system

Abstract

We provide the system. [Solution] A means of collecting business data from an information processing device, A method for analyzing collected business data and classifying business processes into multiple types, A means for selecting the optimal automation algorithm for each type based on the classification results, A means of integrating the selected automation algorithm into the information system, A means to continuously monitor the performance of integrated automation algorithms and propose performance improvements, A means for displaying algorithm optimization information in real time on a display device, 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 method for controlling a persona chatbot performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] When a company introduces an artificial intelligence agent to improve business efficiency, there may be a problem that it is not effectively utilized and the expected results cannot be obtained. In addition, there is also a problem that the introduction of an artificial intelligence agent results in waste of time and resources because the effect does not continue. An object of the present invention is to solve such inefficient introduction and operation of artificial intelligence agents within a company.

Means for Solving the Problems

[0005] First, we provide a means to collect business process data from companies. By precisely analyzing this data, we classify business processes into multiple categories: workflow-type, employee-type, and unsuitable for implementation. Next, based on this classification, we select the most suitable artificial intelligence agent for each category. The selected artificial intelligence agent is then integrated into the business process, and monitoring is conducted thereafter. By continuously providing suggestions for improvement, we build a system that maximizes the effectiveness of the artificial intelligence agent.

[0006] "Business processing data" refers to a collection of information related to a company's business activities, including the content, time, and resource usage of each process and task.

[0007] "Analysis" is the process of examining business processing data, converting it into structured information, and understanding and classifying its content.

[0008] "Categorizing" means dividing the analyzed business processes into groups based on specific characteristics or conditions.

[0009] An "artificial intelligence agent" is a software-based intelligent system designed to automate or assist specific business processes.

[0010] "Selection" is the act of determining the most suitable artificial intelligence agent based on given criteria and requirements.

[0011] "Integrating" means bringing a selected artificial intelligence agent into a state where it can be integrated into existing business processes and systems and put into operation.

[0012] "Monitoring" refers to the continuous observation and evaluation of whether the implemented artificial intelligence agent is functioning correctly and achieving the expected results.

[0013] "Suggestions for improving effectiveness" refers to recommending adjustments or new strategies to obtain better results by adjusting the functions and operations of the artificial intelligence agent based on monitoring results. [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]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Embodiments 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 processor with a reference number (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 RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor. [[ID=​​​​​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 is a system for effectively selecting, deploying, and operating artificial intelligence agents to improve the operational efficiency of a company. A server accesses the company's systems to collect extensive data on business processes. This collected data includes work content, working hours, resource utilization, and process history, forming the foundation for a detailed understanding of business operations.

[0036] Next, the server classifies this data into several categories through advanced data analysis algorithms. Specifically, it classifies the data into categories such as "workflow type" based on the characteristics, frequency, and complexity of the tasks, "employee type" which is repetitive and suitable for automation, and "unsuitable for deployment" which is not suitable for the introduction of artificial intelligence agents.

[0037] Subsequently, the server selects the most suitable artificial intelligence agent based on the classification results. This involves using a performance database of existing agents to achieve the best possible match between business requirements and agent capabilities. The selected artificial intelligence agent is then proposed to the user terminal, and its details (predicted effectiveness, implementation costs, operation methods, etc.) are presented.

[0038] Once the user approves the server's proposal, the server automatically integrates the selected artificial intelligence agent into the necessary business processes. This integration includes installing and configuring the agent's software, as well as coordinating its interface with existing systems.

[0039] After implementation, the server continuously monitors the operational status of the artificial intelligence agent. This monitoring collects and analyzes data on operational efficiency, agent effectiveness, and employee feedback. Based on the analysis results, the server proposes specific adjustments and new strategies to improve the agent's effectiveness to user terminals, thereby supporting the continuous enhancement of the company's operational efficiency.

[0040] As a concrete example, consider a case where this system is implemented in the customer support department of a certain company. The server collects inquiry response data and classifies tasks related to FAQs as workflow-type tasks. Next, the server selects an artificial intelligence agent capable of automatic replies and sends suggestions to the user's terminal. By implementing the system's automatic reply function and receiving effective operation and improvement support through the server, the efficiency of customer support can be dramatically improved.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server accesses the company's systems and collects processing data related to business operations. This data includes business content, processing time, and resource usage. The collected data is stored in a database for later analysis.

[0044] Step 2:

[0045] The server executes a pre-configured algorithm to analyze the collected data. Using natural language processing techniques, it analyzes business content in a documented form and converts business processes into an evaluable format.

[0046] Step 3:

[0047] Based on the data analyzed by the server, a model is applied to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This model classifies processes by analyzing their characteristics, frequency, and complexity.

[0048] Step 4:

[0049] The server consults a database of agents to select an artificial intelligence agent suitable for each category. The selection is made considering how well the agent's capabilities match the business requirements.

[0050] Step 5:

[0051] The terminal displays a proposal for an artificial intelligence agent selected by the server. This proposal includes the agent's functions, implementation costs, and projected effects. The user uses this information to decide whether to approve the implementation.

[0052] Step 6:

[0053] Once the user approves the proposed artificial intelligence agent, the server initiates the installation and configuration process to integrate the selected agent into the business process.

[0054] Step 7:

[0055] The server monitors the performance of the artificial intelligence agents it deploys. This monitoring collects data related to operational efficiency, reduced working hours, and operational accuracy.

[0056] Step 8:

[0057] The server analyzes performance based on monitoring results and, if necessary, sends agent configuration adjustments or additional suggestions to the user terminal. This ensures that the agent's effectiveness is maximized.

[0058] (Example 1)

[0059] 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."

[0060] Improving operational efficiency and implementing effective digital tools are essential for maintaining competitiveness in modern businesses. However, processes such as classifying business data, selecting the optimal advanced computing agents, and monitoring post-implementation effects are complex and burdensome for companies. Therefore, there is a need for comprehensive solutions to support business automation and efficiency.

[0061] 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.

[0062] In this invention, the server includes means for collecting activity data in a business domain, means for analyzing the collected activity data and classifying it into multiple categories based on business characteristics, and means for using the classification results to select the optimal advanced computing agent. This enables companies to automatically and efficiently deploy agents suited to their business processes and optimize their performance.

[0063] "Business domain" refers to the range of various business activities performed within a company, and includes different functions and processes such as production, sales, and human resources.

[0064] "Activity data" refers to all information related to business processes, specifically including working hours, resource usage, progress status, and deliverables.

[0065] "Analysis" refers to the process of examining collected data in detail to understand its patterns and characteristics, and in particular includes data classification and predictive analysis using machine learning.

[0066] A "category" refers to a group or class of data that has been separated through analysis, and it is a collection of similar data based on specific characteristics or conditions.

[0067] An "advanced computing agent" refers to a software program designed to automate and streamline specific business tasks using machine learning and artificial intelligence technologies.

[0068] "Implementation" refers to the act of applying or installing a newly selected advanced computing agent into existing business processes and integrating it into the environment to make it usable.

[0069] "Effect monitoring" refers to the process of continuously observing and recording the performance of already implemented advanced computing agents, and measuring and evaluating their efficiency and results.

[0070] "Efficiency improvement" refers to a series of adjustments and strategic changes made to improve the performance of business processes, particularly including resource optimization and reduction of work time.

[0071] This invention is a system that utilizes artificial intelligence technology to efficiently analyze and automate business processes in order to improve the operational efficiency of companies. This system operates through the collaborative efforts of a server, terminals, and users.

[0072] First, the server connects to the company's internal systems and collects a wide range of activity data within the business domain. This process utilizes database access and APIs to obtain important information such as work content, work time, resource utilization, and process history. This data forms the foundation for a detailed understanding of business workflows.

[0073] Next, the server analyzes the collected data. Here, advanced data analysis algorithms and machine learning models are used to classify the data into categories such as "procedural," "personnel-based," and "non-conforming." This classification helps identify which business processes are suitable for automation.

[0074] Based on the classified data, the server selects the optimal high-performance computing agent. This selection is made by referring to a performance database of existing agents and making the best possible match between business requirements and agent capabilities.

[0075] The selected agent is sent as a suggestion to the user's device, and detailed information about the agent is provided. This includes the agent's expected effectiveness, implementation costs, and operating procedures.

[0076] If the user approves the proposal, the server automatically integrates the agent into the business process. This involves software installation, configuration, and interface adjustments with existing systems.

[0077] As a result of the implementation, operational efficiency improves and the effectiveness of the agents is maximized. The operational status is continuously monitored by the server, and further efficiency improvements are suggested based on the data obtained.

[0078] As a concrete example, consider the case where this system is implemented in the customer support department of a certain company. The server collects inquiry data and classifies FAQ response tasks as "procedural." The server then selects an advanced computing agent capable of automatic replies, sends a proposal to the user's terminal, and if the user approves, it is implemented into the system, which is expected to improve the efficiency of inquiry handling.

[0079] An example of a prompt to input into the generating AI model is, "Based on customer support inquiry data, please suggest how to automate the business process using the most suitable AI agent."

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server accesses the company's systems to collect activity data within the business domain. Inputs include business content, work time, resource usage, and process history accessed via system databases and APIs. Specifically, the server executes scripts and queries to retrieve the necessary data, integrates it, and formats it into an output dataset. This output serves as the foundation for subsequent data analysis.

[0083] Step 2:

[0084] The server analyzes the collected data and classifies it into multiple categories based on business characteristics. The input is the dataset obtained in Step 1, and here data analysis algorithms are used to perform characteristic analysis and pattern recognition. Specifically, the server applies a machine learning model and divides the data into categories such as "procedural," "personnel-based," and "non-conforming" based on features. The output is classification information of business processes.

[0085] Step 3:

[0086] The server selects the most suitable advanced computing agent based on the classification results. The input is the classification information obtained from step 2. Here, the agent characteristics database is matched with the business characteristics, and a machine learning model is used to calculate a prediction score. Specifically, the server compares the characteristics of each agent with the business requirements and identifies the most suitable agent through scoring. The output is information on the selected agent and its recommendation level.

[0087] Step 4:

[0088] The selected advanced computing agent is sent to the user's terminal as a proposal. The input is the output data from step 3. The specific action here is for the server to refine the proposal and output it in a format that the user can review, such as a report or dashboard. The user receives this and reviews the content. The output is the user's approval or revision request for the proposal.

[0089] Step 5:

[0090] If the user approves the proposal, the server automatically integrates the selected agent into the business process. The input here is user approval, and the output is the deployment status of the modified business system. Specific actions include agent software installation, system configuration, interface adjustments with existing systems, and integration into the business application environment.

[0091] Step 6:

[0092] The server continuously monitors the operational status of the advanced computing agent after deployment. Here, the agent's performance data, obtained as output, is used as input for collecting daily operational data, evaluating operations, and identifying and proposing improvements. Specifically, the server analyzes real-time data, evaluates efficiency and impact, and considers improvement measures. The output includes suggestions for improving the agent's effectiveness and performance reports for the user.

[0093] (Application Example 1)

[0094] 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."

[0095] Optimizing operational efficiency in production facilities is a critical challenge for many companies. However, traditional systems often fail to adequately analyze business processes, leading to inappropriate choices in automation implementation. As a result, productivity improvements are hindered. Furthermore, there is a lack of mechanisms to propose rapid, real-time improvements, and there is a need for means to quickly resolve bottlenecks faced by on-site workers.

[0096] 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.

[0097] In this invention, the server includes means for collecting business data from an information processing device, means for analyzing the collected business data and classifying business processes into multiple types, means for selecting the most suitable automation algorithm for each type based on the classification results, and means for displaying algorithm optimization information on a display device in real time. This enables real-time analysis and automation optimization of business processes in production facilities, dramatically improving business productivity.

[0098] An "information processing device" is an electronic device such as a computer or sensor that enables the collection and communication of data in business operations.

[0099] "Business data" refers to information about business activities conducted both inside and outside the company, including working hours, resource utilization, and process history.

[0100] A "business process" refers to a series of tasks and procedures necessary to perform a specific task.

[0101] An "automation algorithm" is a set of computational steps designed to streamline a work process in a specific task.

[0102] An "information system" is a set of information technology infrastructures used to support business activities, and consists of hardware, software, networks, and other components.

[0103] "Performance" is an indicator that shows how effectively a system or algorithm functions for its intended purpose.

[0104] A "display device" is an electronic device such as a screen or projector that provides information to users visually.

[0105] "Optimization information" refers to instructions and suggestions provided to improve business processes and increase their efficiency.

[0106] The system for implementing this invention consists of an information processing device, a cloud server, and a smart display. The server collects business data from the information processing device and analyzes it to classify business processes into various types. Based on these classification results, the server selects the most suitable automation algorithm for each type and integrates it into the information system.

[0107] Furthermore, it features a function that presents on-site workers with optimization information in real time via a smart display. This allows workers to quickly resolve bottlenecks in their work processes and improve work efficiency.

[0108] The hardware includes sensors for data collection, cloud servers for processing (e.g., Amazon Web Services), and smart displays for displaying information (e.g., Google Glass®). The software side utilizes machine learning algorithms for data analysis, automating the classification of business data and the selection of algorithms.

