system

Abstract

We provide the system. [Solution] A means of collecting data on problems that are difficult to solve, A means of analyzing collected data to identify common bottlenecks, A means of generating solutions for identified bottlenecks, A means of notifying relevant organizations of the generated solutions, 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, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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] Cases where many AI agents face difficult-to-realize problems encountered in performing operations are increasing. Many of these problems cannot be processed by existing systems or solutions, which may cause a decrease in business efficiency and a delay in service provision. Furthermore, since each AI agent tries to solve problems independently, it is inevitable that the same problems will occur repeatedly. There is a need to efficiently solve such overlapping problems and improve the performance of agents and the convenience of the whole society.

Means for Solving the Problems

[0005] This invention provides a system that collects data on difficult-to-solve problems faced by AI agents, analyzes this data to identify common bottlenecks, and utilizes natural language processing technology in the analysis to efficiently extract bottlenecks from the collected data. It also includes a means for generating solutions to the identified bottlenecks and notifying relevant organizations. Information is provided in various formats during notification, making it possible to propose approaches in a way that is easy for recipients to understand. This entire process enables rapid and effective resolution of problems hindering the performance of AI agents.

[0006] "Difficult-to-solve problems" refer to situations or challenges that AI agents face that are difficult to resolve automatically and that are difficult to address with existing methods and resources.

[0007] "Means of data collection" refers to methods, devices, or systems for collecting information related to problems reported by AI agents.

[0008] "Methods for analyzing and identifying common bottlenecks" refers to methods and algorithms for analyzing collected data and identifying the causes and obstacles of recurring problems.

[0009] "Means of generating solutions" refers to the means and processes for designing and proposing appropriate solutions to identified bottlenecks.

[0010] "Means of notifying relevant organizations" refers to methods or devices for communicating the generated solutions or proposals to relevant corporations or institutions.

[0011] "Diverse formats" refers to multiple forms of expression used to effectively convey information, such as text, images, videos, and audio. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The system of the present invention provides problem-solving support by efficiently collecting and analyzing difficult-to-solve problems encountered by AI agents in the course of performing their tasks, generating solutions, and notifying relevant organizations. This process is carried out as follows.

[0034] Data collection

[0035] The device stores data on difficult problems collected from the AI ​​agent. This includes problem details, circumstances under which it occurred, and the agent's trial history.

[0036] Data Analysis

[0037] The server analyzes data collected from terminals and uses natural language processing to identify common bottlenecks. This allows it to statistically summarize recurring problems from the analyzed data and reveal their root causes.

[0038] Solution generation

[0039] The server generates solutions for the identified bottlenecks. At this stage, it refers to a database of existing solutions and success stories, and builds new proposals learned from past examples.

[0040] Notifications and suggestions

[0041] The server notifies relevant organizations of the generated solutions and provides information in various formats. This makes the information easier for users to understand and implement. For example, if an AI agent fails to find a flight on the same day multiple times in an area with limited flight options, it will propose a new route to the airline as a solution.

[0042] This system enables AI agents to quickly resolve problems they face, improving operational efficiency and convenience. This allows for a more integrated and comprehensive problem-solving approach than traditional, individual problem-solving methods.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The device collects logs detailing the difficult problems the AI ​​agent encountered. This collection includes the date and time, the nature of the error, user input, and the AI ​​agent's response history.

[0046] Step 2:

[0047] The server collects log data from each terminal at regular intervals. The data is transferred via a secure connection and stored in a central database.

[0048] Step 3:

[0049] The server preprocesses the collected data, removes duplicates, detects outliers, and performs data cleansing. This process prepares the data for improved analysis accuracy.

[0050] Step 4:

[0051] The server applies natural language processing (NLP) to the cleansed data to identify common bottlenecks and problem trends. Topic modeling and clustering techniques are used to systematically classify the data.

[0052] Step 5:

[0053] The server generates solutions based on identified bottlenecks, leveraging historical databases and generative AI. This includes constructing proposals that may include new improvements and unapproved methodologies.

[0054] Step 6:

[0055] The server performs predictive analysis on the effectiveness and risks of solutions and evaluates the proposals. Based on this evaluation, it determines the priority of recommended solutions.

[0056] Step 7:

[0057] The server notifies relevant companies and government agencies of the generated solutions. The notifications are presented in various formats, including text reports, graphs, and infographics, to facilitate understanding.

[0058] Step 8:

[0059] Users will use the provided information to make necessary adjustments and modifications and apply them to their actual work. This process effectively eliminates problems that hinder the AI ​​agent's performance.

[0060] (Example 1)

[0061] 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."

[0062] There is a need to quickly and efficiently resolve complex problems that arise when using business support devices. However, conventional systems have difficulty responding immediately to individual problems, resulting in waste and a decrease in overall business efficiency.

[0063] 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.

[0064] In this invention, the server includes means for collecting information on difficult-to-solve problems that arise in business support devices, means for analyzing the collected information to identify common issues, and means for generating solutions to the identified issues. This enables rapid identification of problems and the provision of effective solutions.

[0065] A "business support device" is a device designed to efficiently assist with various business tasks, possessing functions for problem identification, information gathering, analysis, and solution presentation.

[0066] "Difficult-to-solve problems" refer to challenges or obstacles that are difficult to resolve when a business support system processes data, and which hinder efficient business operations.

[0067] "Means of collecting information" refers to the process by which business support devices systematically collect data related to a problem, record its detailed content and circumstances, and use it for subsequent analysis.

[0068] "Means of analyzing information" refers to using techniques and methods to analyze the causes of problems based on collected data and identify commonalities.

[0069] "Methods for identifying problems" refer to the process of identifying common issues and bottlenecks detected through information analysis, and then narrowing them down to those that need to be addressed.

[0070] "Means of generating solutions" refers to the process of building effective countermeasures for identified problems, and is a method of generating new proposals by utilizing past cases and machine learning models.

[0071] "Means of notifying organizations" refers to methods for communicating the generated solutions to relevant organizations in an appropriate format and prompting them to take action.

[0072] Modes for carrying out the invention

[0073] This invention is a system for quickly and efficiently resolving difficult problems that arise during the execution of business operations, using a business support device. This system resolves problems through the processes of data collection, analysis, solution generation, and notification.

[0074] Hardware and software configuration:

[0075] The terminal functions as a business support device, collecting business-related information in real time. This information is stored in the form of AI agent activity logs and error reports. Log management software and a database management system are used for this purpose.

[0076] The server receives information sent from the terminal and analyzes it. Natural language processing techniques are used for the analysis, specifically Python and its NLP libraries (e.g., NLTK, spaCy). The server identifies common issues from the collected information.

[0077] The server also generates solutions using a generative AI model. This model has learned from past successes and, for example, uses natural language generation software to construct new proposals.

[0078] Users can receive solutions notified by the server and apply them in their work. Notifications are sent via email or online dashboards, and the information is provided in HTML or PDF format.

[0079] Specific examples and prompt statements:

[0080] As a concrete example, when an AI agent providing flight booking assistance encounters the recurring problem of unbookable flights in a specific region, the server analyzes the issue and generates a solution that proposes new flight routes to the airline.

[0081] An example of a prompt message would be, "What specific problem does the AI ​​agent encounter? Refer to past data and suggest a new solution." This message would be input to the generating AI model, and the model would then propose a solution based on this information.

[0082] A system configured in this way aims to improve operational efficiency and enable rapid problem-solving.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The terminal takes data on problems the AI ​​agent faces as input. Specifically, it collects log data and error reports during task execution, organizes them in a database, and stores them there. This data includes the date and time the problem occurred, the history of trial and error, and the specific details of the problem.

[0086] Step 2:

[0087] The terminal organizes the collected data and sends it to the server via a secure communication protocol (e.g., HTTPS). The input is structured JSON or XML data. The terminal formats the data before sending it to make it easier for the server to parse.

[0088] Step 3:

[0089] The server receives data sent from the terminal. Using the acquired data as input, the server analyzes the data using natural language processing techniques (e.g., Python's NLP library). To identify common issues, it performs text pattern recognition and statistical analysis, and outputs an overview of the issues.

[0090] Step 4:

[0091] The server generates solutions using a generative AI model based on the analysis results. It references information about the identified problem and relevant past success stories as input. The AI ​​model processes this data, proposes new solutions, and generates new ideas and suggestions that the model outputs.

[0092] Step 5:

[0093] The server notifies the relevant organizations of the generated solutions. As output, the generated solutions are converted into HTML or PDF format, providing them in an easily understandable format for users. Users apply the received solutions to their work and improve efficiency. Notifications are made via email and an online dashboard.

[0094] (Application Example 1)

[0095] 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."

[0096] Autonomous vehicles face various problems during operation, but conventional systems have struggled to resolve these issues quickly and efficiently. To address this challenge, it is necessary to automate the entire process, from problem identification to solution generation and notification, thereby improving operational efficiency and convenience.

[0097] 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.

[0098] In this invention, the server includes means for collecting information on difficult-to-solve problems, means for analyzing the collected information to identify common failure factors, and means for collecting data from automated vehicles in real time and transmitting it to a cloud system. This enables the rapid identification of problems and the proposal of solutions, thereby improving the operational efficiency of automated vehicles.

[0099] "Difficult-to-solve problems" refer to challenges or obstacles that occur during the operation of autonomous vehicles by AI agents and that are difficult to solve using conventional methods.

[0100] "Means of collecting information" refers to the process or device for acquiring and recording data and problem-related information generated from autonomous vehicles.

[0101] "Common obstacles" refer to the results of analyzing and identifying common problems and constraints that frequently occur from the collected information.

[0102] "Means of generating solutions" refers to a process that uses AI models and algorithms to automatically propose countermeasures and improvements for identified problem factors.

[0103] "Means of notification" refers to mechanisms and systems for efficiently communicating generated solutions to relevant organizations and personnel.

[0104] A "cloud system" refers to distributed computing resources consisting of servers, data storage, and other components that are connected remotely via the internet.

[0105] The system that realizes this invention is designed to efficiently solve difficult problems that arise during the operation of autonomous vehicles. This system consistently performs tasks from data collection and problem analysis to solution generation and notification.

[0106] Specifically, the autonomous vehicle's sensor system first collects operational data in real time and transmits it to a cloud system. The cloud system then analyzes the collected data using natural language processing (NLP) technology to identify common failure factors. During this process, an AI model, such as the OpenAI® API, is used to recognize patterns in the data and statistically extract recurring problems.

[0107] Next, the server generates solutions based on the identified fault factors. This solution generation involves an AI model that refers to past database data while also proposing new solutions. These proposals may include route changes or adjustments to control algorithms for autonomous vehicles.

[0108] The generated solutions are notified from the server to the relevant organizations and personnel. The notification format varies, including via smartphone and desktop applications. Administrators can review the solutions within the application and, if necessary, issue instructions for implementation.

[0109] As a concrete example, consider a scenario where control errors occur repeatedly at a specific intersection. In this case, the server analyzes past data related to that intersection and generates a prompt message that suggests an appropriate detour route. Based on a prompt message such as, "The autonomous vehicle is frequently making control errors at intersection A. Identify the cause and propose a solution," the AI ​​model presents a detailed solution. In this way, this system can significantly improve the operational efficiency of autonomous vehicles.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The terminal (autonomous vehicle) collects data from its sensor system during operation. This data includes location information, vehicle speed, and environmental information (weather, obstacle detection status, etc.). This data is transmitted to a cloud system. The input is real-time data sent from the sensors, and the output is raw data stored on the cloud system.

[0113] Step 2:

[0114] The server analyzes the received raw data using natural language processing techniques. To identify common failure factors, it cleans the data and analyzes patterns using statistical methods and AI models. The input is a set of raw data, and the output is a list of identified failure factors.

