system

Abstract

We provide the system. [Solution] A method for receiving business information, performing preprocessing, and then analyzing it using generative artificial intelligence, A means of identifying business processes that can be automated, A means of presenting the identified, automatable business processes to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When enterprises and individuals promote digital transformation (DX), it is difficult to identify the business parts that can be automated in the initial stage, and it is unclear where to start. As a result, there are obstacles and inefficient resource allocations in the initial stage of DX, which may waste labor and costs. Also, when the business content is complex, natural language input is required, and the labor in the process of converting it into an analyzable form exists as an issue.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides the following means. First, it proposes a system that receives business information, performs preprocessing to convert it into an analyzable format, and then analyzes it using generative artificial intelligence. This system uses AI technology to identify business processes that can be automated from the business information and presents them to the user. Furthermore, it recommends relevant and appropriate tools and methods as needed, thereby indicating a concrete direction for digital transformation and supporting efficient business improvement. This enables users to quickly and accurately get started with digital transformation.

[0006] "Business information" refers to data that describes the details of the tasks that companies and individuals perform on a daily basis.

[0007] "Preprocessing" refers to a series of processes that convert input data into a format necessary for proper analysis.

[0008] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to analyze given data and generate new information and recommendations through specific computational and learning algorithms.

[0009] "Automable business processes" refer to areas or points of work that have been determined through AI analysis to be processable or managed without human intervention.

[0010] A "user" is an individual or organization that uses this system to automate or streamline their operations.

[0011] "Tools" is a general term for hardware or software used to automate or streamline business processes. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0013] 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.

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

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

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

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs 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.

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The following system is configured as an embodiment of the present invention. The user inputs business information in natural language using a dedicated terminal. This information is formatted by the terminal and transmitted to the server as analyzable data. The server analyzes the received data using a pre-built generative artificial intelligence to identify business processes that can be automated.

[0034] In detail, the server first preprocesses the received business information and converts it into a standardized format. This conversion process includes data tokenization and noise filtering. The server then passes this preprocessed data to generative artificial intelligence for analysis. The AI ​​examines the workflow and content, and extracts points suitable for automation.

[0035] The results are sent from the server to the original terminal. The terminal displays the analysis results to the user in a visually easy-to-understand format. This allows the user to review detailed information about the extracted automatable business processes and recommendations for appropriate tools and methods.

[0036] As a concrete example, consider the monthly reporting process in the accounting department of a certain company. When the user inputs each step of the process, the server automatically determines that "automation of the data aggregation portion is possible" and suggests to the user "the introduction of the XX automation tool." This allows the user to quickly implement specific DX (Digital Transformation) measures.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The user inputs business information in natural language using a dedicated terminal. The terminal receives the input information as is and begins preparing to send it.

[0040] Step 2:

[0041] The terminal converts the input natural language business information into a parseable format. This includes preprocessing such as structuring and format conversion.

[0042] Step 3:

[0043] The terminal sends the pre-processed data to the server. The server receives the data and prepares for analysis.

[0044] Step 4:

[0045] The server performs advanced analysis on the received data using generative artificial intelligence. The AI ​​inspects the business information and identifies areas where efficiency can be improved through automation.

[0046] Step 5:

[0047] The server compiles the AI ​​analysis results and converts them into a format that can be presented to the user. This includes detailed explanations of automation points and suggested solutions.

[0048] Step 6:

[0049] The server sends the analysis results to the terminal. The terminal receives these results and prepares them to be displayed appropriately to the user.

[0050] Step 7:

[0051] The terminal displays the analysis results received visually to the user. Based on the information presented, the user can concretely plan and implement the digital transformation of their business operations.

[0052] (Example 1)

[0053] 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."

[0054] In modern business processes, there is a need to efficiently handle everything from information input to identifying elements that can be automated. However, conventional methods present challenges in that it is difficult and time-consuming to automatically analyze information written in natural language, properly standardize it, and then perform analysis using generative artificial intelligence.

[0055] 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.

[0056] In this invention, the server includes means for receiving and pre-processing information, means for converting it into a standardized format and then analyzing it with generative artificial intelligence, and means for identifying parts of the operation that can be automated. This makes it possible to perform the process from inputting business information to identifying parts that can be automated quickly and efficiently.

[0057] "Means of receiving information" refers to the function of receiving data transmitted from an external source and converting it into a format that can be processed within the system.

[0058] "Means of preprocessing" refers to the process of converting received data into a standardized format, including data tokenization and noise filtering.

[0059] "Means of converting to a standardized format" refers to a mechanism for shaping received information into a unified data format so that it can be used in other processing steps.

[0060] "Methods of analysis using generative artificial intelligence" refers to algorithms that use software agents to analyze data and detect patterns that can be automated.

[0061] "Means for identifying operations that can be automated" refers to the process of identifying and clearly indicating parts of a business workflow that can be made more efficient, based on the analysis results.

[0062] "Means of visual presentation" refers to interface technologies that display analysis results to users in a highly visible format, enabling them to intuitively understand the information.

[0063] Embodiments of this invention will now be described. The user uses a dedicated terminal. This terminal provides an interface for inputting business information in natural language. The information entered by the user is converted into a parseable data format by the terminal and sent to the server. Natural language processing technology is used for this conversion, specifically a text analysis library using Python.

[0064] The server has means to preprocess the received data and convert it into a standardized data format. Preprocessing includes tokenization and noise filtering of the data, which makes the information easier to analyze by generative artificial intelligence.

[0065] Next, the server analyzes the pre-processed data using generative artificial intelligence. This AI uses a generative AI model such as OpenAI® to analyze the workflow and identify operations that can be automated.

[0066] The analysis results are sent from the server to the terminal, which then presents them to the user in a visually easy-to-understand format. This utilizes a user interface based on JavaScript (registered trademark) and HTML5. Based on the displayed information, the user can then perform the necessary procedures to automate or optimize business processes.

[0067] A concrete example is the monthly reporting process in a company's accounting department. The user enters the steps of the process into the terminal in natural language, prompted with a message such as, "I have entered each step of the monthly reporting process. Which parts can be automated?" The server then analyzes the data and determines whether "data aggregation can be automated." This result allows the user to quickly decide whether to implement specific automation tools.

[0068] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0069] Step 1:

[0070] Users input work-related information in natural language using a dedicated terminal. The input information includes specific details about their work, such as "procedures for creating monthly reports." This input is received through a text input field on the terminal.

[0071] Step 2:

[0072] The terminal converts the input natural language information into a parseable data format. Here, a text analysis library is used to tokenize the information and structure the data. The input is natural language text, and the output is structured data in JSON format.

[0073] Step 3:

[0074] The server receives structured data sent from the terminal. To convert this data into a standardized format, tokenization and noise filtering are performed. This makes the data suitable for analysis by generative artificial intelligence.

[0075] Step 4:

[0076] The server supplies pre-processed data to a generative artificial intelligence for analysis. This AI analyzes the workflow in detail and identifies operations that can be automated. The input is pre-processed data, and the output is information about points that can be automated.

[0077] Step 5:

[0078] The server uses the results of generative artificial intelligence analysis to generate information including identified areas that can be automated and recommended tools and methods. These results are formatted in JSON.

[0079] Step 6:

[0080] The server sends the analysis results to the terminal. The terminal then visually presents the received information to the user. JavaScript or HTML5 is used to display the information in a dashboard format.

[0081] Step 7:

[0082] Users review the analysis results displayed on their terminals and, if necessary, implement procedures to improve their business processes. This includes actions such as introducing specific automation tools.

[0083] (Application Example 1)

[0084] 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."

[0085] In order to improve the efficiency of operations on the production floor, it is necessary to determine which parts of production lines with a large number of work processes should be automated and to quickly introduce appropriate automation tools. However, manual decision-making and implementation are time-consuming and labor-intensive, and there is a possibility of errors in judgment, so an efficient method is needed.

[0086] 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.

[0087] In this invention, the server includes means for receiving business information, performing preprocessing, and then analyzing it with a generative artificial intelligence control device; means for identifying business categories that can be automated; means for presenting the identified business categories that can be automated to the user; and means for analyzing the business flow from voice input and proposing a control device suitable for the identified categories. This enables the rapid and accurate identification of processes that can be automated at the work site and the introduction of appropriate automation tools.

[0088] "Business information" refers to data that shows the progress and components of business operations, including the workflow and task details in the production site.

[0089] "Preprocessing" refers to a series of operations that prepare received data for analysis, including processes such as data tokenization and noise removal.

[0090] A "generative artificial intelligence control system" is a type of artificial intelligence system that can analyze input data and generate specific outputs, providing appropriate solutions to specific problems.

[0091] "Automable task categories" refer to parts of tasks that have been evaluated as being able to improve efficiency by applying automation technology.

[0092] "Users" refer to individuals or organizations that use systems and devices to perform their duties, and are ultimately responsible for making and executing decisions.

[0093] "Voice input" is a method of inputting voice data using a device such as a microphone, which is then converted into text data through natural language processing.

[0094] A "control device" is a hardware or software system that supervises and automates the execution of a production line or process, and is configured to perform specific actions or tasks.

[0095] A description of the embodiment for carrying out the invention will be given.

[0096] This invention provides an automation support system to promote efficiency in production sites. The system begins with a worker describing the workflow in natural language on-site, using smart glasses as a voice input device. Voice recognition software embedded in the smart glasses converts the voice data into text data, and the terminal sends this text data to a server. The server preprocesses the received work information (including tokenization and noise filtering) and passes the processed data to a generative artificial intelligence control device. In this device, a generative AI model analyzes the data and identifies work categories that can be automated.

[0097] The identified automatable task categories are sent from the server to the terminal and visually displayed on the smart glasses' screen. This allows the user to quickly see which categories can be automated and what control devices and technologies are suitable for them.

[0098] As a concrete example, consider the parts supply process in an electronic component assembly line. When a worker says, "Please tell me how to improve the efficiency of parts supply," the AI ​​model analyzes the process and presents specific suggestions such as, "Automating parts supply is recommended." As a result, the worker can accurately understand which processes should be considered for automation.

[0099] An example of a prompt to the generated AI model would be, "Please describe the workflow of the production line. Which steps could be automated?" This prompt prompts the AI ​​to perform the necessary analysis and extract specific points for automation.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The user inputs their workflow via voice through smart glasses. The smart glasses receive the voice data and convert it into text data using speech recognition software. This conversion process analyzes the voice waveform, recognizes phonemes, and transcribes them into text. The input is voice data, and the output is text data.

[0103] Step 2:

[0104] The terminal sends the generated text data to the server. The server receives the text data and begins preprocessing. This preprocessing includes tokenization and noise filtering of the data. The input is character data, and the output is clear character data with noise removed. This data is then transformed into a state ready for analysis.

[0105] Step 3:

[0106] The server sends pre-processed text data to a generative artificial intelligence control unit. The control unit analyzes the data using a generative AI model. In this analysis process, natural language processing technology is used to analyze the workflow and identify business segments that can be automated. The input is clear text data, and the output is business segments that can be automated.

[0107] Step 4:

[0108] The server sends the identified automatable task categories to the user's terminal. The terminal receives this information and displays it visually on the smart glasses' display. The user can review the presented information and, if necessary, investigate further to determine which parts should be automated. The input is the automatable task categories, and the output is a visual presentation of information.