[0109] As a concrete example, in an assembly line for small parts at a production facility, workers wear smart displays and perform tasks based on instructions from a server. This optimizes specific processes and improves productivity. Another example of a prompt message is, "Identify bottlenecks on the factory floor and propose the optimal work procedure for efficiency."

[0110] The generative AI model generates optimization algorithms based on business data and immediately presents the results to the worker, thereby supporting efficient business operations.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server collects operational data in real time from information processing equipment. Inputs include data from various sensors, such as work time, resource utilization, and process history. The server stores this data and organizes it for subsequent analysis steps.

[0114] Step 2:

[0115] The server begins data analysis using the collected business data. The input is the business data collected in the previous step. The data is analyzed using a generative AI model, and the business processes are classified into several types. At this time, machine learning algorithms are used to identify specific patterns and trends and perform classification, obtaining classification information as output.

[0116] Step 3:

[0117] The server selects the most suitable automation algorithm for each category based on the classification information. The input is the classification information from the previous step. The server refers to a database of existing algorithms and extracts the most suitable one. This selection takes into account the characteristics of each process and the required efficiency, and the selected algorithm is obtained as the output.

[0118] Step 4:

[0119] The server integrates the selected automation algorithm into the information system. The input is the algorithm selected in step 3. The server coordinates the connection between the existing information system and the algorithm and performs the necessary configurations. The output is the integrated information system.

[0120] Step 5:

[0121] Data is sent to a smart display to present information optimized for the user in real time. The input is optimized information generated by an already integrated algorithm. The terminal displays the data, making it immediately accessible to the worker. The output is the optimized information displayed on the screen.

[0122] Step 6:

[0123] The user performs tasks based on information displayed on a smart display and then feeds the results back to the server. The input consists of the user's feedback information and data on the tasks performed. The server collects this feedback information and uses it to further improve the algorithm, resulting in a system that undergoes repeated improvements as output.

[0124] 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.

[0125] This invention is a system that adds user emotion recognition capabilities to an artificial intelligence agent in order to further improve the operational efficiency of a company. The system begins with a server collecting business processing data from a company and precisely analyzing the business processes using natural language processing and machine learning. The analyzed data is used to classify tasks into three categories: "workflow type," "employee type," and "unsuitable for implementation," after which the most suitable artificial intelligence agent is selected.

[0126] In this process, the server integrates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and text data to identify the user's emotional state. For example, if the emotion engine determines that the user is experiencing an emotional state such as fatigue or stress, the server automatically adjusts the behavior of the artificial intelligence agent to provide appropriate support to the user.

[0127] Furthermore, using emotional data from the emotion engine, the server generates suggestions for improving business processes. These suggestions are notified to the user's terminal, and the user can then use them to improve the efficiency of their work. The suggestions include specific strategies to improve the user's emotional state, such as redistributing workload or improving the work environment.

[0128] For example, consider an application in a customer support department. The server analyzes the support staff's interaction history and their emotional state at the time (e.g., frustration or fatigue). If the emotion engine detects signs of fatigue, the server suggests flexible adjustments to the work schedule based on that emotional data. This suggestion is notified to the administrator via the terminal, allowing the administrator to quickly take measures to reduce the burden on the staff.

[0129] In this way, by combining an emotion engine, this system can achieve both efficient operation of artificial intelligence agents and business improvement.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server accesses the company's systems and collects a wide range of business processing data. This data includes details about the tasks performed, working hours, and resources used.

[0133] Step 2:

[0134] The system analyzes the business processing data collected by the server and uses machine learning models to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This classification is based on business characteristics and data patterns.

[0135] Step 3:

[0136] The server selects the most suitable artificial intelligence agent for each classified business process. The selection is based on the matching of each agent's functions with the business requirements.

[0137] Step 4:

[0138] The server operates an emotion engine, analyzing user voice and text within business processes to identify their emotional state. The emotion engine analyzes the user's emotions in real time and classifies their emotional state into categories such as "positive," "negative," and "neutral."

[0139] Step 5:

[0140] The server adjusts the behavior of the artificial intelligence agent based on the results of the emotion engine. For example, if the user is in a negative emotional state, the server will add actions to the agent to encourage relaxation.

[0141] Step 6:

[0142] The terminal displays emotional data obtained from the emotion engine, along with suggestions for business improvements based on that data. These suggestions include workload distribution, improvements to the work environment, and the provision of further support.

[0143] Step 7:

[0144] Based on suggestions displayed on the user's device, the system adjusts business processes and agent settings to improve their emotional state and enhance work efficiency.

[0145] Step 8:

[0146] The server monitors the effects of improved processes and tuned agents. By continuously collecting data and providing new improvement suggestions to users' terminals as needed, it helps maintain an optimal work environment.

[0147] (Example 2)

[0148] 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".

[0149] In modern businesses, as operations become increasingly complex and diverse, there is a need for management that simultaneously considers employee emotions and the efficiency of work procedures. However, traditional systems have faced challenges in adequately analyzing work data and recognizing emotions, making it difficult to propose concrete improvements to operations. This has led to problems such as decreased labor productivity and increased employee stress.

[0150] 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.

[0151] In this invention, the server includes means for collecting information about the business entity, means for analyzing the collected information and classifying business procedures into multiple categories, and means for integrating an emotion engine for recognizing the emotions of users. This enables efficient management of business procedures and business improvement suggestions based on employee emotions.

[0152] A "business entity" refers to a legal entity such as an organization or company, which is a subject that conducts economic activities through specific business operations and activities.

[0153] "Information" refers to data and records related to the business operations of an entity, including data on work progress and employee performance.

[0154] "Business procedures" refer to the processes and procedures that show how business operations are carried out within an organization, representing the specific flow and sequence of work.

[0155] A "category" refers to a classification that groups items with similar characteristics or uses, and is grouped based on the characteristics of business procedures.

[0156] An "intelligent agent" refers to an intelligent program or system that analyzes data and makes predictions and decisions, and has the ability to automate specific tasks.

[0157] An "emotional engine" refers to software technology that analyzes a user's emotional state, and includes devices that recognize emotions using voice data and text data.

[0158] A "proposal" refers to guidelines or advice provided for the purpose of improving the operations and management of an organization, and is information that provides guidance for action.

[0159] "Monitoring" refers to the act of continuously observing the effectiveness of a particular process or agent, and is a process of identifying areas that need improvement or adjustment.

[0160] This invention provides an intelligent system for improving the operational efficiency of businesses. The server is responsible for collecting information about the business entity. Specifically, it uses a business management platform and a database management system to collect data on the progress of operations and employee performance. Based on this data, the server uses Python libraries such as NLTK and SpaCy to analyze the information through natural language processing and classify business procedures into categories such as "procedural," "employee-oriented," and "inappropriate for implementation."

[0161] Furthermore, the server recognizes the user's emotions by integrating an emotion engine. This emotion engine analyzes voice input and text data to identify the user's emotional state. For example, if it determines that the user is experiencing stress, the emotion engine immediately provides that data to the server.

[0162] The server integrates and analyzes identified emotional and operational data to select the most suitable intelligent agent. The intelligent agent uses a generative AI model to support the automation of tasks. After this selection, the server generates suggestions for improving operational efficiency and notifies the user terminal. These suggestions include redistributing workload and improving the work environment, allowing the user to optimize their tasks based on these suggestions.

[0163] As a concrete example, consider its application in a customer support department. The server analyzes the user's work interaction history and sentiment data, and proposes appropriate work adjustments. Users receive these suggestions through their terminals and can, for example, quickly make flexible adjustments to their work schedules.

[0164] Examples of prompts include, "Analyze current business process data and generate improvement suggestions based on emotional states," and "Based on support staff emotional data, suggest a redistribution of workload."

[0165] Thus, the present invention provides a concrete form for achieving efficient management of work procedures and business improvement based on user emotions.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The server collects information from the business entity. Specifically, it retrieves data from business management software and databases via APIs. This input data includes task progress, work time, and employee performance metrics. The server integrates this data and prepares it for analysis.

[0169] Step 2:

[0170] The server analyzes the collected information using natural language processing techniques. Using Python's NLTK and SpaCy, the server tokenizes the data and understands the textual context. This allows it to classify business procedures into "procedural," "employee-based," and "inappropriate for implementation." The output of this process is the classified business procedure data.

[0171] Step 3:

[0172] The server uses an emotion engine to acquire the user's emotional data. The user inputs voice or text data into the terminal via a microphone or keyboard. The server uses the emotion engine to identify emotional states such as stress and fatigue from this data. The output is information about the identified emotional states.

[0173] Step 4:

[0174] The server integrates classified business procedure data and user emotional data to select the optimal intelligent agent. Here, a generative AI model is used to select and customize the agent. The output is the configured intelligent agent settings. These settings facilitate the automation of business processes.

[0175] Step 5:

[0176] The server generates business improvement suggestions using a generation AI model. These suggestions include strategies for redistributing workload and measures to improve the work environment. The suggestions are notified to the user's terminal. The output is a specific improvement suggestion expressed in a notification format.

[0177] Step 6:

[0178] Users receive suggestions through their devices. Based on these suggestions, they take actions to optimize their work. For example, users decide to adjust their work schedules or reallocate resources. The ultimate result of this process is improved work processes and enhanced user emotional well-being.

[0179] (Application Example 2)

[0180] 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".

[0181] Conventional business process support systems prioritize operational efficiency without considering the emotional state of individual users, resulting in insufficient support to address user stress and fatigue. Consequently, there were limitations to improving operational efficiency and user satisfaction. Furthermore, even in the application of automated agents in home and daily life settings, the lack of nuanced responses based on emotion recognition made optimizing the user experience difficult.

[0182] 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.

[0183] In this invention, the server includes means for collecting corporate data, means for analyzing the collected data and classifying business procedures into multiple categories, means for selecting the most suitable automated agent for each category based on the classification results, means for monitoring the effectiveness of the incorporated automated agents, integrating an emotion recognition engine to recognize the emotional state of users and appropriately adjust responses, and means for using data from the emotion recognition engine to propose optimization of workload and improvement of the environment. This makes it possible to provide appropriate business support that takes into account the emotional state of each user and detailed services by home agents.

[0184] "Corporate data" refers to the collective information that an organization generates and collects in the course of its daily operations and activities.

[0185] "Business procedures" refer to the specific tasks and workflows involved in various activities and processes within a company.

[0186] An "automation agent" is a software program or device that autonomously performs tasks in a specific business process to improve efficiency.

[0187] An "emotion recognition engine" is a computer program or system that analyzes and identifies a user's emotional state from audio, text, or video.

[0188] "Data from the emotion recognition engine" refers to information about the user's emotional state that has been analyzed and extracted by the emotion recognition engine.

[0189] "Workload optimization" means taking into account user emotions and efficiency to optimize the resources and timing allocated to each task.

[0190] "Environmental improvement" refers to enhancing the work and living environment in which users engage in activities, thereby reducing stress and fatigue and enabling them to work efficiently and comfortably.

[0191] To implement this invention, the server collects business data from a company and runs a program that analyzes this data to classify business procedures into multiple categories. This analysis utilizes natural language processing and machine learning techniques. For the analysis of the collected data, libraries such as TENSORFLOW® and spaCy are used to classify the data and select the optimal automation agent. The server also integrates an emotion recognition engine to determine the user's emotional state using speech and text data. The Google Cloud Speech-to-Text API can be used for this purpose.

[0192] The terminal is equipped with a user interface for monitoring and feedback, through which users can receive support suggestions and suggestions for improving work processes. Specifically, if a user is experiencing stress at work, the server will recommend schedule changes or appropriate activities to reduce the workload, based on data from the emotion recognition engine.

[0193] As a concrete example, if a home robot is introduced, the robot will be equipped with an emotion recognition engine that detects the voices and facial expressions of individual users within the home and takes the most appropriate action based on their emotional state. For example, if it determines that the user is tired, it can play relaxing music and speak to them in a gentle voice.

[0194] By utilizing a generative AI model and providing example prompts like the following, it is possible to generate more specific actions:

[0195] "We're seeking advice on how to appropriately respond when we detect that a user is fatigued. Please suggest music and activities that can help them refresh."

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server collects corporate data. Specifically, it retrieves datasets related to each business process (e.g., employee work logs, customer interaction data, etc.) from the company's database. Based on this input data, it performs data processing and prepares it for analysis.

[0199] Step 2:

[0200] The server analyzes the collected dataset and classifies the business procedures into multiple categories. It uses natural language processing and machine learning models (using libraries such as TensorFlow and spaCy) to analyze the processes and patterns shown in the data. This process categorizes each process as "procedural," "labor-based," or "inappropriate for implementation," and identifies areas for optimization.

[0201] Step 3:

[0202] The server analyzes the user's voice and text data and uses an emotion recognition engine to identify the user's emotional state. It converts the voice data to text using the Google Cloud Speech-to-Text API and then analyzes it with spaCy to extract emotional patterns. This step yields the result of determining the user's emotional state (e.g., joy, fatigue, stress).