[0115] Step 3:

[0116] The server generates solutions based on identified failure factors, referencing a database of past success stories and current data. Here, a generative AI model is used to create specific countermeasures for particular failure conditions. The input is a list of identified failure factors, and the output is a list of proposed solutions.

[0117] Step 4:

[0118] The server notifies the relevant organizations and individuals of the generated solutions. The solutions are converted into an appropriate format and sent, for example, via a smartphone app or PC terminal. The input is a list of solutions, and the output is the notified proposal.

[0119] Step 5:

[0120] The user receives the notified solution and checks its contents on their smartphone or PC. If necessary, they provide instructions to the system to implement the proposed solution. This resolves the problem and optimizes operations. The input is the notified solution, and the output is user feedback or instructions for implementation.

[0121] 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.

[0122] This invention is a system that collects and analyzes problem data, generates solutions, and notifies relevant organizations in order to efficiently solve difficult problems that AI agents encounter while performing their tasks. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, making it possible to further personalize and optimize the presentation of solutions.

[0123] Data collection and analysis

[0124] The device collects detailed data on difficult-to-solve problems reported by the AI ​​agent. This includes the circumstances under which the problem occurred, error information, user operation history, and input information.

[0125] The server preprocesses the collected data and analyzes it using natural language processing techniques to identify common bottlenecks.

[0126] Emotion recognition and solution generation

[0127] The emotion engine estimates emotions from user behavior and input, and determines the user's psychological state and the most acceptable way to present information in problem-solving situations.

[0128] The server generates solutions based on identified bottlenecks and the user's emotional state. By reflecting the results of the emotion engine, it customizes the information to present solutions in the most effective way for the user.

[0129] Notifications and optimal presentations

[0130] When the server notifies relevant companies and government agencies of the generated solutions, it provides information in a format and media that suits the user's emotional state. This flexible approach enhances the acceptability and actionability of the information.

[0131] Based on the information provided by this system, users can take appropriate actions to improve their work and solve problems.

[0132] As a concrete example, suppose a problem is reported in a business system where certain operations are unclear, leading to frequent user errors. In this case, the server analyzes the commonalities of the problem, and the emotion engine identifies the user's frustration level. The server can then generate a solution tailored to alleviate user frustration and provide it in the form of an easy-to-understand, guided instructional video. This integrated approach streamlines the user's problem-solving process and enables smoother business operations.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The device collects data in real time on problems that occur while the AI ​​agent is running. This process includes user operation logs, error messages, and contextual information.

[0136] Step 2:

[0137] The device uses an emotion engine to process data in order to estimate the user's emotional state from their input and interaction patterns. The emotion engine uses natural language processing and machine learning models to evaluate the stress and frustration that the user may be experiencing.

[0138] Step 3:

[0139] The server receives emotional state data along with problem data sent from each terminal and integrates this into a central database. After collection, the data is filtered to select important information.

[0140] Step 4:

[0141] The server analyzes the collected data to identify common bottlenecks. This analysis utilizes natural language processing techniques to recognize problem patterns and perform clustering.

[0142] Step 5:

[0143] The server generates appropriate solutions based on identified bottlenecks and the user's emotional state. Here, to minimize the user's burden, we design solutions in an acceptable format that takes into account the results of the emotion engine.

[0144] Step 6:

[0145] The server notifies the relevant organizations of the generated solutions. In this process, the solutions are presented in various formats (e.g., video guides, infographics, text summaries) to ensure that the recipients of the information can easily understand them.

[0146] Step 7:

[0147] Based on the solutions provided by the server, users can quickly address problems and take action to improve their operations. As a result, the user's problem-solving process proceeds smoothly.

[0148] (Example 2)

[0149] 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".

[0150] In today's work environment, users often face complex and difficult-to-solve problems, making it challenging to quickly find appropriate solutions. In particular, these problems require solutions that take into account the emotions and stress levels of individual users, and traditional, uniform methods are often ineffective.

[0151] 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.

[0152] In this invention, the server includes means for collecting problem information from data terminals, means for analyzing pre-processed information, and means for generating solutions based on the user's emotional state. This makes it possible to provide solutions that are tailored to the individual circumstances of each user.

[0153] A "data terminal" is a device or apparatus used to collect information from users regarding problems that are difficult to solve.

[0154] "Preprocessing" refers to the process of removing missing or inconsistent data from collected raw data and preparing it for analysis.

[0155] "Analysis techniques" refer to methods and techniques for analyzing collected and pre-processed data to derive useful information and patterns.

[0156] "Obstacles" refer to common bottlenecks or problems encountered during the performance of tasks.

[0157] "Emotion analysis" is a technology that estimates a user's psychological state and emotions from their actions and behavior.

[0158] A "generative model" is an algorithm or model used to generate appropriate solutions based on data or input.

[0159] "Relevant organizations" refers to companies, organizations, or related institutions that are subject to notification and sharing of the generated solutions.

[0160] "Language processing technology" refers to the techniques and methods used to process natural language and analyze its meaning.

[0161] This invention is a comprehensive system for solving difficult-to-resolve challenges encountered during the performance of work.

[0162] Data collection and analysis

[0163] The terminal collects information about problems that occur during the user's work. This information includes operation history, error details, and input data. The collected data is cleansed to impute missing values ​​and correct inconsistencies.

[0164] The server performs analysis using the cleansed data. This analysis employs natural language processing techniques and utilizes software libraries such as Python's spaCy and NLTK. The data analysis makes it possible to identify common failures that cause problems.

[0165] Emotion recognition and solution generation

[0166] The emotion engine analyzes user emotions based on their operation history and input speed to estimate their level of stress and dissatisfaction.

[0167] The server generates solutions using a generative AI model based on the analysis results and sentiment data. The generative AI model is utilized in the solution generation process to provide users with customized and easily understandable information. It is anticipated that TENSORFLOW® and PyTorch will be used in this process.

[0168] Notifications and Information

[0169] The server notifies the relevant organizations and individuals of the identified solutions. The information is provided in a format tailored to the user's emotional state, such as a PDF report or explanatory video. This makes it easy for users to understand and implement the solutions.

[0170] Specific example

[0171] For example, if a user frequently makes input errors in a particular business system, the server can identify the problem, and the emotion engine can determine the user's level of anxiety. Then, it can generate a personalized solution in the form of an explanatory video and send it to the user via email. This kind of flexible solution provision improves operational efficiency.

[0172] Example of a prompt

[0173] "After the new system is implemented, analyze the reasons for user confusion and suggest what kind of information would help them understand it."

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

[0175] Step 1:

[0176] The terminal collects information about issues reported by users in the business system. Specifically, it collects user operation history, input error logs, and error messages. This input information is temporarily stored on the terminal and sent to the server. The collected log data is then generated as output.

[0177] Step 2:

[0178] The server receives log data sent from the terminal and preprocesses it. The input data includes raw data such as operation history and error logs. Specific data processing involves imputing missing data and filtering irrelevant data to generate a clean dataset. The output is data in a state ready for analysis.

[0179] Step 3:

[0180] The server analyzes the pre-processed data. The input data includes clean operation history and error logs. Natural language processing techniques are used to perform data calculations on this data to identify frequent problem patterns and common failures. Specifically, text data is tokenized, and highly relevant keywords are extracted. A list of identified problems is generated as output.

[0181] Step 4:

[0182] The emotion engine performs sentiment analysis based on user behavior logs and analyzed data. Input data includes the user's action speed and frequency. Specifically, it analyzes this data to quantify stress and dissatisfaction levels. The output is an analysis result indicating the user's emotional state.

[0183] Step 5:

[0184] The server generates solutions using a generative AI model based on the results of problem analysis and sentiment analysis. Input includes data on identified problems and the user's emotional state. Specifically, prompts are sent to generative AI models such as GPT-3 (registered trademark) to request solutions. The output is a customized solution proposal.

[0185] Step 6:

[0186] The server notifies relevant organizations and users of the generated solutions. Based on the input solutions, it converts them into a format that suits the user's emotional state, such as an operation guide or video manual. The output is information provided in an easy-to-understand format.

[0187] Step 7:

[0188] Users implement business improvement measures based on the solutions they receive. Specifically, they can improve work efficiency by trying out the countermeasures when problems arise, while referring to the provided guides. This promotes the continuous development of the latest and most optimal business improvements.

[0189] (Application Example 2)

[0190] 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".

[0191] In modern online retail systems, support for user problems is uniform and does not address the individual emotional state of each user. As a result, users often become dissatisfied, hindering the quick and effective resolution of problems. Addressing this challenge is crucial.

[0192] 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.

[0193] In this invention, the server includes means for collecting information on challenges that users find difficult to overcome, means for analyzing the collected information and identifying common obstacles, and means for recognizing the user's emotional state and adjusting the solution means accordingly. This enables personalized responses that are tailored to the user's emotional state.

[0194] "Difficult-to-solve challenges" refer to problems that users deem difficult to solve using conventional means or existing knowledge.

[0195] "Means of collecting information" refers to devices or software that have the function of collecting data on user operations, inputs, and errors.

[0196] "Means of analyzing information and identifying common problems" refers to analytical processes and techniques used to find patterns of related problems and issues based on collected information.

[0197] "Means for generating solutions" refers to a mechanism for designing and proposing effective countermeasures or improvement measures for identified problems.

[0198] "Means of informing relevant organizations" refers to methods or systems for notifying the appropriate organizations or departments of the generated solutions and for sharing information.

[0199] "Means of recognizing a user's emotional state" refers to technologies that infer and evaluate a user's emotions from their behavior and input data.

[0200] "Providing communication methods" refers to the act of selecting and presenting the most appropriate form and method of information transmission according to the user's emotional state and needs.

[0201] To implement this application, the server first collects information from the terminal about the difficult challenges the user encounters. This information includes the user's operation history and input error information. The collected information is then analyzed by the server using natural language processing technology to identify common problems.

[0202] Next, the server generates solutions to the identified problems. Since the user's emotional state is a crucial factor in this process, an emotion engine is used to estimate the user's emotions from their behavior and optimize the solutions accordingly. For example, if the user is feeling anxious, the solutions are adjusted to be more intuitive and easier to understand.

[0203] The generated solutions are not only communicated to the relevant organizations, but are also directly provided to users through a variety of information dissemination methods. For example, communication methods that match the user's emotional state are selected, such as video guides or user-friendly, conversational guidance.

[0204] Software used to perform emotion recognition and natural language processing includes EmotionEngine and NLPProcessor. These are important tools for effectively analyzing collected data and accurately assessing the user's emotional state.

[0205] As a concrete example, consider a scenario where an error occurs during the user's purchase process on an e-commerce site. When frustration is detected from the user's input, the server suggests a user-friendly video guide to reassure the user and support the resolution of the problem. An example of a prompt for the generative AI model is, "How should we alleviate user frustration with e-commerce site error messages?"

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The terminal collects information about the user's operation history and input errors. This input information is sent to the server and stored in a database. The collected information includes product selection, errors during the purchase flow, and screen transition history.

[0209] Step 2:

[0210] The server receives the collected information and performs analysis using natural language processing (NLP) techniques. Specifically, it uses an NLP Processor to extract common failures and problem patterns from the data. The input is the user data collected in step 1, and the output is the common failure points identified through the analysis.

[0211] Step 3:

[0212] The server generates solutions to the identified problems based on the analysis results. In this process, it uses EmotionEngine to infer the user's emotional state. The input is the output from step 2 plus data about the user's emotions, and the output is a personalized solution. This could include, for example, video guides or FAQ suggestions.

