System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting digital data generated from each department; means for pre-processing and converting the collected digital data into text information; means for inputting the pre-processed data into a generative artificial intelligence model and generating a recommendation; and means for notifying a representative of the generated recommendation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a need to effectively utilize the digital data (slide presentations, spreadsheets, conference audio data, etc.) generated daily by each department within a company to improve business efficiency and prevent problems from occurring. However, manually collecting, analyzing, and utilizing this data requires a great deal of time and effort, which creates challenges in information sharing between departments and delays in rapid problem resolution. For this reason, there is a need to develop a system that automatically collects and preprocesses data and uses generative artificial intelligence (AI) models to analyze and provide advice. [Means for solving the problem]

[0005] To solve this problem, a system is provided that includes the following means. That is, by providing a means for collecting digital data generated by each department, the necessary data can be collected automatically. Then, by providing a means for preprocessing the collected digital data and converting it into text information, all data, including voice data, can be integrated in text format. Next, by providing a means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, data analysis can be automated and useful information can be obtained quickly. Finally, by providing a means for notifying the person in charge of the generated advice, the person in charge can respond quickly. In this way, work efficiency can be improved and problems can be prevented through advance input of information and advice.

[0006] "Digital data" refers to information generated and stored in electronic form, such as slide decks, spreadsheets, and audio recordings.

[0007] "Means of collection" refers to the system for automatically or manually collecting digital data generated from each department.

[0008] "Preprocessing" refers to the process of converting collected digital data into text information, and includes optical character recognition and speech-to-text techniques.

[0009] "Text information" refers to character data extracted or converted from slides, spreadsheets, and audio data.

[0010] "Generative artificial intelligence model" refers to an AI model used to analyze and generate advice based on collected and pre-processed digital data.

[0011] "Means for generating advice" refers to a function for inputting preprocessed data into a generative artificial intelligence model and creating advice resulting from the analysis.

[0012] The "notification means" is a mechanism for notifying the person in charge of the generated advice, and includes sending an email, displaying a dashboard, etc.

[0013] "Person in Charge" refers to an individual or department within a company that is responsible for carrying out a specific task. [Brief explanation of the drawings]

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

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

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

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

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, 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), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

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

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

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

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

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0035] This system automatically collects digital data (slides, spreadsheets, conference audio data, etc.) generated by each department in a company in the course of their daily work, analyzes and advises using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention can be embodied in the following specific forms.

[0036] Data collection

[0037] server

[0038] The server automatically collects digital data from each department's file sharing system, cloud storage, and meeting tools. This can be done by directly retrieving data using APIs, periodically monitoring folders, or using file upload triggers. For example, it can monitor cloud storage such as S3 buckets and Google Drive and collect files when new files are added.

[0039] Terminal

[0040] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires the data in real time.

[0041] Data Preprocessing

[0042] server

[0043] The server preprocesses the various digital data collected. It extracts text information from slides and spreadsheets, and uses OCR (optical character recognition) technology to obtain text from image files. It converts meeting audio data into text using speech-to-text software. This allows all digital data to be integrated into a text format. The preprocessed data is integrated into a single data format, which can then be input into the subsequent generative artificial intelligence model.

[0044] Collaboration with generative artificial intelligence models

[0045] server

[0046] The preprocessed text data is fed into a generative artificial intelligence (AI) model, using natural language processing (NLP) for example, to understand the context of the data and identify relevant information. The AI ​​model then automatically analyzes relevant problems and solutions and generates specific recommendations.

[0047] Advisory Output

[0048] server

[0049] The server analyzes the advice obtained from the generative AI model and determines how to notify the person in charge. Notification methods include email notifications, messages sent to internal chat tools, or real-time display on a dashboard. The notification content is formatted and provided to the person in charge in a specific, easy-to-understand format.

[0050] User Utilization

[0051] User

[0052] The user (person in charge) then proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and issues that have occurred in other departments, allowing them to revise the integration plan for the target station and reduce the risk of malfunctions. Furthermore, during disaster recovery, they can refer to the optimal recovery route proposed by the AI ​​model to carry out efficient recovery activities.

[0053] Specific examples

[0054] Example 1: Radio integration

[0055] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the advice, who then uses it to revise the integration plan.

