system

Abstract

We provide the system. [Solution] A means for receiving unresolved problems from multiple intelligent agents using natural language processing technology, analyzing the problems, and identifying common obstacles, A means for generating recommendations based on identified failure factors using generative artificial intelligence technology, Means for notifying relevant organizations of the recommendations, A means of instantly inputting problems via a mobile terminal and distributing 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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] The problem to be solved by the present invention is to provide a comprehensive method for efficiently and effectively solving problems in areas where individual agents cannot solve alone, for the difficult-to-realize problems faced when a large number of artificial intelligence agents perform tasks. Specifically, it aims to improve the convenience of customer service and public services by grasping bottlenecks in business processes and taking appropriate measures promptly.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a means for receiving unresolved problems from multiple artificial intelligence agents using natural language processing technology, analyzing them, and identifying common failure points. Furthermore, it includes a means for generating proposals based on the identified failure points using generative artificial intelligence technology and notifying relevant parties. This provides information to quickly resolve problems faced by artificial intelligence agents and improves the overall efficiency of the system. It also includes a mechanism for receiving feedback based on the generated proposals and analyzing that feedback to continuously improve the system.

[0006] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, including the analysis of text data and the extraction of meaning.

[0007] An "artificial intelligence agent" is a program that operates to solve specific tasks or problems, and is autonomous software that performs its duties through its own judgment and learning.

[0008] "Generative artificial intelligence technology" is a technology that automatically generates new information and content based on given data and conditions.

[0009] "Unresolved issues" refer to matters or problems that have not been resolved at present and are hindering the performance of business operations.

[0010] A "point of failure" refers to a part of a system or process that malfunctions or hinders efficiency, and is a factor that disrupts the flow of business operations.

[0011] A "proposal" refers to a solution or improvement plan devised to solve a specific problem.

[0012] "Related organizations" refers to organizations or institutions that are involved with a particular problem or issue and are capable of implementing or affected by solutions to it.

[0013] "Feedback" refers to evaluations and opinions on generated suggestions and measures, and is information used to improve systems and processes. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The system of the present invention effectively collects and analyzes unresolved problems processed by multiple artificial intelligence agents, generates solutions based on these analyses, and provides them to relevant organizations. An embodiment of this system is shown below.

[0036] The server receives problem data from each artificial intelligence agent. During this receiving process, unresolved problems are periodically sent via the API, and the server stores them in a temporary data buffer. Accuracy is maintained by checking for data duplication and format consistency.

[0037] Next, the server systematically classifies the stored problem data into a database based on business category and frequency of occurrence. This enables efficient data management and establishes a foundation for problem analysis.

[0038] Next, the server utilizes natural language processing technology to explore frequently occurring themes and failure points in the problem data. This identifies major bottlenecks and highlights critical issues that require attention.

[0039] Subsequently, the server uses generative artificial intelligence technology to generate specific proposals from the analysis results. This proposal generation process can utilize various data formats and output as text, images, and videos.

[0040] As a concrete example, consider a problem in the travel industry. When a user tries to plan a trip, an AI agent attempts to optimize flight bookings, but a problem arises where there are no suitable flights for the desired time slot. This problem is collected on a server, and frequency analysis reveals trends in demand for specific time slots. Based on this information, the server generates suggestions for new flights or alternative options and notifies the relevant airlines.

[0041] Finally, the server notifies relevant organizations of the generated proposals via email and dashboards, and receives feedback. Through this feedback, stakeholders can evaluate the feasibility and effectiveness of the proposals and use it to further improve the system.

[0042] As a result, the system of the present invention provides a comprehensive platform for rapidly resolving problems faced by artificial intelligence agents and can improve the quality of services in various industries.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives problem data from each artificial intelligence agent. The data sent from the agents via the API includes metadata such as problem details, date and time of occurrence, and related business information. The server stores this data in a temporary data buffer and performs duplicate checks and format consistency verification.

[0046] Step 2:

[0047] The server classifies received problem data based on business category and frequency before saving it to the database. The server uses a category classification algorithm to assign problems to the appropriate categories and adds tags to facilitate searching.

[0048] Step 3:

[0049] The server utilizes a natural language processing engine to analyze stored problem data. This analysis extracts frequently occurring keywords and phrases and identifies common failure points. The analysis results provide fundamental information to clarify the root cause of the problem.

[0050] Step 4:

[0051] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. These suggestions are generated as specific solutions or improvement proposals and are expressed in data formats such as text, images, and videos.

[0052] Step 5:

[0053] The server notifies relevant organizations and individuals of the generated proposals. These notifications are delivered via email or a dedicated dashboard, and the notification format can be customized upon request. The notification includes an overview of the solution and instructions for implementation.

[0054] Step 6:

[0055] Users, as affiliated organizations, access the system's dashboard to review the proposed ideas. Users evaluate the feasibility of the proposals and provide feedback for implementation as needed.

[0056] Step 7:

[0057] The server analyzes the received feedback and records the effectiveness of the suggestions and areas for improvement. This feedback information is incorporated into the system's improvement cycle and used to enhance the accuracy of the suggestion generation algorithm.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In modern society, there is a demand to respond quickly and effectively to unresolved issues by utilizing information processing technology. However, existing systems have suffered from issues such as duplication of issues received from different information processing devices, inconsistent formats, and problems with the speed and accuracy of generating and implementing appropriate proposals. Furthermore, the effective use of feedback on generated proposals and its link to system improvement has not been sufficiently implemented.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for receiving unresolved issues from multiple information processing devices using natural language processing technology, analyzing the issues to identify common problems, generating proposals based on the identified problems using generative artificial intelligence technology, and notifying relevant organizations of the proposals. This enables effective management and analysis of unresolved issues, rapid generation and notification of appropriate proposals, and continuous improvement of the system through the use of feedback.

[0063] "Natural language processing technology" refers to technologies for handling human language using computers, and includes techniques for analyzing text data and understanding its meaning and structure.

[0064] An "information processing device" is a machine designed to process data, and refers to computers, servers, and other devices that have functions for calculation and data management.

[0065] "Unresolved issues" refer to problems or obstacles for which solutions have not yet been found, and which require processing or action.

[0066] "Generative artificial intelligence technology" is a general term for algorithms and models that have the ability to generate text, images, and other data based on input information.

[0067] "Related organizations" refers to groups or companies that share specific objectives or activities, and are the organizations to which generated proposals and information will be notified.

[0068] A "proposal" refers to a specific plan or proposal offered to improve or resolve an identified problem.

[0069] "Feedback" refers to a response or evaluation of a received suggestion, including information for further improvement or modification.

[0070] This system consists of a server, multiple terminals, and users, and each device works together to identify and analyze unresolved issues and propose solutions.

[0071] The server receives unresolved issues from terminals, which are information processing devices. Specifically, the terminals transmit data through their built-in communication modules, and this data is temporarily stored on the server. The server checks the received data for duplication and format consistency, and then classifies the data based on these criteria. This classification uses business categories and frequency of occurrence, and is systematized in a management database. In this process, a management system that is standardly used as server software is employed.

[0072] Natural language processing (NLP) techniques will be used to analyze the problem data. Specifically, open-source NLP libraries (e.g., spaCy and NLTK) will be used to perform text analysis and topic modeling, thereby highlighting common problems.

[0073] Generative AI models are used to generate proposals based on the analyzed data. These models possess text generation capabilities, for example, employing natural language generation techniques as part of their generation algorithms. As a result, the server generates proposals in text and image formats and includes communication capabilities to disseminate them to relevant organizations.

[0074] As a concrete example, consider a problem users encounter in the travel industry. When a user tries to book a flight and cannot find a flight at their desired time, this information is sent from the terminal to the server. The server analyzes this problem, understands the demand for that time slot, and generates suggestions for new flights. Subsequently, the relevant airlines are notified, and the feasibility of the suggestions is evaluated.

[0075] An example of a prompt might be: "Collect unresolved issues regarding flight booking optimization in the travel industry and analyze the needs using natural language processing techniques. Based on the analysis results, generate new flight suggestions and notify the relevant airlines."

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

[0077] Step 1:

[0078] The terminal receives unresolved issue data as input from the user. This data is in text format and includes specific issues such as flight reservations. The terminal sends this data to the server using a communication protocol.

[0079] Step 2:

[0080] The server receives task data sent from the terminal via the API and temporarily stores it in a data buffer. The server interprets the received data in JSON format and checks for data duplication and format consistency. Data that has been verified for consistency is passed on to the next processing step.

[0081] Step 3:

[0082] The server classifies consistent data based on business categories and frequency of occurrence. A database management system is used to place data into predefined categories. This data classification enables efficient management and subsequent data analysis.

[0083] Step 4:

[0084] The server analyzes the classified data using natural language processing (NLP) techniques. Specifically, it uses an NLP library to extract common problems and themes. The information extracted from the input data is evaluated based on its importance.

[0085] Step 5:

[0086] The server uses a generative AI model to generate suggestions based on the identified problems. The server provides pre-configured prompts to the generative AI model and retrieves the suggested content as output. The suggestions are output in text or image format.

[0087] Step 6:

[0088] The server notifies the relevant organizations of the generated proposals via email or a dashboard. This communication method is used to configure the addresses for receiving the generated proposals and the permissions to access the dashboard.

[0089] Step 7:

[0090] Users receive and evaluate feedback from relevant organizations. Based on this feedback, the server improves the proposals and adjusts the system to further optimize it.

[0091] (Application Example 1)

[0092] 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."

[0093] The problem that this invention aims to solve is to support immediate problem-solving on-site and improve the efficiency of the entire organization. In particular, there has been a lack of sufficient means to quickly aggregate and analyze issues from multiple intelligent agents and provide optimal solutions to the relevant organizations and personnel. This has led to demands for improved customer satisfaction and optimization of business processes.

[0094] 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.

[0095] This invention includes a server that utilizes natural language processing technology to receive unresolved issues from multiple intelligent agents, analyzes the issues to identify common failure factors, generates recommendations based on the identified failure factors using generative artificial intelligence technology, notifies relevant organizations of the recommendations, and immediately inputs issues via mobile terminals and distributes solutions. This enables rapid response to on-site problems and improves the overall efficiency of the organization.

[0096] "Natural language processing technology" is a technology that enables computers to understand and process human language.

[0097] An "intelligent agent" is a program or system that processes information independently and performs specific tasks.

[0098] A "problem" is an unresolved issue or a matter that needs to be resolved.

[0099] "Obstacle factors" are elements that cause problems or act as bottlenecks.

[0100] "Generative artificial intelligence technology" is an artificial intelligence technology that automatically generates new information and suggestions based on data.

[0101] A "recommendation" is a solution or policy proposed based on identified information.

[0102] "Relevant organizations" refer to institutions or groups that are responsible for accepting and responding to the generated recommendations.

[0103] A "mobile terminal" is a device that is portable and can be operated on-site.

[0104] "Real-time input" refers to the act of entering information in real time at the site.

[0105] A "solution" is a proposed method of dealing with a specific problem.

[0106] In the system that implements this application, a server plays a central role. The server uses natural language processing techniques to analyze unresolved issues collected from multiple intelligent agents. This allows the server to identify common failure factors. Subsequently, generative artificial intelligence techniques are used to generate recommendations based on the identified failure factors.

[0107] Mobile terminals, such as smartphones, are devices for users to input information instantly. Using these terminals, users can input problems that arise on-site via voice or text. The data is sent to a cloud server, where the received problems are analyzed in real time.

[0108] The server manages data using AWS® RDS and analyzes key themes and bottlenecks from input text using Amazon Comprehend. Based on the analysis results, the server generates solutions using a generative AI model such as ChatGPT® and delivers them to the user's terminal in text format.

[0109] For example, if a store staff member is asked by a customer about the availability of a particular product, they can input "Is this product in stock?" into an application on their smartphone. The server will then immediately analyze the data and provide recommendations, including "It's in stock at a nearby store" and "The next shipment is due soon."

[0110] An example of a prompt in a generative AI model would be a sentence like, "A customer has inquired about product inventory at the store. Please automatically generate a solution."

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

[0112] Step 1:

[0113] The device receives task data entered by the user via voice or text and sends it to a cloud server. The input includes specific problems or questions that require resolution. This data is received in real time.

[0114] Step 2:

[0115] The server saves issue data received on the cloud to Amazon RDS. During saving, data duplication checks and format consistency checks are performed to maintain accurate information. This ensures that issues are registered in the database in an organized format.