[0109] Step 5:

[0110] Based on the information presented, the user considers the control devices and automation methods recommended by the generated AI model and decides to implement them as needed. This step involves gathering feedback from user testing and developing an actual implementation plan. The inputs are visual information and the user's judgment, while the output is the implementation decision.

[0111] 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.

[0112] To implement the present invention, a system is constructed that processes business information and provides information accordingly while recognizing the user's emotional state. The user inputs business information in natural language using a dedicated terminal, and emotional data is acquired simultaneously. This includes the user's voice tone, facial expression recognition, or emotional analysis from text.

[0113] The terminal formats business information and sends it to the server along with emotional data. The server uses generative artificial intelligence to analyze the business information and identify parts of the business that can be automated, while an emotional engine analyzes the user's emotional state. As a result of the analysis, the server generates recommendations tailored to the user's emotions, along with information indicating what can be automated, and presents measures such as actions to reduce stress and changes in work priorities.

[0114] This data is transmitted from the server to the terminal, which then visually displays the results to the user. The display is adjusted based on sentiment data, ensuring it is in the most optimal format for the user.

[0115] As a concrete example, suppose a user working in the sales department of a certain company inputs customer service tasks. When the emotion engine detects the user's dissatisfaction or stress, the system suggests "automation using XX tool" and also proposes stress reduction measures such as "taking a break." This allows the user to perform their tasks efficiently while reducing physical and mental strain.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] When users input business information into the terminal using natural language, an emotion sensor detects the user's voice tone and facial expressions, and simultaneously collects emotional data.

[0119] Step 2:

[0120] The terminal converts the entered business information into an analyzable format, packages it together with sentiment data, and sends it to the server.

[0121] Step 3:

[0122] The server receives business information and passes it to a generative artificial intelligence (AI) to identify parts of the business that can be automated. The AI ​​evaluates the processing efficiency of each task and extracts the parts that should be automated.

[0123] Step 4:

[0124] The server uses an emotion engine to analyze user emotional data. It evaluates the user's current stress level and emotional state, and considers measures to reduce the psychological burden on them during work.

[0125] Step 5:

[0126] The server aggregates results from generative AI and emotion engines and formats the information to be presented to the user. This information includes automation recommendations and emotion-based advice.

[0127] Step 6:

[0128] The server formats the information and sends it to the terminal. The terminal displays the received content in a format suitable for the user, providing a visually easy-to-understand message board.

[0129] Step 7:

[0130] Users review the results displayed on their devices, readjust their work plans and priorities based on suggested automation methods and emotion-based actions, and then execute them.

[0131] (Example 2)

[0132] 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".

[0133] While typical business support systems focus on analyzing business information and proposing automation solutions, they fail to provide information that takes into account the user's emotional state. This presents a challenge in simultaneously achieving improved user work efficiency and reduced stress.

[0134] 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.

[0135] In this invention, the server includes means for receiving business information and emotion data and performing preprocessing based on them; means for analyzing business information with generative artificial intelligence and identifying business parts that can be automated; and means for analyzing the user's emotional state using an emotion engine and generating recommendations based on the analysis results. This makes it possible not only to improve the efficiency of business operations but also to provide information that reduces the psychological burden on the user.

[0136] "Business information" refers to information entered by users in relation to their work, and is data provided in natural language format.

[0137] "Emotional data" refers to data that indicates a user's emotional state, and is obtained through voice tone, facial expressions, or text analysis.

[0138] "Generative artificial intelligence" is an artificial intelligence technology that learns from large amounts of data and has the ability to respond to newly generated questions in natural language.

[0139] "Automable business processes" refer to the parts of repetitive or rule-based business processes that can be made more efficient or fully automated through technology.

[0140] An "emotion engine" is software or an algorithm that analyzes input emotional data and evaluates the user's psychological state.

[0141] "Recommendations" are suggestions and improvement measures presented to the user based on the analysis results, with the aim of improving work efficiency and reducing stress.

[0142] "Resources" refers to tools, technologies, or other available means that can be used to perform or assist in the specified tasks.

[0143] "Improvement measures" refer to specific actions or changes proposed to enhance the user's work efficiency or psychological comfort.

[0144] This invention provides a system that enables improved work efficiency and the provision of information tailored to the user's emotions through the cooperation of a user terminal and a data processing server. The user uses a dedicated terminal to input work information in natural language. The terminal also simultaneously acquires the user's emotional data using speech recognition technology (e.g., speech recognition API) and facial recognition technology (e.g., OpenCV). As a result, the input work information and emotional data are aggregated on the terminal.

[0145] The terminal converts business information into an analyzable format and sends it to the server along with sentiment data. A RESTful API is used for transmission via the internet, and the data is sent to the server in a standardized format (e.g., JSON). The server analyzes the business information using a generative AI model (e.g., a natural language processing engine) to identify business processes that can be automated.

[0146] Furthermore, the server uses an emotion engine to analyze emotional data and understand the user's emotional state. Based on this, suggestions for automating tasks and stress reduction measures are generated. Finally, the server sends this information to the terminal, which displays the results to the user in a visual format. This display can be done using, for example, a web browser or a mobile application.

[0147] For example, if a user in the sales department enters "I'm exhausted from a long meeting with a client" into their terminal, the system can analyze the user's work and provide recommendations such as, "Next time, please use a customer management tool to streamline your work. We recommend taking a break." Through such suggestions, users can improve their work efficiency and reduce their psychological burden.

[0148] Examples of prompt statements include the following:

[0149] "My current job is causing me stress. How can I improve it?"

[0150] "I'm exhausted from all the meetings. Are there any ways to make my work more efficient?"

[0151] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0152] Step 1:

[0153] Users input work information in natural language using a dedicated terminal. The terminal analyzes voice tone using speech recognition technology and acquires emotional data from facial expressions using facial recognition technology. In addition, it performs sentiment analysis based on the input text. This emotional data serves as foundational information for evaluating the user's psychological state. Input consists of natural language text and audio / visual data, while output consists of structured text data and emotional data.

[0154] Step 2:

[0155] The terminal converts natural language business information into a parseable format. Specifically, it uses a natural language processing library to analyze the text, extracts relevant keywords, and converts them into JSON format. This parseable format, along with sentiment data, is sent to the server. The input consists of user-entered business information and sentiment data, and the output is the parsed JSON data.

[0156] Step 3:

[0157] The server uses a generative AI model to analyze business information. Here, data in an analyzable format is input to the AI ​​model to identify parts of the business process that can be automated. Natural language processing techniques are used to classify common business tasks and select those that can be proposed for automation. The input is business data in JSON format, and the output is a list of business parts that can be automated.

[0158] Step 4:

[0159] The server analyzes emotional data using an emotion engine. This analysis evaluates the user's emotional state and identifies psychological indicators such as stress and dissatisfaction. The emotion engine processes input data using an emotion analysis tool. The input is emotional data, and the output is the analysis result of the user's emotional state.

[0160] Step 5:

[0161] The server generates recommendations based on the analysis of business information and emotional data. These recommendations include specific suggestions for automating tasks and stress reduction measures. In this process, the recommendation engine proposes the optimal action considering the analysis results and emotional state. Inputs are a list of automatable business processes and the results of the emotional state analysis, while output is a list of recommendations.

[0162] Step 6:

[0163] The server sends the generated recommendations to the terminal, which then displays the results visually. Through a user-friendly interface, it presents suggestions for improving work efficiency and reducing psychological burden. The input is a list of recommendations, and the output is the visual information presented to the user.

[0164] (Application Example 2)

[0165] 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."

[0166] In brick-and-mortar stores, such as those in the retail industry, it is difficult to quickly grasp customers' emotional states and provide individually optimized services. Furthermore, consistency in service quality is a challenge, as it relies heavily on the responsiveness of individual employees. A new customer service system is needed to solve these problems and respond to customer needs in real time.

[0167] 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.

[0168] In this invention, the server includes means for receiving business information, pre-processing it, and then analyzing it with generative artificial intelligence; means for analyzing the emotions of a subject using audio and video data; and means for providing dynamically generated recommendations to the subject based on the analyzed emotions. This makes it possible to provide personalized services based on the emotional state of the customer.

[0169] "Business information" refers to data and instructions related to an organization's or business activities, and serves as the foundation for improving or automating various business processes.

[0170] "Generative artificial intelligence" is a software technology that has the ability to analyze diverse data and generate new information and suggestions, thereby improving business efficiency and supporting decision-making.

[0171] "Automable business processes" refer to tasks and operations within existing work processes that can be carried out without human intervention by utilizing technology.

[0172] "Audio data and video data" refers to information about the subject's voice and visual information, and the purpose of analyzing this data is to understand their emotional and behavioral patterns.

[0173] "Methods for analyzing emotions" refers to techniques that analyze biological elements such as voice and facial expressions in order to understand the emotional state of a subject.

[0174] "Recommendations" refer to guidance policies or action plans provided to encourage specific actions or decisions based on analysis results.

[0175] The system for implementing this invention efficiently handles business information using natural language processing, analyzes the emotional state of the target person in real time, and provides appropriate recommendations. Specifically, the following hardware and software are used for implementation.

[0176] The terminal is equipped with a camera and microphone for capturing audio and video, and transmits this data, along with the user's inputted work information, to the server. The terminal utilizes NLP (Natural Language Processing) technology to convert the information into a format that can be analyzed, and is particularly executed using a system based on Python and TENSORFLOW®.

[0177] The server uses generative artificial intelligence to perform necessary analyses based on the received business information. OpenCV and Google's (registered trademark) sentiment analysis API are combined to analyze audio and video data, understanding the user's emotional state. Based on these analysis results, the system dynamically constructs recommendations using a generative AI model.

[0178] For example, in a physical store, if an employee using a terminal detects customer dissatisfaction, the server will display recommendations on the terminal in real time, such as "Suggest a rest area." This prompt is generated based on the customer's sentiment text, in the form of "Please suggest a course of action if the customer appears confused."

[0179] This system enables faster and more optimized service delivery in customer interactions, ultimately contributing to improved customer satisfaction.

[0180] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0181] Step 1:

[0182] Users input business information in natural language through their terminals. During this process, the terminal's camera and microphone simultaneously capture audio and video data. This input data is then sent to the terminal's pre-processing system.

[0183] Step 2:

[0184] The terminal converts the received natural language business information into a parseable format. Specifically, it uses natural language processing techniques with Python to tokenize and structure the text data. Simultaneously, audio data is converted to text using speech recognition technology, and facial expression recognition is performed on video data using OpenCV. The results of these processes are then sent to the server.

[0185] Step 3:

[0186] The server uses generative artificial intelligence to analyze the received business information. It also uses Google's sentiment analysis API to analyze the user's emotional state from audio and video data. This analysis clearly identifies parts of the business that can be automated and the user's emotions, and then the generation of recommendations begins.

[0187] Step 4:

[0188] The server dynamically constructs recommendations based on the analysis results using a generative AI model. Specifically, it generates suggestions for automating tasks and customer response strategies tailored to the user's emotions. For example, it creates prompt messages such as "What to do if the customer is confused." These generated results are then sent to the terminal.

[0189] Step 5:

[0190] The terminal displays recommendations sent from the server to the user. These recommendations are presented in a visually accessible format, using concise text or graphical interfaces. This allows the user to respond quickly and appropriately to customer inquiries.