[0213] Step 4:

[0214] The server notifies relevant organizations and users of the generated solutions. As a specific communication method, it provides user-friendly messages and guides tailored to the user's emotions. The input is the solution generated in step 3, and the output is information as a notification to the user or stakeholders.

[0215] Step 5:

[0216] The user receives information from the server and solves the problem by following the instructions. It is expected that the information provided will be helpful and reduce the user's anxiety and frustration. User feedback will be reflected in subsequent data analysis. The input is the notification from the server, and the output is the user's problem-solving actions.

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

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

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

[0220] [Second Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0233] The system of the present invention provides problem-solving support by efficiently collecting and analyzing difficult-to-solve problems encountered by AI agents in the course of performing their tasks, generating solutions, and notifying relevant organizations. This process is carried out as follows.

[0234] Data collection

[0235] The device stores data on difficult problems collected from the AI ​​agent. This includes problem details, circumstances under which it occurred, and the agent's trial history.

[0236] Data Analysis

[0237] The server analyzes data collected from terminals and uses natural language processing to identify common bottlenecks. This allows it to statistically summarize recurring problems from the analyzed data and reveal their root causes.

[0238] Solution generation

[0239] The server generates solutions for the identified bottlenecks. At this stage, it refers to a database of existing solutions and success stories, and builds new proposals learned from past examples.

[0240] Notifications and suggestions

[0241] The server notifies relevant organizations of the generated solutions and provides information in various formats. This makes the information easier for users to understand and implement. For example, if an AI agent fails to find a flight on the same day multiple times in an area with limited flight options, it will propose a new route to the airline as a solution.

[0242] This system enables AI agents to quickly resolve problems they face, improving operational efficiency and convenience. This allows for a more integrated and comprehensive problem-solving approach than traditional, individual problem-solving methods.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The device collects logs detailing the difficult problems the AI ​​agent encountered. This collection includes the date and time, the nature of the error, user input, and the AI ​​agent's response history.

[0246] Step 2:

[0247] The server collects log data from each terminal at regular intervals. The data is transferred via a secure connection and stored in a central database.

[0248] Step 3:

[0249] The server preprocesses the collected data, removes duplicates, detects outliers, and performs data cleansing. This process prepares the data for improved analysis accuracy.

[0250] Step 4:

[0251] The server applies natural language processing (NLP) to the cleansed data to identify common bottlenecks and problem trends. Topic modeling and clustering techniques are used to systematically classify the data.

[0252] Step 5:

[0253] The server generates solutions based on identified bottlenecks, leveraging historical databases and generative AI. This includes constructing proposals that may include new improvements and unapproved methodologies.

[0254] Step 6:

[0255] The server performs predictive analysis on the effectiveness and risks of solutions and evaluates the proposals. Based on this evaluation, it determines the priority of recommended solutions.

[0256] Step 7:

[0257] The server notifies relevant companies and government agencies of the generated solutions. The notifications are presented in various formats, including text reports, graphs, and infographics, to facilitate understanding.

[0258] Step 8:

[0259] Users will use the provided information to make necessary adjustments and modifications and apply them to their actual work. This process effectively eliminates problems that hinder the AI ​​agent's performance.

[0260] (Example 1)

[0261] 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."

[0262] There is a need to quickly and efficiently resolve complex problems that arise when using business support devices. However, conventional systems have difficulty responding immediately to individual problems, resulting in waste and a decrease in overall business efficiency.

[0263] 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.

[0264] In this invention, the server includes means for collecting information on difficult-to-solve problems that arise in business support devices, means for analyzing the collected information to identify common issues, and means for generating solutions to the identified issues. This enables rapid identification of problems and the provision of effective solutions.

[0265] A "business support device" is a device designed to efficiently assist with various business tasks, possessing functions for problem identification, information gathering, analysis, and solution presentation.

[0266] "Difficult-to-solve problems" refer to challenges or obstacles that are difficult to resolve when a business support system processes data, and which hinder efficient business operations.

[0267] "Means of collecting information" refers to the process by which business support devices systematically collect data related to a problem, record its detailed content and circumstances, and use it for subsequent analysis.

[0268] "Means of analyzing information" refers to using techniques and methods to analyze the causes of problems based on collected data and identify commonalities.

[0269] "Methods for identifying problems" refer to the process of identifying common issues and bottlenecks detected through information analysis, and then narrowing them down to those that need to be addressed.

[0270] "Means of generating solutions" refers to the process of building effective countermeasures for identified problems, and is a method of generating new proposals by utilizing past cases and machine learning models.

[0271] "Means of notifying organizations" refers to methods for communicating the generated solutions to relevant organizations in an appropriate format and prompting them to take action.

[0272] Modes for carrying out the invention

[0273] This invention is a system for quickly and efficiently resolving difficult problems that arise during the execution of business operations, using a business support device. This system resolves problems through the processes of data collection, analysis, solution generation, and notification.

[0274] Hardware and software configuration:

[0275] The terminal functions as a business support device, collecting business-related information in real time. This information is stored in the form of AI agent activity logs and error reports. Log management software and a database management system are used for this purpose.

[0276] The server receives information sent from the terminal and analyzes it. Natural language processing techniques are used for the analysis, specifically Python and its NLP libraries (e.g., NLTK, spaCy). The server identifies common issues from the collected information.

[0277] The server also uses a generative AI model to generate solutions. This model has learned from past success cases and, for example, utilizes natural language generation software to construct new proposals.

[0278] The user can receive the solutions notified by the server and apply them in the business. The notifications are made in forms such as emails or online dashboards, and the information is provided in HTML or PDF format.

[0279] Specific examples and prompt sentences:

[0280] As a specific example, when an AI agent for flight reservation assistance faces the problem of flight unavailability that repeatedly occurs in a specific region, the server analyzes the issue and generates a solution to propose setting up new flight routes to the airline.

[0281] As an example of a prompt sentence, it is input into the generative AI model in the form of "What is the specific problem encountered by the AI agent? Please refer to past data and present a new solution." Based on this information, the model proposes a solution.

[0282] The system configured in this way aims to improve business efficiency and enable rapid problem-solving.

[0283] The flow of specific processing in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The terminal acquires, as input, data on the problems faced by the AI agent. Specifically, it collects log data and error reports during business operations, organizes them in a database, and stores them. This data includes the date and time of the problem occurrence, the history of trial and error, and the specific content of the problem.

[0286] Step 2:

[0287] The terminal organizes the collected data and sends it to the server via a secure communication protocol (e.g., HTTPS). The input is structured JSON or XML data. The terminal formats the data before sending it to make it easier for the server to parse.

[0288] Step 3:

[0289] The server receives data sent from the terminal. Using the acquired data as input, the server analyzes the data using natural language processing techniques (e.g., Python's NLP library). To identify common issues, it performs text pattern recognition and statistical analysis, and outputs an overview of the issues.

[0290] Step 4:

[0291] The server generates solutions using a generative AI model based on the analysis results. It references information about the identified problem and relevant past success stories as input. The AI ​​model processes this data, proposes new solutions, and generates new ideas and suggestions that the model outputs.

[0292] Step 5:

[0293] The server notifies the relevant organizations of the generated solutions. As output, the generated solutions are converted into HTML or PDF format, providing them in an easily understandable format for users. Users apply the received solutions to their work and improve efficiency. Notifications are made via email and an online dashboard.

[0294] (Application Example 1)

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

[0296] Autonomous vehicles face various problems during operation, but conventional systems have struggled to resolve these issues quickly and efficiently. To address this challenge, it is necessary to automate the entire process, from problem identification to solution generation and notification, thereby improving operational efficiency and convenience.

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

[0298] In this invention, the server includes means for collecting information on difficult-to-solve problems, means for analyzing the collected information to identify common failure factors, and means for collecting data from automated vehicles in real time and transmitting it to a cloud system. This enables the rapid identification of problems and the proposal of solutions, thereby improving the operational efficiency of automated vehicles.

[0299] "Difficult-to-solve problems" refer to challenges or obstacles that occur during the operation of autonomous vehicles by AI agents and that are difficult to solve using conventional methods.

[0300] "Means of collecting information" refers to the process or device for acquiring and recording data and problem-related information generated from autonomous vehicles.

[0301] "Common obstacles" refer to the results of analyzing and identifying common problems and constraints that frequently occur from the collected information.

[0302] "Means of generating solutions" refers to a process that uses AI models and algorithms to automatically propose countermeasures and improvements for identified problem factors.

[0303] "Means of notification" refers to mechanisms and systems for efficiently communicating generated solutions to relevant organizations and personnel.

[0304] The "cloud system" refers to distributed computing resources composed of servers, data storage, etc. that are remotely connected via the Internet.

[0305] The system for realizing the present invention is designed to efficiently solve difficult-to-realize problems that occur during the operation of autonomous vehicles. This system consistently implements from data collection to problem analysis, generation, and notification of solutions.

[0306] Specifically, first, the sensor system of the autonomous vehicle collects operation data in real time and transmits it to the cloud system. In the cloud system, the collected data is analyzed using natural language processing technology (NLP) to identify common failure factors. At this time, an AI model, such as the API of OpenAI, is used to recognize data patterns and statistically extract recurring problems.

[0307] Next, the server generates a solution based on the identified failure factors. When generating the solution, the AI model makes new proposals while referring to the past database. This proposal may include route changes for autonomous vehicles or adjustments to control algorithms.

[0308] The generated solution is notified from the server to relevant organizations or responsible persons. The notification forms are diverse and are carried out via smartphone apps, desktop apps, etc. The administrator can consider the solution on the app and issue an implementation instruction if necessary.

[0309] As a specific example, consider the case where control errors occur repeatedly at a specific intersection. In this case, the server analyzes the past data related to that intersection and generates a prompt sentence for proposing a detour route suitable for the situation. Based on the prompt sentence "An autonomous vehicle frequently makes control errors at intersection A. Please identify the cause and propose a solution.", the AI model presents a detailed solution. Thus, it is possible to significantly improve the operation efficiency of autonomous vehicles with this system.

[0310] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0311] Step 1:

[0312] The terminal (autonomous vehicle) collects data from its sensor system during operation. This data includes location information, vehicle speed, and environmental information (weather, obstacle detection status, etc.). This data is transmitted to a cloud system. The input is real-time data sent from the sensors, and the output is raw data stored on the cloud system.

[0313] Step 2:

[0314] The server analyzes the received raw data using natural language processing techniques. To identify common failure factors, it cleans the data and analyzes patterns using statistical methods and AI models. The input is a set of raw data, and the output is a list of identified failure factors.

[0315] Step 3:

[0316] The server generates solutions based on identified failure factors, referencing a database of past success stories and current data. Here, a generative AI model is used to create specific countermeasures for particular failure conditions. The input is a list of identified failure factors, and the output is a list of proposed solutions.

[0317] Step 4:

[0318] The server notifies the relevant organizations and individuals of the generated solutions. The solutions are converted into an appropriate format and sent, for example, via a smartphone app or PC terminal. The input is a list of solutions, and the output is the notified proposal.

[0319] Step 5:

[0320] The user receives the notified solution and checks its contents on their smartphone or PC. If necessary, they provide instructions to the system to implement the proposed solution. This resolves the problem and optimizes operations. The input is the notified solution, and the output is user feedback or instructions for implementation.

[0321] 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.

[0322] This invention is a system that collects and analyzes problem data, generates solutions, and notifies relevant organizations in order to efficiently solve difficult problems that AI agents encounter while performing their tasks. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, making it possible to further personalize and optimize the presentation of solutions.

[0323] Data collection and analysis

[0324] The device collects detailed data on difficult-to-solve problems reported by the AI ​​agent. This includes the circumstances under which the problem occurred, error information, user operation history, and input information.