[0056] Example 2: Disaster recovery

[0057] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the person in charge of the generated advice, who then uses it to carry out efficient recovery activities.

[0058] The above-described embodiments enable the present invention to be effectively carried out.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] server

[0062] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses direct acquisition using APIs, regular monitoring of specified directories, and file upload triggers. For example, it monitors cloud storage (e.g., Google Drive, S3 buckets) and downloads new files when they are detected.

[0063] Step 2:

[0064] Terminal

[0065] On the terminal side, the staff manually uploads the required digital data to the server. Through a dedicated interface, the staff can select files and upload them by dragging and dropping them. This data is sent to the server in real time and saved.

[0066] Step 3:

[0067] server

[0068] The server preprocesses the collected data. Specifically, it extracts text information from slide decks and spreadsheets, extracts text from image files using OCR (optical character recognition), and converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[0069] Step 4:

[0070] server

[0071] The preprocessed text data is fed into a generative artificial intelligence (AI) model. An API is called to send the data to the AI ​​model, which then performs the analysis task. The AI ​​model uses natural language processing (NLP) techniques to understand the context of the data and identify relevant information and potential issues.

[0072] Step 5:

[0073] server

[0074] Receive the response from the AI ​​model, analyze the generated advice, format the advice in an easy-to-understand format, and decide how to notify the responsible person. For example, select whether to notify the person via email, internal chat tool, or dashboard based on importance and urgency.

[0075] Step 6:

[0076] server

[0077] The system notifies the responsible person with formatted advice. In the case of email notification, the advice is sent to the responsible person's email address. In the case of using an internal chat tool, a message is sent to promote real-time communication. In the case of dashboard display, the responsible person can check the advice through a web interface.

[0078] Step 7:

[0079] User

[0080] The person in charge will review the advice provided. For example, when implementing wireless equipment integration, they will receive advice based on past bug information and problems that have occurred in other departments, and plan specific countermeasures.

[0081] Step 8:

[0082] User

[0083] The person in charge will proceed with their work based on the advice received. By modifying the integration plan and taking preventative measures against problems, they aim to improve work efficiency and reduce risks. In the event of a disaster, they will be able to respond quickly by referring to the optimal recovery route.

[0084] The above are the specific processing steps in this system.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] There is a need for a system that can efficiently collect a wide variety of digital data generated by each department within a company, centrally manage and analyze it, and provide personnel with specific advice that will help improve business operations and carry out their work. However, conventional methods require time-consuming data collection and preprocessing, and analyzing the data to obtain useful advice requires a great deal of time and effort. In addition, when personnel manually collect data, it often lacks real-time capabilities.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes means for collecting digital data generated by each department, means for preprocessing the collected digital data and converting it into text information, and means for inputting the preprocessed data into a generative artificial intelligence model and generating advice. This makes it possible to efficiently collect and preprocess data generated within a company and quickly generate and provide useful advice from that data.

[0090] "Digital data" refers to information, records, or materials that are generated or stored electronically, including, for example, slides, spreadsheets, audio files, etc.

[0091] "Collection methods" refers to the methods, tools, or processes used to automatically or manually collect digital data generated from each department.

[0092] "Preprocessing means" refers to the process of converting collected digital data into a format that is easy to analyze, and specifically includes converting it into text information and removing noise.

[0093] "Generative artificial intelligence model" refers to an artificial intelligence algorithm or system used to generate useful information or advice from collected and pre-processed digital data.

[0094] "Advice generation means" refers to a method, tool, or process for inputting pre-processed data into a generative artificial intelligence model, analyzing it, and generating specific advice or suggestions.

[0095] "Notification means" refers to the methods, tools, or processes for effectively communicating generated advice and suggestions to relevant personnel, including, for example, email, chat tools, dashboards, etc.

[0096] This system automatically or manually collects digital data (e.g., slides, spreadsheets, audio files, etc.) generated by each department in a company in the course of their daily work, analyzes and provides advice using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention is embodied in the following specific forms.

[0097] Data collection

[0098] server

[0099] The server collects digital data from each department's file sharing system or cloud storage. Specifically, the server uses an API to monitor designated folders in cloud storage (e.g., Amazon S3 or Google Drive) and automatically retrieves newly uploaded files. This collection process can be performed periodically or in real time using a file upload trigger.