[0116] Step 3:

[0117] The server analyzes issue data stored using Amazon Comprehend to identify recurring themes and bottlenecks. The input is structured issue data, and the output includes classifications of identified themes and problems. This analysis is performed using advanced natural language processing techniques.

[0118] Step 4:

[0119] The server uses a generative AI model, such as ChatGPT, to generate recommendations based on the analysis results. This process generates specific solutions and recommendations based on themes and bottlenecks. The input is the analyzed data, and the output is the generated suggestions. Prompts such as "Generate solutions for this problem" are used.

[0120] Step 5:

[0121] The server sends solutions based on the generated recommendations to the terminal. The information displayed on the terminal includes recommendations in a format that the user can immediately understand and act upon. This on-screen display enables the user to make quick decisions in the field.

[0122] 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.

[0123] This invention is a system that employs an emotion engine to recognize user emotions, analyzes unresolved problems collected by an artificial intelligence agent, generates suggestions, and provides notifications. This system aims to provide more effective and personalized solutions by tailoring suggestions based on emotions.

[0124] The server first receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details as well as related business information. The server stores this data in a temporary data buffer and verifies its integrity.

[0125] Next, the server analyzes the problem data using natural language processing technology and identifies common failure points. Based on the insights gained, it uses generative AI to generate specific suggestions.

[0126] A key feature here is the use of an emotion engine. The emotion engine allows the server to acquire the user's emotional state in real time and adjust the suggestions generated based on this information. For example, if a user is feeling dissatisfied, the content and expression of the suggestions can be changed to be more polite and approachable.

[0127] As a concrete example, consider an AI agent in the travel industry. If a user encounters a problem where their desired flight is fully booked and unavailable, the server analyzes the issue and suggests alternative flights or modes of transport at special prices. If the emotion engine detects user disappointment, it will add special offers and additional support information to the suggestions, implementing measures to alleviate the user's frustration.

[0128] After a proposal is generated, the server notifies the relevant organizations and individuals. Notifications are sent via email or a dashboard, from which users can review the proposal details.

[0129] Users evaluate the provided suggestions and send feedback to the server. This feedback includes the success rate of implementing the suggestions and areas for further improvement. The server analyzes this feedback and uses it to tune the sentiment engine and improve the suggestion generation algorithm.

[0130] Thus, the present invention utilizes an emotion engine to provide a flexible and sophisticated solution for enhancing the user experience.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details, the circumstances under which it occurred, and the relevant business context. This data is stored in a temporary data buffer, where duplicate checks and data format consistency verification are performed.

[0134] Step 2:

[0135] The server classifies received problem data into a database based on business category and frequency of occurrence. Using a category classification algorithm, it assigns each problem to the appropriate category and tags it to improve searchability.

[0136] Step 3:

[0137] The server utilizes natural language processing technology to analyze problem data stored in the database. This analysis identifies common failure points through frequency analysis and keyword extraction, thereby revealing the root cause of the problem.

[0138] Step 4:

[0139] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. The generated suggestions are presented in various formats, such as text, images, and videos, in a way that is easy for the user to understand.

[0140] Step 5:

[0141] The server utilizes an emotion engine that recognizes the user's emotions in real time and adjusts the content of the generated suggestions. By acquiring data on the user's emotional state and adapting the expression and content of the suggestions, it provides more appropriate and effective solutions.

[0142] Step 6:

[0143] The server notifies relevant organizations and individuals of the generated proposals. Notifications are sent via email or a dedicated dashboard, and the content of the notifications can be customized. This allows stakeholders to review the proposals in detail and develop implementation plans.

[0144] Step 7:

[0145] Users review the proposals they receive and provide feedback to the server. This feedback includes evaluations of the feasibility and effectiveness of the proposals.

[0146] Step 8:

[0147] The server analyzes user feedback and uses it to improve the emotion engine settings and suggestion generation algorithms. This allows the system to continuously evolve and improve the user experience.

[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] Traditional systems struggle to provide personalized solutions tailored to individual emotional states in response to unresolved user issues, resulting in insufficient personalized responses necessary to improve the user experience. Furthermore, a lack of rapid suggestion generation and notification makes it difficult to resolve user dissatisfaction. Additionally, the insufficient means of efficiently using received feedback to improve the system makes daily optimization challenging.

[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 receiving and analyzing unresolved problems from multiple intelligent systems using natural language processing technology, means for generating suggestions based on identified fault points using generative artificial intelligence technology, and means for using an emotion processing engine that acquires the user's emotional state in real time and adjusts the generated suggestions based on the emotional state. This makes it possible to quickly provide detailed suggestions tailored to each user's emotional state and to improve the system based on the received feedback.

[0153] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0154] An "intelligent system" is an automated system equipped with sophisticated computational models for processing data and making decisions and solving problems.

[0155] An "unresolved issue" is a challenge or requirement that users or systems face but for which an appropriate solution has not yet been provided.

[0156] "Generative artificial intelligence technology" refers to technologies that use artificial intelligence to generate new data and proposals.

[0157] A "point of failure" refers to the element or location within a particular process or system that causes a problem to occur.

[0158] An "emotion processing engine" is a specialized technology that analyzes the user's emotional state in real time and adjusts responses and suggestions based on the information obtained.

[0159] "Related organizations" refer to organizations or individuals responsible for making decisions or taking actions based on the generated proposals.

[0160] A "classification algorithm" refers to a method or process for organizing and classifying data into categories based on specific criteria.

[0161] This invention aims to enable a server to receive unresolved problems from various intelligent systems, analyze them, and identify common points of failure. The server utilizes natural language processing techniques to perform this process. Specifically, it uses machine learning frameworks such as TENSORFLOW® and PyTorch to analyze the received text data.

[0162] Based on the insights gained from the analysis, the server generates suggestions using a generative artificial intelligence model. This process employs advanced generative AI models such as OpenAI's GPT. To refine the generated suggestions, the server obtains the user's emotional state in real time through an emotion processing engine. This data is obtained by analyzing the user's input text and voice data using an emotion recognition API.

[0163] As a concrete example, consider a travel agency's support system. Suppose a user's desired flight is fully booked and unavailable. In this case, the server can analyze the problem and suggest alternative options, such as other flights or ground transportation to the same destination at a special price. Furthermore, if the emotion processing engine detects user disappointment, it can add special offers or additional support information to the suggestions, thereby improving user satisfaction.

[0164] Once a proposal is generated, the server notifies the relevant organizations and individuals via email or a dashboard. Users can review the proposed proposal and provide feedback through this notification. This feedback is analyzed by the server to help it continuously improve the system. For example, a prompt such as, "How should the proposal be adjusted if the user is dissatisfied with the service?" can be input into the AI ​​model, and better proposals will be provided based on the response.

[0165] In this way, by integrating diverse technologies, servers can quickly deliver personalized solutions and improve the user experience.

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

[0167] Step 1:

[0168] The server receives unresolved problem data from each intelligent system via an API. Input includes problem details and related operational information. Specifically, the server receives an HTTP request and stores the problem data in a temporary data buffer. Output is a dataset in a consistent format.

[0169] Step 2:

[0170] The server verifies the integrity of the stored data. The input for this step is all the problematic data in the temporary data buffer. It checks whether the data format conforms to the specifications and whether all necessary fields are present. Specifically, it performs JSON schema validation and checks for required fields. The output is the dataset whose integrity has been verified.

[0171] Step 3:

[0172] The server analyzes the problem data using natural language processing techniques to identify common failure points. The input for this step is consistent problem data. The server extracts keywords and context from the problem data and performs text mining, for example, using SpaCy or NLTK. The output is the identified failure points and selected key keywords.

[0173] Step 4:

[0174] The server generates suggestions using generative artificial intelligence technology based on identified fault points. It uses analysis results and identified fault points as input. Specifically, the server inputs prompts into a generative AI model (e.g., a GPT model) and retrieves suggestions from the model. The output is a specific suggestion for the user.

[0175] Step 5:

[0176] The server uses an emotion processing engine to acquire the user's emotional state and adjust the generated suggestions according to that emotion. The input for this step is real-time data about the user's emotions (e.g., text or voice analysis results). Using the API provided by the emotion processing engine, the server identifies the user's current psychological state and optimizes the expression and content of the suggestions. The output is the adjusted suggestions for the user.

[0177] Step 6:

[0178] The server notifies relevant organizations and individuals of the generated proposals via email and a dashboard. The input is the final, adjusted proposal content. Specifically, the server communicates with the mail server to send emails and calls the dashboard update API to provide real-time notifications. The output is a state where the proposals have been reliably notified to the relevant parties.

[0179] Step 7:

[0180] Users evaluate the provided suggestions and submit feedback to the server. The input for this step consists of user ratings and comments. User opinions are collected using feedback forms and surveys. The output is the received feedback data.

[0181] Step 8:

[0182] The server analyzes the received feedback and uses it to improve the system. The input for this step is user feedback data. The server analyzes the collected data and uses it to tune the algorithms and sentiment recognition. The output is the improvement plan and specific implementation items.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0185] Traditional problem-solving systems offer uniform suggestions without considering user emotions, resulting in limited user satisfaction. Furthermore, suggestions for unresolved issues are often roundabout or mismatched with the user's emotional state, making it difficult to improve the customer support experience. A systematic approach to address this is needed.

[0186] 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.

[0187] In this invention, the server includes means for receiving unresolved problems from multiple intelligent programs using natural language processing technology, analyzing the problems and identifying common failure points, using an emotion engine that adjusts the generated suggestions based on the user's emotional state, and notifying relevant organizations of the generated suggestions. This makes it possible to provide personalized suggestions that take the user's emotions into consideration.

[0188] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0189] An "intelligent program" is software that uses artificial intelligence to autonomously perform specific tasks.

[0190] A "point of failure" refers to the cause or factor that is leading to an unresolved problem.

[0191] "Generative artificial intelligence technology" is an artificial intelligence technology that can generate new proposals and ideas from data.

[0192] An "emotion engine" is a technology for measuring and understanding a user's emotional state.

[0193] "Related organizations" refers to the organizations or individuals who should receive the generated proposals and notifications.

[0194] The system realizing this invention mainly consists of a server, terminals, and a user. The server uses natural language processing technology to analyze unresolved problems received from terminals through multiple intelligent programs and identifies common fault points. The software used here leverages natural language processing libraries and APIs. The server also uses generative artificial intelligence technology to generate appropriate suggestions for the user based on the identified fault points. A generative AI model is used in this generation process.

[0195] Furthermore, the server is equipped with an emotion engine that senses the user's emotional state in real time and adjusts its suggestions accordingly. The emotion engine interprets data from the user using software such as an emotion analysis API. For example, if a user fails to book a flight, the server can offer alternatives and include additional benefits or information to alleviate the user's dissatisfaction. In this way, it provides personalized solutions that respond to the user's emotions.

[0196] As a concrete example, consider the problem of delays in logistics. The server receives delay information, identifies the cause of the problem, and proposes appropriate solutions. This system can also further optimize its suggestions based on user feedback.

[0197] An example of a prompt message is, "Suggest how to report to and follow up with a customer who is frustrated because their product hasn't arrived." The aim is to provide a more meaningful experience for the user.

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The server receives unresolved issues from terminals through multiple intelligent programs. The received data contains details of the issues reported by users, and the server temporarily stores this in a data buffer. This process includes integrity checks to verify the accuracy of the data.

[0201] Step 2:

[0202] The server analyzes unresolved problems stored in a data buffer using natural language processing techniques. This identifies common failure points. Text analysis is performed based on the problem data as input, and a list of failure points is generated as output. Through this analysis, the structure of the problem is understood, and areas requiring correction are identified.

[0203] Step 3:

[0204] The server utilizes generative artificial intelligence technology to generate specific suggestions based on identified fault points. The generative AI model receives fault points as input and generates suggestions as output. The generated suggestions present concrete and practical methods for solving the user's problems.

[0205] Step 4:

[0206] The server uses an emotion engine to acquire the user's emotional state in real time and adjusts the generated suggestions according to the user's emotions. It receives emotional data as input and modifies the content and expression of the suggestions. This adjustment improves the user experience and increases the suggestion acceptance rate.

[0207] Step 5:

[0208] The server notifies the relevant parties of the finalized proposal. Notifications are made via email and a dashboard, converting the finalized proposal (as input) into notification messages (as output). This process is designed to ensure that necessary information is properly communicated to the relevant parties.