[0191] 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.

[0192] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0193] 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.

[0194] [Second Embodiment]

[0195] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0196] 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.

[0197] 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).

[0198] 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.

[0199] 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.

[0200] 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).

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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".

[0207] The following system is configured as an embodiment of the present invention. The user inputs business information in natural language using a dedicated terminal. This information is formatted by the terminal and transmitted to the server as analyzable data. The server analyzes the received data using a pre-built generative artificial intelligence to identify business processes that can be automated.

[0208] In detail, the server first preprocesses the received business information and converts it into a standardized format. This conversion process includes data tokenization and noise filtering. The server then passes this preprocessed data to generative artificial intelligence for analysis. The AI ​​examines the workflow and content, and extracts points suitable for automation.

[0209] The results are sent from the server to the original terminal. The terminal displays the analysis results to the user in a visually easy-to-understand format. This allows the user to review detailed information about the extracted automatable business processes and recommendations for appropriate tools and methods.

[0210] As a concrete example, consider the monthly reporting process in the accounting department of a certain company. When the user inputs each step of the process, the server automatically determines that "automation of the data aggregation portion is possible" and suggests to the user "the introduction of the XX automation tool." This allows the user to quickly implement specific DX (Digital Transformation) measures.

[0211] The following describes the processing flow.

[0212] Step 1:

[0213] The user inputs business information in natural language using a dedicated terminal. The terminal receives the input information as is and begins preparing to send it.

[0214] Step 2:

[0215] The terminal converts the input natural language business information into a parseable format. This includes preprocessing such as structuring and format conversion.

[0216] Step 3:

[0217] The terminal sends the pre-processed data to the server. The server receives the data and prepares for analysis.

[0218] Step 4:

[0219] The server performs advanced analysis on the received data using generative artificial intelligence. The AI ​​inspects the business information and identifies areas where efficiency can be improved through automation.

[0220] Step 5:

[0221] The server compiles the AI ​​analysis results and converts them into a format that can be presented to the user. This includes detailed explanations of automation points and suggested solutions.

[0222] Step 6:

[0223] The server sends the analysis results to the terminal. The terminal receives these results and prepares them to be displayed appropriately to the user.

[0224] Step 7:

[0225] The terminal displays the analysis results received visually to the user. Based on the information presented, the user can concretely plan and implement the digital transformation of their business operations.

[0226] (Example 1)

[0227] 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."

[0228] In modern business processes, there is a need to efficiently handle everything from information input to identifying elements that can be automated. However, conventional methods present challenges in that it is difficult and time-consuming to automatically analyze information written in natural language, properly standardize it, and then perform analysis using generative artificial intelligence.

[0229] 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.

[0230] In this invention, the server includes means for receiving and pre-processing information, means for converting it into a standardized format and then analyzing it with generative artificial intelligence, and means for identifying parts of the operation that can be automated. This makes it possible to perform the process from inputting business information to identifying parts that can be automated quickly and efficiently.

[0231] "Means of receiving information" refers to the function of receiving data transmitted from an external source and converting it into a format that can be processed within the system.

[0232] "Means of preprocessing" refers to the process of converting received data into a standardized format, including data tokenization and noise filtering.

[0233] "Means of converting to a standardized format" refers to a mechanism for shaping received information into a unified data format so that it can be used in other processing steps.

[0234] "Methods of analysis using generative artificial intelligence" refers to algorithms that use software agents to analyze data and detect patterns that can be automated.

[0235] "Means for identifying operations that can be automated" refers to the process of identifying and clearly indicating parts of a business workflow that can be made more efficient, based on the analysis results.

[0236] "Means of visual presentation" refers to interface technologies that display analysis results to users in a highly visible format, enabling them to intuitively understand the information.

[0237] Embodiments of this invention will now be described. The user uses a dedicated terminal. This terminal provides an interface for inputting business information in natural language. The information entered by the user is converted into a parseable data format by the terminal and sent to the server. Natural language processing technology is used for this conversion, specifically a text analysis library using Python.

[0238] The server has means to preprocess the received data and convert it into a standardized data format. Preprocessing includes tokenization and noise filtering of the data, which makes the information easier to analyze by generative artificial intelligence.

[0239] Next, the server analyzes the pre-processed data using generative artificial intelligence. This AI uses a generative AI model such as OpenAI to analyze the workflow and identify operations that can be automated.

[0240] The analysis results are sent from the server to the terminal, which then presents them to the user in a visually easy-to-understand format. This utilizes a user interface based on JavaScript and HTML5. Based on the displayed information, the user can then perform the necessary steps to automate or optimize business processes.

[0241] A concrete example is the monthly reporting process in a company's accounting department. The user enters the steps of the process into the terminal in natural language, prompted with a message such as, "I have entered each step of the monthly reporting process. Which parts can be automated?" The server then analyzes the data and determines whether "data aggregation can be automated." This result allows the user to quickly decide whether to implement specific automation tools.

[0242] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0243] Step 1:

[0244] Users input work-related information in natural language using a dedicated terminal. The input information includes specific details about their work, such as "procedures for creating monthly reports." This input is received through a text input field on the terminal.

[0245] Step 2:

[0246] The terminal converts the input natural language information into a parseable data format. Here, a text analysis library is used to tokenize the information and structure the data. The input is natural language text, and the output is structured data in JSON format.

[0247] Step 3:

[0248] The server receives structured data sent from the terminal. To convert this data into a standardized format, tokenization and noise filtering are performed. This makes the data suitable for analysis by generative artificial intelligence.

[0249] Step 4:

[0250] The server supplies pre-processed data to a generative artificial intelligence for analysis. This AI analyzes the workflow in detail and identifies operations that can be automated. The input is pre-processed data, and the output is information about points that can be automated.

[0251] Step 5:

[0252] The server uses the results of generative artificial intelligence analysis to generate information including identified areas that can be automated and recommended tools and methods. These results are formatted in JSON.

[0253] Step 6:

[0254] The server sends the analysis results to the terminal. The terminal then visually presents the received information to the user. JavaScript or HTML5 is used to display the information in a dashboard format.

[0255] Step 7:

[0256] Users review the analysis results displayed on their terminals and, if necessary, implement procedures to improve their business processes. This includes actions such as introducing specific automation tools.

[0257] (Application Example 1)

[0258] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] In order to improve the efficiency of operations on the production floor, it is necessary to determine which parts of production lines with a large number of work processes should be automated and to quickly introduce appropriate automation tools. However, manual decision-making and implementation are time-consuming and labor-intensive, and there is a possibility of errors in judgment, so an efficient method is needed.

[0260] 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.

[0261] In this invention, the server includes means for receiving business information, performing preprocessing, and then analyzing it with a generative artificial intelligence control device; means for identifying business categories that can be automated; means for presenting the identified business categories that can be automated to the user; and means for analyzing the business flow from voice input and proposing a control device suitable for the identified categories. This enables the rapid and accurate identification of processes that can be automated at the work site and the introduction of appropriate automation tools.

[0262] "Business information" refers to data that shows the progress and components of business operations, including the workflow and task details in the production site.

[0263] "Preprocessing" refers to a series of operations that prepare received data for analysis, including processes such as data tokenization and noise removal.

[0264] A "generative artificial intelligence control system" is a type of artificial intelligence system that can analyze input data and generate specific outputs, providing appropriate solutions to specific problems.

[0265] "Automable task categories" refer to parts of tasks that have been evaluated as being able to improve efficiency by applying automation technology.

[0266] "Users" refer to individuals or organizations that use systems and devices to perform their duties, and are ultimately responsible for making and executing decisions.

[0267] "Voice input" is a method of inputting voice data using a device such as a microphone, which is then converted into text data through natural language processing.

[0268] A "control device" is a hardware or software system that supervises and automates the execution of a production line or process, and is configured to perform specific actions or tasks.

[0269] A description of the embodiment for carrying out the invention will be given.

[0270] This invention provides an automation support system to promote efficiency in production sites. The system begins with a worker describing the workflow in natural language on-site, using smart glasses as a voice input device. Voice recognition software embedded in the smart glasses converts the voice data into text data, and the terminal sends this text data to a server. The server preprocesses the received work information (including tokenization and noise filtering) and passes the processed data to a generative artificial intelligence control device. In this device, a generative AI model analyzes the data and identifies work categories that can be automated.

[0271] The identified automatable task categories are sent from the server to the terminal and visually displayed on the smart glasses' screen. This allows the user to quickly see which categories can be automated and what control devices and technologies are suitable for them.

[0272] As a concrete example, consider the parts supply process in an electronic component assembly line. When a worker says, "Please tell me how to improve the efficiency of parts supply," the AI ​​model analyzes the process and presents specific suggestions such as, "Automating parts supply is recommended." As a result, the worker can accurately understand which processes should be considered for automation.

[0273] An example of a prompt to the generated AI model would be, "Please describe the workflow of the production line. Which steps could be automated?" This prompt prompts the AI ​​to perform the necessary analysis and extract specific points for automation.

[0274] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0275] Step 1:

[0276] The user inputs their workflow via voice through smart glasses. The smart glasses receive the voice data and convert it into text data using speech recognition software. This conversion process analyzes the voice waveform, recognizes phonemes, and transcribes them into text. The input is voice data, and the output is text data.

[0277] Step 2:

[0278] The terminal sends the generated text data to the server. The server receives the text data and begins preprocessing. This preprocessing includes tokenization and noise filtering of the data. The input is character data, and the output is clear character data with noise removed. This data is then transformed into a state ready for analysis.

[0279] Step 3:

[0280] The server sends the preprocessed character data to the generative artificial control device. The control device analyzes the data using a generative AI model. In this analysis process, natural language processing technology is used to analyze the business process and identify business segments that can be automated. The input is clear character data, and the output is the business segments that can be automated.

[0281] Step 4:

[0282] The server sends the identified business segments that can be automated to the user terminal. The terminal receives this information and visually displays it on the smart glasses' display. The user can check the presented information and investigate details as needed to determine which parts should be automated. The input is the business segments that can be automated, and the output is the visual information presentation.

[0283] Step 5:

[0284] Based on the presented information, the user considers the control devices and automation methods recommended by the generative AI model and decides whether to introduce them as needed. In this step, user test feedback and actual implementation plans are established. The input is the visual information and the user's judgment, and the output is the decision to introduce.

[0285] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0286] To implement the present invention, a system for providing information corresponding to the user's emotional state while recognizing the user's emotional state is constructed together with the processing of business information. The user inputs business information in natural language using a dedicated terminal, and at the same time, emotion data is also acquired. This includes the tone of the user's voice, facial expression recognition, or emotion analysis from text.

[0287] The terminal formats business information and sends it to the server along with emotional data. The server uses generative artificial intelligence to analyze the business information and identify parts of the business that can be automated, while an emotional engine analyzes the user's emotional state. As a result of the analysis, the server generates recommendations tailored to the user's emotions, along with information indicating what can be automated, and presents measures such as actions to reduce stress and changes in work priorities.

[0288] This data is transmitted from the server to the terminal, which then visually displays the results to the user. The display is adjusted based on sentiment data, ensuring it is in the most optimal format for the user.

[0289] As a concrete example, suppose a user working in the sales department of a certain company inputs customer service tasks. When the emotion engine detects the user's dissatisfaction or stress, the system suggests "automation using XX tool" and also proposes stress reduction measures such as "taking a break." This allows the user to perform their tasks efficiently while reducing physical and mental strain.