[0100] Terminal

[0101] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator simply accesses the interface on a browser and drags and drops the files they want to collect, which sends the files to the server, allowing the server to acquire data in real time.

[0102] Data Preprocessing

[0103] server

[0104] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition) technology. For example, it uses an OCR tool such as Tesseract. It converts the meeting audio data into text using transcription software (for example, Google Cloud Speech-to-Text API). The preprocessed data is then converted into a unified text format.

[0105] Collaboration with generative artificial intelligence models

[0106] server

[0107] The preprocessed text data is fed into a generative artificial intelligence (AI) model, which uses natural language processing (NLP) techniques to analyze the context of the data and extract relevant information. For example, by using an AI model such as OpenAI's GPT-3, useful advice and suggestions can be generated from each piece of data.

[0108] Advisory Output

[0109] server

[0110] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification methods include email notification, sending a message to an internal chat tool (such as Slack), or displaying the information in real time on a dashboard. The generated content is formatted in HTML or other formats and provided to the person in charge.

[0111] User Utilization

[0112] User

[0113] The user (person in charge) carries out their work based on the advice provided. For example, when integrating radio equipment, they can revise the integration plan by referring to past bug information and advice on problems in other departments. During disaster recovery, the optimal recovery route proposed by the AI ​​model is executed.

[0114] Specific examples

[0115] Example 1: Radio integration

[0116] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the generated advice, who then modifies the integration plan.

[0117] Example 2: Disaster recovery

[0118] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the responsible party of the generated advice, who then carries out efficient recovery activities.

[0119] Prompt Sentence Examples

[0120] Please analyze the slides and audio data for the radio integration and provide advice based on past bug information and issues. Please also include known bugs and workarounds for specific radio models.

[0121]

[0122] Analyze slide decks and meeting audio related to recent disasters to suggest optimal recovery routes and procedures. Generate recommendations taking into account relevant data.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1: Data Collection (Server)

[0125] The server automatically collects digital data from cloud storage (Amazon S3 or Google Drive) or file sharing systems. Specifically, the server uses an API to monitor specified folders and collects any newly added files. The collected files are saved in local storage. The input is digital data obtained via the API, and the output is data saved in the server's local storage. For example, when a new file is uploaded to a specified S3 bucket, it detects it and downloads it.

[0126] Step 2: Data collection (device)

[0127] The person in charge manually uploads digital data to the server via a terminal. The file is sent to the server by dragging and dropping it into the interface on the browser and clicking the upload button. The input is the file uploaded by the person in charge, and the output is the file saved on the server. Specifically, the person in charge uploads the slide materials.

[0128] Step 3: Data Preprocessing (Server)

[0129] The collected digital data is preprocessed. The server extracts text information from slides and spreadsheets, and uses OCR technology to obtain text from image files. Audio files are also converted to text using speech-to-text software. The input is the collected raw data, and the output is data in a unified text format. Specifically, a Python script is used to extract text from PDFs, Tesseract is used to perform character recognition from images, and the speech is converted to text using the Google Cloud Speech-to-Text API.

[0130] Step 4: Input data into the generative AI model (server)

[0131] The preprocessed text data is input into a generative artificial intelligence model. The server converts the text data into JSON format and sends it to the AI ​​model. The input is the preprocessed text data, and the output is advice or suggestions generated by the AI ​​model. Specifically, the preprocessed data is input into an AI model such as OpenAI's GPT-3 via an API, and the analysis results are received in text format.

[0132] Step 5: Advisory Output and Notification (Server)

[0133] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification formats include email, internal chat tools, and dashboards, and notifications are sent in the most effective way for each. The input is the results generated by the AI ​​model, and the output is advice formatted in the notification format. Specifically, the generated advice is formatted into HTML and sent via email via an SMTP server, or a chat notification is sent using the Slack API.

[0134] Step 6: Use the advice (user)

[0135] The user (person in charge) proceeds with the work based on the advice notified. They utilize the advice, such as referring to past bug information when integrating radio equipment, or implementing the optimal recovery route when planning disaster recovery. The input is the notified advice, and the output is work improvement measures and plans based on that advice. Specifically, they check the advice received by email and revise the integration plan. Or they can respond quickly by referring to recovery routes in the event of a disaster.

