The server compares information processing systems based on calculated evaluation metrics and presents the results visually, allowing users to easily select the information processing system that best suits their needs.

[0599] For information processing systems selected by the user, the server automatically configures them. In this process, necessary installation and configuration are automated by the program, freeing the user from the hassle of manual adjustments.

[0600] For example, if a user is looking for an information processing system optimized for text generation, this system analyzes relevant performance information and automates the selection process. Ultimately, the selected information processing system is applied to the user's environment and becomes immediately available. In this way, users can perform their tasks efficiently.

[0601] As a concrete example of a prompt, the instruction "Based on user reviews, please select the most efficient AI agent" can be used. This allows the server to perform appropriate data analysis and select the appropriate information processing system.

[0602] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0603] Step 1:

[0604] The server collects performance information from multiple information processing systems using APIs and web scraping techniques. It obtains access information from information processing systems and URLs of user review sites as input. Based on this input, the server collects performance data such as response speed, success rate, and user satisfaction, and structures and stores this data. The output is the collected structured data.

[0605] Step 2:

[0606] The server analyzes the collected performance information. It uses the structured data collected in step 1 as input. The server performs sentiment analysis of user reviews using natural language processing, quantifying positive, negative, and neutral ratings. Furthermore, it uses statistical methods to organize data on response speed and success rate, calculating an overall evaluation index for each information processing system. The output is analyzed data including the evaluation index.

[0607] Step 3:

[0608] The server compares information processing systems based on the analyzed data. It uses the evaluation metrics obtained in step 2 as input. Based on these metrics, the server generates a ranking of the information processing systems and organizes the data in a visually comparable format. Specifically, it creates graphs and charts and displays them clearly on the user interface. The output provides visualized comparative information.

[0609] Step 4:

[0610] The user selects a suitable information processing system based on visualized comparative information. The data visualized in step 3 is provided as input. Based on this input, the user selects the optimal information processing system according to their business needs. The selection is made using clicks and taps on the user interface. The output provides information about the selected information processing system.

[0611] Step 5:

[0612] The server automatically configures the information processing system selected by the user. It uses the information about the information processing system selected in step 4 as input. The server executes the system's installation script and automatically applies the necessary configurations. Specifically, the API key input and environment settings adjustments are performed programmatically. The configured information processing system is then provided to the user environment as output.

[0613] (Application Example 1)

[0614] 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".

[0615] Selecting and configuring the most suitable AI agent from a diverse range of agents to meet user needs requires advanced expertise and is time-consuming and labor-intensive. Furthermore, electronic payments constantly face security threats and the risk of fraudulent use, necessitating the rapid selection of the most appropriate security measures.

[0616] 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.

[0617] In this invention, the server includes means for collecting characteristic information of artificial intelligence agents using generated information, means for analyzing the collected characteristic information and evaluating the characteristic indicators of each artificial intelligence agent, and means for analyzing payment history and patterns to select the safest and most appropriate artificial intelligence agent and enhance security. This enables the automatic selection of artificial intelligence agents that meet user needs and rapid security enhancement.

[0618] "Generated information" refers to the data necessary to evaluate the characteristics of an artificial intelligence agent. This data includes information about the agent's performance and user evaluations.

[0619] An "artificial intelligence agent" is a program that has the ability to autonomously perform specific tasks, and typically utilizes machine learning and natural language processing technologies.

[0620] "Characteristic information" refers to various pieces of information related to the performance and functions of an artificial intelligence agent, and is used as a standard for evaluation and comparison.

[0621] A "characteristic index" is an evaluation criterion that quantifies or scores the performance of an artificial intelligence agent, and is used for comparison and selection.

[0622] "Payment history and patterns" refers to a user's past transaction data and trends, which are important factors for enhancing security and selecting appropriate agents.

[0623] "Methods to enhance security" refer to measures and technologies used to protect systems from misuse and fraud, and are employed to ensure user safety.