[0203] Step 4:

[0204] The server generates improvement suggestions to adjust work steps and the behavior of home robots based on emotional data obtained from the emotion recognition engine. Using a generative AI model, it generates prompt sentences and proposes specific actions to improve the user's emotional state. The generated output includes measures to reduce the workload and action plans tailored to the user's state.

[0205] Step 5:

[0206] The terminal receives improvement suggestions from the server and notifies the user through an interface. The user can then use this information to review and optimize their work processes and daily actions. The output in this step is a user-friendly presentation of the suggested results.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] This invention is a system for effectively selecting, deploying, and operating artificial intelligence agents to improve the operational efficiency of a company. A server accesses the company's systems to collect extensive data on business processes. This collected data includes work content, working hours, resource utilization, and process history, forming the foundation for a detailed understanding of business operations.

[0224] Next, the server classifies this data into several categories through advanced data analysis algorithms. Specifically, it classifies the data into categories such as "workflow type" based on the characteristics, frequency, and complexity of the tasks, "employee type" which is repetitive and suitable for automation, and "unsuitable for deployment" which is not suitable for the introduction of artificial intelligence agents.

[0225] Subsequently, the server selects the most suitable artificial intelligence agent based on the classification results. This involves using a performance database of existing agents to achieve the best possible match between business requirements and agent capabilities. The selected artificial intelligence agent is then proposed to the user terminal, and its details (predicted effectiveness, implementation costs, operation methods, etc.) are presented.

[0226] Once the user approves the server's proposal, the server automatically integrates the selected artificial intelligence agent into the necessary business processes. This integration includes installing and configuring the agent's software, as well as coordinating its interface with existing systems.

[0227] After implementation, the server continuously monitors the operational status of the artificial intelligence agent. This monitoring collects and analyzes data on operational efficiency, agent effectiveness, and employee feedback. Based on the analysis results, the server proposes specific adjustments and new strategies to improve the agent's effectiveness to user terminals, thereby supporting the continuous enhancement of the company's operational efficiency.

[0228] As a concrete example, consider a case where this system is implemented in the customer support department of a certain company. The server collects inquiry response data and classifies tasks related to FAQs as workflow-type tasks. Next, the server selects an artificial intelligence agent capable of automatic replies and sends suggestions to the user's terminal. By implementing the system's automatic reply function and receiving effective operation and improvement support through the server, the efficiency of customer support can be dramatically improved.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The server accesses the company's systems and collects processing data related to business operations. This data includes business content, processing time, and resource usage. The collected data is stored in a database for later analysis.

[0232] Step 2:

[0233] The server executes a pre-configured algorithm to analyze the collected data. Using natural language processing techniques, it analyzes business content in a documented form and converts business processes into an evaluable format.

[0234] Step 3:

[0235] Based on the data analyzed by the server, a model is applied to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This model classifies processes by analyzing their characteristics, frequency, and complexity.

[0236] Step 4:

[0237] The server consults a database of agents to select an artificial intelligence agent suitable for each category. The selection is made considering how well the agent's capabilities match the business requirements.

[0238] Step 5:

[0239] The terminal displays a proposal for an artificial intelligence agent selected by the server. This proposal includes the agent's functions, implementation costs, and projected effects. The user uses this information to decide whether to approve the implementation.

[0240] Step 6:

[0241] Once the user approves the proposed artificial intelligence agent, the server initiates the installation and configuration process to integrate the selected agent into the business process.

[0242] Step 7:

[0243] The server monitors the performance of the artificial intelligence agents it deploys. This monitoring collects data related to operational efficiency, reduced working hours, and operational accuracy.

[0244] Step 8:

[0245] The server analyzes performance based on monitoring results and, if necessary, sends agent configuration adjustments or additional suggestions to the user terminal. This ensures that the agent's effectiveness is maximized.

[0246] (Example 1)

[0247] 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."

[0248] Improving operational efficiency and implementing effective digital tools are essential for maintaining competitiveness in modern businesses. However, processes such as classifying business data, selecting the optimal advanced computing agents, and monitoring post-implementation effects are complex and burdensome for companies. Therefore, there is a need for comprehensive solutions to support business automation and efficiency.

[0249] 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.

[0250] In this invention, the server includes means for collecting activity data in a business domain, means for analyzing the collected activity data and classifying it into multiple categories based on business characteristics, and means for using the classification results to select the optimal advanced computing agent. This enables companies to automatically and efficiently deploy agents suited to their business processes and optimize their performance.

[0251] "Business domain" refers to the range of various business activities performed within a company, and includes different functions and processes such as production, sales, and human resources.

[0252] "Activity data" refers to all information related to business processes, specifically including working hours, resource usage, progress status, and deliverables.

[0253] "Analysis" refers to the process of examining collected data in detail to understand its patterns and characteristics, and in particular includes data classification and predictive analysis using machine learning.

[0254] A "category" refers to a group or class of data that has been separated through analysis, and it is a collection of similar data based on specific characteristics or conditions.

[0255] An "advanced computing agent" refers to a software program designed to automate and streamline specific business tasks using machine learning and artificial intelligence technologies.

[0256] "Implementation" refers to the act of applying or installing a newly selected advanced computing agent into existing business processes and integrating it into the environment to make it usable.

[0257] "Effect monitoring" refers to the process of continuously observing and recording the performance of already implemented advanced computing agents, and measuring and evaluating their efficiency and results.

[0258] "Efficiency improvement" refers to a series of adjustments and strategic changes made to improve the performance of business processes, particularly including resource optimization and reduction of work time.

[0259] This invention is a system that utilizes artificial intelligence technology to efficiently analyze and automate business processes in order to improve the operational efficiency of companies. This system operates through the collaborative efforts of a server, terminals, and users.

[0260] First, the server connects to the company's internal systems and collects a wide range of activity data within the business domain. This process utilizes database access and APIs to obtain important information such as work content, work time, resource utilization, and process history. This data forms the foundation for a detailed understanding of business workflows.

[0261] Next, the server analyzes the collected data. Here, advanced data analysis algorithms and machine learning models are used to classify the data into categories such as "procedural," "personnel-based," and "non-conforming." This classification helps identify which business processes are suitable for automation.

[0262] Based on the classified data, the server selects the optimal high-performance computing agent. This selection is made by referring to a performance database of existing agents and making the best possible match between business requirements and agent capabilities.

[0263] The selected agent is sent as a suggestion to the user's device, and detailed information about the agent is provided. This includes the agent's expected effectiveness, implementation costs, and operating procedures.

[0264] If the user approves the proposal, the server automatically integrates the agent into the business process. This involves software installation, configuration, and interface adjustments with existing systems.

[0265] As a result of the implementation, operational efficiency improves and the effectiveness of the agents is maximized. The operational status is continuously monitored by the server, and further efficiency improvements are suggested based on the data obtained.

[0266] As a concrete example, consider the case where this system is implemented in the customer support department of a certain company. The server collects inquiry data and classifies FAQ response tasks as "procedural." The server then selects an advanced computing agent capable of automatic replies, sends a proposal to the user's terminal, and if the user approves, it is implemented into the system, which is expected to improve the efficiency of inquiry handling.

[0267] An example of a prompt to input into the generating AI model is, "Based on customer support inquiry data, please suggest how to automate the business process using the most suitable AI agent."

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server accesses the company's systems to collect activity data within the business domain. Inputs include business content, work time, resource usage, and process history accessed via system databases and APIs. Specifically, the server executes scripts and queries to retrieve the necessary data, integrates it, and formats it into an output dataset. This output serves as the foundation for subsequent data analysis.

[0271] Step 2:

[0272] The server analyzes the collected data and classifies it into multiple categories based on business characteristics. The input is the dataset obtained in Step 1, and here data analysis algorithms are used to perform characteristic analysis and pattern recognition. Specifically, the server applies a machine learning model and divides the data into categories such as "procedural," "personnel-based," and "non-conforming" based on features. The output is classification information of business processes.

[0273] Step 3:

[0274] The server selects the most suitable advanced computing agent based on the classification results. The input is the classification information obtained from step 2. Here, the agent characteristics database is matched with the business characteristics, and a machine learning model is used to calculate a prediction score. Specifically, the server compares the characteristics of each agent with the business requirements and identifies the most suitable agent through scoring. The output is information on the selected agent and its recommendation level.

[0275] Step 4:

[0276] The selected advanced computing agent is sent to the user's terminal as a proposal. The input is the output data from step 3. The specific action here is for the server to refine the proposal and output it in a format that the user can review, such as a report or dashboard. The user receives this and reviews the content. The output is the user's approval or revision request for the proposal.

[0277] Step 5:

[0278] If the user approves the proposal, the server automatically integrates the selected agent into the business process. The input here is user approval, and the output is the deployment status of the modified business system. Specific actions include agent software installation, system configuration, interface adjustments with existing systems, and integration into the business application environment.

[0279] Step 6:

[0280] After the introduction, the server continuously monitors the operation status of the advanced computing agent. Here, the performance data of the agent obtained as output is used as input to collect daily operation data, conduct operation evaluations, and discover and propose improvement points. As a specific operation, the server analyzes real-time data, evaluates efficiency and impact, and considers improvement measures. The output is a proposal for improving the effectiveness of the agent for the user and a performance report.

[0281] (Application Example 1)

[0282] Next, Application Example 1 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".

[0283] Optimizing business efficiency in production facilities is an important issue for many companies. However, in conventional systems, the analysis of business processes is insufficient, and inappropriate selections may be made for the introduction of automation. As a result, the improvement of business productivity is hindered. In addition, there is a lack of a mechanism for quickly proposing business improvements in real time, and means for quickly eliminating the bottlenecks faced by on-site workers are required.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0285] In this invention, the server includes means for collecting business data from an information processing device, means for analyzing the collected business data to classify business processes into multiple types, means for selecting an optimal automation algorithm for each type based on the classification result, and means for presenting algorithm optimization information to a display device in real time. As a result, the analysis and optimization of automation of business processes in production facilities can be performed in real time, and the productivity of business can be significantly improved.

[0286] An "information processing device" is an electronic device such as a computer or sensor that enables data collection and communication in business operations.

[0287] "Business data" refers to information related to business activities conducted inside and outside the company, including working hours, resource utilization status, process history, etc.

[0288] A "business process" refers to a series of operations and procedures required to perform a specific business.

[0289] An "automation algorithm" is a series of calculation procedures designed to streamline the work process in a specific business.

[0290] An "information system" is a series of information technology infrastructures used to support business activities, and is composed of hardware, software, networks, etc.

[0291] "Performance" is an indicator that shows how effectively a system or algorithm functions with respect to its purpose.

[0292] A "display device" is an electronic device such as a screen or projector for visually providing information to users.

[0293] "Optimization information" refers to instructions and proposals provided to improve business processes and enhance their efficiency.

[0294] The system for implementing this invention is configured using an information processing device, a cloud server, and a smart display. The server collects business data from the information processing device and classifies business processes into various types by analyzing this data. Based on this classification result, the server selects the optimal automation algorithm for each type and integrates it into the information system.

[0295] Furthermore, it features a function that presents on-site workers with optimization information in real time via a smart display. This allows workers to quickly resolve bottlenecks in their work processes and improve work efficiency.

[0296] The hardware includes sensors for data collection, cloud servers for processing (e.g., Amazon Web Services), and smart displays for displaying information (e.g., Google Glass). The software side utilizes machine learning algorithms for data analysis, automating the classification of business data and the selection of algorithms.

[0297] As a concrete example, in an assembly line for small parts at a production facility, workers wear smart displays and perform tasks based on instructions from a server. This optimizes specific processes and improves productivity. Another example of a prompt message is, "Identify bottlenecks on the factory floor and propose the optimal work procedure for efficiency."

[0298] The generative AI model generates optimization algorithms based on business data and immediately presents the results to the worker, thereby supporting efficient business operations.

[0299] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0300] Step 1:

[0301] The server collects operational data in real time from information processing equipment. Inputs include data from various sensors, such as work time, resource utilization, and process history. The server stores this data and organizes it for subsequent analysis steps.

[0302] Step 2:

[0303] The server starts data analysis using the collected business data. The input is the business data collected in the previous step. The data is analyzed using a generated AI model to classify business processes into multiple types. At this time, a machine learning algorithm is used to identify and classify specific patterns and trends, and classification information is obtained as the output.

[0304] Step 3:

[0305] The server selects the optimal automation algorithm for each type based on the classification information. The input is the classification information from the previous step. The server refers to the database of existing algorithms and extracts the optimal one. This selection takes into account the characteristics of each process and the required efficiency, and the selected algorithm is obtained as the output.

[0306] Step 4:

[0307] The server integrates the selected automation algorithm into the information system. The input is the algorithm selected in Step 3. The server adjusts the connection between the existing information system and the algorithm and implements the necessary settings. As the output, an integrated information system is obtained.

[0308] <00​​​​​​​​​​​​The user performs tasks based on information displayed on a smart display and then feeds the results back to the server. The input consists of the user's feedback information and data on the tasks performed. The server collects this feedback information and uses it to further improve the algorithm, resulting in a system that undergoes repeated improvements as output.

[0312] 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.