[0290] The following describes the processing flow.

[0291] Step 1:

[0292] When users input business information into the terminal using natural language, an emotion sensor detects the user's voice tone and facial expressions, and simultaneously collects emotional data.

[0293] Step 2:

[0294] The terminal converts the entered business information into an analyzable format, packages it together with sentiment data, and sends it to the server.

[0295] Step 3:

[0296] The server receives business information and passes it to a generative artificial intelligence (AI) to identify parts of the business that can be automated. The AI ​​evaluates the processing efficiency of each task and extracts the parts that should be automated.

[0297] Step 4:

[0298] The server uses an emotion engine to analyze user emotional data. It evaluates the user's current stress level and emotional state, and considers measures to reduce the psychological burden on them during work.

[0299] Step 5:

[0300] The server aggregates results from generative AI and emotion engines and formats the information to be presented to the user. This information includes automation recommendations and emotion-based advice.

[0301] Step 6:

[0302] The server formats the information and sends it to the terminal. The terminal displays the received content in a format suitable for the user, providing a visually easy-to-understand message board.

[0303] Step 7:

[0304] Users review the results displayed on their devices, readjust their work plans and priorities based on suggested automation methods and emotion-based actions, and then execute them.

[0305] (Example 2)

[0306] 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".

[0307] While typical business support systems focus on analyzing business information and proposing automation solutions, they fail to provide information that takes into account the user's emotional state. This presents a challenge in simultaneously achieving improved user work efficiency and reduced stress.

[0308] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means.

[0309] In this invention, the server includes means for receiving business information and emotional data and performing preprocessing based on them, means for analyzing the business information with generative artificial intelligence to identify business parts that can be automated, and means for analyzing the user's emotional state using an emotion engine and generating recommendations based on the analysis results. Thereby, not only the efficiency of the business can be improved, but also information can be provided to reduce the psychological burden of the user.

[0310] "Business information" is information input by the user related to business and is data provided in the form of natural language.

[0311] "Emotional data" is data indicating the user's emotional state and is obtained by voice tone, expression, or text analysis.

[0312] "Generative artificial intelligence" is an artificial intelligence technology that learns based on a large amount of data and has the ability to respond in natural language to newly generated questions.

[0313] "Automation-possible business parts" refer to parts in repetitive or rule-based business processes that can be made more efficient or fully automated by technology.

[0314] "Emotion engine" is software or an algorithm for analyzing the input emotional data and evaluating the user's psychological state.

[0315] "Recommendations" are advice or improvement measures presented to the user based on the analysis results and are aimed at improving business efficiency and reducing stress.

[0316] "Resources" refer to tools, technologies, or other available means that can be used to execute or support a specific business.

[0317] "Improvement measures" refer to specific actions or changes proposed to enhance the user's work efficiency or psychological comfort.

[0318] This invention provides a system that enables improved work efficiency and the provision of information tailored to the user's emotions through the cooperation of a user terminal and a data processing server. The user uses a dedicated terminal to input work information in natural language. The terminal also simultaneously acquires the user's emotional data using speech recognition technology (e.g., speech recognition API) and facial recognition technology (e.g., OpenCV). As a result, the input work information and emotional data are aggregated on the terminal.

[0319] The terminal converts business information into an analyzable format and sends it to the server along with sentiment data. A RESTful API is used for transmission via the internet, and the data is sent to the server in a standardized format (e.g., JSON). The server analyzes the business information using a generative AI model (e.g., a natural language processing engine) to identify business processes that can be automated.

[0320] Furthermore, the server uses an emotion engine to analyze emotional data and understand the user's emotional state. Based on this, suggestions for automating tasks and stress reduction measures are generated. Finally, the server sends this information to the terminal, which displays the results to the user in a visual format. This display can be done using, for example, a web browser or a mobile application.

[0321] For example, if a user in the sales department enters "I'm exhausted from a long meeting with a client" into their terminal, the system can analyze the user's work and provide recommendations such as, "Next time, please use a customer management tool to streamline your work. We recommend taking a break." Through such suggestions, users can improve their work efficiency and reduce their psychological burden.

[0322] Examples of prompt statements include the following:

[0323] "My current job is causing me stress. How can I improve it?"

[0324] "I'm exhausted from all the meetings. Are there any ways to make my work more efficient?"

[0325] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0326] Step 1:

[0327] Users input work information in natural language using a dedicated terminal. The terminal analyzes voice tone using speech recognition technology and acquires emotional data from facial expressions using facial recognition technology. In addition, it performs sentiment analysis based on the input text. This emotional data serves as foundational information for evaluating the user's psychological state. Input consists of natural language text and audio / visual data, while output consists of structured text data and emotional data.

[0328] Step 2:

[0329] The terminal converts natural language business information into a parseable format. Specifically, it uses a natural language processing library to analyze the text, extracts relevant keywords, and converts them into JSON format. This parseable format, along with sentiment data, is sent to the server. The input consists of user-entered business information and sentiment data, and the output is the parsed JSON data.

[0330] Step 3:

[0331] The server uses a generative AI model to analyze business information. Here, data in an analyzable format is input to the AI ​​model to identify parts of the business process that can be automated. Natural language processing techniques are used to classify common business tasks and select those that can be proposed for automation. The input is business data in JSON format, and the output is a list of business parts that can be automated.

[0332] Step 4:

[0333] The server analyzes emotional data using an emotion engine. This analysis evaluates the user's emotional state and identifies psychological indicators such as stress and dissatisfaction. The emotion engine processes input data using an emotion analysis tool. The input is emotional data, and the output is the analysis result of the user's emotional state.

[0334] Step 5:

[0335] The server generates recommendations based on the analysis of business information and emotional data. These recommendations include specific suggestions for automating tasks and stress reduction measures. In this process, the recommendation engine proposes the optimal action considering the analysis results and emotional state. Inputs are a list of automatable business processes and the results of the emotional state analysis, while output is a list of recommendations.

[0336] Step 6:

[0337] The server sends the generated recommendations to the terminal, which then displays the results visually. Through a user-friendly interface, it presents suggestions for improving work efficiency and reducing psychological burden. The input is a list of recommendations, and the output is the visual information presented to the user.

[0338] (Application Example 2)

[0339] 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."

[0340] In brick-and-mortar stores, such as those in the retail industry, it is difficult to quickly grasp customers' emotional states and provide individually optimized services. Furthermore, consistency in service quality is a challenge, as it relies heavily on the responsiveness of individual employees. A new customer service system is needed to solve these problems and respond to customer needs in real time.

[0341] 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.

[0342] In this invention, the server includes means for receiving business information, pre-processing it, and then analyzing it with generative artificial intelligence; means for analyzing the emotions of a subject using audio and video data; and means for providing dynamically generated recommendations to the subject based on the analyzed emotions. This makes it possible to provide personalized services based on the emotional state of the customer.

[0343] "Business information" refers to data and instructions related to an organization's or business activities, and serves as the foundation for improving or automating various business processes.

[0344] "Generative artificial intelligence" is a software technology that has the ability to analyze diverse data and generate new information and suggestions, thereby improving business efficiency and supporting decision-making.

[0345] "Automable business processes" refer to tasks and operations within existing work processes that can be carried out without human intervention by utilizing technology.

[0346] "Audio data and video data" refers to information about the subject's voice and visual information, and the purpose of analyzing this data is to understand their emotional and behavioral patterns.

[0347] "Methods for analyzing emotions" refers to techniques that analyze biological elements such as voice and facial expressions in order to understand the emotional state of a subject.

[0348] "Recommendations" refer to guidance policies or action plans provided to encourage specific actions or decisions based on analysis results.

[0349] The system for implementing this invention efficiently handles business information using natural language processing, analyzes the emotional state of the target person in real time, and provides appropriate recommendations. Specifically, the following hardware and software are used for implementation.

[0350] The terminal is equipped with a camera and microphone for capturing audio and video, and sends this data to the server along with the business information entered by the user. The terminal utilizes NLP (Natural Language Processing) technology to convert the information into a format that can be analyzed, and is particularly executed using a system based on Python and TensorFlow.

[0351] The server uses generative artificial intelligence to perform necessary analyses based on the received business information. OpenCV and Google's sentiment analysis API are combined to analyze audio and video data, understanding the user's emotional state. Based on these analysis results, the system dynamically constructs recommendations using a generative AI model.

[0352] For example, in a physical store, if an employee using a terminal detects customer dissatisfaction, the server will display recommendations on the terminal in real time, such as "Suggest a rest area." This prompt is generated based on the customer's sentiment text, in the form of "Please suggest a course of action if the customer appears confused."

[0353] This system enables faster and more optimized service delivery in customer interactions, ultimately contributing to improved customer satisfaction.

[0354] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0355] Step 1:

[0356] Users input business information in natural language through their terminals. During this process, the terminal's camera and microphone simultaneously capture audio and video data. This input data is then sent to the terminal's pre-processing system.

[0357] Step 2:

[0358] The terminal converts the received natural language business information into a parseable format. Specifically, it uses natural language processing techniques with Python to tokenize and structure the text data. Simultaneously, audio data is converted to text using speech recognition technology, and facial expression recognition is performed on video data using OpenCV. The results of these processes are then sent to the server.

[0359] Step 3:

[0360] The server uses generative artificial intelligence to analyze the received business information. It also uses Google's sentiment analysis API to analyze the user's emotional state from audio and video data. This analysis clearly identifies parts of the business that can be automated and the user's emotions, and then the generation of recommendations begins.

[0361] Step 4:

[0362] The server dynamically constructs recommendations based on the analysis results using a generative AI model. Specifically, it generates suggestions for automating tasks and customer response strategies tailored to the user's emotions. For example, it creates prompt messages such as "What to do if the customer is confused." These generated results are then sent to the terminal.

[0363] Step 5:

[0364] The terminal displays recommendations sent from the server to the user. These recommendations are presented in a visually accessible format, using concise text or graphical interfaces. This allows the user to respond quickly and appropriately to customer inquiries.

[0365] 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.

[0366] 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.

[0367] 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.

[0368] [Third Embodiment]

[0369] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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".

[0381] The following system is configured as an embodiment of the present invention. The user inputs business information in natural language using a dedicated terminal. This information is formatted by the terminal and transmitted to the server as analyzable data. The server analyzes the received data using a pre-built generative artificial intelligence to identify business processes that can be automated.

[0382] In detail, the server first preprocesses the received business information and converts it into a standardized format. This conversion process includes data tokenization and noise filtering. The server then passes this preprocessed data to generative artificial intelligence for analysis. The AI ​​examines the workflow and content, and extracts points suitable for automation.

[0383] The results are sent from the server to the original terminal. The terminal displays the analysis results to the user in a visually easy-to-understand format. This allows the user to review detailed information about the extracted automatable business processes and recommendations for appropriate tools and methods.

[0384] As a concrete example, consider the monthly reporting process in the accounting department of a certain company. When the user inputs each step of the process, the server automatically determines that "automation of the data aggregation portion is possible" and suggests to the user "the introduction of the XX automation tool." This allows the user to quickly implement specific DX (Digital Transformation) measures.

[0385] The following describes the processing flow.

[0386] Step 1:

[0387] The user inputs business information in natural language using a dedicated terminal. The terminal receives the input information as is and begins preparing to send it.