[0136] (Application example 1)

[0137] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0138] Modern autonomous vehicles generate large amounts of sensor data and operational data, but there is a lack of systems that can analyze this data in real time and provide appropriate operational advice. This can result in insufficient operational efficiency and safety for autonomous vehicles. There is also a growing need for a system that integrates a series of processes for data collection, preprocessing, analysis using AI models, and appropriate notification of advice. This will enable drivers and supervisors to receive advice in a timely manner, enabling safer and more efficient management of autonomous vehicle operations.

[0139] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0140] In this invention, the server includes: means for collecting digital data generated by each department; means for preprocessing the collected digital data and converting it into text information; means for inputting the preprocessed data into a generative artificial intelligence model and generating advice; means for notifying a responsible person of the generated advice; means for collecting sensor data and operation data generated by autonomous vehicles and uploading it to cloud storage; means for preprocessing the collected autonomous vehicle data, removing unnecessary parts, and converting it into text and numerical data; means for inputting the preprocessed autonomous vehicle data into a generative artificial intelligence model and generating advice based on operating conditions and traffic conditions; and means for notifying a driver or supervisor of the generated advice via a smartphone application. This makes it possible to efficiently manage autonomous vehicle data through a series of processes and provide appropriate advice to drivers and supervisors in real time.

[0141] "Digital data" means data generated by electronic devices, including slide decks, spreadsheets, audio data, and autonomous vehicle sensor and operational data.

[0142] "Preprocessing" refers to the process of removing unnecessary parts and converting collected digital data into text information and numerical data in order to convert it into an analyzable format.

[0143] A "generative artificial intelligence model" refers to an algorithm or model that uses natural language processing and machine learning techniques to analyze data and generate advice.

[0144] "Sensor data" refers to data obtained from various sensors (cameras, lidar, radar, etc.) installed in autonomous vehicles.

[0145] "Operational data" refers to data related to the operational status of an autonomous vehicle, such as its speed, location, and driving conditions.

[0146] "Cloud storage" refers to a service or system that stores digital data on remote servers via the Internet.

[0147] "Smartphone application" refers to a software program that runs on a smartphone and provides specific functionality.

[0148] "Operation status" refers to information about the current operating status of an autonomous vehicle and the surrounding traffic conditions.

[0149] "Notification" refers to a means of communicating the generated advice to the driver or supervisor, and includes push notification, screen display, voice guidance, etc.

[0150] This invention is a system that efficiently collects and analyzes digital data generated within a company or in an autonomous vehicle, and provides useful advice using a generative artificial intelligence model. Specific embodiments for implementing the invention are described below.

[0151] Data collection

[0152] server

[0153] The server collects digital data generated by each department within a company and from autonomous vehicles. Within a company, the server automatically collects digital data from file sharing systems, cloud storage, and conferencing tools. For example, it monitors cloud storage and collects new files when they are added. In the case of autonomous vehicles, the server collects sensor data and operational data and uploads the data to cloud storage.

[0154] Terminal

[0155] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires data in real time.Data collection from autonomous vehicles involves acquiring data directly from the vehicle's ECU (Engine Control Unit) and other sensors.

[0156] Data Preprocessing

[0157] server

[0158] The server preprocesses the collected digital data. For internal company data, text information is extracted from slides and spreadsheets, and text is also obtained from image files using OCR (optical character recognition) technology. Voice data is converted into text using speech transcription technology. This unifies all digital data into text format. For autonomous vehicle data, sensor data and operational data are preprocessed into an analyzable format, unnecessary parts are removed, and the data is converted into text and numerical data.

[0159] Collaboration with generative artificial intelligence models

[0160] server

[0161] The preprocessed text data is fed into a generative AI model to understand the context of the data and generate relevant advice. For example, it can identify problems and improvements from a company's internal business data and generate advice based on the operation status and traffic conditions of autonomous vehicles.