[0624] To realize this invention, it is necessary to construct a data collection and analysis system using a server. The server will use the generated information to collect and analyze characteristic information of the artificial intelligence agent. This includes a process of collecting information from multiple data sources. Specifically, it will utilize data collection via APIs and scraping techniques from user review sites.

[0625] The server runs on a Python-based program and utilizes Flask as its backend framework. Machine learning libraries such as TensorFlow and PyTorch are used for performance analysis. These tools are used to analyze characteristic information and generate characteristic metrics for each artificial intelligence agent.

[0626] The user terminal displays characteristic indicators based on analyzed data and provides a means for selecting an agent. The selected agent is automatically applied to the user terminal, ensuring safe and efficient operation. In particular, security is enhanced by analyzing payment history and patterns on the server and selecting the optimal agent.

[0627] As a concrete example, when a user makes an electronic payment while traveling abroad, the system automatically analyzes the payment pattern, selects the optimal AI agent, and enhances fraud detection capabilities. This allows users to make payments with peace of mind. The system generates a prompt message such as, "Please select the optimal AI agent for overseas use and instruct me on how to detect fraudulent activity."

[0628] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0629] Step 1:

[0630] The server receives a request from the user's terminal. This request contains information about the user's requests and needs. Based on this information, the server prepares to begin collecting appropriate data.

[0631] Step 2:

[0632] The server collects characteristic information from multiple artificial intelligence agents via APIs. Specifically, it obtains performance data, response speed, success rate, etc., for each agent. This data collection uses the API endpoint of the specified agent. The input is an API request, and the output is a collection of characteristic data.

[0633] Step 3:

[0634] The server analyzes the collected characteristic information. This analysis uses TensorFlow or PyTorch to calculate characteristic metrics for each agent and evaluate their performance. The input is the collected characteristic data, and the output is the characteristic metrics for each agent. The analysis results are generated after data processing through model training.

[0635] Step 4:

[0636] The server compares artificial intelligence agents based on the analyzed characteristic metrics. This comparison ranks the agents based on these metrics and selects the optimal agent. The input is a set of characteristic metrics, and the output is the selected optimal agent. Factors such as the degree of fit to user needs and safety are also considered.

[0637] Step 5:

[0638] The server configures the selected agent on the user terminal. In this step, a script is executed to quickly deploy the selected agent's functions to the user environment. The input is the selected agent information, and the output is the agent activated on the user terminal.

[0639] Step 6:

[0640] The server enhances security by analyzing the user's payment history and patterns, and then selecting the most suitable artificial intelligence agent. Here, a fraud detection model is applied based on past transaction data. The input is the payment history, and the output is the relevant agent with enhanced security settings.

[0641] Step 7:

[0642] The user uses an artificial intelligence agent configured by the server to perform actions such as electronic payments. This process is based on a previously configured prompt: "Select the optimal AI agent for overseas use and instruct on how to detect fraudulent activity." The input is the user action, and the output is the securely and quickly completed transaction.

[0643] 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.

[0644] This invention provides a system for effectively selecting and configuring AI agents by combining generated data and an emotion engine. This system automates the process of selecting the agent best suited to the user's needs by collecting, analyzing, and comparing agent performance information. Furthermore, it uses an emotion engine to recognize the user's emotional state and reflects the results in agent selection and configuration, thereby providing a more user-friendly solution.

[0645] First, the server collects performance data from multiple AI agents. This includes data acquisition via APIs and text collection from user review sites, encompassing agent response speed, success rate, and user feedback sentiment.

[0646] Next, the device analyzes the user's real-time emotional state via an emotion engine. This engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. The results of the emotion engine's analysis are then incorporated into the subsequent agent selection process.

[0647] Next, the server analyzes the generated data and calculates performance metrics for each agent using statistical methods. This analysis also takes into account collected user reviews and sentiment data, thereby quantifying the agent's satisfaction level and efficiency.