[0388] Step 2:

[0389] The terminal converts the input natural language business information into a parseable format. This includes preprocessing such as structuring and format conversion.

[0390] Step 3:

[0391] The terminal sends the pre-processed data to the server. The server receives the data and prepares for analysis.

[0392] Step 4:

[0393] The server performs advanced analysis on the received data using generative artificial intelligence. The AI ​​inspects the business information and identifies areas where efficiency can be improved through automation.

[0394] Step 5:

[0395] The server compiles the AI ​​analysis results and converts them into a format that can be presented to the user. This includes detailed explanations of automation points and suggested solutions.

[0396] Step 6:

[0397] The server sends the analysis results to the terminal. The terminal receives these results and prepares them to be displayed appropriately to the user.

[0398] Step 7:

[0399] The terminal displays the analysis results received visually to the user. Based on the information presented, the user can concretely plan and implement the digital transformation of their business operations.

[0400] (Example 1)

[0401] 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."

[0402] In modern business processes, there is a need to efficiently handle everything from information input to identifying elements that can be automated. However, conventional methods present challenges in that it is difficult and time-consuming to automatically analyze information written in natural language, properly standardize it, and then perform analysis using generative artificial intelligence.

[0403] 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.

[0404] In this invention, the server includes means for receiving and pre-processing information, means for converting it into a standardized format and then analyzing it with generative artificial intelligence, and means for identifying parts of the operation that can be automated. This makes it possible to perform the process from inputting business information to identifying parts that can be automated quickly and efficiently.

[0405] "Means of receiving information" refers to the function of receiving data transmitted from an external source and converting it into a format that can be processed within the system.

[0406] "Means of preprocessing" refers to the process of converting received data into a standardized format, including data tokenization and noise filtering.

[0407] "Means of converting to a standardized format" refers to a mechanism for shaping received information into a unified data format so that it can be used in other processing steps.

[0408] "Methods of analysis using generative artificial intelligence" refers to algorithms that use software agents to analyze data and detect patterns that can be automated.

[0409] "Means for identifying operations that can be automated" refers to the process of identifying and clearly indicating parts of a business workflow that can be made more efficient, based on the analysis results.

[0410] "Means of visual presentation" refers to interface technologies that display analysis results to users in a highly visible format, enabling them to intuitively understand the information.

[0411] Embodiments of this invention will now be described. The user uses a dedicated terminal. This terminal provides an interface for inputting business information in natural language. The information entered by the user is converted into a parseable data format by the terminal and sent to the server. Natural language processing technology is used for this conversion, specifically a text analysis library using Python.

[0412] The server has means to preprocess the received data and convert it into a standardized data format. Preprocessing includes tokenization and noise filtering of the data, which makes the information easier to analyze by generative artificial intelligence.

[0413] Next, the server analyzes the pre-processed data using generative artificial intelligence. This AI uses a generative AI model such as OpenAI to analyze the workflow and identify operations that can be automated.

[0414] The analysis results are sent from the server to the terminal, which then presents them to the user in a visually easy-to-understand format. This utilizes a user interface based on JavaScript and HTML5. Based on the displayed information, the user can then perform the necessary steps to automate or optimize business processes.

[0415] A concrete example is the monthly reporting process in a company's accounting department. The user enters the steps of the process into the terminal in natural language, prompted with a message such as, "I have entered each step of the monthly reporting process. Which parts can be automated?" The server then analyzes the data and determines whether "data aggregation can be automated." This result allows the user to quickly decide whether to implement specific automation tools.

[0416] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0417] Step 1:

[0418] Users input work-related information in natural language using a dedicated terminal. The input information includes specific details about their work, such as "procedures for creating monthly reports." This input is received through a text input field on the terminal.

[0419] Step 2:

[0420] The terminal converts the input natural language information into a parseable data format. Here, a text analysis library is used to tokenize the information and structure the data. The input is natural language text, and the output is structured data in JSON format.

[0421] Step 3:

[0422] The server receives structured data sent from the terminal. To convert this data into a standardized format, tokenization and noise filtering are performed. This makes the data suitable for analysis by generative artificial intelligence.

[0423] Step 4:

[0424] The server supplies pre-processed data to a generative artificial intelligence for analysis. This AI analyzes the workflow in detail and identifies operations that can be automated. The input is pre-processed data, and the output is information about points that can be automated.

[0425] Step 5:

[0426] The server uses the results of generative artificial intelligence analysis to generate information including identified areas that can be automated and recommended tools and methods. These results are formatted in JSON.

[0427] Step 6:

[0428] The server sends the analysis results to the terminal. The terminal then visually presents the received information to the user. JavaScript or HTML5 is used to display the information in a dashboard format.

[0429] Step 7:

[0430] Users review the analysis results displayed on their terminals and, if necessary, implement procedures to improve their business processes. This includes actions such as introducing specific automation tools.

[0431] (Application Example 1)

[0432] 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."

[0433] In order to improve the efficiency of operations on the production floor, it is necessary to determine which parts of production lines with a large number of work processes should be automated and to quickly introduce appropriate automation tools. However, manual decision-making and implementation are time-consuming and labor-intensive, and there is a possibility of errors in judgment, so an efficient method is needed.

[0434] 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.

[0435] In this invention, the server includes means for receiving business information, performing preprocessing, and then analyzing it with a generative artificial intelligence control device; means for identifying business categories that can be automated; means for presenting the identified business categories that can be automated to the user; and means for analyzing the business flow from voice input and proposing a control device suitable for the identified categories. This enables the rapid and accurate identification of processes that can be automated at the work site and the introduction of appropriate automation tools.

[0436] "Business information" refers to data that shows the progress and components of business operations, including the workflow and task details in the production site.

[0437] "Preprocessing" refers to a series of operations that prepare received data for analysis, including processes such as data tokenization and noise removal.

[0438] A "generative artificial intelligence control system" is a type of artificial intelligence system that can analyze input data and generate specific outputs, providing appropriate solutions to specific problems.

[0439] "Automable task categories" refer to parts of tasks that have been evaluated as being able to improve efficiency by applying automation technology.

[0440] "Users" refer to individuals or organizations that use systems and devices to perform their duties, and are ultimately responsible for making and executing decisions.

[0441] "Voice input" is a method of inputting voice data using a device such as a microphone, which is then converted into text data through natural language processing.

[0442] A "control device" is a hardware or software system that supervises and automates the execution of a production line or process, and is configured to perform specific actions or tasks.

[0443] A description of the embodiment for carrying out the invention will be given.

[0444] This invention provides an automation support system to promote efficiency in production sites. The system begins with a worker describing the workflow in natural language on-site, using smart glasses as a voice input device. Voice recognition software embedded in the smart glasses converts the voice data into text data, and the terminal sends this text data to a server. The server preprocesses the received work information (including tokenization and noise filtering) and passes the processed data to a generative artificial intelligence control device. In this device, a generative AI model analyzes the data and identifies work categories that can be automated.

[0445] The identified automatable task categories are sent from the server to the terminal and visually displayed on the smart glasses' screen. This allows the user to quickly see which categories can be automated and what control devices and technologies are suitable for them.

[0446] As a concrete example, consider the parts supply process in an electronic component assembly line. When a worker says, "Please tell me how to improve the efficiency of parts supply," the AI ​​model analyzes the process and presents specific suggestions such as, "Automating parts supply is recommended." As a result, the worker can accurately understand which processes should be considered for automation.

[0447] An example of a prompt to the generated AI model would be, "Please describe the workflow of the production line. Which steps could be automated?" This prompt prompts the AI ​​to perform the necessary analysis and extract specific points for automation.

[0448] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0449] Step 1:

[0450] The user inputs their workflow via voice through smart glasses. The smart glasses receive the voice data and convert it into text data using speech recognition software. This conversion process analyzes the voice waveform, recognizes phonemes, and transcribes them into text. The input is voice data, and the output is text data.

[0451] Step 2:

[0452] The terminal sends the generated text data to the server. The server receives the text data and begins preprocessing. This preprocessing includes tokenization and noise filtering of the data. The input is character data, and the output is clear character data with noise removed. This data is then transformed into a state ready for analysis.

[0453] Step 3:

[0454] The server sends pre-processed text data to a generative artificial intelligence control unit. The control unit analyzes the data using a generative AI model. In this analysis process, natural language processing technology is used to analyze the workflow and identify business segments that can be automated. The input is clear text data, and the output is business segments that can be automated.

[0455] Step 4:

[0456] The server sends the identified automatable task categories to the user's terminal. The terminal receives this information and displays it visually on the smart glasses' display. The user can review the presented information and, if necessary, investigate further to determine which parts should be automated. The input is the automatable task categories, and the output is a visual presentation of information.

[0457] Step 5:

[0458] Based on the information presented, the user considers the control devices and automation methods recommended by the generated AI model and decides to implement them as needed. This step involves gathering feedback from user testing and developing an actual implementation plan. The inputs are visual information and the user's judgment, while the output is the implementation decision.

[0459] 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.

[0460] To implement the present invention, a system is constructed that processes business information and provides information accordingly while recognizing the user's emotional state. The user inputs business information in natural language using a dedicated terminal, and emotional data is acquired simultaneously. This includes the user's voice tone, facial expression recognition, or emotional analysis from text.

[0461] The terminal formats business information and sends it to the server along with emotional data. The server uses generative artificial intelligence to analyze the business information and identify parts of the business that can be automated, while an emotional engine analyzes the user's emotional state. As a result of the analysis, the server generates recommendations tailored to the user's emotions, along with information indicating what can be automated, and presents measures such as actions to reduce stress and changes in work priorities.

[0462] This data is transmitted from the server to the terminal, which then visually displays the results to the user. The display is adjusted based on sentiment data, ensuring it is in the most optimal format for the user.

[0463] As a concrete example, suppose a user working in the sales department of a certain company inputs customer service tasks. When the emotion engine detects the user's dissatisfaction or stress, the system suggests "automation using XX tool" and also proposes stress reduction measures such as "taking a break." This allows the user to perform their tasks efficiently while reducing physical and mental strain.

[0464] The following describes the processing flow.

[0465] Step 1:

[0466] When users input business information into the terminal using natural language, an emotion sensor detects the user's voice tone and facial expressions, and simultaneously collects emotional data.

[0467] Step 2:

[0468] The terminal converts the entered business information into an analyzable format, packages it together with sentiment data, and sends it to the server.

[0469] Step 3:

[0470] The server receives business information and passes it to a generative artificial intelligence (AI) to identify parts of the business that can be automated. The AI ​​evaluates the processing efficiency of each task and extracts the parts that should be automated.

[0471] Step 4:

[0472] The server uses an emotion engine to analyze user emotional data. It evaluates the user's current stress level and emotional state, and considers measures to reduce the psychological burden on them during work.

[0473] Step 5:

[0474] The server aggregates results from generative AI and emotion engines and formats the information to be presented to the user. This information includes automation recommendations and emotion-based advice.

[0475] Step 6:

[0476] The server formats the information and sends it to the terminal. The terminal displays the received content in a format suitable for the user, providing a visually easy-to-understand message board.

[0477] Step 7:

[0478] Users review the results displayed on their devices, readjust their work plans and priorities based on suggested automation methods and emotion-based actions, and then execute them.