[0209] Step 6:

[0210] Users provide feedback based on suggestions provided by the server. This feedback includes details about the problem resolution status and the usefulness of the suggestions. This feedback is sent to the server, and the system uses the feedback data as input to make further improvements. The feedback helps optimize the emotion engine and generative AI model.

[0211] Through a clear data flow and processing at each step, we enable better suggestions and improved user experience based on user feedback regarding their problems.

[0212] 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.

[0213] 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 (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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] The system of the present invention effectively collects and analyzes unresolved problems processed by multiple artificial intelligence agents, generates solutions based on these analyses, and provides them to relevant organizations. An embodiment of this system is shown below.

[0229] The server receives problem data from each artificial intelligence agent. During this receiving process, unresolved problems are periodically sent via the API, and the server stores them in a temporary data buffer. Accuracy is maintained by checking for data duplication and format consistency.

[0230] Next, the server systematically classifies the stored problem data into a database based on business category and frequency of occurrence. This enables efficient data management and establishes a foundation for problem analysis.

[0231] Next, the server utilizes natural language processing technology to explore frequently occurring themes and failure points in the problem data. This identifies major bottlenecks and highlights critical issues that require attention.

[0232] Subsequently, the server uses generative artificial intelligence technology to generate specific proposals from the analysis results. This proposal generation process can utilize various data formats and output as text, images, and videos.

[0233] As a concrete example, consider a problem in the travel industry. When a user tries to plan a trip, an AI agent attempts to optimize flight bookings, but a problem arises where there are no suitable flights for the desired time slot. This problem is collected on a server, and frequency analysis reveals trends in demand for specific time slots. Based on this information, the server generates suggestions for new flights or alternative options and notifies the relevant airlines.

[0234] Finally, the server notifies relevant organizations of the generated proposals via email and dashboards, and receives feedback. Through this feedback, stakeholders can evaluate the feasibility and effectiveness of the proposals and use it to further improve the system.

[0235] As a result, the system of the present invention provides a comprehensive platform for rapidly resolving problems faced by artificial intelligence agents and can improve the quality of services in various industries.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server receives problem data from each artificial intelligence agent. The data sent from the agents via the API includes metadata such as problem details, date and time of occurrence, and related business information. The server stores this data in a temporary data buffer and performs duplicate checks and format consistency verification.

[0239] Step 2:

[0240] The server classifies received problem data based on business category and frequency before saving it to the database. The server uses a category classification algorithm to assign problems to the appropriate categories and adds tags to facilitate searching.

[0241] Step 3:

[0242] The server utilizes a natural language processing engine to analyze stored problem data. This analysis extracts frequently occurring keywords and phrases and identifies common failure points. The analysis results provide fundamental information to clarify the root cause of the problem.

[0243] Step 4:

[0244] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. These suggestions are generated as specific solutions or improvement proposals and are expressed in data formats such as text, images, and videos.

[0245] Step 5:

[0246] The server notifies relevant organizations and individuals of the generated proposals. These notifications are delivered via email or a dedicated dashboard, and the notification format can be customized upon request. The notification includes an overview of the solution and instructions for implementation.

[0247] Step 6:

[0248] Users, as affiliated organizations, access the system's dashboard to review the proposed ideas. Users evaluate the feasibility of the proposals and provide feedback for implementation as needed.

[0249] Step 7:

[0250] The server analyzes the received feedback and records the effectiveness of the suggestions and areas for improvement. This feedback information is incorporated into the system's improvement cycle and used to enhance the accuracy of the suggestion generation algorithm.

[0251] (Example 1)

[0252] 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."

[0253] In modern society, there is a demand to respond quickly and effectively to unresolved issues by utilizing information processing technology. However, existing systems have suffered from issues such as duplication of issues received from different information processing devices, inconsistent formats, and problems with the speed and accuracy of generating and implementing appropriate proposals. Furthermore, the effective use of feedback on generated proposals and its link to system improvement has not been sufficiently implemented.

[0254] 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.

[0255] In this invention, the server includes means for receiving unresolved issues from multiple information processing devices using natural language processing technology, analyzing the issues to identify common problems, generating proposals based on the identified problems using generative artificial intelligence technology, and notifying relevant organizations of the proposals. This enables effective management and analysis of unresolved issues, rapid generation and notification of appropriate proposals, and continuous improvement of the system through the use of feedback.

[0256] "Natural language processing technology" refers to technologies for handling human language using computers, and includes techniques for analyzing text data and understanding its meaning and structure.

[0257] An "information processing device" is a machine designed to process data, and refers to computers, servers, and other devices that have functions for calculation and data management.

[0258] "Unresolved issues" refer to problems or obstacles for which solutions have not yet been found, and which require processing or action.

[0259] "Generative artificial intelligence technology" is a general term for algorithms and models that have the ability to generate text, images, and other data based on input information.

[0260] "Related organizations" refers to groups or companies that share specific objectives or activities, and are the organizations to which generated proposals and information will be notified.

[0261] A "proposal" refers to a specific plan or proposal offered to improve or resolve an identified problem.

[0262] "Feedback" refers to a response or evaluation of a received suggestion, including information for further improvement or modification.

[0263] This system consists of a server, multiple terminals, and users, and each device works together to identify and analyze unresolved issues and propose solutions.

[0264] The server receives unresolved issues from terminals, which are information processing devices. Specifically, the terminals transmit data through their built-in communication modules, and this data is temporarily stored on the server. The server checks the received data for duplication and format consistency, and then classifies the data based on these criteria. This classification uses business categories and frequency of occurrence, and is systematized in a management database. In this process, a management system that is standardly used as server software is employed.

[0265] Natural language processing (NLP) techniques will be used to analyze the problem data. Specifically, open-source NLP libraries (e.g., spaCy and NLTK) will be used to perform text analysis and topic modeling, thereby highlighting common problems.

[0266] Generative AI models are used to generate proposals based on the analyzed data. These models possess text generation capabilities, for example, employing natural language generation techniques as part of their generation algorithms. As a result, the server generates proposals in text and image formats and includes communication capabilities to disseminate them to relevant organizations.

[0267] As a concrete example, consider a problem users encounter in the travel industry. When a user tries to book a flight and cannot find a flight at their desired time, this information is sent from the terminal to the server. The server analyzes this problem, understands the demand for that time slot, and generates suggestions for new flights. Subsequently, the relevant airlines are notified, and the feasibility of the suggestions is evaluated.

[0268] An example of a prompt might be: "Collect unresolved issues regarding flight booking optimization in the travel industry and analyze the needs using natural language processing techniques. Based on the analysis results, generate new flight suggestions and notify the relevant airlines."

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] The terminal receives unresolved issue data as input from the user. This data is in text format and includes specific issues such as flight reservations. The terminal sends this data to the server using a communication protocol.

[0272] Step 2:

[0273] The server receives task data sent from the terminal via the API and temporarily stores it in a data buffer. The server interprets the received data in JSON format and checks for data duplication and format consistency. Data that has been verified for consistency is passed on to the next processing step.

[0274] Step 3:

[0275] The server classifies consistent data based on business categories and frequency of occurrence. A database management system is used to place data into predefined categories. This data classification enables efficient management and subsequent data analysis.

[0276] Step 4:

[0277] The server analyzes the classified data using natural language processing (NLP) techniques. Specifically, it uses an NLP library to extract common problems and themes. The information extracted from the input data is evaluated based on its importance.

[0278] Step 5:

[0279] The server uses a generative AI model to generate suggestions based on the identified problems. The server provides pre-configured prompts to the generative AI model and retrieves the suggested content as output. The suggestions are output in text or image format.

[0280] Step 6:

[0281] The server notifies the relevant organization of the generated proposal via email or a dashboard. Through this communication means, an address for receiving the generated proposal and access rights to the dashboard are set.

[0282] Step 7:

[0283] The user receives the feedback returned from the relevant organization and conducts an evaluation. Based on the feedback, the server implements improvements to the proposal and adjusts the system for further optimization.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] The problem to be solved by the present invention is to support immediate problem-solving at the site and improve the efficiency of the entire organization. In particular, there has not been a sufficient means to quickly aggregate and analyze issues from multiple intelligent agents and provide optimal solutions to relevant organizations and responsible persons. As a result, an improvement in customer satisfaction and optimization of the business process are required.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0288] This invention includes a server that utilizes natural language processing technology to receive unresolved issues from multiple intelligent agents, analyzes the issues to identify common failure factors, generates recommendations based on the identified failure factors using generative artificial intelligence technology, notifies relevant organizations of the recommendations, and immediately inputs issues via mobile terminals and distributes solutions. This enables rapid response to on-site problems and improves the overall efficiency of the organization.

[0289] "Natural language processing technology" is a technology that enables computers to understand and process human language.

[0290] An "intelligent agent" is a program or system that processes information independently and performs specific tasks.

[0291] A "problem" is an unresolved issue or a matter that needs to be resolved.

[0292] "Obstacle factors" are elements that cause problems or act as bottlenecks.

[0293] "Generative artificial intelligence technology" is an artificial intelligence technology that automatically generates new information and suggestions based on data.

[0294] A "recommendation" is a solution or policy proposed based on identified information.

[0295] "Relevant organizations" refer to institutions or groups that are responsible for accepting and responding to the generated recommendations.

[0296] A "mobile terminal" is a device that is portable and can be operated on-site.

[0297] "Real-time input" refers to the act of entering information in real time at the site.

[0298] A "solution" is a proposed method of dealing with a specific problem.

[0299] In the system that implements this application, a server plays a central role. The server uses natural language processing techniques to analyze unresolved issues collected from multiple intelligent agents. This allows the server to identify common failure factors. Subsequently, generative artificial intelligence techniques are used to generate recommendations based on the identified failure factors.

[0300] Mobile terminals, such as smartphones, are devices for users to input information instantly. Using these terminals, users can input problems that arise on-site via voice or text. The data is sent to a cloud server, where the received problems are analyzed in real time.

[0301] The server manages data using AWS RDS and analyzes key themes and bottlenecks from input text using Amazon Comprehend. Based on the analysis results, the server generates solutions using generative AI models such as ChatGPT and delivers them to the user's terminal in text format.

[0302] For example, if a store staff member is asked by a customer about the availability of a particular product, they can input "Is this product in stock?" into an application on their smartphone. The server will then immediately analyze the data and provide recommendations, including "It's in stock at a nearby store" and "The next shipment is due soon."

[0303] An example of a prompt in a generative AI model would be a sentence like, "A customer has inquired about product inventory at the store. Please automatically generate a solution."

[0304] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0305] Step 1:

[0306] The terminal receives the task data input by the user in voice or text and sends it to the cloud server. The input includes specific problems or questions for which solutions are sought. This data is received in real time.

[0307] Step 2:

[0308] The server saves the task data received on the cloud to Amazon RDS. When saving, duplicate data checking and format consistency verification are performed to maintain accurate information. As a result, the tasks are registered in an organized format in the database.

[0309] Step 3:

[0310] The server analyzes the saved task data using Amazon Comprehend to identify frequent themes and bottlenecks. The input is structured task data, and the output includes the identified theme and problem classification results. This analysis is performed using natural language processing technology.

[0311] Step 4:

[0312] The server uses a generative AI model such as ChatGPT to generate recommendations based on the analysis results. In this process, specific solutions and recommendations based on themes and bottlenecks are generated. The input is the analyzed data, and the output is the generated proposal. Prompt sentences such as "Please generate solutions for this problem." are used.

[0313] Step 5:

[0314] The server sends the solutions based on the generated recommendations to the terminal. The information displayed on the terminal includes recommendations in a format that the user can immediately understand and act upon. Through the display on the terminal, the user can make quick decisions on-site.

[0315] 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.

[0316] This invention is a system that employs an emotion engine to recognize user emotions, analyzes unresolved problems collected by an artificial intelligence agent, generates suggestions, and provides notifications. This system aims to provide more effective and personalized solutions by tailoring suggestions based on emotions.

[0317] The server first receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details as well as related business information. The server stores this data in a temporary data buffer and verifies its integrity.

[0318] Next, the server analyzes the problem data using natural language processing technology and identifies common failure points. Based on the insights gained, it uses generative AI to generate specific suggestions.

[0319] A key feature here is the use of an emotion engine. The emotion engine allows the server to acquire the user's emotional state in real time and adjust the suggestions generated based on this information. For example, if a user is feeling dissatisfied, the content and expression of the suggestions can be changed to be more polite and approachable.