[0648] The server then compares agents based on the analysis results. It selects the optimal agent by comparing it with the user's emotional data and business objectives. In this selection process, the user's emotional state is directly reflected in the agent settings and selection results, resulting in a more personalized experience.

[0649] Finally, the server automatically installs the selected agent into the user's environment and performs the initial setup. Users can immediately use the customized agent from the first boot, and this invention achieves improved operational efficiency and user experience.

[0650] For example, if a user is looking for an AI agent suitable for call center work, this system will select the optimal agent after considering the stress level of the work. The selected agent will be configured based on the user's emotional state, thereby enhancing the support system in call center operations. Such automated processes support users' work and improve convenience.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The server periodically retrieves relevant data using an API to collect performance data from each generated AI agent. This process includes information such as the success rate and response time of tasks handled by the agent. Furthermore, it performs scraping from user review sites to collect user feedback on the agents in text format.

[0654] Step 2:

[0655] The device activates an emotion engine to recognize the user's real-time emotional state. This engine analyzes the user's emotions, such as excitement and anxiety levels, through voice analysis and text sentiment analysis, and stores the results as emotion data. This information is obtained from the voice and text input when the user interacts with the system.

[0656] Step 3:

[0657] The server initiates the analysis process using the collected performance and sentiment data. It utilizes natural language processing techniques to analyze user reviews and quantify user satisfaction. Furthermore, statistical analysis tools are used to calculate performance metrics such as response time and accuracy, generating evaluation scores for each agent.

[0658] Step 4:

[0659] The server automatically compares agents by combining the generated evaluation scores with the user's emotional state. This process is carried out through a visual dashboard, taking emotional data into account to select agents that the user is more likely to consciously respond to.

[0660] Step 5:

[0661] The server selects the most suitable agent based on the user's business objectives and emotional state. The selected agent is displayed to the user as a suggestion, with detailed explanations of the agent's characteristics and past performance as the reason for the selection.

[0662] Step 6:

[0663] The server installs the selected agent on the user's terminal and applies a pre-configured profile. This process is fully automated, and the user does not need to change any settings. As a result, the user can immediately enjoy improved service provided by the selected agent.

[0664] (Example 2)

[0665] 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".

[0666] In user environments utilizing intelligent agents, the process of evaluating and selecting agent performance is not efficient, and selecting the optimal agent, particularly one that takes the user's emotional state into consideration, is a challenge. Furthermore, the complex agent configuration process impairs user convenience.

[0667] 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.

[0668] In this invention, the server includes means for collecting performance information of intelligent agents using generated data, means for analyzing the collected performance information and user evaluations to evaluate the performance indicators of each intelligent agent, and means for selecting the optimal intelligent agent based on the comparison results and the user's emotional state. This enables the automatic selection and setting of the optimal intelligent agent adapted to the user's emotional state, thereby realizing the construction of an efficient user environment.

[0669] "Generated data" refers to information and numerical data collected to evaluate the performance and operation of intelligent agents.

[0670] An "intelligent agent" refers to a software function that uses natural language processing and machine learning algorithms to automate specific tasks based on user instructions.

[0671] "Performance information" refers to indicators and data related to the capabilities and characteristics of an intelligent agent, specifically information on evaluation items such as response speed and success rate.

[0672] "User evaluation" refers to feedback and emotional ratings provided by users based on their experience using intelligent agents.

[0673] "Emotional state" refers to information that represents the emotions and psychological state a user is feeling at a specific point in time, such as stress levels or satisfaction levels.

[0674] "Performance metrics" refer to scores or metrics used to numerically evaluate the performance of intelligent agents.

[0675] "Automatically setting" means that the system will configure and adjust settings based on pre-programmed conditions without manual intervention.

[0676] This invention provides a system for effectively selecting and configuring intelligent agents by combining generated data and an emotion engine. The objective of this system is to improve the user experience by automatically selecting and configuring the optimal agent to meet the user's needs.