[0162] Advisory Output

[0163] server

[0164] The server analyzes the advice obtained from the generative AI model and determines the format in which to notify the person in charge. Notification methods include email notification, sending a message to an internal chat tool, displaying the advice in real time on a dashboard, and notifying the person in charge via a smartphone application. The generated advice is formatted and provided in a specific and easy-to-understand format.

[0165] User Utilization

[0166] User

[0167] Users (staff and drivers) can then carry out their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. Drivers of autonomous vehicles receive advice based on operational and traffic conditions to optimize operations. Operations control centers also receive data and advice in the same way, enabling them to manage operations more efficiently.

[0168] Prompt Sentence Examples

[0169] For example, a prompt to input to a generative artificial intelligence model might look like this:

[0170] "October 6, 2023, 12:34, Vehicle ID: vehicle_123, Speed: 35km / h, Location: Latitude 35.6895, Longitude 139.6917, Environmental Data: Includes camera images and lidar points."

[0171] By sending this prompt sentence to a generative artificial intelligence model, appropriate advice is generated.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] The server collects digital data generated by various departments within the company and from autonomous vehicles. Within the company, data is automatically acquired from file sharing systems, cloud storage, and conference tools. For example, new files are monitored and added using the cloud storage API. Meanwhile, in autonomous vehicles, sensor data and operational data are collected and uploaded to cloud storage. The input to this step is digital data from within the company and from autonomous vehicles, and the output is the collected data stored on the server.

[0175] Step 2:

[0176] The server preprocesses the collected digital data. For internal company data, this preprocessing involves using OCR technology to extract text information from slides and image files, and using speech-to-text technology to convert voice data into text. For autonomous vehicle data, unnecessary parts are removed and the data is converted into analyzable text and numerical data. The input for this step is the collected digital data, and the output is preprocessed text data.

[0177] Step 3:

[0178] The server inputs the preprocessed text data into a generative AI model. The generative AI model analyzes the context of the input data and generates appropriate advice. For example, it can identify problems and improvement measures from internal business data, or generate driving advice based on driving and traffic conditions from data on autonomous vehicles. The input for this step is the preprocessed text data, and the output is the generated advice.

[0179] Step 4:

[0180] The server analyzes the advice obtained from the generative artificial intelligence model and notifies the person in charge or the driver in an appropriate format. Specific notification methods include email notification, sending a message to an internal chat tool, displaying the information in real time on a dashboard, or notifying via a smartphone application. The input of this step is the generated advice, and the output is the information notified to the person in charge or the driver.

[0181] Step 5:

[0182] The user (person in charge or driver) proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. The driver of an autonomous vehicle receives advice based on operational and traffic conditions to optimize operation. The input to this step is the advice they receive, and the output is the result of the user taking action.

[0183] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0184] This system automatically collects and preprocesses digital data generated by each department within a company, analyzes and provides advice using a generative artificial intelligence (AI) model, and adjusts the importance and display method of the advice content by combining it with an emotion engine that recognizes the user's emotions. This invention is embodied in the following specific forms.

[0185] Data collection

[0186] server

[0187] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. This can be done by using APIs to obtain data, periodically monitoring designated directories, or triggering file uploads. For example, it can monitor cloud storage (e.g., Google Drive, S3 buckets) and automatically download new files when they are detected.

[0188] Terminal

[0189] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator can select the files from the interface and upload them easily with a drag-and-drop operation. This allows the data to be sent to the server in real time.

[0190] Data Preprocessing

[0191] server

[0192] The server preprocesses the collected digital data. Specifically, it extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. The preprocessed data is organized into a unified format and prepared for input into the generative AI model.

[0193] Collaboration with generative artificial intelligence models

[0194] server

[0195] The preprocessed text data is fed into a generative AI model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential issues. Recommendations are generated as a result of the analysis by the AI ​​model.

[0196] Introducing the Emotion Engine

[0197] server

[0198] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes emotions from the user's voice and text data to understand the user's current psychological state. The emotion data is used to dynamically adjust the importance and display method of the advice provided by the AI ​​model.

[0199] Advisory Output

[0200] server

[0201] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice content will be simplified and only the most important information will be emphasized.

[0202] User

[0203] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing the psychological burden on the person in charge and promoting effective decision-making.