[0320] As a concrete example, consider an AI agent in the travel industry. If a user encounters a problem where their desired flight is fully booked and unavailable, the server analyzes the issue and suggests alternative flights or modes of transport at special prices. If the emotion engine detects user disappointment, it will add special offers and additional support information to the suggestions, implementing measures to alleviate the user's frustration.

[0321] After a proposal is generated, the server notifies the relevant organizations and individuals. Notifications are sent via email or a dashboard, from which users can review the proposal details.

[0322] Users evaluate the provided suggestions and send feedback to the server. This feedback includes the success rate of implementing the suggestions and areas for further improvement. The server analyzes this feedback and uses it to tune the sentiment engine and improve the suggestion generation algorithm.

[0323] Thus, the present invention utilizes an emotion engine to provide a flexible and sophisticated solution for enhancing the user experience.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The server receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details, the circumstances under which it occurred, and the relevant business context. This data is stored in a temporary data buffer, where duplicate checks and data format consistency verification are performed.

[0327] Step 2:

[0328] The server classifies received problem data into a database based on business category and frequency of occurrence. Using a category classification algorithm, it assigns each problem to the appropriate category and tags it to improve searchability.

[0329] Step 3:

[0330] The server utilizes natural language processing technology to analyze problem data stored in the database. This analysis identifies common failure points through frequency analysis and keyword extraction, thereby revealing the root cause of the problem.

[0331] Step 4:

[0332] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. The generated suggestions are presented in various formats, such as text, images, and videos, in a way that is easy for the user to understand.

[0333] Step 5:

[0334] The server utilizes an emotion engine that recognizes the user's emotions in real time and adjusts the content of the generated suggestions. By acquiring data on the user's emotional state and adapting the expression and content of the suggestions, it provides more appropriate and effective solutions.

[0335] Step 6:

[0336] The server notifies relevant organizations and individuals of the generated proposals. Notifications are sent via email or a dedicated dashboard, and the content of the notifications can be customized. This allows stakeholders to review the proposals in detail and develop implementation plans.

[0337] Step 7:

[0338] Users review the proposals they receive and provide feedback to the server. This feedback includes evaluations of the feasibility and effectiveness of the proposals.

[0339] Step 8:

[0340] The server analyzes user feedback and uses it to improve the emotion engine settings and suggestion generation algorithms. This allows the system to continuously evolve and improve the user experience.

[0341] (Example 2)

[0342] 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".

[0343] Traditional systems struggle to provide personalized solutions tailored to individual emotional states in response to unresolved user issues, resulting in insufficient personalized responses necessary to improve the user experience. Furthermore, a lack of rapid suggestion generation and notification makes it difficult to resolve user dissatisfaction. Additionally, the insufficient means of efficiently using received feedback to improve the system makes daily optimization challenging.

[0344] 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.

[0345] In this invention, the server includes means for receiving and analyzing unresolved problems from multiple intelligent systems using natural language processing technology, means for generating suggestions based on identified fault points using generative artificial intelligence technology, and means for using an emotion processing engine that acquires the user's emotional state in real time and adjusts the generated suggestions based on the emotional state. This makes it possible to quickly provide detailed suggestions tailored to each user's emotional state and to improve the system based on the received feedback.

[0346] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0347] An "intelligent system" is an automated system equipped with sophisticated computational models for processing data and making decisions and solving problems.

[0348] An "unresolved issue" is a challenge or requirement that users or systems face but for which an appropriate solution has not yet been provided.

[0349] "Generative artificial intelligence technology" refers to technologies that use artificial intelligence to generate new data and proposals.

[0350] A "point of failure" refers to the element or location within a particular process or system that causes a problem to occur.

[0351] An "emotion processing engine" is a specialized technology that analyzes the user's emotional state in real time and adjusts responses and suggestions based on the information obtained.

[0352] "Related organizations" refer to organizations or individuals responsible for making decisions or taking actions based on the generated proposals.

[0353] A "classification algorithm" refers to a method or process for organizing and classifying data into categories based on specific criteria.

[0354] This invention aims to have a server receive unresolved problems from various intelligent systems, analyze them, and identify common points of failure. The server utilizes natural language processing techniques to perform this process. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the received text data.

[0355] Based on the insights gained from the analysis, the server generates suggestions using a generative artificial intelligence model. This process employs advanced generative AI models such as OpenAI's GPT. To refine the generated suggestions, the server obtains the user's emotional state in real time through an emotion processing engine. This data is obtained by analyzing user-input text and voice data using an emotion recognition API.

[0356] As a concrete example, consider a travel agency's support system. Suppose a user's desired flight is fully booked and unavailable. In this case, the server can analyze the problem and suggest alternative options, such as other flights or ground transportation to the same destination at a special price. Furthermore, if the emotion processing engine detects user disappointment, it can add special offers or additional support information to the suggestions, thereby improving user satisfaction.

[0357] Once a proposal is generated, the server notifies the relevant organizations and individuals via email or a dashboard. Users can review the proposed proposal and provide feedback through this notification. This feedback is analyzed by the server to help it continuously improve the system. For example, a prompt such as, "How should the proposal be adjusted if the user is dissatisfied with the service?" can be input into the AI ​​model, and better proposals will be provided based on the response.

[0358] In this way, by integrating diverse technologies, servers can quickly deliver personalized solutions and improve the user experience.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The server receives unresolved problem data from each intelligent system via an API. Input includes problem details and related operational information. Specifically, the server receives an HTTP request and stores the problem data in a temporary data buffer. Output is a dataset in a consistent format.

[0362] Step 2:

[0363] The server verifies the integrity of the stored data. The input for this step is all the problematic data in the temporary data buffer. It checks whether the data format conforms to the specifications and whether all necessary fields are present. Specifically, it performs JSON schema validation and checks for required fields. The output is the dataset whose integrity has been verified.

[0364] Step 3:

[0365] The server analyzes the problem data using natural language processing techniques to identify common failure points. The input for this step is consistent problem data. The server extracts keywords and context from the problem data and performs text mining, for example, using SpaCy or NLTK. The output is the identified failure points and selected key keywords.

[0366] Step 4:

[0367] The server generates suggestions using generative artificial intelligence technology based on identified fault points. It uses analysis results and identified fault points as input. Specifically, the server inputs prompts into a generative AI model (e.g., a GPT model) and retrieves suggestions from the model. The output is a specific suggestion for the user.

[0368] Step 5:

[0369] The server uses an emotion processing engine to acquire the user's emotional state and adjust the generated suggestions according to that emotion. The input for this step is real-time data about the user's emotions (e.g., text or voice analysis results). Using the API provided by the emotion processing engine, the server identifies the user's current psychological state and optimizes the expression and content of the suggestions. The output is the adjusted suggestions for the user.

[0370] Step 6:

[0371] The server notifies relevant organizations and individuals of the generated proposals via email and a dashboard. The input is the final, adjusted proposal content. Specifically, the server communicates with the mail server to send emails and calls the dashboard update API to provide real-time notifications. The output is a state where the proposals have been reliably notified to the relevant parties.

[0372] Step 7:

[0373] Users evaluate the provided suggestions and submit feedback to the server. The input for this step consists of user ratings and comments. User opinions are collected using feedback forms and surveys. The output is the received feedback data.

[0374] Step 8:

[0375] The server analyzes the received feedback and uses it to improve the system. The input for this step is user feedback data. The server analyzes the collected data and uses it to tune the algorithms and sentiment recognition. The output is the improvement plan and specific implementation items.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] Traditional problem-solving systems offer uniform suggestions without considering user emotions, resulting in limited user satisfaction. Furthermore, suggestions for unresolved issues are often roundabout or mismatched with the user's emotional state, making it difficult to improve the customer support experience. A systematic approach to address this is needed.

[0379] 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.

[0380] In this invention, the server includes means for receiving unresolved problems from multiple intelligent programs using natural language processing technology, analyzing the problems and identifying common failure points, using an emotion engine that adjusts the generated suggestions based on the user's emotional state, and notifying relevant organizations of the generated suggestions. This makes it possible to provide personalized suggestions that take the user's emotions into consideration.

[0381] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0382] An "intelligent program" is software that uses artificial intelligence to autonomously perform specific tasks.

[0383] A "point of failure" refers to the cause or factor that is leading to an unresolved problem.

[0384] "Generative artificial intelligence technology" is an artificial intelligence technology that can generate new proposals and ideas from data.

[0385] An "emotion engine" is a technology for measuring and understanding a user's emotional state.

[0386] "Related organizations" refers to the organizations or individuals who should receive the generated proposals and notifications.

[0387] The system realizing this invention mainly consists of a server, terminals, and a user. The server uses natural language processing technology to analyze unresolved problems received from terminals through multiple intelligent programs and identifies common fault points. The software used here leverages natural language processing libraries and APIs. The server also uses generative artificial intelligence technology to generate appropriate suggestions for the user based on the identified fault points. A generative AI model is used in this generation process.

[0388] Furthermore, the server is equipped with an emotion engine that senses the user's emotional state in real time and adjusts its suggestions accordingly. The emotion engine interprets data from the user using software such as an emotion analysis API. For example, if a user fails to book a flight, the server can offer alternatives and include additional benefits or information to alleviate the user's dissatisfaction. In this way, it provides personalized solutions that respond to the user's emotions.

[0389] As a concrete example, consider the problem of delays in logistics. The server receives delay information, identifies the cause of the problem, and proposes appropriate solutions. This system can also further optimize its suggestions based on user feedback.

[0390] An example of a prompt message is, "Suggest how to report to and follow up with a customer who is frustrated because their product hasn't arrived." The aim is to provide a more meaningful experience for the user.

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The server receives unresolved issues from terminals through multiple intelligent programs. The received data contains details of the issues reported by users, and the server temporarily stores this in a data buffer. This process includes integrity checks to verify the accuracy of the data.

[0394] Step 2:

[0395] The server analyzes unresolved problems stored in a data buffer using natural language processing techniques. This identifies common failure points. Text analysis is performed based on the problem data as input, and a list of failure points is generated as output. Through this analysis, the structure of the problem is understood, and areas requiring correction are identified.

[0396] Step 3:

[0397] The server utilizes generative artificial intelligence technology to generate specific suggestions based on identified fault points. The generative AI model receives fault points as input and generates suggestions as output. The generated suggestions present concrete and practical methods for solving the user's problems.

[0398] Step 4:

[0399] The server uses an emotion engine to acquire the user's emotional state in real time and adjusts the generated suggestions according to the user's emotions. It receives emotional data as input and modifies the content and expression of the suggestions. This adjustment improves the user experience and increases the suggestion acceptance rate.

[0400] Step 5:

[0401] The server notifies the relevant parties of the finalized proposal. Notifications are made via email and a dashboard, converting the finalized proposal (as input) into notification messages (as output). This process is designed to ensure that necessary information is properly communicated to the relevant parties.

[0402] Step 6:

[0403] Users provide feedback based on suggestions provided by the server. This feedback includes details about the problem resolution status and the usefulness of the suggestions. This feedback is sent to the server, and the system uses the feedback data as input to make further improvements. The feedback helps optimize the emotion engine and generative AI model.

[0404] Through a clear data flow and processing at each step, we enable better suggestions and improved user experience based on user feedback regarding their problems.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] [Third Embodiment]

[0409] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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".

[0421] The system of the present invention effectively collects and analyzes unresolved problems processed by multiple artificial intelligence agents, generates solutions based on these analyses, and provides them to relevant organizations. An embodiment of this system is shown below.

[0422] The server receives problem data from each artificial intelligence agent. During this receiving process, unresolved problems are periodically sent via the API, and the server stores them in a temporary data buffer. Accuracy is maintained by checking for data duplication and format consistency.

[0423] Next, the server systematically classifies the stored problem data into a database based on business category and frequency of occurrence. This enables efficient data management and establishes a foundation for problem analysis.

[0424] Next, the server utilizes natural language processing technology to explore frequently occurring themes and failure points in the problem data. This identifies major bottlenecks and highlights critical issues that require attention.

[0425] Subsequently, the server uses generative artificial intelligence technology to generate specific proposals from the analysis results. This proposal generation process can utilize various data formats and output as text, images, and videos.

[0426] As a concrete example, consider a problem in the travel industry. When a user tries to plan a trip, an AI agent attempts to optimize flight bookings, but a problem arises where there are no suitable flights for the desired time slot. This problem is collected on a server, and frequency analysis reveals trends in demand for specific time slots. Based on this information, the server generates suggestions for new flights or alternative options and notifies the relevant airlines.