[0325] The server preprocesses the collected data and analyzes it using natural language processing techniques to identify common bottlenecks.

[0326] Emotion recognition and solution generation

[0327] The emotion engine estimates emotions from user behavior and input, and determines the user's psychological state and the most acceptable way to present information in problem-solving situations.

[0328] The server generates solutions based on identified bottlenecks and the user's emotional state. By reflecting the results of the emotion engine, it customizes the information to present solutions in the most effective way for the user.

[0329] Notifications and optimal presentations

[0330] When the server notifies relevant companies and government agencies of the generated solutions, it provides information in a format and media that suits the user's emotional state. This flexible approach enhances the acceptability and actionability of the information.

[0331] Based on the information provided by this system, users can take appropriate actions to improve their work and solve problems.

[0332] As a concrete example, suppose a problem is reported in a business system where certain operations are unclear, leading to frequent user errors. In this case, the server analyzes the commonalities of the problem, and the emotion engine identifies the user's frustration level. The server can then generate a solution tailored to alleviate user frustration and provide it in the form of an easy-to-understand, guided instructional video. This integrated approach streamlines the user's problem-solving process and enables smoother business operations.

[0333] The following describes the processing flow.

[0334] Step 1:

[0335] The device collects data in real time on problems that occur while the AI ​​agent is running. This process includes user operation logs, error messages, and contextual information.

[0336] Step 2:

[0337] The device uses an emotion engine to process data in order to estimate the user's emotional state from their input and interaction patterns. The emotion engine uses natural language processing and machine learning models to evaluate the stress and frustration that the user may be experiencing.

[0338] Step 3:

[0339] The server receives emotional state data along with problem data sent from each terminal and integrates this into a central database. After collection, the data is filtered to select important information.

[0340] Step 4:

[0341] The server analyzes the collected data to identify common bottlenecks. This analysis utilizes natural language processing techniques to recognize problem patterns and perform clustering.

[0342] Step 5:

[0343] The server generates appropriate solutions based on identified bottlenecks and the user's emotional state. Here, to minimize the user's burden, we design solutions in an acceptable format that takes into account the results of the emotion engine.

[0344] Step 6:

[0345] The server notifies the relevant organizations of the generated solutions. In this process, the solutions are presented in various formats (e.g., video guides, infographics, text summaries) to ensure that the recipients of the information can easily understand them.

[0346] Step 7:

[0347] Based on the solutions provided by the server, users can quickly address problems and take action to improve their operations. As a result, the user's problem-solving process proceeds smoothly.

[0348] (Example 2)

[0349] 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".

[0350] In today's work environment, users often face complex and difficult-to-solve problems, making it challenging to quickly find appropriate solutions. In particular, these problems require solutions that take into account the emotions and stress levels of individual users, and traditional, uniform methods are often ineffective.

[0351] 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.

[0352] In this invention, the server includes means for collecting problem information from data terminals, means for analyzing pre-processed information, and means for generating solutions based on the user's emotional state. This makes it possible to provide solutions that are tailored to the individual circumstances of each user.

[0353] A "data terminal" is a device or apparatus used to collect information from users regarding problems that are difficult to solve.

[0354] "Preprocessing" refers to the process of removing missing or inconsistent data from collected raw data and preparing it for analysis.

[0355] "Analysis techniques" refer to methods and techniques for analyzing collected and pre-processed data to derive useful information and patterns.

[0356] "Obstacles" refer to common bottlenecks or problems encountered during the performance of tasks.

[0357] "Emotion analysis" is a technology that estimates a user's psychological state and emotions from their actions and behavior.

[0358] A "generative model" is an algorithm or model used to generate appropriate solutions based on data or input.

[0359] "Relevant organizations" refers to companies, organizations, or related institutions that are subject to notification and sharing of the generated solutions.

[0360] "Language processing technology" refers to the techniques and methods used to process natural language and analyze its meaning.

[0361] This invention is a comprehensive system for solving difficult-to-resolve challenges encountered during the performance of work.

[0362] Data collection and analysis

[0363] The terminal collects information about problems that occur during the user's work. This information includes operation history, error details, and input data. The collected data is cleansed to impute missing values ​​and correct inconsistencies.

[0364] The server performs analysis using the cleansed data. This analysis employs natural language processing techniques and utilizes software libraries such as Python's spaCy and NLTK. The data analysis makes it possible to identify common failures that cause problems.

[0365] Emotion recognition and solution generation

[0366] The emotion engine analyzes user emotions based on their operation history and input speed to estimate their level of stress and dissatisfaction.

[0367] The server generates solutions using a generative AI model based on the analysis results and sentiment data. The generative AI model is utilized in the solution generation process to provide users with customized and easily understandable information. TensorFlow and PyTorch are expected to be used in this process.

[0368] Notifications and Information

[0369] The server notifies the relevant organizations and individuals of the identified solutions. The information is provided in a format tailored to the user's emotional state, such as a PDF report or explanatory video. This makes it easy for users to understand and implement the solutions.

[0370] Specific example

[0371] For example, if a user frequently makes input errors in a particular business system, the server can identify the problem, and the emotion engine can determine the user's level of anxiety. Then, it can generate a personalized solution in the form of an explanatory video and send it to the user via email. This kind of flexible solution provision improves operational efficiency.

[0372] Example of a prompt

[0373] "After the new system is implemented, analyze the reasons for user confusion and suggest what kind of information would help them understand it."

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1:

[0376] The terminal collects information about issues reported by users in the business system. Specifically, it collects user operation history, input error logs, and error messages. This input information is temporarily stored on the terminal and sent to the server. The collected log data is then generated as output.

[0377] Step 2:

[0378] The server receives log data sent from the terminal and preprocesses it. The input data includes raw data such as operation history and error logs. Specific data processing involves imputing missing data and filtering irrelevant data to generate a clean dataset. The output is data in a state ready for analysis.

[0379] Step 3:

[0380] The server analyzes the pre-processed data. The input data includes clean operation history and error logs. Natural language processing techniques are used to perform data calculations on this data to identify frequent problem patterns and common failures. Specifically, text data is tokenized, and highly relevant keywords are extracted. A list of identified problems is generated as output.

[0381] Step 4:

[0382] The emotion engine performs sentiment analysis based on user behavior logs and analyzed data. Input data includes the user's action speed and frequency. Specifically, it analyzes this data to quantify stress and dissatisfaction levels. The output is an analysis result indicating the user's emotional state.

[0383] Step 5:

[0384] The server generates solutions using a generative AI model based on the results of problem analysis and sentiment analysis. Input includes data on identified problems and the user's emotional state. Specifically, prompts are sent to a generative AI model such as GPT-3 to request solutions. The output is a customized solution proposal.

[0385] Step 6:

[0386] The server notifies relevant organizations and users of the generated solutions. Based on the input solutions, it converts them into a format that suits the user's emotional state, such as an operation guide or video manual. The output is information provided in an easy-to-understand format.

[0387] Step 7:

[0388] Users implement business improvement measures based on the solutions they receive. Specifically, they can improve work efficiency by trying out the countermeasures when problems arise, while referring to the provided guides. This promotes the continuous development of the latest and most optimal business improvements.

[0389] (Application Example 2)

[0390] 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".

[0391] In modern online retail systems, support for user problems is uniform and does not address the individual emotional state of each user. As a result, users often become dissatisfied, hindering the quick and effective resolution of problems. Addressing this challenge is crucial.

[0392] 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.

[0393] In this invention, the server includes means for collecting information on challenges that users find difficult to overcome, means for analyzing the collected information and identifying common obstacles, and means for recognizing the user's emotional state and adjusting the solution means accordingly. This enables personalized responses that are tailored to the user's emotional state.

[0394] "Difficult-to-solve challenges" refer to problems that users deem difficult to solve using conventional means or existing knowledge.

[0395] "Means of collecting information" refers to devices or software that have the function of collecting data on user operations, inputs, and errors.

[0396] "Means of analyzing information and identifying common problems" refers to analytical processes and techniques used to find patterns of related problems and issues based on collected information.

[0397] "Means for generating solutions" refers to a mechanism for designing and proposing effective countermeasures or improvement measures for identified problems.

[0398] "Means of informing relevant organizations" refers to methods or systems for notifying the appropriate organizations or departments of the generated solutions and for sharing information.

[0399] "Means of recognizing a user's emotional state" refers to technologies that infer and evaluate a user's emotions from their behavior and input data.

[0400] "Providing communication methods" refers to the act of selecting and presenting the most appropriate form and method of information transmission according to the user's emotional state and needs.

[0401] To implement this application, the server first collects information from the terminal about the difficult challenges the user encounters. This information includes the user's operation history and input error information. The collected information is then analyzed by the server using natural language processing technology to identify common problems.

[0402] Next, the server generates solutions to the identified problems. Since the user's emotional state is a crucial factor in this process, an emotion engine is used to estimate the user's emotions from their behavior and optimize the solutions accordingly. For example, if the user is feeling anxious, the solutions are adjusted to be more intuitive and easier to understand.

[0403] The generated solutions are not only communicated to the relevant organizations, but are also directly provided to users through a variety of information dissemination methods. For example, communication methods that match the user's emotional state are selected, such as video guides or user-friendly, conversational guidance.

[0404] Software used to perform emotion recognition and natural language processing includes EmotionEngine and NLPProcessor. These are important tools for effectively analyzing collected data and accurately assessing the user's emotional state.

[0405] As a concrete example, consider a scenario where an error occurs during the user's purchase process on an e-commerce site. When frustration is detected from the user's input, the server suggests a user-friendly video guide to reassure the user and support the resolution of the problem. An example of a prompt for the generative AI model is, "How should we alleviate user frustration with e-commerce site error messages?"

[0406] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0407] Step 1:

[0408] The terminal collects information about the user's operation history and input errors. This input information is sent to the server and stored in a database. The collected information includes product selection, errors during the purchase flow, and screen transition history.

[0409] Step 2:

[0410] The server receives the collected information and performs analysis using natural language processing (NLP) techniques. Specifically, it uses an NLP Processor to extract common failures and problem patterns from the data. The input is the user data collected in step 1, and the output is the common failure points identified through the analysis.

[0411] Step 3:

[0412] The server generates solutions to the identified problems based on the analysis results. In this process, it uses EmotionEngine to infer the user's emotional state. The input is the output from step 2 plus data about the user's emotions, and the output is a personalized solution. This could include, for example, video guides or FAQ suggestions.

[0413] Step 4:

[0414] The server notifies relevant organizations and users of the generated solutions. As a specific communication method, it provides user-friendly messages and guides tailored to the user's emotions. The input is the solution generated in step 3, and the output is information as a notification to the user or stakeholders.

[0415] Step 5:

[0416] The user receives information from the server and solves the problem by following the instructions. It is expected that the information provided will be helpful and reduce the user's anxiety and frustration. User feedback will be reflected in subsequent data analysis. The input is the notification from the server, and the output is the user's problem-solving actions.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] The system of the present invention provides problem-solving support by efficiently collecting and analyzing difficult-to-solve problems encountered by AI agents in the course of performing their tasks, generating solutions, and notifying relevant organizations. This process is carried out as follows.

[0434] Data collection

[0435] The device stores data on difficult problems collected from the AI ​​agent. This includes problem details, circumstances under which it occurred, and the agent's trial history.

[0436] Data Analysis

[0437] The server analyzes data collected from terminals and uses natural language processing to identify common bottlenecks. This allows it to statistically summarize recurring problems from the analyzed data and reveal their root causes.

[0438] Solution generation

[0439] The server generates solutions for the identified bottlenecks. At this stage, it refers to a database of existing solutions and success stories, and builds new proposals learned from past examples.