[0313] This invention is a system that adds user emotion recognition capabilities to an artificial intelligence agent in order to further improve the operational efficiency of a company. The system begins with a server collecting business processing data from a company and precisely analyzing the business processes using natural language processing and machine learning. The analyzed data is used to classify tasks into three categories: "workflow type," "employee type," and "unsuitable for implementation," after which the most suitable artificial intelligence agent is selected.

[0314] In this process, the server integrates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and text data to identify the user's emotional state. For example, if the emotion engine determines that the user is experiencing an emotional state such as fatigue or stress, the server automatically adjusts the behavior of the artificial intelligence agent to provide appropriate support to the user.

[0315] Furthermore, using emotional data from the emotion engine, the server generates suggestions for improving business processes. These suggestions are notified to the user's terminal, and the user can then use them to improve the efficiency of their work. The suggestions include specific strategies to improve the user's emotional state, such as redistributing workload or improving the work environment.

[0316] For example, consider an application in a customer support department. The server analyzes the support staff's interaction history and their emotional state at the time (e.g., frustration or fatigue). If the emotion engine detects signs of fatigue, the server suggests flexible adjustments to the work schedule based on that emotional data. This suggestion is notified to the administrator via the terminal, allowing the administrator to quickly take measures to reduce the burden on the staff.

[0317] In this way, by combining an emotion engine, this system can achieve both efficient operation of artificial intelligence agents and business improvement.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The server accesses the company's systems and collects a wide range of business processing data. This data includes details about the tasks performed, working hours, and resources used.

[0321] Step 2:

[0322] The system analyzes the business processing data collected by the server and uses machine learning models to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This classification is based on business characteristics and data patterns.

[0323] Step 3:

[0324] The server selects the most suitable artificial intelligence agent for each classified business process. The selection is based on the matching of each agent's functions with the business requirements.

[0325] Step 4:

[0326] The server operates an emotion engine, analyzing user voice and text within business processes to identify their emotional state. The emotion engine analyzes the user's emotions in real time and classifies their emotional state into categories such as "positive," "negative," and "neutral."

[0327] Step 5:

[0328] The server adjusts the behavior of the artificial intelligence agent based on the results of the emotion engine. For example, if the user is in a negative emotional state, the server will add actions to the agent to encourage relaxation.

[0329] Step 6:

[0330] The terminal displays emotional data obtained from the emotion engine, along with suggestions for business improvements based on that data. These suggestions include workload distribution, improvements to the work environment, and the provision of further support.

[0331] Step 7:

[0332] Based on suggestions displayed on the user's device, the system adjusts business processes and agent settings to improve their emotional state and enhance work efficiency.

[0333] Step 8:

[0334] The server monitors the effects of improved processes and tuned agents. By continuously collecting data and providing new improvement suggestions to users' terminals as needed, it helps maintain an optimal work environment.

[0335] (Example 2)

[0336] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0337] In modern businesses, as operations become increasingly complex and diverse, there is a need for management that simultaneously considers employee emotions and the efficiency of work procedures. However, traditional systems have faced challenges in adequately analyzing work data and recognizing emotions, making it difficult to propose concrete improvements to operations. This has led to problems such as decreased labor productivity and increased employee stress.

[0338] 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.

[0339] In this invention, the server includes means for collecting information about the business entity, means for analyzing the collected information and classifying business procedures into multiple categories, and means for integrating an emotion engine for recognizing the emotions of users. This enables efficient management of business procedures and business improvement suggestions based on employee emotions.

[0340] A "business entity" refers to a legal entity such as an organization or company, which is a subject that conducts economic activities through specific business operations and activities.

[0341] "Information" refers to data and records related to the business operations of an entity, including data on work progress and employee performance.

[0342] "Business procedures" refer to the processes and procedures that show how business operations are carried out within an organization, representing the specific flow and sequence of work.

[0343] A "category" refers to a classification that groups items with similar characteristics or uses, and is grouped based on the characteristics of business procedures.

[0344] An "intelligent agent" refers to an intelligent program or system that analyzes data and makes predictions and decisions, and has the ability to automate specific tasks.

[0345] An "emotional engine" refers to software technology that analyzes a user's emotional state, and includes devices that recognize emotions using voice data and text data.

[0346] A "proposal" refers to guidelines or advice provided for the purpose of improving the operations and management of an organization, and is information that provides guidance for action.

[0347] "Monitoring" refers to the act of continuously observing the effectiveness of a particular process or agent, and is a process of identifying areas that need improvement or adjustment.

[0348] This invention provides an intelligent system for improving the operational efficiency of businesses. The server is responsible for collecting information about the business entity. Specifically, it uses a business management platform and a database management system to collect data on the progress of operations and employee performance. Based on this data, the server uses Python libraries such as NLTK and SpaCy to analyze the information through natural language processing and classify business procedures into categories such as "procedural," "employee-oriented," and "inappropriate for implementation."

[0349] Furthermore, the server recognizes the user's emotions by integrating an emotion engine. This emotion engine analyzes voice input and text data to identify the user's emotional state. For example, if it determines that the user is experiencing stress, the emotion engine immediately provides that data to the server.

[0350] The server integrates and analyzes identified emotional and operational data to select the most suitable intelligent agent. The intelligent agent uses a generative AI model to support the automation of tasks. After this selection, the server generates suggestions for improving operational efficiency and notifies the user terminal. These suggestions include redistributing workload and improving the work environment, allowing the user to optimize their tasks based on these suggestions.

[0351] As a concrete example, consider its application in a customer support department. The server analyzes the user's work interaction history and sentiment data, and proposes appropriate work adjustments. Users receive these suggestions through their terminals and can, for example, quickly make flexible adjustments to their work schedules.

[0352] Examples of prompts include, "Analyze current business process data and generate improvement suggestions based on emotional states," and "Based on support staff emotional data, suggest a redistribution of workload."

[0353] Thus, the present invention provides a concrete form for achieving efficient management of work procedures and business improvement based on user emotions.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The server collects information from the business entity. Specifically, it retrieves data from business management software and databases via APIs. This input data includes task progress, work time, and employee performance metrics. The server integrates this data and prepares it for analysis.

[0357] Step 2:

[0358] The server analyzes the collected information using natural language processing techniques. Using Python's NLTK and SpaCy, the server tokenizes the data and understands the textual context. This allows it to classify business procedures into "procedural," "employee-based," and "inappropriate for implementation." The output of this process is the classified business procedure data.

[0359] Step 3:

[0360] The server uses an emotion engine to acquire the user's emotional data. The user inputs voice or text data into the terminal via a microphone or keyboard. The server uses the emotion engine to identify emotional states such as stress and fatigue from this data. The output is information about the identified emotional states.

[0361] Step 4:

[0362] The server integrates classified business procedure data and user emotional data to select the optimal intelligent agent. Here, a generative AI model is used to select and customize the agent. The output is the configured intelligent agent settings. These settings facilitate the automation of business processes.

[0363] Step 5:

[0364] The server generates business improvement suggestions using a generation AI model. These suggestions include strategies for redistributing workload and measures to improve the work environment. The suggestions are notified to the user's terminal. The output is a specific improvement suggestion expressed in a notification format.

[0365] Step 6:

[0366] Users receive suggestions through their devices. Based on these suggestions, they take actions to optimize their work. For example, users decide to adjust their work schedules or reallocate resources. The ultimate result of this process is improved work processes and enhanced user emotional well-being.

[0367] (Application Example 2)

[0368] 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 as the "terminal".

[0369] Conventional business process support systems prioritize operational efficiency without considering the emotional state of individual users, resulting in insufficient support to address user stress and fatigue. Consequently, there were limitations to improving operational efficiency and user satisfaction. Furthermore, even in the application of automated agents in home and daily life settings, the lack of nuanced responses based on emotion recognition made optimizing the user experience difficult.

[0370] 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.

[0371] In this invention, the server includes means for collecting corporate data, means for analyzing the collected data and classifying business procedures into multiple categories, means for selecting the most suitable automated agent for each category based on the classification results, means for monitoring the effectiveness of the incorporated automated agents, integrating an emotion recognition engine to recognize the emotional state of users and appropriately adjust responses, and means for using data from the emotion recognition engine to propose optimization of workload and improvement of the environment. This makes it possible to provide appropriate business support that takes into account the emotional state of each user and detailed services by home agents.

[0372] "Corporate data" refers to the collective information that an organization generates and collects in the course of its daily operations and activities.

[0373] "Business procedures" refer to the specific tasks and workflows involved in various activities and processes within a company.

[0374] An "automation agent" is a software program or device that autonomously performs tasks in a specific business process to improve efficiency.

[0375] An "emotion recognition engine" is a computer program or system that analyzes and identifies a user's emotional state from audio, text, or video.

[0376] "Data from the emotion recognition engine" refers to information about the user's emotional state that has been analyzed and extracted by the emotion recognition engine.

[0377] "Workload optimization" means taking into account user emotions and efficiency to optimize the resources and timing allocated to each task.

[0378] "Environmental improvement" refers to enhancing the work and living environment in which users engage in activities, thereby reducing stress and fatigue and enabling them to work efficiently and comfortably.

[0379] To implement this invention, the server collects business data from a company and runs a program that analyzes this data to classify business procedures into multiple categories. This analysis utilizes natural language processing and machine learning techniques. Libraries such as TensorFlow and spaCy are used to analyze the collected data, classify the data, and select the optimal automation agent. The server also integrates an emotion recognition engine to determine the user's emotional state using speech and text data. The Google Cloud Speech-to-Text API can be used for this purpose.

[0380] The terminal is equipped with a user interface for monitoring and feedback, through which users can receive support suggestions and suggestions for improving work processes. Specifically, if a user is experiencing stress at work, the server will recommend schedule changes or appropriate activities to reduce the workload, based on data from the emotion recognition engine.

[0381] As a concrete example, if a home robot is introduced, the robot will be equipped with an emotion recognition engine that detects the voices and facial expressions of individual users within the home and takes the most appropriate action based on their emotional state. For example, if it determines that the user is tired, it can play relaxing music and speak to them in a gentle voice.

[0382] By utilizing a generative AI model and providing example prompts like the following, it is possible to generate more specific actions:

[0383] "We're seeking advice on how to appropriately respond when we detect that a user is fatigued. Please suggest music and activities that can help them refresh."

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server collects corporate data. Specifically, it retrieves datasets related to each business process (e.g., employee work logs, customer interaction data, etc.) from the company's database. Based on this input data, it performs data processing and prepares it for analysis.

[0387] Step 2:

[0388] The server analyzes the collected dataset and classifies the business procedures into multiple categories. It uses natural language processing and machine learning models (using libraries such as TensorFlow and spaCy) to analyze the processes and patterns shown in the data. This process categorizes each process as "procedural," "labor-based," or "inappropriate for implementation," and identifies areas for optimization.

[0389] Step 3:

[0390] The server analyzes the user's voice and text data and uses an emotion recognition engine to identify the user's emotional state. It converts the voice data to text using the Google Cloud Speech-to-Text API and then analyzes it with spaCy to extract emotional patterns. This step yields the result of determining the user's emotional state (e.g., joy, fatigue, stress).

[0391] Step 4:

[0392] The server generates improvement suggestions to adjust work steps and the behavior of home robots based on emotional data obtained from the emotion recognition engine. Using a generative AI model, it generates prompt sentences and proposes specific actions to improve the user's emotional state. The generated output includes measures to reduce the workload and action plans tailored to the user's state.

[0393] Step 5:

[0394] The terminal receives improvement suggestions from the server and notifies the user through an interface. The user can then use this information to review and optimize their work processes and daily actions. The output in this step is a user-friendly presentation of the suggested results.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] [Third Embodiment]

[0399] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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".

[0411] This invention is a system for effectively selecting, deploying, and operating artificial intelligence agents to improve the operational efficiency of a company. A server accesses the company's systems to collect extensive data on business processes. This collected data includes work content, working hours, resource utilization, and process history, forming the foundation for a detailed understanding of business operations.

[0412] Next, the server classifies this data into several categories through advanced data analysis algorithms. Specifically, it classifies the data into categories such as "workflow type" based on the characteristics, frequency, and complexity of the tasks, "employee type" which is repetitive and suitable for automation, and "unsuitable for deployment" which is not suitable for the introduction of artificial intelligence agents.

[0413] Subsequently, the server selects the most suitable artificial intelligence agent based on the classification results. This involves using a performance database of existing agents to achieve the best possible match between business requirements and agent capabilities. The selected artificial intelligence agent is then proposed to the user terminal, and its details (predicted effectiveness, implementation costs, operation methods, etc.) are presented.

[0414] Once the user approves the server's proposal, the server automatically integrates the selected artificial intelligence agent into the necessary business processes. This integration includes installing and configuring the agent's software, as well as coordinating its interface with existing systems.

[0415] After implementation, the server continuously monitors the operational status of the artificial intelligence agent. This monitoring collects and analyzes data on operational efficiency, agent effectiveness, and employee feedback. Based on the analysis results, the server proposes specific adjustments and new strategies to improve the agent's effectiveness to user terminals, thereby supporting the continuous enhancement of the company's operational efficiency.