[0427] Finally, the server notifies relevant organizations of the generated proposals via email and dashboards, and receives feedback. Through this feedback, stakeholders can evaluate the feasibility and effectiveness of the proposals and use it to further improve the system.

[0428] As a result, the system of the present invention provides a comprehensive platform for rapidly resolving problems faced by artificial intelligence agents and can improve the quality of services in various industries.

[0429] The following describes the processing flow.

[0430] Step 1:

[0431] The server receives problem data from each artificial intelligence agent. The data sent from the agents via the API includes metadata such as problem details, date and time of occurrence, and related business information. The server stores this data in a temporary data buffer and performs duplicate checks and format consistency verification.

[0432] Step 2:

[0433] The server classifies received problem data based on business category and frequency before saving it to the database. The server uses a category classification algorithm to assign problems to the appropriate categories and adds tags to facilitate searching.

[0434] Step 3:

[0435] The server utilizes a natural language processing engine to analyze stored problem data. This analysis extracts frequently occurring keywords and phrases and identifies common failure points. The analysis results provide fundamental information to clarify the root cause of the problem.

[0436] Step 4:

[0437] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. These suggestions are generated as specific solutions or improvement proposals and are expressed in data formats such as text, images, and videos.

[0438] Step 5:

[0439] The server notifies relevant organizations and individuals of the generated proposals. These notifications are delivered via email or a dedicated dashboard, and the notification format can be customized upon request. The notification includes an overview of the solution and instructions for implementation.

[0440] Step 6:

[0441] Users, as affiliated organizations, access the system's dashboard to review the proposed ideas. Users evaluate the feasibility of the proposals and provide feedback for implementation as needed.

[0442] Step 7:

[0443] The server analyzes the received feedback and records the effectiveness of the suggestions and areas for improvement. This feedback information is incorporated into the system's improvement cycle and used to enhance the accuracy of the suggestion generation algorithm.

[0444] (Example 1)

[0445] 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."

[0446] In modern society, there is a demand to respond quickly and effectively to unresolved issues by utilizing information processing technology. However, existing systems have suffered from issues such as duplication of issues received from different information processing devices, inconsistent formats, and problems with the speed and accuracy of generating and implementing appropriate proposals. Furthermore, the effective use of feedback on generated proposals and its link to system improvement has not been sufficiently implemented.

[0447] 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.

[0448] In this invention, the server includes means for receiving unresolved issues from multiple information processing devices using natural language processing technology, analyzing the issues to identify common problems, generating proposals based on the identified problems using generative artificial intelligence technology, and notifying relevant organizations of the proposals. This enables effective management and analysis of unresolved issues, rapid generation and notification of appropriate proposals, and continuous improvement of the system through the use of feedback.

[0449] "Natural language processing technology" refers to technologies for handling human language using computers, and includes techniques for analyzing text data and understanding its meaning and structure.

[0450] An "information processing device" is a machine designed to process data, and refers to computers, servers, and other devices that have functions for calculation and data management.

[0451] "Unresolved issues" refer to problems or obstacles for which solutions have not yet been found, and which require processing or action.

[0452] "Generative artificial intelligence technology" is a general term for algorithms and models that have the ability to generate text, images, and other data based on input information.

[0453] "Related organizations" refers to groups or companies that share specific objectives or activities, and are the organizations to which generated proposals and information will be notified.

[0454] A "proposal" refers to a specific plan or proposal offered to improve or resolve an identified problem.

[0455] "Feedback" refers to a response or evaluation of a received suggestion, including information for further improvement or modification.

[0456] This system consists of a server, multiple terminals, and users, and each device works together to identify and analyze unresolved issues and propose solutions.

[0457] The server receives unresolved issues from terminals, which are information processing devices. Specifically, the terminals transmit data through their built-in communication modules, and this data is temporarily stored on the server. The server checks the received data for duplication and format consistency, and then classifies the data based on these criteria. This classification uses business categories and frequency of occurrence, and is systematized in a management database. In this process, a management system that is standardly used as server software is employed.

[0458] Natural language processing (NLP) techniques will be used to analyze the problem data. Specifically, open-source NLP libraries (e.g., spaCy and NLTK) will be used to perform text analysis and topic modeling, thereby highlighting common problems.

[0459] Generative AI models are used to generate proposals based on the analyzed data. These models possess text generation capabilities, for example, employing natural language generation techniques as part of their generation algorithms. As a result, the server generates proposals in text and image formats and includes communication capabilities to disseminate them to relevant organizations.

[0460] As a concrete example, consider a problem users encounter in the travel industry. When a user tries to book a flight and cannot find a flight at their desired time, this information is sent from the terminal to the server. The server analyzes this problem, understands the demand for that time slot, and generates suggestions for new flights. Subsequently, the relevant airlines are notified, and the feasibility of the suggestions is evaluated.

[0461] An example of a prompt might be: "Collect unresolved issues regarding flight booking optimization in the travel industry and analyze the needs using natural language processing techniques. Based on the analysis results, generate new flight suggestions and notify the relevant airlines."

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The terminal receives unresolved issue data as input from the user. This data is in text format and includes specific issues such as flight reservations. The terminal sends this data to the server using a communication protocol.

[0465] Step 2:

[0466] The server receives task data sent from the terminal via the API and temporarily stores it in a data buffer. The server interprets the received data in JSON format and checks for data duplication and format consistency. Data that has been verified for consistency is passed on to the next processing step.

[0467] Step 3:

[0468] The server classifies consistent data based on business categories and frequency of occurrence. A database management system is used to place data into predefined categories. This data classification enables efficient management and subsequent data analysis.

[0469] Step 4:

[0470] The server analyzes the classified data using natural language processing (NLP) techniques. Specifically, it uses an NLP library to extract common problems and themes. The information extracted from the input data is evaluated based on its importance.

[0471] Step 5:

[0472] The server uses a generative AI model to generate suggestions based on the identified problems. The server provides pre-configured prompts to the generative AI model and retrieves the suggested content as output. The suggestions are output in text or image format.

[0473] Step 6:

[0474] The server notifies the relevant organizations of the generated proposals via email or a dashboard. This communication method is used to configure the addresses for receiving the generated proposals and the permissions to access the dashboard.

[0475] Step 7:

[0476] Users receive and evaluate feedback from relevant organizations. Based on this feedback, the server improves the proposals and adjusts the system to further optimize it.

[0477] (Application Example 1)

[0478] 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."

[0479] The problem that this invention aims to solve is to support immediate problem-solving on-site and improve the efficiency of the entire organization. In particular, there has been a lack of sufficient means to quickly aggregate and analyze issues from multiple intelligent agents and provide optimal solutions to the relevant organizations and personnel. This has led to demands for improved customer satisfaction and optimization of business processes.

[0480] 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.

[0481] This invention includes a server that utilizes natural language processing technology to receive unresolved issues from multiple intelligent agents, analyzes the issues to identify common failure factors, generates recommendations based on the identified failure factors using generative artificial intelligence technology, notifies relevant organizations of the recommendations, and immediately inputs issues via mobile terminals and distributes solutions. This enables rapid response to on-site problems and improves the overall efficiency of the organization.

[0482] "Natural language processing technology" is a technology that enables computers to understand and process human language.

[0483] An "intelligent agent" is a program or system that processes information independently and performs specific tasks.

[0484] A "problem" is an unresolved issue or a matter that needs to be resolved.

[0485] "Obstacle factors" are elements that cause problems or act as bottlenecks.

[0486] "Generative artificial intelligence technology" is an artificial intelligence technology that automatically generates new information and suggestions based on data.

[0487] A "recommendation" is a solution or policy proposed based on identified information.

[0488] "Relevant organizations" refer to institutions or groups that are responsible for accepting and responding to the generated recommendations.

[0489] A "mobile terminal" is a device that is portable and can be operated on-site.

[0490] "Real-time input" refers to the act of entering information in real time at the site.

[0491] A "solution" is a proposed method of dealing with a specific problem.

[0492] In the system that implements this application, a server plays a central role. The server uses natural language processing techniques to analyze unresolved issues collected from multiple intelligent agents. This allows the server to identify common failure factors. Subsequently, generative artificial intelligence techniques are used to generate recommendations based on the identified failure factors.

[0493] Mobile terminals, such as smartphones, are devices for users to input information instantly. Using these terminals, users can input problems that arise on-site via voice or text. The data is sent to a cloud server, where the received problems are analyzed in real time.

[0494] The server manages data using AWS RDS and analyzes key themes and bottlenecks from input text using Amazon Comprehend. Based on the analysis results, the server generates solutions using generative AI models such as ChatGPT and delivers them to the user's terminal in text format.

[0495] For example, if a store staff member is asked by a customer about the availability of a particular product, they can input "Is this product in stock?" into an application on their smartphone. The server will then immediately analyze the data and provide recommendations, including "It's in stock at a nearby store" and "The next shipment is due soon."

[0496] An example of a prompt in a generative AI model would be a sentence like, "A customer has inquired about product inventory at the store. Please automatically generate a solution."

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] The device receives task data entered by the user via voice or text and sends it to a cloud server. The input includes specific problems or questions that require resolution. This data is received in real time.

[0500] Step 2:

[0501] The server saves issue data received on the cloud to Amazon RDS. During saving, data duplication checks and format consistency checks are performed to maintain accurate information. This ensures that issues are registered in the database in an organized format.

[0502] Step 3:

[0503] The server analyzes issue data stored using Amazon Comprehend to identify recurring themes and bottlenecks. The input is structured issue data, and the output includes classifications of identified themes and problems. This analysis is performed using advanced natural language processing techniques.

[0504] Step 4:

[0505] The server uses a generative AI model, such as ChatGPT, to generate recommendations based on the analysis results. This process generates specific solutions and recommendations based on themes and bottlenecks. The input is the analyzed data, and the output is the generated suggestions. Prompts such as "Generate solutions for this problem" are used.

[0506] Step 5:

[0507] The server sends solutions based on the generated recommendations to the terminal. The information displayed on the terminal includes recommendations in a format that the user can immediately understand and act upon. This on-screen display enables the user to make quick decisions in the field.

[0508] 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.

[0509] This invention is a system that employs an emotion engine to recognize user emotions, analyzes unresolved problems collected by an artificial intelligence agent, generates suggestions, and provides notifications. This system aims to provide more effective and personalized solutions by tailoring suggestions based on emotions.

[0510] The server first receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details as well as related business information. The server stores this data in a temporary data buffer and verifies its integrity.

[0511] Next, the server analyzes the problem data using natural language processing technology and identifies common failure points. Based on the insights gained, it uses generative AI to generate specific suggestions.

[0512] A key feature here is the use of an emotion engine. The emotion engine allows the server to acquire the user's emotional state in real time and adjust the suggestions generated based on this information. For example, if a user is feeling dissatisfied, the content and expression of the suggestions can be changed to be more polite and approachable.

[0513] As a concrete example, consider an AI agent in the travel industry. If a user encounters a problem where their desired flight is fully booked and unavailable, the server analyzes the issue and suggests alternative flights or modes of transport at special prices. If the emotion engine detects user disappointment, it will add special offers and additional support information to the suggestions, implementing measures to alleviate the user's frustration.

[0514] After a proposal is generated, the server notifies the relevant organizations and individuals. Notifications are sent via email or a dashboard, from which users can review the proposal details.

[0515] Users evaluate the provided suggestions and send feedback to the server. This feedback includes the success rate of implementing the suggestions and areas for further improvement. The server analyzes this feedback and uses it to tune the sentiment engine and improve the suggestion generation algorithm.

[0516] Thus, the present invention utilizes an emotion engine to provide a flexible and sophisticated solution for enhancing the user experience.

[0517] The following describes the processing flow.

[0518] Step 1:

[0519] The server receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details, the circumstances under which it occurred, and the relevant business context. This data is stored in a temporary data buffer, where duplicate checks and data format consistency verification are performed.

[0520] Step 2:

[0521] The server classifies received problem data into a database based on business category and frequency of occurrence. Using a category classification algorithm, it assigns each problem to the appropriate category and tags it to improve searchability.

[0522] Step 3:

[0523] The server utilizes natural language processing technology to analyze problem data stored in the database. This analysis identifies common failure points through frequency analysis and keyword extraction, thereby revealing the root cause of the problem.

[0524] Step 4:

[0525] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. The generated suggestions are presented in various formats, such as text, images, and videos, in a way that is easy for the user to understand.

[0526] Step 5:

[0527] The server utilizes an emotion engine that recognizes the user's emotions in real time and adjusts the content of the generated suggestions. By acquiring data on the user's emotional state and adapting the expression and content of the suggestions, it provides more appropriate and effective solutions.