[0204] Specific examples

[0205] Example 1: Radio integration

[0206] The server collects slides and conference audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which the server receives. At the same time, an emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the appropriate person.

[0207] Example 2: Disaster recovery

[0208] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. This data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model combines the relevant data to generate advice, which the server receives. An emotion engine analyzes the user's psychological state and adjusts the content and priorities of the advice. The server notifies the responsible party of the adjusted advice, and the user uses it to carry out efficient recovery activities.

[0209] The above-described embodiments enable the present invention to be effectively carried out.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] server

[0213] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses APIs to retrieve files, regularly monitors designated directories, and automatically downloads new files when they are found. This process includes monitoring cloud storage such as Google Drive and S3 buckets.

[0214] Step 2:

[0215] Terminal

[0216] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator selects the files using a dedicated web interface and uploads them by dragging and dropping them. The files are then saved to the server in real time.

[0217] Step 3:

[0218] server

[0219] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[0220] Step 4:

[0221] server

[0222] The preprocessed text data is input into a generative artificial intelligence (AI) model. An API call is made to the AI ​​model to send the data. The AI ​​model uses NLP (natural language processing) techniques to analyze the context of the data and identify relevant information and potential issues. This processing results in the generation of appropriate advice.

[0223] Step 5:

[0224] server

[0225] After receiving the response from the AI ​​model, the generated advice is further processed by the emotion engine, which analyzes the user's voice and text data to recognize their emotional state. For example, if the user is feeling stressed, the content and presentation of the advice can be adjusted based on this information.

[0226] Step 6:

[0227] server

[0228] The adjusted advice is then sent to the person in charge. This is where the appropriate notification format is selected. For example, email notification, notification via an internal chat tool, or real-time display on the management dashboard may be selected. The advice is adjusted using an emotion engine, so the importance and display method are reflected according to the user's psychological state.

[0229] Step 7:

[0230] User

[0231] The user (person in charge) checks the notified advice. When implementing radio equipment integration, the user receives advice on past bugs and problems that have occurred in other departments, and plans specific countermeasures. In addition, when recovering from a disaster, the AI ​​model proposes optimal recovery routes, which can be used as a reference to quickly respond. At this time, the emotion engine provides advice in a way that reduces the user's psychological burden.

[0232] Step 8:

[0233] User

[0234] We proceed with the work based on the advice we receive. For example, we aim to improve operational efficiency and reduce risk by revising integration plans and taking preventative measures. In disaster recovery cases, we act quickly and efficiently based on the optimal recovery route.

[0235] The above steps ensure that the system is implemented effectively and efficiently.

[0236] Example 2

[0237] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0238] Many companies face challenges in efficiently collecting and preprocessing large amounts of digital data generated by various departments within a company and generating useful advice using generative artificial intelligence models. Furthermore, the generated advice must be optimally displayed for the staff member and adjusted to reduce the psychological burden. However, current systems lack the ability to recognize the user's emotions and dynamically adjust the advice content, and a system that solves this problem is needed.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0240] In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for notifying a person in charge of the generated advice, and means for activating an emotion engine for recognizing the user's emotions and adjusting the advice content based on the emotion data. This makes it possible to efficiently collect and preprocess a wide variety of digital data within a company, generate advanced advice using a generative artificial intelligence model, and provide optimal advice that takes the user's emotions into consideration.

[0241] "Digital data" means information or data stored in electronic form.

[0242] "Preprocessing" refers to the process of converting and shaping digital data to make it easier to analyze and use.

[0243] "Text information" refers to information expressed in characters or symbols.

[0244] A "generative artificial intelligence model" is an algorithm or system that analyzes patterns and trends from given data and generates predictions and suggestions.

[0245] An "emotion engine" is an analysis system for recognizing a user's emotional state, and is a technology for grasping a user's psychological state from voice and text.

[0246] "Advice" is information intended to provide solutions or guidance to a particular situation or problem.

[0247] A "notification" is a method or action for informing a user of specific information.

[0248] This invention is a system that efficiently collects and preprocesses digital data generated by each department within a company and provides analysis and advice using a generative artificial intelligence (AI) model. Furthermore, it aims to reduce psychological burden by combining an emotion engine that recognizes the user's emotions and adjusting the importance and display method of advice. Below, we will explain how to specifically implement this invention.