[0416] As a concrete example, consider a case where this system is implemented in the customer support department of a certain company. The server collects inquiry response data and classifies tasks related to FAQs as workflow-type tasks. Next, the server selects an artificial intelligence agent capable of automatic replies and sends suggestions to the user's terminal. By implementing the system's automatic reply function and receiving effective operation and improvement support through the server, the efficiency of customer support can be dramatically improved.

[0417] The following describes the processing flow.

[0418] Step 1:

[0419] The server accesses the company's systems and collects processing data related to business operations. This data includes business content, processing time, and resource usage. The collected data is stored in a database for later analysis.

[0420] Step 2:

[0421] The server executes a pre-configured algorithm to analyze the collected data. Using natural language processing techniques, it analyzes business content in a documented form and converts business processes into an evaluable format.

[0422] Step 3:

[0423] Based on the data analyzed by the server, a model is applied to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This model classifies processes by analyzing their characteristics, frequency, and complexity.

[0424] Step 4:

[0425] The server consults a database of agents to select an artificial intelligence agent suitable for each category. The selection is made considering how well the agent's capabilities match the business requirements.

[0426] Step 5:

[0427] The terminal displays a proposal for an artificial intelligence agent selected by the server. This proposal includes the agent's functions, implementation costs, and projected effects. The user uses this information to decide whether to approve the implementation.

[0428] Step 6:

[0429] Once the user approves the proposed artificial intelligence agent, the server initiates the installation and configuration process to integrate the selected agent into the business process.

[0430] Step 7:

[0431] The server monitors the performance of the artificial intelligence agents it deploys. This monitoring collects data related to operational efficiency, reduced working hours, and operational accuracy.

[0432] Step 8:

[0433] The server analyzes performance based on monitoring results and, if necessary, sends agent configuration adjustments or additional suggestions to the user terminal. This ensures that the agent's effectiveness is maximized.

[0434] (Example 1)

[0435] 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."

[0436] Improving operational efficiency and implementing effective digital tools are essential for maintaining competitiveness in modern businesses. However, processes such as classifying business data, selecting the optimal advanced computing agents, and monitoring post-implementation effects are complex and burdensome for companies. Therefore, there is a need for comprehensive solutions to support business automation and efficiency.

[0437] 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.

[0438] In this invention, the server includes means for collecting activity data in a business domain, means for analyzing the collected activity data and classifying it into multiple categories based on business characteristics, and means for using the classification results to select the optimal advanced computing agent. This enables companies to automatically and efficiently deploy agents suited to their business processes and optimize their performance.

[0439] "Business domain" refers to the range of various business activities performed within a company, and includes different functions and processes such as production, sales, and human resources.

[0440] "Activity data" refers to all information related to business processes, specifically including working hours, resource usage, progress status, and deliverables.

[0441] "Analysis" refers to the process of examining collected data in detail to understand its patterns and characteristics, and in particular includes data classification and predictive analysis using machine learning.

[0442] A "category" refers to a group or class of data that has been separated through analysis, and it is a collection of similar data based on specific characteristics or conditions.

[0443] An "advanced computing agent" refers to a software program designed to automate and streamline specific business tasks using machine learning and artificial intelligence technologies.

[0444] "Implementation" refers to the act of applying or installing a newly selected advanced computing agent into existing business processes and integrating it into the environment to make it usable.

[0445] "Effect monitoring" refers to the process of continuously observing and recording the performance of already implemented advanced computing agents, and measuring and evaluating their efficiency and results.

[0446] "Efficiency improvement" refers to a series of adjustments and strategic changes made to improve the performance of business processes, particularly including resource optimization and reduction of work time.

[0447] This invention is a system that utilizes artificial intelligence technology to efficiently analyze and automate business processes in order to improve the operational efficiency of companies. This system operates through the collaborative efforts of a server, terminals, and users.

[0448] First, the server connects to the company's internal systems and collects a wide range of activity data within the business domain. This process utilizes database access and APIs to obtain important information such as work content, work time, resource utilization, and process history. This data forms the foundation for a detailed understanding of business workflows.

[0449] Next, the server analyzes the collected data. Here, advanced data analysis algorithms and machine learning models are used to classify the data into categories such as "procedural," "personnel-based," and "non-conforming." This classification helps identify which business processes are suitable for automation.

[0450] Based on the classified data, the server selects the optimal high-performance computing agent. This selection is made by referring to a performance database of existing agents and making the best possible match between business requirements and agent capabilities.

[0451] The selected agent is sent as a suggestion to the user's device, and detailed information about the agent is provided. This includes the agent's expected effectiveness, implementation costs, and operating procedures.

[0452] If the user approves the proposal, the server automatically integrates the agent into the business process. This involves software installation, configuration, and interface adjustments with existing systems.

[0453] As a result of the implementation, operational efficiency improves and the effectiveness of the agents is maximized. The operational status is continuously monitored by the server, and further efficiency improvements are suggested based on the data obtained.

[0454] As a concrete example, consider the case where this system is implemented in the customer support department of a certain company. The server collects inquiry data and classifies FAQ response tasks as "procedural." The server then selects an advanced computing agent capable of automatic replies, sends a proposal to the user's terminal, and if the user approves, it is implemented into the system, which is expected to improve the efficiency of inquiry handling.

[0455] An example of a prompt to input into the generating AI model is, "Based on customer support inquiry data, please suggest how to automate the business process using the most suitable AI agent."

[0456] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0457] Step 1:

[0458] The server accesses the company's systems to collect activity data within the business domain. Inputs include business content, work time, resource usage, and process history accessed via system databases and APIs. Specifically, the server executes scripts and queries to retrieve the necessary data, integrates it, and formats it into an output dataset. This output serves as the foundation for subsequent data analysis.

[0459] Step 2:

[0460] The server analyzes the collected data and classifies it into multiple categories based on business characteristics. The input is the dataset obtained in Step 1, and here data analysis algorithms are used to perform characteristic analysis and pattern recognition. Specifically, the server applies a machine learning model and divides the data into categories such as "procedural," "personnel-based," and "non-conforming" based on features. The output is classification information of business processes.

[0461] Step 3:

[0462] The server selects the most suitable advanced computing agent based on the classification results. The input is the classification information obtained from step 2. Here, the agent characteristics database is matched with the business characteristics, and a machine learning model is used to calculate a prediction score. Specifically, the server compares the characteristics of each agent with the business requirements and identifies the most suitable agent through scoring. The output is information on the selected agent and its recommendation level.

[0463] Step 4:

[0464] The selected advanced computing agent is sent to the user's terminal as a proposal. The input is the output data from step 3. The specific action here is for the server to refine the proposal and output it in a format that the user can review, such as a report or dashboard. The user receives this and reviews the content. The output is the user's approval or revision request for the proposal.

[0465] Step 5:

[0466] If the user approves the proposal, the server automatically integrates the selected agent into the business process. The input here is user approval, and the output is the deployment status of the modified business system. Specific actions include agent software installation, system configuration, interface adjustments with existing systems, and integration into the business application environment.

[0467] Step 6:

[0468] The server continuously monitors the operational status of the advanced computing agent after deployment. Here, the agent's performance data, obtained as output, is used as input for collecting daily operational data, evaluating operations, and identifying and proposing improvements. Specifically, the server analyzes real-time data, evaluates efficiency and impact, and considers improvement measures. The output includes suggestions for improving the agent's effectiveness and performance reports for the user.

[0469] (Application Example 1)

[0470] 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."

[0471] Optimizing operational efficiency in production facilities is a critical challenge for many companies. However, traditional systems often fail to adequately analyze business processes, leading to inappropriate choices in automation implementation. As a result, productivity improvements are hindered. Furthermore, there is a lack of mechanisms to propose rapid, real-time improvements, and there is a need for means to quickly resolve bottlenecks faced by on-site workers.

[0472] 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.

[0473] In this invention, the server includes means for collecting business data from an information processing device, means for analyzing the collected business data and classifying business processes into multiple types, means for selecting the most suitable automation algorithm for each type based on the classification results, and means for displaying algorithm optimization information on a display device in real time. This enables real-time analysis and automation optimization of business processes in production facilities, dramatically improving business productivity.

[0474] An "information processing device" is an electronic device such as a computer or sensor that enables the collection and communication of data in business operations.

[0475] "Business data" refers to information about business activities conducted both inside and outside the company, including working hours, resource utilization, and process history.

[0476] A "business process" refers to a series of tasks and procedures necessary to perform a specific task.

[0477] An "automation algorithm" is a set of computational steps designed to streamline a work process in a specific task.

[0478] An "information system" is a set of information technology infrastructures used to support business activities, and consists of hardware, software, networks, and other components.

[0479] "Performance" is an indicator that shows how effectively a system or algorithm functions for its intended purpose.

[0480] A "display device" is an electronic device such as a screen or projector that provides information to users visually.

[0481] "Optimization information" refers to instructions and suggestions provided to improve business processes and increase their efficiency.

[0482] The system for implementing this invention consists of an information processing device, a cloud server, and a smart display. The server collects business data from the information processing device and analyzes it to classify business processes into various types. Based on these classification results, the server selects the most suitable automation algorithm for each type and integrates it into the information system.

[0483] Furthermore, it features a function that presents on-site workers with optimization information in real time via a smart display. This allows workers to quickly resolve bottlenecks in their work processes and improve work efficiency.

[0484] The hardware includes sensors for data collection, cloud servers for processing (e.g., Amazon Web Services), and smart displays for displaying information (e.g., Google Glass). The software side utilizes machine learning algorithms for data analysis, automating the classification of business data and the selection of algorithms.

[0485] As a concrete example, in an assembly line for small parts at a production facility, workers wear smart displays and perform tasks based on instructions from a server. This optimizes specific processes and improves productivity. Another example of a prompt message is, "Identify bottlenecks on the factory floor and propose the optimal work procedure for efficiency."

[0486] The generative AI model generates optimization algorithms based on business data and immediately presents the results to the worker, thereby supporting efficient business operations.

[0487] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0488] Step 1:

[0489] The server collects operational data in real time from information processing equipment. Inputs include data from various sensors, such as work time, resource utilization, and process history. The server stores this data and organizes it for subsequent analysis steps.

[0490] Step 2:

[0491] The server begins data analysis using the collected business data. The input is the business data collected in the previous step. The data is analyzed using a generative AI model, and the business processes are classified into several types. At this time, machine learning algorithms are used to identify specific patterns and trends and perform classification, obtaining classification information as output.

[0492] Step 3:

[0493] The server selects the most suitable automation algorithm for each category based on the classification information. The input is the classification information from the previous step. The server refers to a database of existing algorithms and extracts the most suitable one. This selection takes into account the characteristics of each process and the required efficiency, and the selected algorithm is obtained as the output.

[0494] Step 4:

[0495] The server integrates the selected automation algorithm into the information system. The input is the algorithm selected in step 3. The server coordinates the connection between the existing information system and the algorithm and performs the necessary configurations. The output is the integrated information system.

[0496] Step 5:

[0497] Data is sent to a smart display to present information optimized for the user in real time. The input is optimized information generated by an already integrated algorithm. The terminal displays the data, making it immediately accessible to the worker. The output is the optimized information displayed on the screen.

[0498] Step 6:

[0499] The user performs tasks based on information displayed on a smart display and then feeds the results back to the server. The input consists of the user's feedback information and data on the tasks performed. The server collects this feedback information and uses it to further improve the algorithm, resulting in a system that undergoes repeated improvements as output.

[0500] 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.

[0501] This invention is a system that adds user emotion recognition capabilities to an artificial intelligence agent in order to further improve the operational efficiency of a company. The system begins with a server collecting business processing data from a company and precisely analyzing the business processes using natural language processing and machine learning. The analyzed data is used to classify tasks into three categories: "workflow type," "employee type," and "unsuitable for implementation," after which the most suitable artificial intelligence agent is selected.

[0502] In this process, the server integrates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and text data to identify the user's emotional state. For example, if the emotion engine determines that the user is experiencing an emotional state such as fatigue or stress, the server automatically adjusts the behavior of the artificial intelligence agent to provide appropriate support to the user.

[0503] Furthermore, using emotional data from the emotion engine, the server generates suggestions for improving business processes. These suggestions are notified to the user's terminal, and the user can then use them to improve the efficiency of their work. The suggestions include specific strategies to improve the user's emotional state, such as redistributing workload or improving the work environment.

[0504] For example, consider an application in a customer support department. The server analyzes the support staff's interaction history and their emotional state at the time (e.g., frustration or fatigue). If the emotion engine detects signs of fatigue, the server suggests flexible adjustments to the work schedule based on that emotional data. This suggestion is notified to the administrator via the terminal, allowing the administrator to quickly take measures to reduce the burden on the staff.

[0505] In this way, by combining an emotion engine, this system can achieve both efficient operation of artificial intelligence agents and business improvement.

[0506] The following describes the processing flow.

[0507] Step 1:

[0508] The server accesses the company's systems and collects a wide range of business processing data. This data includes details about the tasks performed, working hours, and resources used.