[0528] Step 6:

[0529] The server notifies relevant organizations and individuals of the generated proposals. Notifications are sent via email or a dedicated dashboard, and the content of the notifications can be customized. This allows stakeholders to review the proposals in detail and develop implementation plans.

[0530] Step 7:

[0531] Users review the proposals they receive and provide feedback to the server. This feedback includes evaluations of the feasibility and effectiveness of the proposals.

[0532] Step 8:

[0533] The server analyzes user feedback and uses it to improve the emotion engine settings and suggestion generation algorithms. This allows the system to continuously evolve and improve the user experience.

[0534] (Example 2)

[0535] 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."

[0536] Traditional systems struggle to provide personalized solutions tailored to individual emotional states in response to unresolved user issues, resulting in insufficient personalized responses necessary to improve the user experience. Furthermore, a lack of rapid suggestion generation and notification makes it difficult to resolve user dissatisfaction. Additionally, the insufficient means of efficiently using received feedback to improve the system makes daily optimization challenging.

[0537] 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.

[0538] In this invention, the server includes means for receiving and analyzing unresolved problems from multiple intelligent systems using natural language processing technology, means for generating suggestions based on identified fault points using generative artificial intelligence technology, and means for using an emotion processing engine that acquires the user's emotional state in real time and adjusts the generated suggestions based on the emotional state. This makes it possible to quickly provide detailed suggestions tailored to each user's emotional state and to improve the system based on the received feedback.

[0539] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0540] An "intelligent system" is an automated system equipped with sophisticated computational models for processing data and making decisions and solving problems.

[0541] An "unresolved issue" is a challenge or requirement that users or systems face but for which an appropriate solution has not yet been provided.

[0542] "Generative artificial intelligence technology" refers to technologies that use artificial intelligence to generate new data and proposals.

[0543] A "point of failure" refers to the element or location within a particular process or system that causes a problem to occur.

[0544] An "emotion processing engine" is a specialized technology that analyzes the user's emotional state in real time and adjusts responses and suggestions based on the information obtained.

[0545] "Related organizations" refer to organizations or individuals responsible for making decisions or taking actions based on the generated proposals.

[0546] A "classification algorithm" refers to a method or process for organizing and classifying data into categories based on specific criteria.

[0547] This invention aims to have a server receive unresolved problems from various intelligent systems, analyze them, and identify common points of failure. The server utilizes natural language processing techniques to perform this process. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the received text data.

[0548] Based on the insights gained from the analysis, the server generates suggestions using a generative artificial intelligence model. This process employs advanced generative AI models such as OpenAI's GPT. To refine the generated suggestions, the server obtains the user's emotional state in real time through an emotion processing engine. This data is obtained by analyzing user-input text and voice data using an emotion recognition API.

[0549] As a concrete example, consider a travel agency's support system. Suppose a user's desired flight is fully booked and unavailable. In this case, the server can analyze the problem and suggest alternative options, such as other flights or ground transportation to the same destination at a special price. Furthermore, if the emotion processing engine detects user disappointment, it can add special offers or additional support information to the suggestions, thereby improving user satisfaction.

[0550] Once a proposal is generated, the server notifies the relevant organizations and individuals via email or a dashboard. Users can review the proposed proposal and provide feedback through this notification. This feedback is analyzed by the server to help it continuously improve the system. For example, a prompt such as, "How should the proposal be adjusted if the user is dissatisfied with the service?" can be input into the AI ​​model, and better proposals will be provided based on the response.

[0551] In this way, by integrating diverse technologies, servers can quickly deliver personalized solutions and improve the user experience.

[0552] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0553] Step 1:

[0554] The server receives unresolved problem data from each intelligent system via an API. Input includes problem details and related operational information. Specifically, the server receives an HTTP request and stores the problem data in a temporary data buffer. Output is a dataset in a consistent format.

[0555] Step 2:

[0556] The server verifies the integrity of the stored data. The input for this step is all the problematic data in the temporary data buffer. It checks whether the data format conforms to the specifications and whether all necessary fields are present. Specifically, it performs JSON schema validation and checks for required fields. The output is the dataset whose integrity has been verified.

[0557] Step 3:

[0558] The server analyzes the problem data using natural language processing techniques to identify common failure points. The input for this step is consistent problem data. The server extracts keywords and context from the problem data and performs text mining, for example, using SpaCy or NLTK. The output is the identified failure points and selected key keywords.

[0559] Step 4:

[0560] The server generates suggestions using generative artificial intelligence technology based on identified fault points. It uses analysis results and identified fault points as input. Specifically, the server inputs prompts into a generative AI model (e.g., a GPT model) and retrieves suggestions from the model. The output is a specific suggestion for the user.

[0561] Step 5:

[0562] The server uses an emotion processing engine to acquire the user's emotional state and adjust the generated suggestions according to that emotion. The input for this step is real-time data about the user's emotions (e.g., text or voice analysis results). Using the API provided by the emotion processing engine, the server identifies the user's current psychological state and optimizes the expression and content of the suggestions. The output is the adjusted suggestions for the user.

[0563] Step 6:

[0564] The server notifies relevant organizations and individuals of the generated proposals via email and a dashboard. The input is the final, adjusted proposal content. Specifically, the server communicates with the mail server to send emails and calls the dashboard update API to provide real-time notifications. The output is a state where the proposals have been reliably notified to the relevant parties.

[0565] Step 7:

[0566] Users evaluate the provided suggestions and submit feedback to the server. The input for this step consists of user ratings and comments. User opinions are collected using feedback forms and surveys. The output is the received feedback data.

[0567] Step 8:

[0568] The server analyzes the received feedback and uses it to improve the system. The input for this step is user feedback data. The server analyzes the collected data and uses it to tune the algorithms and sentiment recognition. The output is the improvement plan and specific implementation items.

[0569] (Application Example 2)

[0570] 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."

[0571] Traditional problem-solving systems offer uniform suggestions without considering user emotions, resulting in limited user satisfaction. Furthermore, suggestions for unresolved issues are often roundabout or mismatched with the user's emotional state, making it difficult to improve the customer support experience. A systematic approach to address this is needed.

[0572] 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.

[0573] In this invention, the server includes means for receiving unresolved problems from multiple intelligent programs using natural language processing technology, analyzing the problems and identifying common failure points, using an emotion engine that adjusts the generated suggestions based on the user's emotional state, and notifying relevant organizations of the generated suggestions. This makes it possible to provide personalized suggestions that take the user's emotions into consideration.

[0574] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0575] An "intelligent program" is software that uses artificial intelligence to autonomously perform specific tasks.

[0576] A "point of failure" refers to the cause or factor that is leading to an unresolved problem.

[0577] "Generative artificial intelligence technology" is an artificial intelligence technology that can generate new proposals and ideas from data.

[0578] An "emotion engine" is a technology for measuring and understanding a user's emotional state.

[0579] "Related organizations" refers to the organizations or individuals who should receive the generated proposals and notifications.

[0580] The system realizing this invention mainly consists of a server, terminals, and a user. The server uses natural language processing technology to analyze unresolved problems received from terminals through multiple intelligent programs and identifies common fault points. The software used here leverages natural language processing libraries and APIs. The server also uses generative artificial intelligence technology to generate appropriate suggestions for the user based on the identified fault points. A generative AI model is used in this generation process.

[0581] Furthermore, the server is equipped with an emotion engine that senses the user's emotional state in real time and adjusts its suggestions accordingly. The emotion engine interprets data from the user using software such as an emotion analysis API. For example, if a user fails to book a flight, the server can offer alternatives and include additional benefits or information to alleviate the user's dissatisfaction. In this way, it provides personalized solutions that respond to the user's emotions.

[0582] As a concrete example, consider the problem of delays in logistics. The server receives delay information, identifies the cause of the problem, and proposes appropriate solutions. This system can also further optimize its suggestions based on user feedback.

[0583] An example of a prompt message is, "Suggest how to report to and follow up with a customer who is frustrated because their product hasn't arrived." The aim is to provide a more meaningful experience for the user.

[0584] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0585] Step 1:

[0586] The server receives unresolved issues from terminals through multiple intelligent programs. The received data contains details of the issues reported by users, and the server temporarily stores this in a data buffer. This process includes integrity checks to verify the accuracy of the data.

[0587] Step 2:

[0588] The server analyzes unresolved problems stored in a data buffer using natural language processing techniques. This identifies common failure points. Text analysis is performed based on the problem data as input, and a list of failure points is generated as output. Through this analysis, the structure of the problem is understood, and areas requiring correction are identified.

[0589] Step 3:

[0590] The server utilizes generative artificial intelligence technology to generate specific suggestions based on identified fault points. The generative AI model receives fault points as input and generates suggestions as output. The generated suggestions present concrete and practical methods for solving the user's problems.

[0591] Step 4:

[0592] The server uses an emotion engine to acquire the user's emotional state in real time and adjusts the generated suggestions according to the user's emotions. It receives emotional data as input and modifies the content and expression of the suggestions. This adjustment improves the user experience and increases the suggestion acceptance rate.

[0593] Step 5:

[0594] The server notifies the relevant parties of the finalized proposal. Notifications are made via email and a dashboard, converting the finalized proposal (as input) into notification messages (as output). This process is designed to ensure that necessary information is properly communicated to the relevant parties.

[0595] Step 6:

[0596] Users provide feedback based on suggestions provided by the server. This feedback includes details about the problem resolution status and the usefulness of the suggestions. This feedback is sent to the server, and the system uses the feedback data as input to make further improvements. The feedback helps optimize the emotion engine and generative AI model.

[0597] Through a clear data flow and processing at each step, we enable better suggestions and improved user experience based on user feedback regarding their problems.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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".

[0615] The system of the present invention effectively collects and analyzes unresolved problems processed by multiple artificial intelligence agents, generates solutions based on these analyses, and provides them to relevant organizations. An embodiment of this system is shown below.

[0616] The server receives problem data from each artificial intelligence agent. During this receiving process, unresolved problems are periodically sent via the API, and the server stores them in a temporary data buffer. Accuracy is maintained by checking for data duplication and format consistency.

[0617] Next, the server systematically classifies the stored problem data into a database based on business category and frequency of occurrence. This enables efficient data management and establishes a foundation for problem analysis.

[0618] Next, the server utilizes natural language processing technology to explore frequently occurring themes and failure points in the problem data. This identifies major bottlenecks and highlights critical issues that require attention.

[0619] Subsequently, the server uses generative artificial intelligence technology to generate specific proposals from the analysis results. This proposal generation process can utilize various data formats and output as text, images, and videos.

[0620] As a concrete example, consider a problem in the travel industry. When a user tries to plan a trip, an AI agent attempts to optimize flight bookings, but a problem arises where there are no suitable flights for the desired time slot. This problem is collected on a server, and frequency analysis reveals trends in demand for specific time slots. Based on this information, the server generates suggestions for new flights or alternative options and notifies the relevant airlines.

[0621] Finally, the server notifies relevant organizations of the generated proposals via email and dashboards, and receives feedback. Through this feedback, stakeholders can evaluate the feasibility and effectiveness of the proposals and use it to further improve the system.

[0622] As a result, the system of the present invention provides a comprehensive platform for rapidly resolving problems faced by artificial intelligence agents and can improve the quality of services in various industries.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] The server receives problem data from each artificial intelligence agent. The data sent from the agents via the API includes metadata such as problem details, date and time of occurrence, and related business information. The server stores this data in a temporary data buffer and performs duplicate checks and format consistency verification.

[0626] Step 2:

[0627] The server classifies received problem data based on business category and frequency before saving it to the database. The server uses a category classification algorithm to assign problems to the appropriate categories and adds tags to facilitate searching.

[0628] Step 3:

[0629] The server utilizes a natural language processing engine to analyze stored problem data. This analysis extracts frequently occurring keywords and phrases and identifies common failure points. The analysis results provide fundamental information to clarify the root cause of the problem.

[0630] Step 4:

[0631] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. These suggestions are generated as specific solutions or improvement proposals and are expressed in data formats such as text, images, and videos.

[0632] Step 5:

[0633] The server notifies relevant organizations and individuals of the generated proposals. These notifications are delivered via email or a dedicated dashboard, and the notification format can be customized upon request. The notification includes an overview of the solution and instructions for implementation.

[0634] Step 6:

[0635] Users, as affiliated organizations, access the system's dashboard to review the proposed ideas. Users evaluate the feasibility of the proposals and provide feedback for implementation as needed.