[0479] (Example 2)

[0480] 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."

[0481] While typical business support systems focus on analyzing business information and proposing automation solutions, they fail to provide information that takes into account the user's emotional state. This presents a challenge in simultaneously achieving improved user work efficiency and reduced stress.

[0482] 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.

[0483] In this invention, the server includes means for receiving business information and emotion data and performing preprocessing based on them; means for analyzing business information with generative artificial intelligence and identifying business parts that can be automated; and means for analyzing the user's emotional state using an emotion engine and generating recommendations based on the analysis results. This makes it possible not only to improve the efficiency of business operations but also to provide information that reduces the psychological burden on the user.

[0484] "Business information" refers to information entered by users in relation to their work, and is data provided in natural language format.

[0485] "Emotional data" refers to data that indicates a user's emotional state, and is obtained through voice tone, facial expressions, or text analysis.

[0486] "Generative artificial intelligence" is an artificial intelligence technology that learns from large amounts of data and has the ability to respond to newly generated questions in natural language.

[0487] "Automable business processes" refer to the parts of repetitive or rule-based business processes that can be made more efficient or fully automated through technology.

[0488] An "emotion engine" is software or an algorithm that analyzes input emotional data and evaluates the user's psychological state.

[0489] "Recommendations" are suggestions and improvement measures presented to the user based on the analysis results, with the aim of improving work efficiency and reducing stress.

[0490] "Resources" refers to tools, technologies, or other available means that can be used to perform or assist in the specified tasks.

[0491] "Improvement measures" refer to specific actions or changes proposed to enhance the user's work efficiency or psychological comfort.

[0492] This invention provides a system that enables improved work efficiency and the provision of information tailored to the user's emotions through the cooperation of a user terminal and a data processing server. The user uses a dedicated terminal to input work information in natural language. The terminal also simultaneously acquires the user's emotional data using speech recognition technology (e.g., speech recognition API) and facial recognition technology (e.g., OpenCV). As a result, the input work information and emotional data are aggregated on the terminal.

[0493] The terminal converts business information into an analyzable format and sends it to the server along with sentiment data. A RESTful API is used for transmission via the internet, and the data is sent to the server in a standardized format (e.g., JSON). The server analyzes the business information using a generative AI model (e.g., a natural language processing engine) to identify business processes that can be automated.

[0494] Furthermore, the server uses an emotion engine to analyze emotional data and understand the user's emotional state. Based on this, suggestions for automating tasks and stress reduction measures are generated. Finally, the server sends this information to the terminal, which displays the results to the user in a visual format. This display can be done using, for example, a web browser or a mobile application.

[0495] For example, if a user in the sales department enters "I'm exhausted from a long meeting with a client" into their terminal, the system can analyze the user's work and provide recommendations such as, "Next time, please use a customer management tool to streamline your work. We recommend taking a break." Through such suggestions, users can improve their work efficiency and reduce their psychological burden.

[0496] Examples of prompt statements include the following:

[0497] "My current job is causing me stress. How can I improve it?"

[0498] "I'm exhausted from all the meetings. Are there any ways to make my work more efficient?"

[0499] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0500] Step 1:

[0501] Users input work information in natural language using a dedicated terminal. The terminal analyzes voice tone using speech recognition technology and acquires emotional data from facial expressions using facial recognition technology. In addition, it performs sentiment analysis based on the input text. This emotional data serves as foundational information for evaluating the user's psychological state. Input consists of natural language text and audio / visual data, while output consists of structured text data and emotional data.

[0502] Step 2:

[0503] The terminal converts natural language business information into a parseable format. Specifically, it uses a natural language processing library to analyze the text, extracts relevant keywords, and converts them into JSON format. This parseable format, along with sentiment data, is sent to the server. The input consists of user-entered business information and sentiment data, and the output is the parsed JSON data.

[0504] Step 3:

[0505] The server uses a generative AI model to analyze business information. Here, data in an analyzable format is input to the AI ​​model to identify parts of the business process that can be automated. Natural language processing techniques are used to classify common business tasks and select those that can be proposed for automation. The input is business data in JSON format, and the output is a list of business parts that can be automated.

[0506] Step 4:

[0507] The server analyzes emotional data using an emotion engine. This analysis evaluates the user's emotional state and identifies psychological indicators such as stress and dissatisfaction. The emotion engine processes input data using an emotion analysis tool. The input is emotional data, and the output is the analysis result of the user's emotional state.

[0508] Step 5:

[0509] The server generates recommendations based on the analysis of business information and emotional data. These recommendations include specific suggestions for automating tasks and stress reduction measures. In this process, the recommendation engine proposes the optimal action considering the analysis results and emotional state. Inputs are a list of automatable business processes and the results of the emotional state analysis, while output is a list of recommendations.

[0510] Step 6:

[0511] The server sends the generated recommendations to the terminal, which then displays the results visually. Through a user-friendly interface, it presents suggestions for improving work efficiency and reducing psychological burden. The input is a list of recommendations, and the output is the visual information presented to the user.

[0512] (Application Example 2)

[0513] 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."

[0514] In brick-and-mortar stores, such as those in the retail industry, it is difficult to quickly grasp customers' emotional states and provide individually optimized services. Furthermore, consistency in service quality is a challenge, as it relies heavily on the responsiveness of individual employees. A new customer service system is needed to solve these problems and respond to customer needs in real time.

[0515] 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.

[0516] In this invention, the server includes means for receiving business information, pre-processing it, and then analyzing it with generative artificial intelligence; means for analyzing the emotions of a subject using audio and video data; and means for providing dynamically generated recommendations to the subject based on the analyzed emotions. This makes it possible to provide personalized services based on the emotional state of the customer.

[0517] "Business information" refers to data and instructions related to an organization's or business activities, and serves as the foundation for improving or automating various business processes.

[0518] "Generative artificial intelligence" is a software technology that has the ability to analyze diverse data and generate new information and suggestions, thereby improving business efficiency and supporting decision-making.

[0519] "Automable business processes" refer to tasks and operations within existing work processes that can be carried out without human intervention by utilizing technology.

[0520] "Audio data and video data" refers to information about the subject's voice and visual information, and the purpose of analyzing this data is to understand their emotional and behavioral patterns.

[0521] "Methods for analyzing emotions" refers to techniques that analyze biological elements such as voice and facial expressions in order to understand the emotional state of a subject.

[0522] "Recommendations" refer to guidance policies or action plans provided to encourage specific actions or decisions based on analysis results.

[0523] The system for implementing this invention efficiently handles business information using natural language processing, analyzes the emotional state of the target person in real time, and provides appropriate recommendations. Specifically, the following hardware and software are used for implementation.

[0524] The terminal is equipped with a camera and microphone for capturing audio and video, and sends this data to the server along with the business information entered by the user. The terminal utilizes NLP (Natural Language Processing) technology to convert the information into a format that can be analyzed, and is particularly executed using a system based on Python and TensorFlow.

[0525] The server uses generative artificial intelligence to perform necessary analyses based on the received business information. OpenCV and Google's sentiment analysis API are combined to analyze audio and video data, understanding the user's emotional state. Based on these analysis results, the system dynamically constructs recommendations using a generative AI model.

[0526] For example, in a physical store, if an employee using a terminal detects customer dissatisfaction, the server will display recommendations on the terminal in real time, such as "Suggest a rest area." This prompt is generated based on the customer's sentiment text, in the form of "Please suggest a course of action if the customer appears confused."

[0527] This system enables faster and more optimized service delivery in customer interactions, ultimately contributing to improved customer satisfaction.

[0528] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0529] Step 1:

[0530] Users input business information in natural language through their terminals. During this process, the terminal's camera and microphone simultaneously capture audio and video data. This input data is then sent to the terminal's pre-processing system.

[0531] Step 2:

[0532] The terminal converts the received natural language business information into a parseable format. Specifically, it uses natural language processing techniques with Python to tokenize and structure the text data. Simultaneously, audio data is converted to text using speech recognition technology, and facial expression recognition is performed on video data using OpenCV. The results of these processes are then sent to the server.

[0533] Step 3:

[0534] The server uses generative artificial intelligence to analyze the received business information. It also uses Google's sentiment analysis API to analyze the user's emotional state from audio and video data. This analysis clearly identifies parts of the business that can be automated and the user's emotions, and then the generation of recommendations begins.

[0535] Step 4:

[0536] The server dynamically constructs recommendations based on the analysis results using a generative AI model. Specifically, it generates suggestions for automating tasks and customer response strategies tailored to the user's emotions. For example, it creates prompt messages such as "What to do if the customer is confused." These generated results are then sent to the terminal.

[0537] Step 5:

[0538] The terminal displays recommendations sent from the server to the user. These recommendations are presented in a visually accessible format, using concise text or graphical interfaces. This allows the user to respond quickly and appropriately to customer inquiries.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] [Fourth Embodiment]

[0543] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0544] 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.

[0545] 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).

[0546] 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.

[0547] 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.

[0548] 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).

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] 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".

[0556] The following system is configured as an embodiment of the present invention. The user inputs business information in natural language using a dedicated terminal. This information is formatted by the terminal and transmitted to the server as analyzable data. The server analyzes the received data using a pre-built generative artificial intelligence to identify business processes that can be automated.

[0557] In detail, the server first preprocesses the received business information and converts it into a standardized format. This conversion process includes data tokenization and noise filtering. The server then passes this preprocessed data to generative artificial intelligence for analysis. The AI ​​examines the workflow and content, and extracts points suitable for automation.

[0558] The results are sent from the server to the original terminal. The terminal displays the analysis results to the user in a visually easy-to-understand format. This allows the user to review detailed information about the extracted automatable business processes and recommendations for appropriate tools and methods.

[0559] As a concrete example, consider the monthly reporting process in the accounting department of a certain company. When the user inputs each step of the process, the server automatically determines that "automation of the data aggregation portion is possible" and suggests to the user "the introduction of the XX automation tool." This allows the user to quickly implement specific DX (Digital Transformation) measures.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The user inputs business information in natural language using a dedicated terminal. The terminal receives the input information as is and begins preparing to send it.

[0563] Step 2:

[0564] The terminal converts the input natural language business information into a parseable format. This includes preprocessing such as structuring and format conversion.

[0565] Step 3:

[0566] The terminal sends the pre-processed data to the server. The server receives the data and prepares for analysis.

[0567] Step 4:

[0568] The server performs advanced analysis on the received data using generative artificial intelligence. The AI ​​inspects the business information and identifies areas where efficiency can be improved through automation.

[0569] Step 5:

[0570] The server compiles the AI ​​analysis results and converts them into a format that can be presented to the user. This includes detailed explanations of automation points and suggested solutions.

[0571] Step 6:

[0572] The server sends the analysis results to the terminal. The terminal receives these results and prepares them to be displayed appropriately to the user.

[0573] Step 7:

[0574] The terminal displays the analysis results received visually to the user. Based on the information presented, the user can concretely plan and implement the digital transformation of their business operations.

[0575] (Example 1)

[0576] 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".

[0577] In modern business processes, there is a need to efficiently handle everything from information input to identifying elements that can be automated. However, conventional methods present challenges in that it is difficult and time-consuming to automatically analyze information written in natural language, properly standardize it, and then perform analysis using generative artificial intelligence.

[0578] 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.