[0509] Step 2:

[0510] The system analyzes the business processing data collected by the server and uses machine learning models to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This classification is based on business characteristics and data patterns.

[0511] Step 3:

[0512] The server selects the most suitable artificial intelligence agent for each classified business process. The selection is based on the matching of each agent's functions with the business requirements.

[0513] Step 4:

[0514] The server operates an emotion engine, analyzing user voice and text within business processes to identify their emotional state. The emotion engine analyzes the user's emotions in real time and classifies their emotional state into categories such as "positive," "negative," and "neutral."

[0515] Step 5:

[0516] The server adjusts the behavior of the artificial intelligence agent based on the results of the emotion engine. For example, if the user is in a negative emotional state, the server will add actions to the agent to encourage relaxation.

[0517] Step 6:

[0518] The terminal displays emotional data obtained from the emotion engine, along with suggestions for business improvements based on that data. These suggestions include workload distribution, improvements to the work environment, and the provision of further support.

[0519] Step 7:

[0520] Based on suggestions displayed on the user's device, the system adjusts business processes and agent settings to improve their emotional state and enhance work efficiency.

[0521] Step 8:

[0522] The server monitors the effects of improved processes and tuned agents. By continuously collecting data and providing new improvement suggestions to users' terminals as needed, it helps maintain an optimal work environment.

[0523] (Example 2)

[0524] 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."

[0525] In modern businesses, as operations become increasingly complex and diverse, there is a need for management that simultaneously considers employee emotions and the efficiency of work procedures. However, traditional systems have faced challenges in adequately analyzing work data and recognizing emotions, making it difficult to propose concrete improvements to operations. This has led to problems such as decreased labor productivity and increased employee stress.

[0526] 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.

[0527] In this invention, the server includes means for collecting information about the business entity, means for analyzing the collected information and classifying business procedures into multiple categories, and means for integrating an emotion engine for recognizing the emotions of users. This enables efficient management of business procedures and business improvement suggestions based on employee emotions.

[0528] A "business entity" refers to a legal entity such as an organization or company, which is a subject that conducts economic activities through specific business operations and activities.

[0529] "Information" refers to data and records related to the business operations of an entity, including data on work progress and employee performance.

[0530] "Business procedures" refer to the processes and procedures that show how business operations are carried out within an organization, representing the specific flow and sequence of work.

[0531] A "category" refers to a classification that groups items with similar characteristics or uses, and is grouped based on the characteristics of business procedures.

[0532] An "intelligent agent" refers to an intelligent program or system that analyzes data and makes predictions and decisions, and has the ability to automate specific tasks.

[0533] An "emotional engine" refers to software technology that analyzes a user's emotional state, and includes devices that recognize emotions using voice data and text data.

[0534] A "proposal" refers to guidelines or advice provided for the purpose of improving the operations and management of an organization, and is information that provides guidance for action.

[0535] "Monitoring" refers to the act of continuously observing the effectiveness of a particular process or agent, and is a process of identifying areas that need improvement or adjustment.

[0536] This invention provides an intelligent system for improving the operational efficiency of businesses. The server is responsible for collecting information about the business entity. Specifically, it uses a business management platform and a database management system to collect data on the progress of operations and employee performance. Based on this data, the server uses Python libraries such as NLTK and SpaCy to analyze the information through natural language processing and classify business procedures into categories such as "procedural," "employee-oriented," and "inappropriate for implementation."

[0537] Furthermore, the server recognizes the user's emotions by integrating an emotion engine. This emotion engine analyzes voice input and text data to identify the user's emotional state. For example, if it determines that the user is experiencing stress, the emotion engine immediately provides that data to the server.

[0538] The server integrates and analyzes identified emotional and operational data to select the most suitable intelligent agent. The intelligent agent uses a generative AI model to support the automation of tasks. After this selection, the server generates suggestions for improving operational efficiency and notifies the user terminal. These suggestions include redistributing workload and improving the work environment, allowing the user to optimize their tasks based on these suggestions.

[0539] As a concrete example, consider its application in a customer support department. The server analyzes the user's work interaction history and sentiment data, and proposes appropriate work adjustments. Users receive these suggestions through their terminals and can, for example, quickly make flexible adjustments to their work schedules.

[0540] Examples of prompts include, "Analyze current business process data and generate improvement suggestions based on emotional states," and "Based on support staff emotional data, suggest a redistribution of workload."

[0541] Thus, the present invention provides a concrete form for achieving efficient management of work procedures and business improvement based on user emotions.

[0542] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0543] Step 1:

[0544] The server collects information from the business entity. Specifically, it retrieves data from business management software and databases via APIs. This input data includes task progress, work time, and employee performance metrics. The server integrates this data and prepares it for analysis.

[0545] Step 2:

[0546] The server analyzes the collected information using natural language processing techniques. Using Python's NLTK and SpaCy, the server tokenizes the data and understands the textual context. This allows it to classify business procedures into "procedural," "employee-based," and "inappropriate for implementation." The output of this process is the classified business procedure data.

[0547] Step 3:

[0548] The server uses an emotion engine to acquire the user's emotional data. The user inputs voice or text data into the terminal via a microphone or keyboard. The server uses the emotion engine to identify emotional states such as stress and fatigue from this data. The output is information about the identified emotional states.

[0549] Step 4:

[0550] The server integrates classified business procedure data and user emotional data to select the optimal intelligent agent. Here, a generative AI model is used to select and customize the agent. The output is the configured intelligent agent settings. These settings facilitate the automation of business processes.

[0551] Step 5:

[0552] The server generates business improvement suggestions using a generation AI model. These suggestions include strategies for redistributing workload and measures to improve the work environment. The suggestions are notified to the user's terminal. The output is a specific improvement suggestion expressed in a notification format.

[0553] Step 6:

[0554] Users receive suggestions through their devices. Based on these suggestions, they take actions to optimize their work. For example, users decide to adjust their work schedules or reallocate resources. The ultimate result of this process is improved work processes and enhanced user emotional well-being.

[0555] (Application Example 2)

[0556] 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."

[0557] Conventional business process support systems prioritize operational efficiency without considering the emotional state of individual users, resulting in insufficient support to address user stress and fatigue. Consequently, there were limitations to improving operational efficiency and user satisfaction. Furthermore, even in the application of automated agents in home and daily life settings, the lack of nuanced responses based on emotion recognition made optimizing the user experience difficult.

[0558] 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.

[0559] In this invention, the server includes means for collecting corporate data, means for analyzing the collected data and classifying business procedures into multiple categories, means for selecting the most suitable automated agent for each category based on the classification results, means for monitoring the effectiveness of the incorporated automated agents, integrating an emotion recognition engine to recognize the emotional state of users and appropriately adjust responses, and means for using data from the emotion recognition engine to propose optimization of workload and improvement of the environment. This makes it possible to provide appropriate business support that takes into account the emotional state of each user and detailed services by home agents.

[0560] "Corporate data" refers to the collective information that an organization generates and collects in the course of its daily operations and activities.

[0561] "Business procedures" refer to the specific tasks and workflows involved in various activities and processes within a company.

[0562] An "automation agent" is a software program or device that autonomously performs tasks in a specific business process to improve efficiency.

[0563] An "emotion recognition engine" is a computer program or system that analyzes and identifies a user's emotional state from audio, text, or video.

[0564] "Data from the emotion recognition engine" refers to information about the user's emotional state that has been analyzed and extracted by the emotion recognition engine.

[0565] "Workload optimization" means taking into account user emotions and efficiency to optimize the resources and timing allocated to each task.

[0566] "Environmental improvement" refers to enhancing the work and living environment in which users engage in activities, thereby reducing stress and fatigue and enabling them to work efficiently and comfortably.

[0567] To implement this invention, the server collects business data from a company and runs a program that analyzes this data to classify business procedures into multiple categories. This analysis utilizes natural language processing and machine learning techniques. Libraries such as TensorFlow and spaCy are used to analyze the collected data, classify the data, and select the optimal automation agent. The server also integrates an emotion recognition engine to determine the user's emotional state using speech and text data. The Google Cloud Speech-to-Text API can be used for this purpose.

[0568] The terminal is equipped with a user interface for monitoring and feedback, through which users can receive support suggestions and suggestions for improving work processes. Specifically, if a user is experiencing stress at work, the server will recommend schedule changes or appropriate activities to reduce the workload, based on data from the emotion recognition engine.

[0569] As a concrete example, if a home robot is introduced, the robot will be equipped with an emotion recognition engine that detects the voices and facial expressions of individual users within the home and takes the most appropriate action based on their emotional state. For example, if it determines that the user is tired, it can play relaxing music and speak to them in a gentle voice.

[0570] By utilizing a generative AI model and providing example prompts like the following, it is possible to generate more specific actions:

[0571] "We're seeking advice on how to appropriately respond when we detect that a user is fatigued. Please suggest music and activities that can help them refresh."

[0572] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0573] Step 1:

[0574] The server collects corporate data. Specifically, it retrieves datasets related to each business process (e.g., employee work logs, customer interaction data, etc.) from the company's database. Based on this input data, it performs data processing and prepares it for analysis.

[0575] Step 2:

[0576] The server analyzes the collected dataset and classifies the business procedures into multiple categories. It uses natural language processing and machine learning models (using libraries such as TensorFlow and spaCy) to analyze the processes and patterns shown in the data. This process categorizes each process as "procedural," "labor-based," or "inappropriate for implementation," and identifies areas for optimization.

[0577] Step 3:

[0578] The server analyzes the user's voice and text data and uses an emotion recognition engine to identify the user's emotional state. It converts the voice data to text using the Google Cloud Speech-to-Text API and then analyzes it with spaCy to extract emotional patterns. This step yields the result of determining the user's emotional state (e.g., joy, fatigue, stress).

[0579] Step 4:

[0580] The server generates improvement suggestions to adjust work steps and the behavior of home robots based on emotional data obtained from the emotion recognition engine. Using a generative AI model, it generates prompt sentences and proposes specific actions to improve the user's emotional state. The generated output includes measures to reduce the workload and action plans tailored to the user's state.

[0581] Step 5:

[0582] The terminal receives improvement suggestions from the server and notifies the user through an interface. The user can then use this information to review and optimize their work processes and daily actions. The output in this step is a user-friendly presentation of the suggested results.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] [Fourth Embodiment]

[0587] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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".

[0600] This invention is a system for effectively selecting, deploying, and operating artificial intelligence agents to improve the operational efficiency of a company. A server accesses the company's systems to collect extensive data on business processes. This collected data includes work content, working hours, resource utilization, and process history, forming the foundation for a detailed understanding of business operations.

[0601] Next, the server classifies this data into several categories through advanced data analysis algorithms. Specifically, it classifies the data into categories such as "workflow type" based on the characteristics, frequency, and complexity of the tasks, "employee type" which is repetitive and suitable for automation, and "unsuitable for deployment" which is not suitable for the introduction of artificial intelligence agents.

[0602] Subsequently, the server selects the most suitable artificial intelligence agent based on the classification results. This involves using a performance database of existing agents to achieve the best possible match between business requirements and agent capabilities. The selected artificial intelligence agent is then proposed to the user terminal, and its details (predicted effectiveness, implementation costs, operation methods, etc.) are presented.

[0603] Once the user approves the server's proposal, the server automatically integrates the selected artificial intelligence agent into the necessary business processes. This integration includes installing and configuring the agent's software, as well as coordinating its interface with existing systems.

[0604] After implementation, the server continuously monitors the operational status of the artificial intelligence agent. This monitoring collects and analyzes data on operational efficiency, agent effectiveness, and employee feedback. Based on the analysis results, the server proposes specific adjustments and new strategies to improve the agent's effectiveness to user terminals, thereby supporting the continuous enhancement of the company's operational efficiency.

[0605] As a concrete example, consider a case where this system is implemented in the customer support department of a certain company. The server collects inquiry response data and classifies tasks related to FAQs as workflow-type tasks. Next, the server selects an artificial intelligence agent capable of automatic replies and sends suggestions to the user's terminal. By implementing the system's automatic reply function and receiving effective operation and improvement support through the server, the efficiency of customer support can be dramatically improved.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The server accesses the company's systems and collects processing data related to business operations. This data includes business content, processing time, and resource usage. The collected data is stored in a database for later analysis.

[0609] Step 2:

[0610] The server executes a pre-configured algorithm to analyze the collected data. Using natural language processing techniques, it analyzes business content in a documented form and converts business processes into an evaluable format.

[0611] Step 3:

[0612] Based on the data analyzed by the server, a model is applied to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This model classifies processes by analyzing their characteristics, frequency, and complexity.

[0613] Step 4:

[0614] The server consults a database of agents to select an artificial intelligence agent suitable for each category. The selection is made considering how well the agent's capabilities match the business requirements.

[0615] Step 5:

[0616] The terminal displays a proposal for an artificial intelligence agent selected by the server. This proposal includes the agent's functions, implementation costs, and projected effects. The user uses this information to decide whether to approve the implementation.

[0617] Step 6:

[0618] Once the user approves the proposed artificial intelligence agent, the server initiates the installation and configuration process to integrate the selected agent into the business process.