[0636] Step 7:

[0637] The server analyzes the received feedback and records the effectiveness of the suggestions and areas for improvement. This feedback information is incorporated into the system's improvement cycle and used to enhance the accuracy of the suggestion generation algorithm.

[0638] (Example 1)

[0639] 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".

[0640] In modern society, there is a demand to respond quickly and effectively to unresolved issues by utilizing information processing technology. However, existing systems have suffered from issues such as duplication of issues received from different information processing devices, inconsistent formats, and problems with the speed and accuracy of generating and implementing appropriate proposals. Furthermore, the effective use of feedback on generated proposals and its link to system improvement has not been sufficiently implemented.

[0641] 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.

[0642] In this invention, the server includes means for receiving unresolved issues from multiple information processing devices using natural language processing technology, analyzing the issues to identify common problems, generating proposals based on the identified problems using generative artificial intelligence technology, and notifying relevant organizations of the proposals. This enables effective management and analysis of unresolved issues, rapid generation and notification of appropriate proposals, and continuous improvement of the system through the use of feedback.

[0643] "Natural language processing technology" refers to technologies for handling human language using computers, and includes techniques for analyzing text data and understanding its meaning and structure.

[0644] An "information processing device" is a machine designed to process data, and refers to computers, servers, and other devices that have functions for calculation and data management.

[0645] "Unresolved issues" refer to problems or obstacles for which solutions have not yet been found, and which require processing or action.

[0646] "Generative artificial intelligence technology" is a general term for algorithms and models that have the ability to generate text, images, and other data based on input information.

[0647] "Related organizations" refers to groups or companies that share specific objectives or activities, and are the organizations to which generated proposals and information will be notified.

[0648] A "proposal" refers to a specific plan or proposal offered to improve or resolve an identified problem.

[0649] "Feedback" refers to a response or evaluation of a received suggestion, including information for further improvement or modification.

[0650] This system consists of a server, multiple terminals, and users, and each device works together to identify and analyze unresolved issues and propose solutions.

[0651] The server receives unresolved issues from terminals, which are information processing devices. Specifically, the terminals transmit data through their built-in communication modules, and this data is temporarily stored on the server. The server checks the received data for duplication and format consistency, and then classifies the data based on these criteria. This classification uses business categories and frequency of occurrence, and is systematized in a management database. In this process, a management system that is standardly used as server software is employed.

[0652] Natural language processing (NLP) techniques will be used to analyze the problem data. Specifically, open-source NLP libraries (e.g., spaCy and NLTK) will be used to perform text analysis and topic modeling, thereby highlighting common problems.

[0653] Generative AI models are used to generate proposals based on the analyzed data. These models possess text generation capabilities, for example, employing natural language generation techniques as part of their generation algorithms. As a result, the server generates proposals in text and image formats and includes communication capabilities to disseminate them to relevant organizations.

[0654] As a concrete example, consider a problem users encounter in the travel industry. When a user tries to book a flight and cannot find a flight at their desired time, this information is sent from the terminal to the server. The server analyzes this problem, understands the demand for that time slot, and generates suggestions for new flights. Subsequently, the relevant airlines are notified, and the feasibility of the suggestions is evaluated.

[0655] An example of a prompt might be: "Collect unresolved issues regarding flight booking optimization in the travel industry and analyze the needs using natural language processing techniques. Based on the analysis results, generate new flight suggestions and notify the relevant airlines."

[0656] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0657] Step 1:

[0658] The terminal receives unresolved issue data as input from the user. This data is in text format and includes specific issues such as flight reservations. The terminal sends this data to the server using a communication protocol.

[0659] Step 2:

[0660] The server receives task data sent from the terminal via the API and temporarily stores it in a data buffer. The server interprets the received data in JSON format and checks for data duplication and format consistency. Data that has been verified for consistency is passed on to the next processing step.

[0661] Step 3:

[0662] The server classifies consistent data based on business categories and frequency of occurrence. A database management system is used to place data into predefined categories. This data classification enables efficient management and subsequent data analysis.

[0663] Step 4:

[0664] The server analyzes the classified data using natural language processing (NLP) techniques. Specifically, it uses an NLP library to extract common problems and themes. The information extracted from the input data is evaluated based on its importance.

[0665] Step 5:

[0666] The server uses a generative AI model to generate suggestions based on the identified problems. The server provides pre-configured prompts to the generative AI model and retrieves the suggested content as output. The suggestions are output in text or image format.

[0667] Step 6:

[0668] The server notifies the relevant organizations of the generated proposals via email or a dashboard. This communication method is used to configure the addresses for receiving the generated proposals and the permissions to access the dashboard.

[0669] Step 7:

[0670] Users receive and evaluate feedback from relevant organizations. Based on this feedback, the server improves the proposals and adjusts the system to further optimize it.

[0671] (Application Example 1)

[0672] 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".

[0673] The problem that this invention aims to solve is to support immediate problem-solving on-site and improve the efficiency of the entire organization. In particular, there has been a lack of sufficient means to quickly aggregate and analyze issues from multiple intelligent agents and provide optimal solutions to the relevant organizations and personnel. This has led to demands for improved customer satisfaction and optimization of business processes.

[0674] 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.

[0675] This invention includes a server that utilizes natural language processing technology to receive unresolved issues from multiple intelligent agents, analyzes the issues to identify common failure factors, generates recommendations based on the identified failure factors using generative artificial intelligence technology, notifies relevant organizations of the recommendations, and immediately inputs issues via mobile terminals and distributes solutions. This enables rapid response to on-site problems and improves the overall efficiency of the organization.

[0676] "Natural language processing technology" is a technology that enables computers to understand and process human language.

[0677] An "intelligent agent" is a program or system that processes information independently and performs specific tasks.

[0678] A "problem" is an unresolved issue or a matter that needs to be resolved.

[0679] "Obstacle factors" are elements that cause problems or act as bottlenecks.

[0680] "Generative artificial intelligence technology" is an artificial intelligence technology that automatically generates new information and suggestions based on data.

[0681] A "recommendation" is a solution or policy proposed based on identified information.

[0682] "Relevant organizations" refer to institutions or groups that are responsible for accepting and responding to the generated recommendations.

[0683] A "mobile terminal" is a device that is portable and can be operated on-site.

[0684] "Real-time input" refers to the act of entering information in real time at the site.

[0685] A "solution" is a proposed method of dealing with a specific problem.

[0686] In the system that implements this application, a server plays a central role. The server uses natural language processing techniques to analyze unresolved issues collected from multiple intelligent agents. This allows the server to identify common failure factors. Subsequently, generative artificial intelligence techniques are used to generate recommendations based on the identified failure factors.

[0687] Mobile terminals, such as smartphones, are devices for users to input information instantly. Using these terminals, users can input problems that arise on-site via voice or text. The data is sent to a cloud server, where the received problems are analyzed in real time.

[0688] The server manages data using AWS RDS and analyzes key themes and bottlenecks from input text using Amazon Comprehend. Based on the analysis results, the server generates solutions using generative AI models such as ChatGPT and delivers them to the user's terminal in text format.

[0689] For example, if a store staff member is asked by a customer about the availability of a particular product, they can input "Is this product in stock?" into an application on their smartphone. The server will then immediately analyze the data and provide recommendations, including "It's in stock at a nearby store" and "The next shipment is due soon."

[0690] An example of a prompt in a generative AI model would be a sentence like, "A customer has inquired about product inventory at the store. Please automatically generate a solution."

[0691] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0692] Step 1:

[0693] The device receives task data entered by the user via voice or text and sends it to a cloud server. The input includes specific problems or questions that require resolution. This data is received in real time.

[0694] Step 2:

[0695] The server saves issue data received on the cloud to Amazon RDS. During saving, data duplication checks and format consistency checks are performed to maintain accurate information. This ensures that issues are registered in the database in an organized format.

[0696] Step 3:

[0697] The server analyzes issue data stored using Amazon Comprehend to identify recurring themes and bottlenecks. The input is structured issue data, and the output includes classifications of identified themes and problems. This analysis is performed using advanced natural language processing techniques.

[0698] Step 4:

[0699] The server uses a generative AI model, such as ChatGPT, to generate recommendations based on the analysis results. This process generates specific solutions and recommendations based on themes and bottlenecks. The input is the analyzed data, and the output is the generated suggestions. Prompts such as "Generate solutions for this problem" are used.

[0700] Step 5:

[0701] The server sends solutions based on the generated recommendations to the terminal. The information displayed on the terminal includes recommendations in a format that the user can immediately understand and act upon. This on-screen display enables the user to make quick decisions in the field.

[0702] 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.

[0703] This invention is a system that employs an emotion engine to recognize user emotions, analyzes unresolved problems collected by an artificial intelligence agent, generates suggestions, and provides notifications. This system aims to provide more effective and personalized solutions by tailoring suggestions based on emotions.

[0704] The server first receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details as well as related business information. The server stores this data in a temporary data buffer and verifies its integrity.

[0705] Next, the server analyzes the problem data using natural language processing technology and identifies common failure points. Based on the insights gained, it uses generative AI to generate specific suggestions.

[0706] A key feature here is the use of an emotion engine. The emotion engine allows the server to acquire the user's emotional state in real time and adjust the suggestions generated based on this information. For example, if a user is feeling dissatisfied, the content and expression of the suggestions can be changed to be more polite and approachable.

[0707] As a concrete example, consider an AI agent in the travel industry. If a user encounters a problem where their desired flight is fully booked and unavailable, the server analyzes the issue and suggests alternative flights or modes of transport at special prices. If the emotion engine detects user disappointment, it will add special offers and additional support information to the suggestions, implementing measures to alleviate the user's frustration.

[0708] After a proposal is generated, the server notifies the relevant organizations and individuals. Notifications are sent via email or a dashboard, from which users can review the proposal details.

[0709] Users evaluate the provided suggestions and send feedback to the server. This feedback includes the success rate of implementing the suggestions and areas for further improvement. The server analyzes this feedback and uses it to tune the sentiment engine and improve the suggestion generation algorithm.

[0710] Thus, the present invention utilizes an emotion engine to provide a flexible and sophisticated solution for enhancing the user experience.

[0711] The following describes the processing flow.

[0712] Step 1:

[0713] The server receives unresolved problem data from each artificial intelligence agent via API. This data includes problem details, the circumstances under which it occurred, and the relevant business context. This data is stored in a temporary data buffer, where duplicate checks and data format consistency verification are performed.

[0714] Step 2:

[0715] The server classifies received problem data into a database based on business category and frequency of occurrence. Using a category classification algorithm, it assigns each problem to the appropriate category and tags it to improve searchability.

[0716] Step 3:

[0717] The server utilizes natural language processing technology to analyze problem data stored in the database. This analysis identifies common failure points through frequency analysis and keyword extraction, thereby revealing the root cause of the problem.

[0718] Step 4:

[0719] The server uses generative artificial intelligence technology to generate suggestions based on identified fault points. The generated suggestions are presented in various formats, such as text, images, and videos, in a way that is easy for the user to understand.

[0720] Step 5:

[0721] The server utilizes an emotion engine that recognizes the user's emotions in real time and adjusts the content of the generated suggestions. By acquiring data on the user's emotional state and adapting the expression and content of the suggestions, it provides more appropriate and effective solutions.

[0722] Step 6:

[0723] The server notifies relevant organizations and individuals of the generated proposals. Notifications are sent via email or a dedicated dashboard, and the content of the notifications can be customized. This allows stakeholders to review the proposals in detail and develop implementation plans.

[0724] Step 7:

[0725] Users review the proposals they receive and provide feedback to the server. This feedback includes evaluations of the feasibility and effectiveness of the proposals.

[0726] Step 8:

[0727] The server analyzes user feedback and uses it to improve the emotion engine settings and suggestion generation algorithms. This allows the system to continuously evolve and improve the user experience.

[0728] (Example 2)

[0729] 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".

[0730] Traditional systems struggle to provide personalized solutions tailored to individual emotional states in response to unresolved user issues, resulting in insufficient personalized responses necessary to improve the user experience. Furthermore, a lack of rapid suggestion generation and notification makes it difficult to resolve user dissatisfaction. Additionally, the insufficient means of efficiently using received feedback to improve the system makes daily optimization challenging.

[0731] 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.