[0579] In this invention, the server includes means for receiving and pre-processing information, means for converting it into a standardized format and then analyzing it with generative artificial intelligence, and means for identifying parts of the operation that can be automated. This makes it possible to perform the process from inputting business information to identifying parts that can be automated quickly and efficiently.

[0580] "Means of receiving information" refers to the function of receiving data transmitted from an external source and converting it into a format that can be processed within the system.

[0581] "Means of preprocessing" refers to the process of converting received data into a standardized format, including data tokenization and noise filtering.

[0582] "Means of converting to a standardized format" refers to a mechanism for shaping received information into a unified data format so that it can be used in other processing steps.

[0583] "Methods of analysis using generative artificial intelligence" refers to algorithms that use software agents to analyze data and detect patterns that can be automated.

[0584] "Means for identifying operations that can be automated" refers to the process of identifying and clearly indicating parts of a business workflow that can be made more efficient, based on the analysis results.

[0585] "Means of visual presentation" refers to interface technologies that display analysis results to users in a highly visible format, enabling them to intuitively understand the information.

[0586] Embodiments of this invention will now be described. The user uses a dedicated terminal. This terminal provides an interface for inputting business information in natural language. The information entered by the user is converted into a parseable data format by the terminal and sent to the server. Natural language processing technology is used for this conversion, specifically a text analysis library using Python.

[0587] The server has means to preprocess the received data and convert it into a standardized data format. Preprocessing includes tokenization and noise filtering of the data, which makes the information easier to analyze by generative artificial intelligence.

[0588] Next, the server analyzes the pre-processed data using generative artificial intelligence. This AI uses a generative AI model such as OpenAI to analyze the workflow and identify operations that can be automated.

[0589] The analysis results are sent from the server to the terminal, which then presents them to the user in a visually easy-to-understand format. This utilizes a user interface based on JavaScript and HTML5. Based on the displayed information, the user can then perform the necessary steps to automate or optimize business processes.

[0590] A concrete example is the monthly reporting process in a company's accounting department. The user enters the steps of the process into the terminal in natural language, prompted with a message such as, "I have entered each step of the monthly reporting process. Which parts can be automated?" The server then analyzes the data and determines whether "data aggregation can be automated." This result allows the user to quickly decide whether to implement specific automation tools.

[0591] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0592] Step 1:

[0593] Users input work-related information in natural language using a dedicated terminal. The input information includes specific details about their work, such as "procedures for creating monthly reports." This input is received through a text input field on the terminal.

[0594] Step 2:

[0595] The terminal converts the input natural language information into a parseable data format. Here, a text analysis library is used to tokenize the information and structure the data. The input is natural language text, and the output is structured data in JSON format.

[0596] Step 3:

[0597] The server receives structured data sent from the terminal. To convert this data into a standardized format, tokenization and noise filtering are performed. This makes the data suitable for analysis by generative artificial intelligence.

[0598] Step 4:

[0599] The server supplies pre-processed data to a generative artificial intelligence for analysis. This AI analyzes the workflow in detail and identifies operations that can be automated. The input is pre-processed data, and the output is information about points that can be automated.

[0600] Step 5:

[0601] The server uses the results of generative artificial intelligence analysis to generate information including identified areas that can be automated and recommended tools and methods. These results are formatted in JSON.

[0602] Step 6:

[0603] The server sends the analysis results to the terminal. The terminal then visually presents the received information to the user. JavaScript or HTML5 is used to display the information in a dashboard format.

[0604] Step 7:

[0605] Users review the analysis results displayed on their terminals and, if necessary, implement procedures to improve their business processes. This includes actions such as introducing specific automation tools.

[0606] (Application Example 1)

[0607] 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".

[0608] In order to improve the efficiency of operations on the production floor, it is necessary to determine which parts of production lines with a large number of work processes should be automated and to quickly introduce appropriate automation tools. However, manual decision-making and implementation are time-consuming and labor-intensive, and there is a possibility of errors in judgment, so an efficient method is needed.

[0609] 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.

[0610] In this invention, the server includes means for receiving business information, performing preprocessing, and then analyzing it with a generative artificial intelligence control device; means for identifying business categories that can be automated; means for presenting the identified business categories that can be automated to the user; and means for analyzing the business flow from voice input and proposing a control device suitable for the identified categories. This enables the rapid and accurate identification of processes that can be automated at the work site and the introduction of appropriate automation tools.

[0611] "Business information" refers to data that shows the progress and components of business operations, including the workflow and task details in the production site.

[0612] "Preprocessing" refers to a series of operations that prepare received data for analysis, including processes such as data tokenization and noise removal.

[0613] A "generative artificial intelligence control system" is a type of artificial intelligence system that can analyze input data and generate specific outputs, providing appropriate solutions to specific problems.

[0614] "Automable task categories" refer to parts of tasks that have been evaluated as being able to improve efficiency by applying automation technology.

[0615] "Users" refer to individuals or organizations that use systems and devices to perform their duties, and are ultimately responsible for making and executing decisions.

[0616] "Voice input" is a method of inputting voice data using a device such as a microphone, which is then converted into text data through natural language processing.

[0617] A "control device" is a hardware or software system that supervises and automates the execution of a production line or process, and is configured to perform specific actions or tasks.

[0618] A description of the embodiment for carrying out the invention will be given.

[0619] This invention provides an automation support system to promote efficiency in production sites. The system begins with a worker describing the workflow in natural language on-site, using smart glasses as a voice input device. Voice recognition software embedded in the smart glasses converts the voice data into text data, and the terminal sends this text data to a server. The server preprocesses the received work information (including tokenization and noise filtering) and passes the processed data to a generative artificial intelligence control device. In this device, a generative AI model analyzes the data and identifies work categories that can be automated.

[0620] The identified automatable task categories are sent from the server to the terminal and visually displayed on the smart glasses' screen. This allows the user to quickly see which categories can be automated and what control devices and technologies are suitable for them.

[0621] As a concrete example, consider the parts supply process in an electronic component assembly line. When a worker says, "Please tell me how to improve the efficiency of parts supply," the AI ​​model analyzes the process and presents specific suggestions such as, "Automating parts supply is recommended." As a result, the worker can accurately understand which processes should be considered for automation.

[0622] An example of a prompt to the generated AI model would be, "Please describe the workflow of the production line. Which steps could be automated?" This prompt prompts the AI ​​to perform the necessary analysis and extract specific points for automation.

[0623] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0624] Step 1:

[0625] The user inputs their workflow via voice through smart glasses. The smart glasses receive the voice data and convert it into text data using speech recognition software. This conversion process analyzes the voice waveform, recognizes phonemes, and transcribes them into text. The input is voice data, and the output is text data.

[0626] Step 2:

[0627] The terminal sends the generated text data to the server. The server receives the text data and begins preprocessing. This preprocessing includes tokenization and noise filtering of the data. The input is character data, and the output is clear character data with noise removed. This data is then transformed into a state ready for analysis.

[0628] Step 3:

[0629] The server sends pre-processed text data to a generative artificial intelligence control unit. The control unit analyzes the data using a generative AI model. In this analysis process, natural language processing technology is used to analyze the workflow and identify business segments that can be automated. The input is clear text data, and the output is business segments that can be automated.

[0630] Step 4:

[0631] The server sends the identified automatable task categories to the user's terminal. The terminal receives this information and displays it visually on the smart glasses' display. The user can review the presented information and, if necessary, investigate further to determine which parts should be automated. The input is the automatable task categories, and the output is a visual presentation of information.

[0632] Step 5:

[0633] Based on the information presented, the user considers the control devices and automation methods recommended by the generated AI model and decides to implement them as needed. This step involves gathering feedback from user testing and developing an actual implementation plan. The inputs are visual information and the user's judgment, while the output is the implementation decision.

[0634] 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.

[0635] To implement the present invention, a system is constructed that processes business information and provides information accordingly while recognizing the user's emotional state. The user inputs business information in natural language using a dedicated terminal, and emotional data is acquired simultaneously. This includes the user's voice tone, facial expression recognition, or emotional analysis from text.

[0636] The terminal formats business information and sends it to the server along with emotional data. The server uses generative artificial intelligence to analyze the business information and identify parts of the business that can be automated, while an emotional engine analyzes the user's emotional state. As a result of the analysis, the server generates recommendations tailored to the user's emotions, along with information indicating what can be automated, and presents measures such as actions to reduce stress and changes in work priorities.

[0637] This data is transmitted from the server to the terminal, which then visually displays the results to the user. The display is adjusted based on sentiment data, ensuring it is in the most optimal format for the user.

[0638] As a concrete example, suppose a user working in the sales department of a certain company inputs customer service tasks. When the emotion engine detects the user's dissatisfaction or stress, the system suggests "automation using XX tool" and also proposes stress reduction measures such as "taking a break." This allows the user to perform their tasks efficiently while reducing physical and mental strain.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] When users input business information into the terminal using natural language, an emotion sensor detects the user's voice tone and facial expressions, and simultaneously collects emotional data.

[0642] Step 2:

[0643] The terminal converts the entered business information into an analyzable format, packages it together with sentiment data, and sends it to the server.

[0644] Step 3:

[0645] The server receives business information and passes it to a generative artificial intelligence (AI) to identify parts of the business that can be automated. The AI ​​evaluates the processing efficiency of each task and extracts the parts that should be automated.

[0646] Step 4:

[0647] The server uses an emotion engine to analyze user emotional data. It evaluates the user's current stress level and emotional state, and considers measures to reduce the psychological burden on them during work.

[0648] Step 5:

[0649] The server aggregates results from generative AI and emotion engines and formats the information to be presented to the user. This information includes automation recommendations and emotion-based advice.

[0650] Step 6:

[0651] The server formats the information and sends it to the terminal. The terminal displays the received content in a format suitable for the user, providing a visually easy-to-understand message board.

[0652] Step 7:

[0653] Users review the results displayed on their devices, readjust their work plans and priorities based on suggested automation methods and emotion-based actions, and then execute them.

[0654] (Example 2)

[0655] 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".

[0656] While typical business support systems focus on analyzing business information and proposing automation solutions, they fail to provide information that takes into account the user's emotional state. This presents a challenge in simultaneously achieving improved user work efficiency and reduced stress.

[0657] 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.

[0658] In this invention, the server includes means for receiving business information and emotion data and performing preprocessing based on them; means for analyzing business information with generative artificial intelligence and identifying business parts that can be automated; and means for analyzing the user's emotional state using an emotion engine and generating recommendations based on the analysis results. This makes it possible not only to improve the efficiency of business operations but also to provide information that reduces the psychological burden on the user.

[0659] "Business information" refers to information entered by users in relation to their work, and is data provided in natural language format.

[0660] "Emotional data" refers to data that indicates a user's emotional state, and is obtained through voice tone, facial expressions, or text analysis.

[0661] "Generative artificial intelligence" is an artificial intelligence technology that learns from large amounts of data and has the ability to respond to newly generated questions in natural language.

[0662] "Automable business processes" refer to the parts of repetitive or rule-based business processes that can be made more efficient or fully automated through technology.

[0663] An "emotion engine" is software or an algorithm that analyzes input emotional data and evaluates the user's psychological state.

[0664] "Recommendations" are suggestions and improvement measures presented to the user based on the analysis results, with the aim of improving work efficiency and reducing stress.

[0665] "Resources" refers to tools, technologies, or other available means that can be used to perform or assist in the specified tasks.