[0619] Step 7:

[0620] The server monitors the performance of the artificial intelligence agents it deploys. This monitoring collects data related to operational efficiency, reduced working hours, and operational accuracy.

[0621] Step 8:

[0622] The server analyzes performance based on monitoring results and, if necessary, sends agent configuration adjustments or additional suggestions to the user terminal. This ensures that the agent's effectiveness is maximized.

[0623] (Example 1)

[0624] 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".

[0625] Improving operational efficiency and implementing effective digital tools are essential for maintaining competitiveness in modern businesses. However, processes such as classifying business data, selecting the optimal advanced computing agents, and monitoring post-implementation effects are complex and burdensome for companies. Therefore, there is a need for comprehensive solutions to support business automation and efficiency.

[0626] 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.

[0627] In this invention, the server includes means for collecting activity data in a business domain, means for analyzing the collected activity data and classifying it into multiple categories based on business characteristics, and means for using the classification results to select the optimal advanced computing agent. This enables companies to automatically and efficiently deploy agents suited to their business processes and optimize their performance.

[0628] "Business domain" refers to the range of various business activities performed within a company, and includes different functions and processes such as production, sales, and human resources.

[0629] "Activity data" refers to all information related to business processes, specifically including working hours, resource usage, progress status, and deliverables.

[0630] "Analysis" refers to the process of examining collected data in detail to understand its patterns and characteristics, and in particular includes data classification and predictive analysis using machine learning.

[0631] A "category" refers to a group or class of data that has been separated through analysis, and it is a collection of similar data based on specific characteristics or conditions.

[0632] An "advanced computing agent" refers to a software program designed to automate and streamline specific business tasks using machine learning and artificial intelligence technologies.

[0633] "Implementation" refers to the act of applying or installing a newly selected advanced computing agent into existing business processes and integrating it into the environment to make it usable.

[0634] "Effect monitoring" refers to the process of continuously observing and recording the performance of already implemented advanced computing agents, and measuring and evaluating their efficiency and results.

[0635] "Efficiency improvement" refers to a series of adjustments and strategic changes made to improve the performance of business processes, particularly including resource optimization and reduction of work time.

[0636] This invention is a system that utilizes artificial intelligence technology to efficiently analyze and automate business processes in order to improve the operational efficiency of companies. This system operates through the collaborative efforts of a server, terminals, and users.

[0637] First, the server connects to the company's internal systems and collects a wide range of activity data within the business domain. This process utilizes database access and APIs to obtain important information such as work content, work time, resource utilization, and process history. This data forms the foundation for a detailed understanding of business workflows.

[0638] Next, the server analyzes the collected data. Here, advanced data analysis algorithms and machine learning models are used to classify the data into categories such as "procedural," "personnel-based," and "non-conforming." This classification helps identify which business processes are suitable for automation.

[0639] Based on the classified data, the server selects the optimal high-performance computing agent. This selection is made by referring to a performance database of existing agents and making the best possible match between business requirements and agent capabilities.

[0640] The selected agent is sent as a suggestion to the user's device, and detailed information about the agent is provided. This includes the agent's expected effectiveness, implementation costs, and operating procedures.

[0641] If the user approves the proposal, the server automatically integrates the agent into the business process. This involves software installation, configuration, and interface adjustments with existing systems.

[0642] As a result of the implementation, operational efficiency improves and the effectiveness of the agents is maximized. The operational status is continuously monitored by the server, and further efficiency improvements are suggested based on the data obtained.

[0643] As a concrete example, consider the case where this system is implemented in the customer support department of a certain company. The server collects inquiry data and classifies FAQ response tasks as "procedural." The server then selects an advanced computing agent capable of automatic replies, sends a proposal to the user's terminal, and if the user approves, it is implemented into the system, which is expected to improve the efficiency of inquiry handling.

[0644] An example of a prompt to input into the generating AI model is, "Based on customer support inquiry data, please suggest how to automate the business process using the most suitable AI agent."

[0645] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0646] Step 1:

[0647] The server accesses the company's systems to collect activity data within the business domain. Inputs include business content, work time, resource usage, and process history accessed via system databases and APIs. Specifically, the server executes scripts and queries to retrieve the necessary data, integrates it, and formats it into an output dataset. This output serves as the foundation for subsequent data analysis.

[0648] Step 2:

[0649] The server analyzes the collected data and classifies it into multiple categories based on business characteristics. The input is the dataset obtained in Step 1, and here data analysis algorithms are used to perform characteristic analysis and pattern recognition. Specifically, the server applies a machine learning model and divides the data into categories such as "procedural," "personnel-based," and "non-conforming" based on features. The output is classification information of business processes.

[0650] Step 3:

[0651] The server selects the most suitable advanced computing agent based on the classification results. The input is the classification information obtained from step 2. Here, the agent characteristics database is matched with the business characteristics, and a machine learning model is used to calculate a prediction score. Specifically, the server compares the characteristics of each agent with the business requirements and identifies the most suitable agent through scoring. The output is information on the selected agent and its recommendation level.

[0652] Step 4:

[0653] The selected advanced computing agent is sent to the user's terminal as a proposal. The input is the output data from step 3. The specific action here is for the server to refine the proposal and output it in a format that the user can review, such as a report or dashboard. The user receives this and reviews the content. The output is the user's approval or revision request for the proposal.

[0654] Step 5:

[0655] If the user approves the proposal, the server automatically integrates the selected agent into the business process. The input here is user approval, and the output is the deployment status of the modified business system. Specific actions include agent software installation, system configuration, interface adjustments with existing systems, and integration into the business application environment.

[0656] Step 6:

[0657] The server continuously monitors the operational status of the advanced computing agent after deployment. Here, the agent's performance data, obtained as output, is used as input for collecting daily operational data, evaluating operations, and identifying and proposing improvements. Specifically, the server analyzes real-time data, evaluates efficiency and impact, and considers improvement measures. The output includes suggestions for improving the agent's effectiveness and performance reports for the user.

[0658] (Application Example 1)

[0659] 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".

[0660] Optimizing operational efficiency in production facilities is a critical challenge for many companies. However, traditional systems often fail to adequately analyze business processes, leading to inappropriate choices in automation implementation. As a result, productivity improvements are hindered. Furthermore, there is a lack of mechanisms to propose rapid, real-time improvements, and there is a need for means to quickly resolve bottlenecks faced by on-site workers.

[0661] 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.

[0662] In this invention, the server includes means for collecting business data from an information processing device, means for analyzing the collected business data and classifying business processes into multiple types, means for selecting the most suitable automation algorithm for each type based on the classification results, and means for displaying algorithm optimization information on a display device in real time. This enables real-time analysis and automation optimization of business processes in production facilities, dramatically improving business productivity.

[0663] An "information processing device" is an electronic device such as a computer or sensor that enables the collection and communication of data in business operations.

[0664] "Business data" refers to information about business activities conducted both inside and outside the company, including working hours, resource utilization, and process history.

[0665] A "business process" refers to a series of tasks and procedures necessary to perform a specific task.

[0666] An "automation algorithm" is a set of computational steps designed to streamline a work process in a specific task.

[0667] An "information system" is a set of information technology infrastructures used to support business activities, and consists of hardware, software, networks, and other components.

[0668] "Performance" is an indicator that shows how effectively a system or algorithm functions for its intended purpose.

[0669] A "display device" is an electronic device such as a screen or projector that provides information to users visually.

[0670] "Optimization information" refers to instructions and suggestions provided to improve business processes and increase their efficiency.

[0671] The system for implementing this invention consists of an information processing device, a cloud server, and a smart display. The server collects business data from the information processing device and analyzes it to classify business processes into various types. Based on these classification results, the server selects the most suitable automation algorithm for each type and integrates it into the information system.

[0672] Furthermore, it features a function that presents on-site workers with optimization information in real time via a smart display. This allows workers to quickly resolve bottlenecks in their work processes and improve work efficiency.

[0673] The hardware includes sensors for data collection, cloud servers for processing (e.g., Amazon Web Services), and smart displays for displaying information (e.g., Google Glass). The software side utilizes machine learning algorithms for data analysis, automating the classification of business data and the selection of algorithms.

[0674] As a concrete example, in an assembly line for small parts at a production facility, workers wear smart displays and perform tasks based on instructions from a server. This optimizes specific processes and improves productivity. Another example of a prompt message is, "Identify bottlenecks on the factory floor and propose the optimal work procedure for efficiency."

[0675] The generative AI model generates optimization algorithms based on business data and immediately presents the results to the worker, thereby supporting efficient business operations.

[0676] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0677] Step 1:

[0678] The server collects operational data in real time from information processing equipment. Inputs include data from various sensors, such as work time, resource utilization, and process history. The server stores this data and organizes it for subsequent analysis steps.

[0679] Step 2:

[0680] The server begins data analysis using the collected business data. The input is the business data collected in the previous step. The data is analyzed using a generative AI model, and the business processes are classified into several types. At this time, machine learning algorithms are used to identify specific patterns and trends and perform classification, obtaining classification information as output.

[0681] Step 3:

[0682] The server selects the most suitable automation algorithm for each category based on the classification information. The input is the classification information from the previous step. The server refers to a database of existing algorithms and extracts the most suitable one. This selection takes into account the characteristics of each process and the required efficiency, and the selected algorithm is obtained as the output.

[0683] Step 4:

[0684] The server integrates the selected automation algorithm into the information system. The input is the algorithm selected in step 3. The server coordinates the connection between the existing information system and the algorithm and performs the necessary configurations. The output is the integrated information system.

[0685] Step 5:

[0686] Data is sent to a smart display to present information optimized for the user in real time. The input is optimized information generated by an already integrated algorithm. The terminal displays the data, making it immediately accessible to the worker. The output is the optimized information displayed on the screen.

[0687] Step 6:

[0688] The user performs tasks based on information displayed on a smart display and then feeds the results back to the server. The input consists of the user's feedback information and data on the tasks performed. The server collects this feedback information and uses it to further improve the algorithm, resulting in a system that undergoes repeated improvements as output.

[0689] 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.

[0690] This invention is a system that adds user emotion recognition capabilities to an artificial intelligence agent in order to further improve the operational efficiency of a company. The system begins with a server collecting business processing data from a company and precisely analyzing the business processes using natural language processing and machine learning. The analyzed data is used to classify tasks into three categories: "workflow type," "employee type," and "unsuitable for implementation," after which the most suitable artificial intelligence agent is selected.

[0691] In this process, the server integrates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice and text data to identify the user's emotional state. For example, if the emotion engine determines that the user is experiencing an emotional state such as fatigue or stress, the server automatically adjusts the behavior of the artificial intelligence agent to provide appropriate support to the user.

[0692] Furthermore, using emotional data from the emotion engine, the server generates suggestions for improving business processes. These suggestions are notified to the user's terminal, and the user can then use them to improve the efficiency of their work. The suggestions include specific strategies to improve the user's emotional state, such as redistributing workload or improving the work environment.

[0693] For example, consider an application in a customer support department. The server analyzes the support staff's interaction history and their emotional state at the time (e.g., frustration or fatigue). If the emotion engine detects signs of fatigue, the server suggests flexible adjustments to the work schedule based on that emotional data. This suggestion is notified to the administrator via the terminal, allowing the administrator to quickly take measures to reduce the burden on the staff.

[0694] In this way, by combining an emotion engine, this system can achieve both efficient operation of artificial intelligence agents and business improvement.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] The server accesses the company's systems and collects a wide range of business processing data. This data includes details about the tasks performed, working hours, and resources used.

[0698] Step 2:

[0699] The system analyzes the business processing data collected by the server and uses machine learning models to classify business processes into three categories: "workflow type," "employee type," and "inappropriate for implementation." This classification is based on business characteristics and data patterns.

[0700] Step 3:

[0701] The server selects the most suitable artificial intelligence agent for each classified business process. The selection is based on the matching of each agent's functions with the business requirements.

[0702] Step 4:

[0703] The server operates an emotion engine, analyzing user voice and text within business processes to identify their emotional state. The emotion engine analyzes the user's emotions in real time and classifies their emotional state into categories such as "positive," "negative," and "neutral."

[0704] Step 5:

[0705] The server adjusts the behavior of the artificial intelligence agent based on the results of the emotion engine. For example, if the user is in a negative emotional state, the server will add actions to the agent to encourage relaxation.

[0706] Step 6:

[0707] The terminal displays emotional data obtained from the emotion engine, along with suggestions for business improvements based on that data. These suggestions include workload distribution, improvements to the work environment, and the provision of further support.

[0708] Step 7:

[0709] Based on suggestions displayed on the user's device, the system adjusts business processes and agent settings to improve their emotional state and enhance work efficiency.

[0710] Step 8:

[0711] The server monitors the effects of improved processes and tuned agents. By continuously collecting data and providing new improvement suggestions to users' terminals as needed, it helps maintain an optimal work environment.

[0712] (Example 2)

[0713] 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".

[0714] In modern businesses, as operations become increasingly complex and diverse, there is a need for management that simultaneously considers employee emotions and the efficiency of work procedures. However, traditional systems have faced challenges in adequately analyzing work data and recognizing emotions, making it difficult to propose concrete improvements to operations. This has led to problems such as decreased labor productivity and increased employee stress.