[0732] In this invention, the server includes means for receiving and analyzing unresolved problems from multiple intelligent systems using natural language processing technology, means for generating suggestions based on identified fault points using generative artificial intelligence technology, and means for using an emotion processing engine that acquires the user's emotional state in real time and adjusts the generated suggestions based on the emotional state. This makes it possible to quickly provide detailed suggestions tailored to each user's emotional state and to improve the system based on the received feedback.

[0733] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0734] An "intelligent system" is an automated system equipped with sophisticated computational models for processing data and making decisions and solving problems.

[0735] An "unresolved issue" is a challenge or requirement that users or systems face but for which an appropriate solution has not yet been provided.

[0736] "Generative artificial intelligence technology" refers to technologies that use artificial intelligence to generate new data and proposals.

[0737] A "point of failure" refers to the element or location within a particular process or system that causes a problem to occur.

[0738] An "emotion processing engine" is a specialized technology that analyzes the user's emotional state in real time and adjusts responses and suggestions based on the information obtained.

[0739] "Related organizations" refer to organizations or individuals responsible for making decisions or taking actions based on the generated proposals.

[0740] A "classification algorithm" refers to a method or process for organizing and classifying data into categories based on specific criteria.

[0741] This invention aims to have a server receive unresolved problems from various intelligent systems, analyze them, and identify common points of failure. The server utilizes natural language processing techniques to perform this process. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the received text data.

[0742] Based on the insights gained from the analysis, the server generates suggestions using a generative artificial intelligence model. This process employs advanced generative AI models such as OpenAI's GPT. To refine the generated suggestions, the server obtains the user's emotional state in real time through an emotion processing engine. This data is obtained by analyzing user-input text and voice data using an emotion recognition API.

[0743] As a concrete example, consider a travel agency's support system. Suppose a user's desired flight is fully booked and unavailable. In this case, the server can analyze the problem and suggest alternative options, such as other flights or ground transportation to the same destination at a special price. Furthermore, if the emotion processing engine detects user disappointment, it can add special offers or additional support information to the suggestions, thereby improving user satisfaction.

[0744] Once a proposal is generated, the server notifies the relevant organizations and individuals via email or a dashboard. Users can review the proposed proposal and provide feedback through this notification. This feedback is analyzed by the server to help it continuously improve the system. For example, a prompt such as, "How should the proposal be adjusted if the user is dissatisfied with the service?" can be input into the AI ​​model, and better proposals will be provided based on the response.

[0745] In this way, by integrating diverse technologies, servers can quickly deliver personalized solutions and improve the user experience.

[0746] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0747] Step 1:

[0748] The server receives unresolved problem data from each intelligent system via an API. Input includes problem details and related operational information. Specifically, the server receives an HTTP request and stores the problem data in a temporary data buffer. Output is a dataset in a consistent format.

[0749] Step 2:

[0750] The server verifies the integrity of the stored data. The input for this step is all the problematic data in the temporary data buffer. It checks whether the data format conforms to the specifications and whether all necessary fields are present. Specifically, it performs JSON schema validation and checks for required fields. The output is the dataset whose integrity has been verified.

[0751] Step 3:

[0752] The server analyzes the problem data using natural language processing techniques to identify common failure points. The input for this step is consistent problem data. The server extracts keywords and context from the problem data and performs text mining, for example, using SpaCy or NLTK. The output is the identified failure points and selected key keywords.

[0753] Step 4:

[0754] The server generates suggestions using generative artificial intelligence technology based on identified fault points. It uses analysis results and identified fault points as input. Specifically, the server inputs prompts into a generative AI model (e.g., a GPT model) and retrieves suggestions from the model. The output is a specific suggestion for the user.

[0755] Step 5:

[0756] The server uses an emotion processing engine to acquire the user's emotional state and adjust the generated suggestions according to that emotion. The input for this step is real-time data about the user's emotions (e.g., text or voice analysis results). Using the API provided by the emotion processing engine, the server identifies the user's current psychological state and optimizes the expression and content of the suggestions. The output is the adjusted suggestions for the user.

[0757] Step 6:

[0758] The server notifies relevant organizations and individuals of the generated proposals via email and a dashboard. The input is the final, adjusted proposal content. Specifically, the server communicates with the mail server to send emails and calls the dashboard update API to provide real-time notifications. The output is a state where the proposals have been reliably notified to the relevant parties.

[0759] Step 7:

[0760] Users evaluate the provided suggestions and submit feedback to the server. The input for this step consists of user ratings and comments. User opinions are collected using feedback forms and surveys. The output is the received feedback data.

[0761] Step 8:

[0762] The server analyzes the received feedback and uses it to improve the system. The input for this step is user feedback data. The server analyzes the collected data and uses it to tune the algorithms and sentiment recognition. The output is the improvement plan and specific implementation items.

[0763] (Application Example 2)

[0764] 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".

[0765] Traditional problem-solving systems offer uniform suggestions without considering user emotions, resulting in limited user satisfaction. Furthermore, suggestions for unresolved issues are often roundabout or mismatched with the user's emotional state, making it difficult to improve the customer support experience. A systematic approach to address this is needed.

[0766] 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.

[0767] In this invention, the server includes means for receiving unresolved problems from multiple intelligent programs using natural language processing technology, analyzing the problems and identifying common failure points, using an emotion engine that adjusts the generated suggestions based on the user's emotional state, and notifying relevant organizations of the generated suggestions. This makes it possible to provide personalized suggestions that take the user's emotions into consideration.

[0768] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0769] An "intelligent program" is software that uses artificial intelligence to autonomously perform specific tasks.

[0770] A "point of failure" refers to the cause or factor that is leading to an unresolved problem.

[0771] "Generative artificial intelligence technology" is an artificial intelligence technology that can generate new proposals and ideas from data.

[0772] An "emotion engine" is a technology for measuring and understanding a user's emotional state.

[0773] "Related organizations" refers to the organizations or individuals who should receive the generated proposals and notifications.

[0774] The system realizing this invention mainly consists of a server, terminals, and a user. The server uses natural language processing technology to analyze unresolved problems received from terminals through multiple intelligent programs and identifies common fault points. The software used here leverages natural language processing libraries and APIs. The server also uses generative artificial intelligence technology to generate appropriate suggestions for the user based on the identified fault points. A generative AI model is used in this generation process.

[0775] Furthermore, the server is equipped with an emotion engine that senses the user's emotional state in real time and adjusts its suggestions accordingly. The emotion engine interprets data from the user using software such as an emotion analysis API. For example, if a user fails to book a flight, the server can offer alternatives and include additional benefits or information to alleviate the user's dissatisfaction. In this way, it provides personalized solutions that respond to the user's emotions.

[0776] As a concrete example, consider the problem of delays in logistics. The server receives delay information, identifies the cause of the problem, and proposes appropriate solutions. This system can also further optimize its suggestions based on user feedback.

[0777] An example of a prompt message is, "Suggest how to report to and follow up with a customer who is frustrated because their product hasn't arrived." The aim is to provide a more meaningful experience for the user.

[0778] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0779] Step 1:

[0780] The server receives unresolved issues from terminals through multiple intelligent programs. The received data contains details of the issues reported by users, and the server temporarily stores this in a data buffer. This process includes integrity checks to verify the accuracy of the data.

[0781] Step 2:

[0782] The server analyzes unresolved problems stored in a data buffer using natural language processing techniques. This identifies common failure points. Text analysis is performed based on the problem data as input, and a list of failure points is generated as output. Through this analysis, the structure of the problem is understood, and areas requiring correction are identified.

[0783] Step 3:

[0784] The server utilizes generative artificial intelligence technology to generate specific suggestions based on identified fault points. The generative AI model receives fault points as input and generates suggestions as output. The generated suggestions present concrete and practical methods for solving the user's problems.

[0785] Step 4:

[0786] The server uses an emotion engine to acquire the user's emotional state in real time and adjusts the generated suggestions according to the user's emotions. It receives emotional data as input and modifies the content and expression of the suggestions. This adjustment improves the user experience and increases the suggestion acceptance rate.

[0787] Step 5:

[0788] The server notifies the relevant parties of the finalized proposal. Notifications are made via email and a dashboard, converting the finalized proposal (as input) into notification messages (as output). This process is designed to ensure that necessary information is properly communicated to the relevant parties.

[0789] Step 6:

[0790] Users provide feedback based on suggestions provided by the server. This feedback includes details about the problem resolution status and the usefulness of the suggestions. This feedback is sent to the server, and the system uses the feedback data as input to make further improvements. The feedback helps optimize the emotion engine and generative AI model.

[0791] Through a clear data flow and processing at each step, we enable better suggestions and improved user experience based on user feedback regarding their problems.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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."

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0813] The following is further disclosed regarding the embodiments described above.

[0814] (Claim 1)

[0815] A means for receiving unresolved problems from multiple artificial intelligence agents using natural language processing technology, analyzing the problems, and identifying common failure points,

[0816] A means for generating proposals based on identified fault points using generative artificial intelligence technology,

[0817] A system that includes means for notifying relevant organizations of the proposal.

[0818] (Claim 2)

[0819] The system according to claim 1, further comprising means for receiving feedback based on generated suggestions and for improving the system by analyzing such feedback.

[0820] (Claim 3)

[0821] The system according to claim 1, comprising a category classification algorithm for classifying received unresolved issues based on business categories.

[0822] "Example 1"

[0823] (Claim 1)

[0824] A means for receiving unresolved issues from multiple information processing devices using natural language processing technology, analyzing said issues, and identifying common problems,

[0825] A means for generating proposals based on identified problems using generative artificial intelligence technology,

[0826] Means of notifying relevant organizations of the proposal,

[0827] A means of outputting the generated proposals in various information formats,

[0828] A means of systematizing the analyzed issues based on business classification and occurrence rate,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, further comprising means for receiving a response based on the generated proposal and for improving the system by analyzing the response.

[0832] (Claim 3)

[0833] The system according to claim 1, comprising a classification algorithm for organizing received unresolved issues based on business classification.

[0834] "Application Example 1"

[0835] (Claim 1)

[0836] A means for receiving unresolved problems from multiple intelligent agents using natural language processing technology, analyzing the problems, and identifying common obstacles,

[0837] A means for generating recommendations based on identified failure factors using generative artificial intelligence technology,

[0838] Means for notifying relevant organizations of the recommendations,

[0839] A means of instantly inputting problems via a mobile terminal and distributing solutions,

[0840] ...

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, further comprising means for receiving a response based on the generated recommendations and for improving the system by analyzing the response.

[0844] (Claim 3)

[0845] The system according to claim 1, comprising a classification processing algorithm for organizing received unresolved issues based on business areas.

[0846] "Example 2 of combining an emotion engine"

[0847] (Claim 1)

[0848] A means for receiving unresolved problems from multiple intelligent systems using natural language processing technology, analyzing the problems, and identifying common failure points,

[0849] A means for generating proposals based on identified fault points using generative artificial intelligence technology,

[0850] A means of using an emotion processing engine that acquires the user's emotional state in real time and adjusts the generated suggestions based on that emotional state,

[0851] Means of notifying the relevant organizations of the proposal,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, further comprising means for receiving and analyzing feedback based on generated proposals to improve the system.

[0855] (Claim 3)

[0856] The system according to claim 1, comprising a classification algorithm for classifying received unresolved issues based on business classification.

[0857] "Application example 2 when combining with an emotional engine"

[0858] (Claim 1)

[0859] A means for receiving unresolved problems from multiple intelligent programs using natural language processing technology, analyzing the problems, and identifying common failure points,

[0860] A means for generating proposals based on identified fault points using generative artificial intelligence technology,

[0861] A means of acquiring the user's emotional state in real time and using an emotion engine to adjust the generated suggestions,

[0862] A system that includes means for notifying relevant organizations of the proposal.

[0863] (Claim 2)

[0864] The system according to claim 1, further comprising means for receiving feedback based on generated suggestions and for improving the system by analyzing such feedback.

[0865] (Claim 3)

[0866] The system according to claim 1, comprising a classification algorithm for classifying received unresolved issues based on their business domain. [Explanation of Symbols]

[0867] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving unresolved problems from multiple intelligent agents using natural language processing technology, analyzing the problems, and identifying common obstacles, A means for generating recommendations based on identified failure factors using generative artificial intelligence technology, Means for notifying relevant organizations of the recommendations, A means of instantly inputting problems via a mobile terminal and distributing solutions, A system that includes this.

2. The system according to claim 1, further comprising means for receiving a response based on the generated recommendations and for improving the system by analyzing the response.

3. The system according to claim 1, comprising a classification processing algorithm for organizing received unresolved issues based on business areas.

Images