[0440] Notifications and suggestions

[0441] The server notifies relevant organizations of the generated solutions and provides information in various formats. This makes the information easier for users to understand and implement. For example, if an AI agent fails to find a flight on the same day multiple times in an area with limited flight options, it will propose a new route to the airline as a solution.

[0442] This system enables AI agents to quickly resolve problems they face, improving operational efficiency and convenience. This allows for a more integrated and comprehensive problem-solving approach than traditional, individual problem-solving methods.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] The device collects logs detailing the difficult problems the AI ​​agent encountered. This collection includes the date and time, the nature of the error, user input, and the AI ​​agent's response history.

[0446] Step 2:

[0447] The server collects log data from each terminal at regular intervals. The data is transferred via a secure connection and stored in a central database.

[0448] Step 3:

[0449] The server preprocesses the collected data, removes duplicates, detects outliers, and performs data cleansing. This process prepares the data for improved analysis accuracy.

[0450] Step 4:

[0451] The server applies natural language processing (NLP) to the cleansed data to identify common bottlenecks and problem trends. Topic modeling and clustering techniques are used to systematically classify the data.

[0452] Step 5:

[0453] The server generates solutions based on identified bottlenecks, leveraging historical databases and generative AI. This includes constructing proposals that may include new improvements and unapproved methodologies.

[0454] Step 6:

[0455] The server performs predictive analysis on the effectiveness and risks of solutions and evaluates the proposals. Based on this evaluation, it determines the priority of recommended solutions.

[0456] Step 7:

[0457] The server notifies relevant companies and government agencies of the generated solutions. The notifications are presented in various formats, including text reports, graphs, and infographics, to facilitate understanding.

[0458] Step 8:

[0459] Users will use the provided information to make necessary adjustments and modifications and apply them to their actual work. This process effectively eliminates problems that hinder the AI ​​agent's performance.

[0460] (Example 1)

[0461] 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."

[0462] There is a need to quickly and efficiently resolve complex problems that arise when using business support devices. However, conventional systems have difficulty responding immediately to individual problems, resulting in waste and a decrease in overall business efficiency.

[0463] 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.

[0464] In this invention, the server includes means for collecting information on difficult-to-solve problems that arise in business support devices, means for analyzing the collected information to identify common issues, and means for generating solutions to the identified issues. This enables rapid identification of problems and the provision of effective solutions.

[0465] A "business support device" is a device designed to efficiently assist with various business tasks, possessing functions for problem identification, information gathering, analysis, and solution presentation.

[0466] "Difficult-to-solve problems" refer to challenges or obstacles that are difficult to resolve when a business support system processes data, and which hinder efficient business operations.

[0467] "Means of collecting information" refers to the process by which business support devices systematically collect data related to a problem, record its detailed content and circumstances, and use it for subsequent analysis.

[0468] "Means of analyzing information" refers to using techniques and methods to analyze the causes of problems based on collected data and identify commonalities.

[0469] "Methods for identifying problems" refer to the process of identifying common issues and bottlenecks detected through information analysis, and then narrowing them down to those that need to be addressed.

[0470] "Means of generating solutions" refers to the process of building effective countermeasures for identified problems, and is a method of generating new proposals by utilizing past cases and machine learning models.

[0471] "Means of notifying organizations" refers to methods for communicating the generated solutions to relevant organizations in an appropriate format and prompting them to take action.

[0472] Modes for carrying out the invention

[0473] This invention is a system for quickly and efficiently resolving difficult problems that arise during the execution of business operations, using a business support device. This system resolves problems through the processes of data collection, analysis, solution generation, and notification.

[0474] Hardware and software configuration:

[0475] The terminal functions as a business support device, collecting business-related information in real time. This information is stored in the form of AI agent activity logs and error reports. Log management software and a database management system are used for this purpose.

[0476] The server receives information sent from the terminal and analyzes it. Natural language processing techniques are used for the analysis, specifically Python and its NLP libraries (e.g., NLTK, spaCy). The server identifies common issues from the collected information.

[0477] The server also generates solutions using a generative AI model. This model has learned from past successes and, for example, uses natural language generation software to construct new proposals.

[0478] Users can receive solutions notified by the server and apply them in their work. Notifications are sent via email or online dashboards, and the information is provided in HTML or PDF format.

[0479] Specific examples and prompt statements:

[0480] As a concrete example, when an AI agent providing flight booking assistance encounters the recurring problem of unbookable flights in a specific region, the server analyzes the issue and generates a solution that proposes new flight routes to the airline.

[0481] An example of a prompt message would be, "What specific problem does the AI ​​agent encounter? Refer to past data and suggest a new solution." This message would be input to the generating AI model, and the model would then propose a solution based on this information.

[0482] A system configured in this way aims to improve operational efficiency and enable rapid problem-solving.

[0483] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0484] Step 1:

[0485] The terminal takes data on problems the AI ​​agent faces as input. Specifically, it collects log data and error reports during task execution, organizes them in a database, and stores them there. This data includes the date and time the problem occurred, the history of trial and error, and the specific details of the problem.

[0486] Step 2:

[0487] The terminal organizes the collected data and sends it to the server via a secure communication protocol (e.g., HTTPS). The input is structured JSON or XML data. The terminal formats the data before sending it to make it easier for the server to parse.

[0488] Step 3:

[0489] The server receives data sent from the terminal. Using the acquired data as input, the server analyzes the data using natural language processing techniques (e.g., Python's NLP library). To identify common issues, it performs text pattern recognition and statistical analysis, and outputs an overview of the issues.

[0490] Step 4:

[0491] The server generates solutions using a generative AI model based on the analysis results. It references information about the identified problem and relevant past success stories as input. The AI ​​model processes this data, proposes new solutions, and generates new ideas and suggestions that the model outputs.

[0492] Step 5:

[0493] The server notifies the relevant organizations of the generated solutions. As output, the generated solutions are converted into HTML or PDF format, providing them in an easily understandable format for users. Users apply the received solutions to their work and improve efficiency. Notifications are made via email and an online dashboard.

[0494] (Application Example 1)

[0495] 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."

[0496] Autonomous vehicles face various problems during operation, but conventional systems have struggled to resolve these issues quickly and efficiently. To address this challenge, it is necessary to automate the entire process, from problem identification to solution generation and notification, thereby improving operational efficiency and convenience.

[0497] 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.

[0498] In this invention, the server includes means for collecting information on difficult-to-solve problems, means for analyzing the collected information to identify common failure factors, and means for collecting data from automated vehicles in real time and transmitting it to a cloud system. This enables the rapid identification of problems and the proposal of solutions, thereby improving the operational efficiency of automated vehicles.

[0499] "Difficult-to-solve problems" refer to challenges or obstacles that occur during the operation of autonomous vehicles by AI agents and that are difficult to solve using conventional methods.

[0500] "Means of collecting information" refers to the process or device for acquiring and recording data and problem-related information generated from autonomous vehicles.

[0501] "Common obstacles" refer to the results of analyzing and identifying common problems and constraints that frequently occur from the collected information.

[0502] "Means of generating solutions" refers to a process that uses AI models and algorithms to automatically propose countermeasures and improvements for identified problem factors.

[0503] "Means of notification" refers to mechanisms and systems for efficiently communicating generated solutions to relevant organizations and personnel.

[0504] A "cloud system" refers to distributed computing resources consisting of servers, data storage, and other components that are connected remotely via the internet.

[0505] The system that realizes this invention is designed to efficiently solve difficult problems that arise during the operation of autonomous vehicles. This system consistently performs tasks from data collection and problem analysis to solution generation and notification.

[0506] Specifically, the autonomous vehicle's sensor system first collects operational data in real time and transmits it to a cloud system. The cloud system then analyzes the collected data using natural language processing (NLP) to identify common failure factors. During this process, an AI model, such as the OpenAI API, is used to recognize patterns in the data and statistically extract recurring problems.

[0507] Next, the server generates solutions based on the identified fault factors. This solution generation involves an AI model that refers to past database data while also proposing new solutions. These proposals may include route changes or adjustments to control algorithms for autonomous vehicles.

[0508] The generated solutions are notified from the server to the relevant organizations and personnel. The notification format varies, including via smartphone and desktop applications. Administrators can review the solutions within the application and, if necessary, issue instructions for implementation.

[0509] As a concrete example, consider a scenario where control errors occur repeatedly at a specific intersection. In this case, the server analyzes past data related to that intersection and generates a prompt message that suggests an appropriate detour route. Based on a prompt message such as, "The autonomous vehicle is frequently making control errors at intersection A. Identify the cause and propose a solution," the AI ​​model presents a detailed solution. In this way, this system can significantly improve the operational efficiency of autonomous vehicles.

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The terminal (autonomous vehicle) collects data from its sensor system during operation. This data includes location information, vehicle speed, and environmental information (weather, obstacle detection status, etc.). This data is transmitted to a cloud system. The input is real-time data sent from the sensors, and the output is raw data stored on the cloud system.

[0513] Step 2:

[0514] The server analyzes the received raw data using natural language processing techniques. To identify common failure factors, it cleans the data and analyzes patterns using statistical methods and AI models. The input is a set of raw data, and the output is a list of identified failure factors.

[0515] Step 3:

[0516] The server generates solutions based on identified failure factors, referencing a database of past success stories and current data. Here, a generative AI model is used to create specific countermeasures for particular failure conditions. The input is a list of identified failure factors, and the output is a list of proposed solutions.

[0517] Step 4:

[0518] The server notifies the relevant organizations and individuals of the generated solutions. The solutions are converted into an appropriate format and sent, for example, via a smartphone app or PC terminal. The input is a list of solutions, and the output is the notified proposal.

[0519] Step 5:

[0520] The user receives the notified solution and checks its contents on their smartphone or PC. If necessary, they provide instructions to the system to implement the proposed solution. This resolves the problem and optimizes operations. The input is the notified solution, and the output is user feedback or instructions for implementation.

[0521] 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.

[0522] This invention is a system that collects and analyzes problem data, generates solutions, and notifies relevant organizations in order to efficiently solve difficult problems that AI agents encounter while performing their tasks. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, making it possible to further personalize and optimize the presentation of solutions.

[0523] Data collection and analysis

[0524] The device collects detailed data on difficult-to-solve problems reported by the AI ​​agent. This includes the circumstances under which the problem occurred, error information, user operation history, and input information.

[0525] The server preprocesses the collected data and analyzes it using natural language processing techniques to identify common bottlenecks.

[0526] Emotion recognition and solution generation

[0527] The emotion engine estimates emotions from user behavior and input, and determines the user's psychological state and the most acceptable way to present information in problem-solving situations.

[0528] The server generates solutions based on identified bottlenecks and the user's emotional state. By reflecting the results of the emotion engine, it customizes the information to present solutions in the most effective way for the user.

[0529] Notifications and optimal presentations

[0530] When the server notifies relevant companies and government agencies of the generated solutions, it provides information in a format and media that suits the user's emotional state. This flexible approach enhances the acceptability and actionability of the information.

[0531] Based on the information provided by this system, users can take appropriate actions to improve their work and solve problems.

[0532] As a concrete example, suppose a problem is reported in a business system where certain operations are unclear, leading to frequent user errors. In this case, the server analyzes the commonalities of the problem, and the emotion engine identifies the user's frustration level. The server can then generate a solution tailored to alleviate user frustration and provide it in the form of an easy-to-understand, guided instructional video. This integrated approach streamlines the user's problem-solving process and enables smoother business operations.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] The device collects data in real time on problems that occur while the AI ​​agent is running. This process includes user operation logs, error messages, and contextual information.