[0677] First, the server uses generated data to collect performance information about the intelligent agent. This collection includes data acquisition via APIs and text collection from user review sites. This information includes data on various performance metrics, such as the agent's response speed, success rate, and user feedback sentiment.

[0678] Next, the device uses an emotion engine to analyze the user's real-time emotional state. This emotion engine utilizes natural language processing and speech analysis technologies to read emotions from the user's input and interactions. For example, if the user enters keywords such as "tired" or "busy," the emotion engine analyzes this as emotional data. This information is used to consider the user's psychological state in the subsequent intelligent agent selection process.

[0679] As a concrete example, consider a user inputting a prompt into an AI model saying, "Please select the agent that can respond most calmly when I am feeling stressed." The system then automatically selects the most suitable intelligent agent based on the user's emotions, installs it in the user's environment, and performs initial setup. This allows the user to comfortably use the intelligent agent even in stressful situations.

[0680] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0681] Step 1:

[0682] The server uses generated data to collect performance information from intelligent agents. Input at this stage includes API responses from agent providers and text data from user review sites. The server receives this input, analyzes information such as response speed, success rate, and user feedback sentiment, and outputs performance metric data. This process involves data format conversion and extraction of key information to compile a comprehensive evaluation of the agent's performance.

[0683] Step 2:

[0684] The device uses an emotion engine to analyze the user's real-time emotional state. Input here consists of text and voice data from the user. The device receives this data and, utilizing natural language processing and speech analysis technologies, outputs emotional information such as positive or negative. Specifically, an emotion analysis algorithm scans the user's words and voice tone, and provides the results as numerical emotional data.

[0685] Step 3:

[0686] The server analyzes the collected performance metric data and sentiment data, and evaluates the performance metrics of each intelligent agent using statistical methods. The input consists of performance metric data from Step 1 and sentiment data from Step 2. The server integrates this data, evaluates agent responsiveness and user adaptability, and outputs candidates for the optimal agent. This analysis process uses regression analysis and clustering methods to perform a multifaceted evaluation.

[0687] Step 4:

[0688] The server compares intelligent agents based on the analysis results and selects the agent that best matches the user's emotional state and business objectives. The input is a list of optimal agent candidates obtained from step 3. The server evaluates this list and selects the most suitable agent as the final output. This process involves ranking agents based on evaluation scores and checking their suitability to the user's business objectives.

[0689] Step 5:

[0690] The server automatically configures the selected agent in the user's environment. The input is the agent information selected in step 4. Based on this information, the server performs the necessary installation and customization, and the output is an agent optimized for the user's environment. In this step, an environment configuration script is used to complete the setup so that the user can use it immediately.

[0691] (Application Example 2)

[0692] 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".

[0693] Conventional intelligent entity selection systems fail to adequately address the diverse emotional states of users, making it difficult to provide optimal intelligent entities tailored to individual needs. Furthermore, they lack mechanisms to directly reflect user evaluations, resulting in insufficient adaptability and satisfaction levels with selected intelligent entities. This leads to a challenge in that improvements in user convenience are limited.

[0694] 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.

[0695] In this invention, the server includes means for acquiring performance information of intelligent entities using generated data, means for analyzing the acquired performance information and evaluating the performance indicators of each intelligent entity, means for comparing intelligent entities based on the evaluated performance indicators, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the intelligent entities based on the user's emotional state. This makes it possible to automatically select and set individually optimized intelligent entities that take into account the diverse emotional states of the user.

[0696] "Generated data" refers to information used to evaluate the performance of intelligent entities, and includes user feedback and reaction data.

[0697] An "intelligent entity" is an artificial intelligence-based agent or system that operates according to user needs and is a program that has the function of performing a specific task.

[0698] "Performance information" refers to data about the actions performed by an intelligent entity and their results, including metrics such as response speed, success rate, and user satisfaction.