[0715] 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.

[0716] In this invention, the server includes means for collecting information about the business entity, means for analyzing the collected information and classifying business procedures into multiple categories, and means for integrating an emotion engine for recognizing the emotions of users. This enables efficient management of business procedures and business improvement suggestions based on employee emotions.

[0717] A "business entity" refers to a legal entity such as an organization or company, which is a subject that conducts economic activities through specific business operations and activities.

[0718] "Information" refers to data and records related to the business operations of an entity, including data on work progress and employee performance.

[0719] "Business procedures" refer to the processes and procedures that show how business operations are carried out within an organization, representing the specific flow and sequence of work.

[0720] A "category" refers to a classification that groups items with similar characteristics or uses, and is grouped based on the characteristics of business procedures.

[0721] An "intelligent agent" refers to an intelligent program or system that analyzes data and makes predictions and decisions, and has the ability to automate specific tasks.

[0722] An "emotional engine" refers to software technology that analyzes a user's emotional state, and includes devices that recognize emotions using voice data and text data.

[0723] A "proposal" refers to guidelines or advice provided for the purpose of improving the operations and management of an organization, and is information that provides guidance for action.

[0724] "Monitoring" refers to the act of continuously observing the effectiveness of a particular process or agent, and is a process of identifying areas that need improvement or adjustment.

[0725] This invention provides an intelligent system for improving the operational efficiency of businesses. The server is responsible for collecting information about the business entity. Specifically, it uses a business management platform and a database management system to collect data on the progress of operations and employee performance. Based on this data, the server uses Python libraries such as NLTK and SpaCy to analyze the information through natural language processing and classify business procedures into categories such as "procedural," "employee-oriented," and "inappropriate for implementation."

[0726] Furthermore, the server recognizes the user's emotions by integrating an emotion engine. This emotion engine analyzes voice input and text data to identify the user's emotional state. For example, if it determines that the user is experiencing stress, the emotion engine immediately provides that data to the server.

[0727] The server integrates and analyzes identified emotional and operational data to select the most suitable intelligent agent. The intelligent agent uses a generative AI model to support the automation of tasks. After this selection, the server generates suggestions for improving operational efficiency and notifies the user terminal. These suggestions include redistributing workload and improving the work environment, allowing the user to optimize their tasks based on these suggestions.

[0728] As a concrete example, consider its application in a customer support department. The server analyzes the user's work interaction history and sentiment data, and proposes appropriate work adjustments. Users receive these suggestions through their terminals and can, for example, quickly make flexible adjustments to their work schedules.

[0729] Examples of prompts include, "Analyze current business process data and generate improvement suggestions based on emotional states," and "Based on support staff emotional data, suggest a redistribution of workload."

[0730] Thus, the present invention provides a concrete form for achieving efficient management of work procedures and business improvement based on user emotions.

[0731] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0732] Step 1:

[0733] The server collects information from the business entity. Specifically, it retrieves data from business management software and databases via APIs. This input data includes task progress, work time, and employee performance metrics. The server integrates this data and prepares it for analysis.

[0734] Step 2:

[0735] The server analyzes the collected information using natural language processing techniques. Using Python's NLTK and SpaCy, the server tokenizes the data and understands the textual context. This allows it to classify business procedures into "procedural," "employee-based," and "inappropriate for implementation." The output of this process is the classified business procedure data.

[0736] Step 3:

[0737] The server uses an emotion engine to acquire the user's emotional data. The user inputs voice or text data into the terminal via a microphone or keyboard. The server uses the emotion engine to identify emotional states such as stress and fatigue from this data. The output is information about the identified emotional states.

[0738] Step 4:

[0739] The server integrates classified business procedure data and user emotional data to select the optimal intelligent agent. Here, a generative AI model is used to select and customize the agent. The output is the configured intelligent agent settings. These settings facilitate the automation of business processes.

[0740] Step 5:

[0741] The server generates business improvement suggestions using a generation AI model. These suggestions include strategies for redistributing workload and measures to improve the work environment. The suggestions are notified to the user's terminal. The output is a specific improvement suggestion expressed in a notification format.

[0742] Step 6:

[0743] Users receive suggestions through their devices. Based on these suggestions, they take actions to optimize their work. For example, users decide to adjust their work schedules or reallocate resources. The ultimate result of this process is improved work processes and enhanced user emotional well-being.

[0744] (Application Example 2)

[0745] 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".

[0746] Conventional business process support systems prioritize operational efficiency without considering the emotional state of individual users, resulting in insufficient support to address user stress and fatigue. Consequently, there were limitations to improving operational efficiency and user satisfaction. Furthermore, even in the application of automated agents in home and daily life settings, the lack of nuanced responses based on emotion recognition made optimizing the user experience difficult.

[0747] 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.

[0748] In this invention, the server includes means for collecting corporate data, means for analyzing the collected data and classifying business procedures into multiple categories, means for selecting the most suitable automated agent for each category based on the classification results, means for monitoring the effectiveness of the incorporated automated agents, integrating an emotion recognition engine to recognize the emotional state of users and appropriately adjust responses, and means for using data from the emotion recognition engine to propose optimization of workload and improvement of the environment. This makes it possible to provide appropriate business support that takes into account the emotional state of each user and detailed services by home agents.

[0749] "Corporate data" refers to the collective information that an organization generates and collects in the course of its daily operations and activities.

[0750] "Business procedures" refer to the specific tasks and workflows involved in various activities and processes within a company.

[0751] An "automation agent" is a software program or device that autonomously performs tasks in a specific business process to improve efficiency.

[0752] An "emotion recognition engine" is a computer program or system that analyzes and identifies a user's emotional state from audio, text, or video.

[0753] "Data from the emotion recognition engine" refers to information about the user's emotional state that has been analyzed and extracted by the emotion recognition engine.

[0754] "Workload optimization" means taking into account user emotions and efficiency to optimize the resources and timing allocated to each task.

[0755] "Environmental improvement" refers to enhancing the work and living environment in which users engage in activities, thereby reducing stress and fatigue and enabling them to work efficiently and comfortably.

[0756] To implement this invention, the server collects business data from a company and runs a program that analyzes this data to classify business procedures into multiple categories. This analysis utilizes natural language processing and machine learning techniques. Libraries such as TensorFlow and spaCy are used to analyze the collected data, classify the data, and select the optimal automation agent. The server also integrates an emotion recognition engine to determine the user's emotional state using speech and text data. The Google Cloud Speech-to-Text API can be used for this purpose.

[0757] The terminal is equipped with a user interface for monitoring and feedback, through which users can receive support suggestions and suggestions for improving work processes. Specifically, if a user is experiencing stress at work, the server will recommend schedule changes or appropriate activities to reduce the workload, based on data from the emotion recognition engine.

[0758] As a concrete example, if a home robot is introduced, the robot will be equipped with an emotion recognition engine that detects the voices and facial expressions of individual users within the home and takes the most appropriate action based on their emotional state. For example, if it determines that the user is tired, it can play relaxing music and speak to them in a gentle voice.

[0759] By utilizing a generative AI model and providing example prompts like the following, it is possible to generate more specific actions:

[0760] "We're seeking advice on how to appropriately respond when we detect that a user is fatigued. Please suggest music and activities that can help them refresh."

[0761] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0762] Step 1:

[0763] The server collects corporate data. Specifically, it retrieves datasets related to each business process (e.g., employee work logs, customer interaction data, etc.) from the company's database. Based on this input data, it performs data processing and prepares it for analysis.

[0764] Step 2:

[0765] The server analyzes the collected dataset and classifies the business procedures into multiple categories. It uses natural language processing and machine learning models (using libraries such as TensorFlow and spaCy) to analyze the processes and patterns shown in the data. This process categorizes each process as "procedural," "labor-based," or "inappropriate for implementation," and identifies areas for optimization.

[0766] Step 3:

[0767] The server analyzes the user's voice and text data and uses an emotion recognition engine to identify the user's emotional state. It converts the voice data to text using the Google Cloud Speech-to-Text API and then analyzes it with spaCy to extract emotional patterns. This step yields the result of determining the user's emotional state (e.g., joy, fatigue, stress).

[0768] Step 4:

[0769] The server generates improvement suggestions to adjust work steps and the behavior of home robots based on emotional data obtained from the emotion recognition engine. Using a generative AI model, it generates prompt sentences and proposes specific actions to improve the user's emotional state. The generated output includes measures to reduce the workload and action plans tailored to the user's state.

[0770] Step 5:

[0771] The terminal receives improvement suggestions from the server and notifies the user through an interface. The user can then use this information to review and optimize their work processes and daily actions. The output in this step is a user-friendly presentation of the suggested results.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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."

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] The following is further disclosed regarding the embodiments described above.

[0794] (Claim 1)

[0795] Means of collecting business process data from companies,

[0796] A method for analyzing collected business processing data and classifying business processes into multiple categories,

[0797] A means for selecting the most suitable artificial intelligence agent for each category based on the classification results,

[0798] Methods for integrating selected artificial intelligence agents into business processes,

[0799] A means to monitor the effectiveness of the embedded artificial intelligence agent and suggest ways to improve its effectiveness,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, which classifies the analyzed business processes into workflow type, employee type, and inappropriate implementation.

[0803] (Claim 3)

[0804] The system according to claim 1, which uses a machine learning model to predict the effect in selecting an artificial intelligence agent.

[0805] "Example 1"

[0806] (Claim 1)

[0807] Means for collecting activity data in the business domain,

[0808] A means of analyzing collected activity data and classifying it into multiple categories based on business characteristics,

[0809] A means for selecting the optimal advanced computing agent using the classification results,

[0810] A means of introducing the selected advanced computing agent into the required business area,

[0811] A means of monitoring the functions of the implemented advanced computing agent and suggesting efficiency improvements,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, which classifies the analyzed business characteristics into "procedure-based," "personnel-based," and "non-conforming" types.

[0815] (Claim 3)

[0816] The system according to claim 1, which uses a learning model to predict effectiveness in the selection of an advanced computing agent.

[0817] "Application Example 1"

[0818] (Claim 1)

[0819] A means of collecting business data from an information processing device,

[0820] A method for analyzing collected business data and classifying business processes into multiple types,

[0821] A means for selecting the optimal automation algorithm for each type based on the classification results,

[0822] A means of integrating the selected automation algorithm into the information system,

[0823] A means to continuously monitor the performance of integrated automation algorithms and propose performance improvements,

[0824] A means for displaying algorithm optimization information in real time on a display device,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, which classifies the analyzed business processes into assembly line type, personnel-dependent type, and inapplicable type.

[0828] (Claim 3)

[0829] The system according to claim 1, which uses a learning algorithm to predict performance in the selection of an automated algorithm.

[0830] "Example 2 of combining an emotion engine"

[0831] (Claim 1)

[0832] Means of collecting information on business entities,

[0833] A method for analyzing collected information and classifying business procedures into multiple categories,

[0834] A means for selecting the most suitable intelligent agent for each category based on the classification results,

[0835] A means of integrating the selected intelligent agent into the work procedure,

[0836] A means of monitoring the effectiveness of an embedded intelligent agent and suggesting ways to improve its effectiveness,

[0837] A means of integrating an emotional engine for recognizing the user's emotions,

[0838] A means for generating business improvement proposals using emotional data obtained from an emotional engine and notifying users of these proposals at their terminals,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, which classifies the analyzed business procedures into procedural, employee-based, and inappropriately implemented categories.

[0842] (Claim 3)

[0843] The system according to claim 1, which uses a learning model to predict the effect in selecting an intelligent agent.

[0844] "Application example 2 when combining with an emotional engine"

[0845] (Claim 1)

[0846] Means of collecting corporate data,

[0847] A method for analyzing collected data and classifying business procedures into multiple categories,

[0848] A means of selecting the most suitable automation agent for each category based on the classification results,

[0849] Methods for integrating selected automation agents into business procedures,

[0850] A means of monitoring the effectiveness of the built-in automated agent and suggesting ways to improve its effectiveness,

[0851] A means for integrating an emotion recognition engine to recognize the emotional state of users and appropriately adjust responses,

[0852] A method for proposing optimization of workload and improvement of the environment using data from an emotion recognition engine,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, which classifies the analyzed business procedures into procedural, labor-intensive, and inappropriately implemented categories.

[0856] (Claim 3)

[0857] The system according to claim 1, which uses a machine learning model to support predictive analysis in the selection of an automated agent. [Explanation of Symbols]

[0858] 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 business data from an information processing device, A method for analyzing collected business data and classifying business processes into multiple types, A means for selecting the optimal automation algorithm for each type based on the classification results, A means of integrating the selected automation algorithm into the information system, A means to continuously monitor the performance of integrated automation algorithms and propose performance improvements, A means for displaying algorithm optimization information in real time on a display device, A system that includes this.

2. The system according to claim 1, which classifies the analyzed business processes into assembly line type, personnel-dependent type, and inapplicable type.

3. The system according to claim 1, which uses a learning algorithm to predict performance in the selection of an automation algorithm.

Images