[0536] Step 2:

[0537] The device uses an emotion engine to process data in order to estimate the user's emotional state from their input and interaction patterns. The emotion engine uses natural language processing and machine learning models to evaluate the stress and frustration that the user may be experiencing.

[0538] Step 3:

[0539] The server receives emotional state data along with problem data sent from each terminal and integrates this into a central database. After collection, the data is filtered to select important information.

[0540] Step 4:

[0541] The server analyzes the collected data to identify common bottlenecks. This analysis utilizes natural language processing techniques to recognize problem patterns and perform clustering.

[0542] Step 5:

[0543] The server generates appropriate solutions based on identified bottlenecks and the user's emotional state. Here, to minimize the user's burden, we design solutions in an acceptable format that takes into account the results of the emotion engine.

[0544] Step 6:

[0545] The server notifies the relevant organizations of the generated solutions. In this process, the solutions are presented in various formats (e.g., video guides, infographics, text summaries) to ensure that the recipients of the information can easily understand them.

[0546] Step 7:

[0547] Based on the solutions provided by the server, users can quickly address problems and take action to improve their operations. As a result, the user's problem-solving process proceeds smoothly.

[0548] (Example 2)

[0549] 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."

[0550] In today's work environment, users often face complex and difficult-to-solve problems, making it challenging to quickly find appropriate solutions. In particular, these problems require solutions that take into account the emotions and stress levels of individual users, and traditional, uniform methods are often ineffective.

[0551] 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.

[0552] In this invention, the server includes means for collecting problem information from data terminals, means for analyzing pre-processed information, and means for generating solutions based on the user's emotional state. This makes it possible to provide solutions that are tailored to the individual circumstances of each user.

[0553] A "data terminal" is a device or apparatus used to collect information from users regarding problems that are difficult to solve.

[0554] "Preprocessing" refers to the process of removing missing or inconsistent data from collected raw data and preparing it for analysis.

[0555] "Analysis techniques" refer to methods and techniques for analyzing collected and pre-processed data to derive useful information and patterns.

[0556] "Obstacles" refer to common bottlenecks or problems encountered during the performance of tasks.

[0557] "Emotion analysis" is a technology that estimates a user's psychological state and emotions from their actions and behavior.

[0558] A "generative model" is an algorithm or model used to generate appropriate solutions based on data or input.

[0559] "Relevant organizations" refers to companies, organizations, or related institutions that are subject to notification and sharing of the generated solutions.

[0560] "Language processing technology" refers to the techniques and methods used to process natural language and analyze its meaning.

[0561] This invention is a comprehensive system for solving difficult-to-resolve challenges encountered during the performance of work.

[0562] Data collection and analysis

[0563] The terminal collects information about problems that occur during the user's work. This information includes operation history, error details, and input data. The collected data is cleansed to impute missing values ​​and correct inconsistencies.

[0564] The server performs analysis using the cleansed data. This analysis employs natural language processing techniques and utilizes software libraries such as Python's spaCy and NLTK. The data analysis makes it possible to identify common failures that cause problems.

[0565] Emotion recognition and solution generation

[0566] The emotion engine analyzes user emotions based on their operation history and input speed to estimate their level of stress and dissatisfaction.

[0567] The server generates solutions using a generative AI model based on the analysis results and sentiment data. The generative AI model is utilized in the solution generation process to provide users with customized and easily understandable information. TensorFlow and PyTorch are expected to be used in this process.

[0568] Notifications and Information

[0569] The server notifies the relevant organizations and individuals of the identified solutions. The information is provided in a format tailored to the user's emotional state, such as a PDF report or explanatory video. This makes it easy for users to understand and implement the solutions.

[0570] Specific example

[0571] For example, if a user frequently makes input errors in a particular business system, the server can identify the problem, and the emotion engine can determine the user's level of anxiety. Then, it can generate a personalized solution in the form of an explanatory video and send it to the user via email. This kind of flexible solution provision improves operational efficiency.

[0572] Example of a prompt

[0573] "After the new system is implemented, analyze the reasons for user confusion and suggest what kind of information would help them understand it."

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] The terminal collects information about issues reported by users in the business system. Specifically, it collects user operation history, input error logs, and error messages. This input information is temporarily stored on the terminal and sent to the server. The collected log data is then generated as output.

[0577] Step 2:

[0578] The server receives log data sent from the terminal and preprocesses it. The input data includes raw data such as operation history and error logs. Specific data processing involves imputing missing data and filtering irrelevant data to generate a clean dataset. The output is data in a state ready for analysis.

[0579] Step 3:

[0580] The server analyzes the pre-processed data. The input data includes clean operation history and error logs. Natural language processing techniques are used to perform data calculations on this data to identify frequent problem patterns and common failures. Specifically, text data is tokenized, and highly relevant keywords are extracted. A list of identified problems is generated as output.

[0581] Step 4:

[0582] The emotion engine performs sentiment analysis based on user behavior logs and analyzed data. Input data includes the user's action speed and frequency. Specifically, it analyzes this data to quantify stress and dissatisfaction levels. The output is an analysis result indicating the user's emotional state.

[0583] Step 5:

[0584] The server generates solutions using a generative AI model based on the results of problem analysis and sentiment analysis. Input includes data on identified problems and the user's emotional state. Specifically, prompts are sent to a generative AI model such as GPT-3 to request solutions. The output is a customized solution proposal.

[0585] Step 6:

[0586] The server notifies relevant organizations and users of the generated solutions. Based on the input solutions, it converts them into a format that suits the user's emotional state, such as an operation guide or video manual. The output is information provided in an easy-to-understand format.

[0587] Step 7:

[0588] Users implement business improvement measures based on the solutions they receive. Specifically, they can improve work efficiency by trying out the countermeasures when problems arise, while referring to the provided guides. This promotes the continuous development of the latest and most optimal business improvements.

[0589] (Application Example 2)

[0590] 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."

[0591] In modern online retail systems, support for user problems is uniform and does not address the individual emotional state of each user. As a result, users often become dissatisfied, hindering the quick and effective resolution of problems. Addressing this challenge is crucial.

[0592] 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.

[0593] In this invention, the server includes means for collecting information on challenges that users find difficult to overcome, means for analyzing the collected information and identifying common obstacles, and means for recognizing the user's emotional state and adjusting the solution means accordingly. This enables personalized responses that are tailored to the user's emotional state.

[0594] "Difficult-to-solve challenges" refer to problems that users deem difficult to solve using conventional means or existing knowledge.

[0595] "Means of collecting information" refers to devices or software that have the function of collecting data on user operations, inputs, and errors.

[0596] "Means of analyzing information and identifying common problems" refers to analytical processes and techniques used to find patterns of related problems and issues based on collected information.

[0597] "Means for generating solutions" refers to a mechanism for designing and proposing effective countermeasures or improvement measures for identified problems.

[0598] "Means of informing relevant organizations" refers to methods or systems for notifying the appropriate organizations or departments of the generated solutions and for sharing information.

[0599] "Means of recognizing a user's emotional state" refers to technologies that infer and evaluate a user's emotions from their behavior and input data.

[0600] "Providing communication methods" refers to the act of selecting and presenting the most appropriate form and method of information transmission according to the user's emotional state and needs.

[0601] To implement this application, the server first collects information from the terminal about the difficult challenges the user encounters. This information includes the user's operation history and input error information. The collected information is then analyzed by the server using natural language processing technology to identify common problems.

[0602] Next, the server generates solutions to the identified problems. Since the user's emotional state is a crucial factor in this process, an emotion engine is used to estimate the user's emotions from their behavior and optimize the solutions accordingly. For example, if the user is feeling anxious, the solutions are adjusted to be more intuitive and easier to understand.

[0603] The generated solutions are not only communicated to the relevant organizations, but are also directly provided to users through a variety of information dissemination methods. For example, communication methods that match the user's emotional state are selected, such as video guides or user-friendly, conversational guidance.

[0604] Software used to perform emotion recognition and natural language processing includes EmotionEngine and NLPProcessor. These are important tools for effectively analyzing collected data and accurately assessing the user's emotional state.

[0605] As a concrete example, consider a scenario where an error occurs during the user's purchase process on an e-commerce site. When frustration is detected from the user's input, the server suggests a user-friendly video guide to reassure the user and support the resolution of the problem. An example of a prompt for the generative AI model is, "How should we alleviate user frustration with e-commerce site error messages?"

[0606] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0607] Step 1:

[0608] The terminal collects information about the user's operation history and input errors. This input information is sent to the server and stored in a database. The collected information includes product selection, errors during the purchase flow, and screen transition history.

[0609] Step 2:

[0610] The server receives the collected information and performs analysis using natural language processing (NLP) techniques. Specifically, it uses an NLP Processor to extract common failures and problem patterns from the data. The input is the user data collected in step 1, and the output is the common failure points identified through the analysis.

[0611] Step 3:

[0612] The server generates solutions to the identified problems based on the analysis results. In this process, it uses EmotionEngine to infer the user's emotional state. The input is the output from step 2 plus data about the user's emotions, and the output is a personalized solution. This could include, for example, video guides or FAQ suggestions.

[0613] Step 4:

[0614] The server notifies relevant organizations and users of the generated solutions. As a specific communication method, it provides user-friendly messages and guides tailored to the user's emotions. The input is the solution generated in step 3, and the output is information as a notification to the user or stakeholders.

[0615] Step 5:

[0616] The user receives information from the server and solves the problem by following the instructions. It is expected that the information provided will be helpful and reduce the user's anxiety and frustration. User feedback will be reflected in subsequent data analysis. The input is the notification from the server, and the output is the user's problem-solving actions.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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".

[0634] The system of the present invention provides problem-solving support by efficiently collecting and analyzing difficult-to-solve problems encountered by AI agents in the course of performing their tasks, generating solutions, and notifying relevant organizations. This process is carried out as follows.

[0635] Data collection

[0636] The device stores data on difficult problems collected from the AI ​​agent. This includes problem details, circumstances under which it occurred, and the agent's trial history.

[0637] Data Analysis

[0638] The server analyzes data collected from terminals and uses natural language processing to identify common bottlenecks. This allows it to statistically summarize recurring problems from the analyzed data and reveal their root causes.

[0639] Solution generation

[0640] The server generates solutions for the identified bottlenecks. At this stage, it refers to a database of existing solutions and success stories, and builds new proposals learned from past examples.

[0641] Notifications and suggestions

[0642] The server notifies relevant organizations of the generated solutions and provides information in various formats. This makes the information easier for users to understand and implement. For example, if an AI agent fails to find a flight on the same day multiple times in an area with limited flight options, it will propose a new route to the airline as a solution.

[0643] This system enables AI agents to quickly resolve problems they face, improving operational efficiency and convenience. This allows for a more integrated and comprehensive problem-solving approach than traditional, individual problem-solving methods.

[0644] The following describes the processing flow.

[0645] Step 1:

[0646] The device collects logs detailing the difficult problems the AI ​​agent encountered. This collection includes the date and time, the nature of the error, user input, and the AI ​​agent's response history.

[0647] Step 2:

[0648] The server collects log data from each terminal at regular intervals. The data is transferred via a secure connection and stored in a central database.

[0649] Step 3:

[0650] The server preprocesses the collected data, removes duplicates, detects outliers, and performs data cleansing. This process prepares the data for improved analysis accuracy.

[0651] Step 4:

[0652] The server applies natural language processing (NLP) to the cleansed data to identify common bottlenecks and problem trends. Topic modeling and clustering techniques are used to systematically classify the data.

[0653] Step 5:

[0654] The server generates solutions based on identified bottlenecks, leveraging historical databases and generative AI. This includes constructing proposals that may include new improvements and unapproved methodologies.

[0655] Step 6:

[0656] The server performs predictive analysis on the effectiveness and risks of solutions and evaluates the proposals. Based on this evaluation, it determines the priority of recommended solutions.