[0699] An "emotion analysis engine" is software or a system that analyzes a user's emotional state in real time, and utilizes speech recognition and natural language processing technologies.

[0700] A "user" is an individual or organization that uses intelligent entities and is subject to service customization based on their needs and responses.

[0701] "Evaluation metrics" are standards or parameters used to quantify and evaluate the performance of intelligent entities, and they play a crucial role in improving the user experience.

[0702] The system that realizes this invention consists of a server, a terminal, and an interface with the user. The server uses generated data to acquire performance information of intelligent entities, analyzes the performance information, and calculates evaluation metrics. Based on the evaluated performance metrics, it selects the optimal intelligent entity and transmits the result to the terminal.

[0703] The device is equipped with an emotion analysis engine that analyzes the user's emotional state from their input and voice. Specifically, it uses natural language processing and speech recognition technologies to acquire the user's emotional information in real time. This emotional information is sent to a server and used to select an intelligent entity. Based on this information, the server selects and configures an intelligent entity that is appropriate for the user's emotional state.

[0704] Users can receive personalized services using pre-configured intelligent entities. For example, a user analyzed as being tired might be offered services such as playing relaxing music or adjusting the lighting environment.

[0705] This system can quickly select the most suitable intelligent entity for the user and make emotion-based adjustments, thereby significantly improving user convenience and satisfaction.

[0706] An example of a prompt would be, "Please suggest which AI agent is best suited to my emotional state today." This allows the system to receive the user's emotional state and use it as data to select the appropriate intelligent entity.

[0707] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0708] Step 1:

[0709] The server acquires generated data. It collects performance information from intelligent entities and user feedback as input. It automatically retrieves data from external sources via an API, obtaining performance metrics such as response speed and success rate. The output is performance information data for analysis.

[0710] Step 2:

[0711] The device analyzes the user's emotional state. It collects user voice input and text as input and performs natural language processing using an emotion analysis engine. This identifies the user's emotional state, and the emotional data is sent to the server as output.

[0712] Step 3:

[0713] The server calculates evaluation metrics for intelligent entities based on the acquired performance information. It receives performance data for each intelligent entity as input and uses statistical methods to quantify the evaluation metrics for each entity. The output is a list of the evaluated intelligent entities.

[0714] Step 4:

[0715] The server acquires user emotion data and selects the optimal intelligent entity by comparing it with evaluation metrics. The input consists of emotion data and evaluated entity information. This identifies the optimal entity considering the emotional state. The output is information about the selected intelligent entity.

[0716] Step 5:

[0717] The server configures the selected intelligent entity on the terminal. Using the information of the selected entity as input, it performs customized settings according to the user's environment. As a result, the user can immediately use an individually optimized intelligent entity. The output is the configured intelligent entity.

[0718] Step 6:

[0719] Users utilize intelligent entities to streamline their daily tasks. Input consists of user instructions and requests sent to the intelligent entities. The intelligent entities then act upon this input, performing specific tasks. As a result, the user's quality of life improves, and their satisfaction increases. Output includes task completion status and user feedback.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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."

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0741] The following is further disclosed regarding the embodiments described above.

[0742] (Claim 1)

[0743] A means of collecting agent performance information using generated data,

[0744] A means for analyzing collected performance information and evaluating the performance metrics of each agent,

[0745] A means of comparing agents based on evaluated performance metrics,

[0746] A method for selecting the optimal agent based on the comparison results,

[0747] A means of configuring the selected agent in the user environment,

[0748] A system that includes this.

[0749] (Claim 2)

[0750] The system according to claim 1, comprising means for collecting user reviews and reflecting them in the analysis of generated data.

[0751] (Claim 3)

[0752] The system according to claim 1, comprising means for automatically performing benchmark tests on agents and incorporating the results into the evaluation.