[0666] "Improvement measures" refer to specific actions or changes proposed to enhance the user's work efficiency or psychological comfort.

[0667] This invention provides a system that enables improved work efficiency and the provision of information tailored to the user's emotions through the cooperation of a user terminal and a data processing server. The user uses a dedicated terminal to input work information in natural language. The terminal also simultaneously acquires the user's emotional data using speech recognition technology (e.g., speech recognition API) and facial recognition technology (e.g., OpenCV). As a result, the input work information and emotional data are aggregated on the terminal.

[0668] The terminal converts business information into an analyzable format and sends it to the server along with sentiment data. A RESTful API is used for transmission via the internet, and the data is sent to the server in a standardized format (e.g., JSON). The server analyzes the business information using a generative AI model (e.g., a natural language processing engine) to identify business processes that can be automated.

[0669] Furthermore, the server uses an emotion engine to analyze emotional data and understand the user's emotional state. Based on this, suggestions for automating tasks and stress reduction measures are generated. Finally, the server sends this information to the terminal, which displays the results to the user in a visual format. This display can be done using, for example, a web browser or a mobile application.

[0670] For example, if a user in the sales department enters "I'm exhausted from a long meeting with a client" into their terminal, the system can analyze the user's work and provide recommendations such as, "Next time, please use a customer management tool to streamline your work. We recommend taking a break." Through such suggestions, users can improve their work efficiency and reduce their psychological burden.

[0671] Examples of prompt statements include the following:

[0672] "My current job is causing me stress. How can I improve it?"

[0673] "I'm exhausted from all the meetings. Are there any ways to make my work more efficient?"

[0674] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0675] Step 1:

[0676] Users input work information in natural language using a dedicated terminal. The terminal analyzes voice tone using speech recognition technology and acquires emotional data from facial expressions using facial recognition technology. In addition, it performs sentiment analysis based on the input text. This emotional data serves as foundational information for evaluating the user's psychological state. Input consists of natural language text and audio / visual data, while output consists of structured text data and emotional data.

[0677] Step 2:

[0678] The terminal converts natural language business information into a parseable format. Specifically, it uses a natural language processing library to analyze the text, extracts relevant keywords, and converts them into JSON format. This parseable format, along with sentiment data, is sent to the server. The input consists of user-entered business information and sentiment data, and the output is the parsed JSON data.

[0679] Step 3:

[0680] The server uses a generative AI model to analyze business information. Here, data in an analyzable format is input to the AI ​​model to identify parts of the business process that can be automated. Natural language processing techniques are used to classify common business tasks and select those that can be proposed for automation. The input is business data in JSON format, and the output is a list of business parts that can be automated.

[0681] Step 4:

[0682] The server analyzes emotional data using an emotion engine. This analysis evaluates the user's emotional state and identifies psychological indicators such as stress and dissatisfaction. The emotion engine processes input data using an emotion analysis tool. The input is emotional data, and the output is the analysis result of the user's emotional state.

[0683] Step 5:

[0684] The server generates recommendations based on the analysis of business information and emotional data. These recommendations include specific suggestions for automating tasks and stress reduction measures. In this process, the recommendation engine proposes the optimal action considering the analysis results and emotional state. Inputs are a list of automatable business processes and the results of the emotional state analysis, while output is a list of recommendations.

[0685] Step 6:

[0686] The server sends the generated recommendations to the terminal, which then displays the results visually. Through a user-friendly interface, it presents suggestions for improving work efficiency and reducing psychological burden. The input is a list of recommendations, and the output is the visual information presented to the user.

[0687] (Application Example 2)

[0688] 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".

[0689] In brick-and-mortar stores, such as those in the retail industry, it is difficult to quickly grasp customers' emotional states and provide individually optimized services. Furthermore, consistency in service quality is a challenge, as it relies heavily on the responsiveness of individual employees. A new customer service system is needed to solve these problems and respond to customer needs in real time.

[0690] 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.

[0691] In this invention, the server includes means for receiving business information, pre-processing it, and then analyzing it with generative artificial intelligence; means for analyzing the emotions of a subject using audio and video data; and means for providing dynamically generated recommendations to the subject based on the analyzed emotions. This makes it possible to provide personalized services based on the emotional state of the customer.

[0692] "Business information" refers to data and instructions related to an organization's or business activities, and serves as the foundation for improving or automating various business processes.

[0693] "Generative artificial intelligence" is a software technology that has the ability to analyze diverse data and generate new information and suggestions, thereby improving business efficiency and supporting decision-making.

[0694] "Automable business processes" refer to tasks and operations within existing work processes that can be carried out without human intervention by utilizing technology.

[0695] "Audio data and video data" refers to information about the subject's voice and visual information, and the purpose of analyzing this data is to understand their emotional and behavioral patterns.

[0696] "Methods for analyzing emotions" refers to techniques that analyze biological elements such as voice and facial expressions in order to understand the emotional state of a subject.

[0697] "Recommendations" refer to guidance policies or action plans provided to encourage specific actions or decisions based on analysis results.

[0698] The system for implementing this invention efficiently handles business information using natural language processing, analyzes the emotional state of the target person in real time, and provides appropriate recommendations. Specifically, the following hardware and software are used for implementation.

[0699] The terminal is equipped with a camera and microphone for capturing audio and video, and sends this data to the server along with the business information entered by the user. The terminal utilizes NLP (Natural Language Processing) technology to convert the information into a format that can be analyzed, and is particularly executed using a system based on Python and TensorFlow.

[0700] The server uses generative artificial intelligence to perform necessary analyses based on the received business information. OpenCV and Google's sentiment analysis API are combined to analyze audio and video data, understanding the user's emotional state. Based on these analysis results, the system dynamically constructs recommendations using a generative AI model.

[0701] For example, in a physical store, if an employee using a terminal detects customer dissatisfaction, the server will display recommendations on the terminal in real time, such as "Suggest a rest area." This prompt is generated based on the customer's sentiment text, in the form of "Please suggest a course of action if the customer appears confused."

[0702] This system enables faster and more optimized service delivery in customer interactions, ultimately contributing to improved customer satisfaction.

[0703] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0704] Step 1:

[0705] Users input business information in natural language through their terminals. During this process, the terminal's camera and microphone simultaneously capture audio and video data. This input data is then sent to the terminal's pre-processing system.

[0706] Step 2:

[0707] The terminal converts the received natural language business information into a parseable format. Specifically, it uses natural language processing techniques with Python to tokenize and structure the text data. Simultaneously, audio data is converted to text using speech recognition technology, and facial expression recognition is performed on video data using OpenCV. The results of these processes are then sent to the server.

[0708] Step 3:

[0709] The server uses generative artificial intelligence to analyze the received business information. It also uses Google's sentiment analysis API to analyze the user's emotional state from audio and video data. This analysis clearly identifies parts of the business that can be automated and the user's emotions, and then the generation of recommendations begins.

[0710] Step 4:

[0711] The server dynamically constructs recommendations based on the analysis results using a generative AI model. Specifically, it generates suggestions for automating tasks and customer response strategies tailored to the user's emotions. For example, it creates prompt messages such as "What to do if the customer is confused." These generated results are then sent to the terminal.

[0712] Step 5:

[0713] The terminal displays recommendations sent from the server to the user. These recommendations are presented in a visually accessible format, using concise text or graphical interfaces. This allows the user to respond quickly and appropriately to customer inquiries.

[0714] 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.

[0715] 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.

[0716] 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 robot 414.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] 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."

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] The following is further disclosed regarding the embodiments described above.

[0736] (Claim 1)

[0737] A method for receiving business information, performing preprocessing, and then analyzing it using generative artificial intelligence,

[0738] A means of identifying business processes that can be automated,

[0739] A means of presenting the identified, automatable business processes to the user,

[0740] A system that includes this.

[0741] (Claim 2)

[0742] The system according to claim 1, further comprising means for inputting the aforementioned business information in natural language and converting the input into a parseable format.

[0743] (Claim 3)

[0744] The system according to claim 1, further comprising means for recommending relevant and appropriate tools and methods for identified automable business processes.

[0745] "Example 1"

[0746] (Claim 1)

[0747] A means for receiving and pre-processing information,

[0748] One method involves converting the data into a standardized format and then analyzing it with generative artificial intelligence.

[0749] A means of identifying operations that can be automated,

[0750] A means of visually presenting to the user the identified areas of operation that can be automated,

[0751] A system that includes this.

[0752] (Claim 2)

[0753] The system according to claim 1, further comprising means for inputting the aforementioned information in natural language and converting the input into an analyzable information format.

[0754] (Claim 3)

[0755] The system according to claim 1, further comprising means for recommending appropriate equipment or methods relevant to identified automatable operating points.

[0756] "Application Example 1"

[0757] (Claim 1)

[0758] A means for receiving business information, performing preprocessing, and then analyzing it with a generative artificial intelligence control device,

[0759] A means of identifying business processes that can be automated,

[0760] A means of presenting to users the identified business categories that can be automated,

[0761] A means for analyzing the workflow from voice input and proposing a control device suitable for the identified category,

[0762] A system that includes this.

[0763] (Claim 2)

[0764] The system according to claim 1, further comprising means for inputting the aforementioned business information in natural language and converting the input into a parseable format.

[0765] (Claim 3)

[0766] The system according to claim 1, further comprising means for recommending relevant and suitable control devices and methods for identified automable task categories.

[0767] "Example 2 of combining an emotion engine"

[0768] (Claim 1)

[0769] A means for receiving business information and sentiment data and performing preprocessing based on these,

[0770] A means of analyzing business information using generative artificial intelligence and identifying business processes that can be automated,

[0771] A means for analyzing a user's emotional state using an emotion engine and generating recommendations based on the analysis results,

[0772] Identified business processes that can be automated, and means of presenting users with recommendations tailored to their emotions.

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, comprising means for receiving the aforementioned business information in natural language, converting the input into an analyzable format, and simultaneously acquiring emotional data.

[0776] (Claim 3)

[0777] The system according to claim 1, further comprising means for recommending relevant and appropriate resources and improvements for identified business processes that can be automated.

[0778] "Application example 2 of combining emotional engines"

[0779] (Claim 1)

[0780] A method for receiving business information, performing preprocessing, and then analyzing it using generative artificial intelligence,

[0781] A means of identifying business processes that can be automated,

[0782] A means of presenting the identified, automatable business processes to the user,

[0783] A means of analyzing the emotions of a subject using audio and video data,

[0784] A means of providing dynamically generated recommendations to the target person based on analyzed emotions,

[0785] A system that includes this.

[0786] (Claim 2)

[0787] The system according to claim 1, further comprising means for inputting the aforementioned business information in natural language and converting the input into a parseable format.

[0788] (Claim 3)

[0789] The system according to claim 1, further comprising means for recommending relevant and suitable methods and equipment for identified automatable business processes. [Explanation of Symbols]

[0790] 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 method for receiving business information, performing preprocessing, and then analyzing it using generative artificial intelligence, A means of identifying business processes that can be automated, A means of presenting the identified, automatable business processes to the user, A system that includes this.

2. The system according to claim 1, further comprising means for receiving the aforementioned business information in natural language and converting the input into a parseable format.

3. The system according to claim 1, further comprising means for recommending relevant and appropriate tools and methods for identified automable business processes.

Images