[0657] Step 7:

[0658] The server notifies relevant companies and government agencies of the generated solutions. The notifications are presented in various formats, including text reports, graphs, and infographics, to facilitate understanding.

[0659] Step 8:

[0660] Users will use the provided information to make necessary adjustments and modifications and apply them to their actual work. This process effectively eliminates problems that hinder the AI ​​agent's performance.

[0661] (Example 1)

[0662] 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".

[0663] There is a need to quickly and efficiently resolve complex problems that arise when using business support devices. However, conventional systems have difficulty responding immediately to individual problems, resulting in waste and a decrease in overall business efficiency.

[0664] 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.

[0665] In this invention, the server includes means for collecting information on difficult-to-solve problems that arise in business support devices, means for analyzing the collected information to identify common issues, and means for generating solutions to the identified issues. This enables rapid identification of problems and the provision of effective solutions.

[0666] A "business support device" is a device designed to efficiently assist with various business tasks, possessing functions for problem identification, information gathering, analysis, and solution presentation.

[0667] "Difficult-to-solve problems" refer to challenges or obstacles that are difficult to resolve when a business support system processes data, and which hinder efficient business operations.

[0668] "Means of collecting information" refers to the process by which business support devices systematically collect data related to a problem, record its detailed content and circumstances, and use it for subsequent analysis.

[0669] "Means of analyzing information" refers to using techniques and methods to analyze the causes of problems based on collected data and identify commonalities.

[0670] "Methods for identifying problems" refer to the process of identifying common issues and bottlenecks detected through information analysis, and then narrowing them down to those that need to be addressed.

[0671] "Means of generating solutions" refers to the process of building effective countermeasures for identified problems, and is a method of generating new proposals by utilizing past cases and machine learning models.

[0672] "Means of notifying organizations" refers to methods for communicating the generated solutions to relevant organizations in an appropriate format and prompting them to take action.

[0673] Modes for carrying out the invention

[0674] This invention is a system for quickly and efficiently resolving difficult problems that arise during the execution of business operations, using a business support device. This system resolves problems through the processes of data collection, analysis, solution generation, and notification.

[0675] Hardware and software configuration:

[0676] The terminal functions as a business support device, collecting business-related information in real time. This information is stored in the form of AI agent activity logs and error reports. Log management software and a database management system are used for this purpose.

[0677] The server receives information sent from the terminal and analyzes it. Natural language processing techniques are used for the analysis, specifically Python and its NLP libraries (e.g., NLTK, spaCy). The server identifies common issues from the collected information.

[0678] The server also generates solutions using a generative AI model. This model has learned from past successes and, for example, uses natural language generation software to construct new proposals.

[0679] Users can receive solutions notified by the server and apply them in their work. Notifications are sent via email or online dashboards, and the information is provided in HTML or PDF format.

[0680] Specific examples and prompt statements:

[0681] As a concrete example, when an AI agent providing flight booking assistance encounters the recurring problem of unbookable flights in a specific region, the server analyzes the issue and generates a solution that proposes new flight routes to the airline.

[0682] An example of a prompt message would be, "What specific problem does the AI ​​agent encounter? Refer to past data and suggest a new solution." This message would be input to the generating AI model, and the model would then propose a solution based on this information.

[0683] A system configured in this way aims to improve operational efficiency and enable rapid problem-solving.

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The terminal takes data on problems the AI ​​agent faces as input. Specifically, it collects log data and error reports during task execution, organizes them in a database, and stores them there. This data includes the date and time the problem occurred, the history of trial and error, and the specific details of the problem.

[0687] Step 2:

[0688] The terminal organizes the collected data and sends it to the server via a secure communication protocol (e.g., HTTPS). The input is structured JSON or XML data. The terminal formats the data before sending it to make it easier for the server to parse.

[0689] Step 3:

[0690] The server receives data sent from the terminal. Using the acquired data as input, the server analyzes the data using natural language processing techniques (e.g., Python's NLP library). To identify common issues, it performs text pattern recognition and statistical analysis, and outputs an overview of the issues.

[0691] Step 4:

[0692] The server generates solutions using a generative AI model based on the analysis results. It references information about the identified problem and relevant past success stories as input. The AI ​​model processes this data, proposes new solutions, and generates new ideas and suggestions that the model outputs.

[0693] Step 5:

[0694] The server notifies the relevant organizations of the generated solutions. As output, the generated solutions are converted into HTML or PDF format, providing them in an easily understandable format for users. Users apply the received solutions to their work and improve efficiency. Notifications are made via email and an online dashboard.

[0695] (Application Example 1)

[0696] 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".

[0697] Autonomous vehicles face various problems during operation, but conventional systems have struggled to resolve these issues quickly and efficiently. To address this challenge, it is necessary to automate the entire process, from problem identification to solution generation and notification, thereby improving operational efficiency and convenience.

[0698] 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.

[0699] In this invention, the server includes means for collecting information on difficult-to-solve problems, means for analyzing the collected information to identify common failure factors, and means for collecting data from automated vehicles in real time and transmitting it to a cloud system. This enables the rapid identification of problems and the proposal of solutions, thereby improving the operational efficiency of automated vehicles.

[0700] "Difficult-to-solve problems" refer to challenges or obstacles that occur during the operation of autonomous vehicles by AI agents and that are difficult to solve using conventional methods.

[0701] "Means of collecting information" refers to the process or device for acquiring and recording data and problem-related information generated from autonomous vehicles.

[0702] "Common obstacles" refer to the results of analyzing and identifying common problems and constraints that frequently occur from the collected information.

[0703] "Means of generating solutions" refers to a process that uses AI models and algorithms to automatically propose countermeasures and improvements for identified problem factors.

[0704] "Means of notification" refers to mechanisms and systems for efficiently communicating generated solutions to relevant organizations and personnel.

[0705] A "cloud system" refers to distributed computing resources consisting of servers, data storage, and other components that are connected remotely via the internet.

[0706] The system that realizes this invention is designed to efficiently solve difficult problems that arise during the operation of autonomous vehicles. This system consistently performs tasks from data collection and problem analysis to solution generation and notification.

[0707] Specifically, the autonomous vehicle's sensor system first collects operational data in real time and transmits it to a cloud system. The cloud system then analyzes the collected data using natural language processing (NLP) to identify common failure factors. During this process, an AI model, such as the OpenAI API, is used to recognize patterns in the data and statistically extract recurring problems.

[0708] Next, the server generates solutions based on the identified fault factors. This solution generation involves an AI model that refers to past database data while also proposing new solutions. These proposals may include route changes or adjustments to control algorithms for autonomous vehicles.

[0709] The generated solutions are notified from the server to the relevant organizations and personnel. The notification format varies, including via smartphone and desktop applications. Administrators can review the solutions within the application and, if necessary, issue instructions for implementation.

[0710] As a concrete example, consider a scenario where control errors occur repeatedly at a specific intersection. In this case, the server analyzes past data related to that intersection and generates a prompt message that suggests an appropriate detour route. Based on a prompt message such as, "The autonomous vehicle is frequently making control errors at intersection A. Identify the cause and propose a solution," the AI ​​model presents a detailed solution. In this way, this system can significantly improve the operational efficiency of autonomous vehicles.

[0711] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0712] Step 1:

[0713] The terminal (autonomous vehicle) collects data from its sensor system during operation. This data includes location information, vehicle speed, and environmental information (weather, obstacle detection status, etc.). This data is transmitted to a cloud system. The input is real-time data sent from the sensors, and the output is raw data stored on the cloud system.

[0714] Step 2:

[0715] The server analyzes the received raw data using natural language processing techniques. To identify common failure factors, it cleans the data and analyzes patterns using statistical methods and AI models. The input is a set of raw data, and the output is a list of identified failure factors.

[0716] Step 3:

[0717] The server generates solutions based on identified failure factors, referencing a database of past success stories and current data. Here, a generative AI model is used to create specific countermeasures for particular failure conditions. The input is a list of identified failure factors, and the output is a list of proposed solutions.

[0718] Step 4:

[0719] The server notifies the relevant organizations and individuals of the generated solutions. The solutions are converted into an appropriate format and sent, for example, via a smartphone app or PC terminal. The input is a list of solutions, and the output is the notified proposal.

[0720] Step 5:

[0721] The user receives the notified solution and checks its contents on their smartphone or PC. If necessary, they provide instructions to the system to implement the proposed solution. This resolves the problem and optimizes operations. The input is the notified solution, and the output is user feedback or instructions for implementation.

[0722] 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.

[0723] This invention is a system that collects and analyzes problem data, generates solutions, and notifies relevant organizations in order to efficiently solve difficult problems that AI agents encounter while performing their tasks. Furthermore, this system incorporates an emotion engine that recognizes the user's emotions, making it possible to further personalize and optimize the presentation of solutions.

[0724] Data collection and analysis

[0725] The device collects detailed data on difficult-to-solve problems reported by the AI ​​agent. This includes the circumstances under which the problem occurred, error information, user operation history, and input information.

[0726] The server preprocesses the collected data and analyzes it using natural language processing techniques to identify common bottlenecks.

[0727] Emotion recognition and solution generation

[0728] The emotion engine estimates emotions from user behavior and input, and determines the user's psychological state and the most acceptable way to present information in problem-solving situations.

[0729] The server generates solutions based on identified bottlenecks and the user's emotional state. By reflecting the results of the emotion engine, it customizes the information to present solutions in the most effective way for the user.

[0730] Notifications and optimal presentations

[0731] When the server notifies relevant companies and government agencies of the generated solutions, it provides information in a format and media that suits the user's emotional state. This flexible approach enhances the acceptability and actionability of the information.

[0732] Based on the information provided by this system, users can take appropriate actions to improve their work and solve problems.

[0733] As a concrete example, suppose a problem is reported in a business system where certain operations are unclear, leading to frequent user errors. In this case, the server analyzes the commonalities of the problem, and the emotion engine identifies the user's frustration level. The server can then generate a solution tailored to alleviate user frustration and provide it in the form of an easy-to-understand, guided instructional video. This integrated approach streamlines the user's problem-solving process and enables smoother business operations.

[0734] The following describes the processing flow.

[0735] Step 1:

[0736] The device collects data in real time on problems that occur while the AI ​​agent is running. This process includes user operation logs, error messages, and contextual information.

[0737] Step 2:

[0738] The device uses an emotion engine to process data in order to estimate the user's emotional state from their input and interaction patterns. The emotion engine uses natural language processing and machine learning models to evaluate the stress and frustration that the user may be experiencing.

[0739] Step 3:

[0740] The server receives emotional state data along with problem data sent from each terminal and integrates this into a central database. After collection, the data is filtered to select important information.

[0741] Step 4:

[0742] The server analyzes the collected data to identify common bottlenecks. This analysis utilizes natural language processing techniques to recognize problem patterns and perform clustering.

[0743] Step 5:

[0744] The server generates appropriate solutions based on identified bottlenecks and the user's emotional state. Here, to minimize the user's burden, we design solutions in an acceptable format that takes into account the results of the emotion engine.

[0745] Step 6:

[0746] The server notifies the relevant organizations of the generated solutions. In this process, the solutions are presented in various formats (e.g., video guides, infographics, text summaries) to ensure that the recipients of the information can easily understand them.

[0747] Step 7:

[0748] Based on the solutions provided by the server, users can quickly address problems and take action to improve their operations. As a result, the user's problem-solving process proceeds smoothly.

[0749] (Example 2)

[0750] 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".

[0751] In today's work environment, users often face complex and difficult-to-solve problems, making it challenging to quickly find appropriate solutions. In particular, these problems require solutions that take into account the emotions and stress levels of individual users, and traditional, uniform methods are often ineffective.