[0753] "Example 1"

[0754] (Claim 1)

[0755] A means for collecting performance information from multiple information processing systems via data collection means,

[0756] A means for analyzing collected performance information using natural language processing and statistical methods to calculate evaluation metrics for an information processing system,

[0757] A means of comparing information processing systems based on calculated evaluation indicators,

[0758] A means of visually presenting comparison results to the user and allowing them to select the optimal information processing system,

[0759] Means for automatically configuring and applying the selected information processing system,

[0760] A system that includes this.

[0761] (Claim 2)

[0762] The system according to claim 1, comprising means for collecting user evaluations and reflecting them in the analysis.

[0763] (Claim 3)

[0764] The system according to claim 1, comprising means for automatically performing performance tests on an information processing system and incorporating the results into an evaluation.

[0765] "Application Example 1"

[0766] (Claim 1)

[0767] A means for collecting characteristic information of an artificial intelligence agent using generated information,

[0768] A means for analyzing collected characteristic information and evaluating the characteristic indicators of each artificial intelligence agent,

[0769] A means for comparing artificial intelligence agents based on evaluated characteristic indicators,

[0770] A method for selecting the optimal artificial intelligence agent based on the comparison results,

[0771] A means of setting up the selected artificial intelligence agent in the user environment,

[0772] A means of enhancing security by analyzing payment history and patterns to select the safest and most appropriate artificial intelligence agent,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, comprising means for collecting user evaluation information and reflecting it in the analysis of generated information.

[0776] (Claim 3)

[0777] The system according to claim 1, comprising means for automatically conducting performance tests of an artificial intelligence agent and incorporating the results into the evaluation.

[0778] "Example 2 of combining an emotion engine"

[0779] (Claim 1)

[0780] A means for collecting performance information of an intelligent agent using generated data,

[0781] A means for analyzing collected performance information and user evaluations to evaluate the performance indicators of each intelligent agent,

[0782] A means of comparing intelligent agents based on evaluated performance metrics,

[0783] A means for selecting the optimal intelligent agent based on comparison results and the user's emotional state,

[0784] A means for automatically setting up the selected intelligent agent in the user's environment,

[0785] A system that includes this.

[0786] (Claim 2)

[0787] The system according to claim 1, comprising means for analyzing the emotional state of the user and reflecting the results in the analysis of generated data.

[0788] (Claim 3)

[0789] The system according to claim 1, comprising means for using speech analysis technology and natural language processing technology in the evaluation and selection process of intelligent agents.

[0790] "Application example 2 when combining with an emotional engine"

[0791] (Claim 1)

[0792] A means of obtaining performance information of an intelligent entity using generated data,

[0793] A means for analyzing acquired performance information and evaluating the performance indicators of each intelligent entity,

[0794] A means for comparing intelligent entities based on evaluated performance metrics,

[0795] A means for selecting the optimal intelligent entity based on the comparison results,

[0796] A means for setting up the selected intelligent entity in the user environment,

[0797] A means of analyzing a user's emotional state using an emotion analysis engine,

[0798] A means of adjusting intelligent entities based on the user's emotional state,

[0799] A system that includes this.

[0800] (Claim 2)

[0801] The system according to claim 1, comprising means for collecting user evaluations and reflecting them in the analysis of generated data.

[0802] (Claim 3)

[0803] The system according to claim 1, comprising means for automatically performing a baseline performance test of an intelligent entity and incorporating the results into an evaluation. [Explanation of symbols]

[0804] 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 of collecting agent performance information using generated data, A means for analyzing collected performance information and evaluating the performance metrics of each agent, A means of comparing agents based on evaluated performance metrics, A method for selecting the optimal agent based on the comparison results, A means of configuring the selected agent in the user environment, A system that includes this.

2. The system according to claim 1, comprising means for collecting user reviews and reflecting them in the analysis of generated data.

3. The system according to claim 1, comprising means for automatically conducting benchmark tests on agents and incorporating the results into the evaluation.

Images