[0752] 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.

[0753] In this invention, the server includes means for collecting problem information from data terminals, means for analyzing pre-processed information, and means for generating solutions based on the user's emotional state. This makes it possible to provide solutions that are tailored to the individual circumstances of each user.

[0754] A "data terminal" is a device or apparatus used to collect information from users regarding problems that are difficult to solve.

[0755] "Preprocessing" refers to the process of removing missing or inconsistent data from collected raw data and preparing it for analysis.

[0756] "Analysis techniques" refer to methods and techniques for analyzing collected and pre-processed data to derive useful information and patterns.

[0757] "Obstacles" refer to common bottlenecks or problems encountered during the performance of tasks.

[0758] "Emotion analysis" is a technology that estimates a user's psychological state and emotions from their actions and behavior.

[0759] A "generative model" is an algorithm or model used to generate appropriate solutions based on data or input.

[0760] "Relevant organizations" refers to companies, organizations, or related institutions that are subject to notification and sharing of the generated solutions.

[0761] "Language processing technology" refers to the techniques and methods used to process natural language and analyze its meaning.

[0762] This invention is a comprehensive system for solving difficult-to-resolve challenges encountered during the performance of work.

[0763] Data collection and analysis

[0764] The terminal collects information about problems that occur during the user's work. This information includes operation history, error details, and input data. The collected data is cleansed to impute missing values ​​and correct inconsistencies.

[0765] The server performs analysis using the cleansed data. This analysis employs natural language processing techniques and utilizes software libraries such as Python's spaCy and NLTK. The data analysis makes it possible to identify common failures that cause problems.

[0766] Emotion recognition and solution generation

[0767] The emotion engine analyzes user emotions based on their operation history and input speed to estimate their level of stress and dissatisfaction.

[0768] The server generates solutions using a generative AI model based on the analysis results and sentiment data. The generative AI model is utilized in the solution generation process to provide users with customized and easily understandable information. TensorFlow and PyTorch are expected to be used in this process.

[0769] Notifications and Information

[0770] The server notifies the relevant organizations and individuals of the identified solutions. The information is provided in a format tailored to the user's emotional state, such as a PDF report or explanatory video. This makes it easy for users to understand and implement the solutions.

[0771] Specific example

[0772] For example, if a user frequently makes input errors in a particular business system, the server can identify the problem, and the emotion engine can determine the user's level of anxiety. Then, it can generate a personalized solution in the form of an explanatory video and send it to the user via email. This kind of flexible solution provision improves operational efficiency.

[0773] Example of a prompt

[0774] "After the new system is implemented, analyze the reasons for user confusion and suggest what kind of information would help them understand it."

[0775] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0776] Step 1:

[0777] The terminal collects information about issues reported by users in the business system. Specifically, it collects user operation history, input error logs, and error messages. This input information is temporarily stored on the terminal and sent to the server. The collected log data is then generated as output.

[0778] Step 2:

[0779] The server receives log data sent from the terminal and preprocesses it. The input data includes raw data such as operation history and error logs. Specific data processing involves imputing missing data and filtering irrelevant data to generate a clean dataset. The output is data in a state ready for analysis.

[0780] Step 3:

[0781] The server analyzes the pre-processed data. The input data includes clean operation history and error logs. Natural language processing techniques are used to perform data calculations on this data to identify frequent problem patterns and common failures. Specifically, text data is tokenized, and highly relevant keywords are extracted. A list of identified problems is generated as output.

[0782] Step 4:

[0783] The emotion engine performs sentiment analysis based on user behavior logs and analyzed data. Input data includes the user's action speed and frequency. Specifically, it analyzes this data to quantify stress and dissatisfaction levels. The output is an analysis result indicating the user's emotional state.

[0784] Step 5:

[0785] The server generates solutions using a generative AI model based on the results of problem analysis and sentiment analysis. Input includes data on identified problems and the user's emotional state. Specifically, prompts are sent to a generative AI model such as GPT-3 to request solutions. The output is a customized solution proposal.

[0786] Step 6:

[0787] The server notifies relevant organizations and users of the generated solutions. Based on the input solutions, it converts them into a format that suits the user's emotional state, such as an operation guide or video manual. The output is information provided in an easy-to-understand format.

[0788] Step 7:

[0789] Users implement business improvement measures based on the solutions they receive. Specifically, they can improve work efficiency by trying out the countermeasures when problems arise, while referring to the provided guides. This promotes the continuous development of the latest and most optimal business improvements.

[0790] (Application Example 2)

[0791] 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".

[0792] In modern online retail systems, support for user problems is uniform and does not address the individual emotional state of each user. As a result, users often become dissatisfied, hindering the quick and effective resolution of problems. Addressing this challenge is crucial.

[0793] 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.

[0794] In this invention, the server includes means for collecting information on challenges that users find difficult to overcome, means for analyzing the collected information and identifying common obstacles, and means for recognizing the user's emotional state and adjusting the solution means accordingly. This enables personalized responses that are tailored to the user's emotional state.

[0795] "Difficult-to-solve challenges" refer to problems that users deem difficult to solve using conventional means or existing knowledge.

[0796] "Means of collecting information" refers to devices or software that have the function of collecting data on user operations, inputs, and errors.

[0797] "Means of analyzing information and identifying common problems" refers to analytical processes and techniques used to find patterns of related problems and issues based on collected information.

[0798] "Means for generating solutions" refers to a mechanism for designing and proposing effective countermeasures or improvement measures for identified problems.

[0799] "Means of informing relevant organizations" refers to methods or systems for notifying the appropriate organizations or departments of the generated solutions and for sharing information.

[0800] "Means of recognizing a user's emotional state" refers to technologies that infer and evaluate a user's emotions from their behavior and input data.

[0801] "Providing communication methods" refers to the act of selecting and presenting the most appropriate form and method of information transmission according to the user's emotional state and needs.

[0802] To implement this application, the server first collects information from the terminal about the difficult challenges the user encounters. This information includes the user's operation history and input error information. The collected information is then analyzed by the server using natural language processing technology to identify common problems.

[0803] Next, the server generates solutions to the identified problems. Since the user's emotional state is a crucial factor in this process, an emotion engine is used to estimate the user's emotions from their behavior and optimize the solutions accordingly. For example, if the user is feeling anxious, the solutions are adjusted to be more intuitive and easier to understand.

[0804] The generated solutions are not only communicated to the relevant organizations, but are also directly provided to users through a variety of information dissemination methods. For example, communication methods that match the user's emotional state are selected, such as video guides or user-friendly, conversational guidance.

[0805] Software used to perform emotion recognition and natural language processing includes EmotionEngine and NLPProcessor. These are important tools for effectively analyzing collected data and accurately assessing the user's emotional state.

[0806] As a concrete example, consider a scenario where an error occurs during the user's purchase process on an e-commerce site. When frustration is detected from the user's input, the server suggests a user-friendly video guide to reassure the user and support the resolution of the problem. An example of a prompt for the generative AI model is, "How should we alleviate user frustration with e-commerce site error messages?"

[0807] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0808] Step 1:

[0809] The terminal collects information about the user's operation history and input errors. This input information is sent to the server and stored in a database. The collected information includes product selection, errors during the purchase flow, and screen transition history.

[0810] Step 2:

[0811] The server receives the collected information and performs analysis using natural language processing (NLP) techniques. Specifically, it uses an NLP Processor to extract common failures and problem patterns from the data. The input is the user data collected in step 1, and the output is the common failure points identified through the analysis.

[0812] Step 3:

[0813] The server generates solutions to the identified problems based on the analysis results. In this process, it uses EmotionEngine to infer the user's emotional state. The input is the output from step 2 plus data about the user's emotions, and the output is a personalized solution. This could include, for example, video guides or FAQ suggestions.

[0814] Step 4:

[0815] The server notifies relevant organizations and users of the generated solutions. As a specific communication method, it provides user-friendly messages and guides tailored to the user's emotions. The input is the solution generated in step 3, and the output is information as a notification to the user or stakeholders.

[0816] Step 5:

[0817] The user receives information from the server and solves the problem by following the instructions. It is expected that the information provided will be helpful and reduce the user's anxiety and frustration. User feedback will be reflected in subsequent data analysis. The input is the notification from the server, and the output is the user's problem-solving actions.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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."

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] The following is further disclosed regarding the embodiments described above.

[0840] (Claim 1)

[0841] A means of collecting data on problems that are difficult to solve,

[0842] A means of analyzing collected data to identify common bottlenecks,

[0843] A means of generating solutions for identified bottlenecks,

[0844] A means of notifying relevant organizations of the generated solutions,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, wherein the collected data is analyzed using natural language processing technology.

[0848] (Claim 3)

[0849] The system according to claim 1, which provides the generated solutions in various formats.

[0850] "Example 1"

[0851] (Claim 1)

[0852] A means of collecting information on difficult-to-solve problems that arise with business support devices,

[0853] A means of analyzing collected information to identify common issues,

[0854] A means of generating solutions to identified problems,

[0855] A means of notifying relevant organizations of the generated solutions,

[0856] A means of attempting to improve operations using the generated solutions,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, which analyzes the information using language processing technology based on the information collected.

[0860] (Claim 3)

[0861] The system according to claim 1, which provides the generated solution in a different format.

[0862] "Application Example 1"

[0863] (Claim 1)

[0864] Means for collecting information on problems that are difficult to solve,

[0865] A means of analyzing the collected information to identify common failure factors,

[0866] A means for generating solutions to identified failure factors,

[0867] A means of notifying relevant organizations of the generated solutions,

[0868] A means of collecting data from an automated vehicle in real time and transmitting it to a cloud system,

[0869] A means of analyzing collected data and proposing adjustments to the control algorithm using an AI model,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, which analyzes data based on the information collected and uses a generating AI model.

[0873] (Claim 3)

[0874] The system according to claim 1, which provides the generated solutions in various formats and proposes alternative routes after the problem has been identified.

[0875] "Example 2 of combining an emotion engine"

[0876] (Claim 1)

[0877] A means of collecting information on difficult-to-solve challenges from data terminals,

[0878] A means for preprocessing the collected information,

[0879] A means of analyzing pre-processed information using analytical techniques to identify common problems,

[0880] A means of analyzing user sentiment,

[0881] A means of generating solutions based on identified problems and the user's emotional state,

[0882] Means for notifying relevant organizations of the generated solutions and providing them in various formats,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, wherein language processing techniques are used in the preprocessing and analysis of the aforementioned data.

[0886] (Claim 3)

[0887] The system according to claim 1, which utilizes a generative model in the process of generating the aforementioned solution.

[0888] "Application example 2 when combining with an emotional engine"

[0889] (Claim 1)

[0890] Means for collecting information on difficult-to-achieve challenges,

[0891] A means of analyzing the collected information to identify common problems,

[0892] A means for generating solutions to identified problems,

[0893] A means of informing relevant organizations of the generated solutions,

[0894] A means of recognizing the user's emotional state and adjusting the solution based on it,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, which analyzes the information using natural language processing technology based on the information collected and optimizes the solution taking into account the user's emotions.

[0898] (Claim 3)

[0899] The system according to claim 1, which provides the generated solution in various formats and offers a communication method suitable for the user's emotional state. [Explanation of symbols]

[0900] 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 data on problems that are difficult to solve, A means of analyzing collected data to identify common bottlenecks, A means of generating solutions for identified bottlenecks, A means of notifying relevant organizations of the generated solutions, A system that includes this.

2. The system according to claim 1, wherein the collected data is analyzed using natural language processing technology.

3. The system according to claim 1, which provides the generated solution as information in various formats.

Images