[0249] Data collection

[0250] server

[0251] The server automatically collects digital data generated by each department within the company. The system obtains data using API access to file sharing systems and cloud storage (e.g., Google Drive, Amazon S3 buckets). It also uses periodic monitoring of designated directories and file upload triggers. For example, it monitors Google Drive and automatically downloads new files when they are uploaded.

[0252] Terminal

[0253] The terminal provides an interface for the person in charge to manually upload the necessary files to the server. Using this interface, users can upload files with a simple drag-and-drop operation, and the resulting data is sent to the server in real time.

[0254] Data Preprocessing

[0255] server

[0256] The server preprocesses the collected digital data. It uses OCR technology (e.g., Tesseract OCR) to extract text information from slides and spreadsheets. It also converts the meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format, ready to be fed into the generative AI model in the next step.

[0257] Collaboration with generative artificial intelligence models

[0258] server

[0259] The server inputs the preprocessed text data into a generative AI model. The AI ​​model uses NLP techniques to understand the context of the data and identify relevant information and potential problems. For example, it analyzes past meeting notes and technical documents to extract trends and risk factors. Specific advice is generated as a result of the analysis.

[0260] Introducing the Emotion Engine

[0261] server

[0262] The server receives advice from the AI ​​model and simultaneously activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and text data to understand their current psychological state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. This dynamically adjusts the importance of the advice and how it is displayed.

[0263] Advisory Output

[0264] server

[0265] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice will be brief and only the important information will be highlighted.

[0266] User

[0267] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing psychological burden and promoting effective decision-making.

[0268] Specific examples

[0269] Example 1: Radio integration

[0270] The server collects and preprocesses the slides and meeting audio data generated for the radio integration. It extracts text information from the slides and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which is received by the server. At the same time, the emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the person in charge. An example of a prompt is, "Please generate advice on future measures based on the bug information and meeting audio data for the past year regarding the radio integration."

[0271] Example 2: Disaster recovery

[0272] When a disaster occurs, the server automatically collects and pre-processes relevant documents and conference audio data. This data is pre-processed and input into a generative AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with the relevant data to generate advice, which the server receives. The emotion engine analyzes the user's psychological state and adjusts the advice content and priorities. The adjusted advice content is notified to the person in charge, who then uses it to carry out efficient recovery activities. An example of a prompt is, "Please provide advice on the optimal recovery routes and procedures based on the conference audio data and related documents from the most recent disaster."

[0273] The above is a specific embodiment for carrying out the present invention.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1: Data collection

[0276] server

[0277] Input: Digital data generated by each department (e.g., electronic documents, spreadsheet data, audio data)

[0278] The server collects digital data using API access to each department's file sharing system and cloud storage. It automatically imports data when a file is added by using periodic monitoring of designated directories or file upload triggers. For example, it can detect new files from cloud storage and automatically download them to the server.

[0279] Output: Collected digital data (electronic file)

[0280] Terminal

[0281] Input: Necessary files held by the person in charge

[0282] The terminal provides an interface for the staff member to manually upload files, allowing them to select files and send them by dragging and dropping them.

[0283] Output: The file uploaded to the server.

[0284] Step 2: Data Preprocessing

[0285] server

[0286] Input: Collected digital data

[0287] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, extracts text information from image files using OCR technology (e.g., Tesseract OCR), and converts meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The resulting text data is then organized into a unified format.

[0288] Output: Preprocessed text data

[0289] Step 3: Collaboration with generative AI models

[0290] server

[0291] Input: Preprocessed text data

[0292] The server inputs the preprocessed data into a generative artificial intelligence model (e.g., GPT-3). This AI model uses NLP techniques to understand the context of the data and analyze it for relevant information and potential problems. The AI ​​model analyzes the data and generates specific advice, such as extracting trends and risk factors based on past meeting notes and technical documents.

[0293] Output: Generated advice

[0294] Step 4: Implementing the Emotion Engine

[0295] server

[0296] Input: Advice from the generative AI model, user emotional data (voice data, text data)

[0297] The server activates an emotion engine based on the advice received from the generative AI model. The emotion engine analyzes the user's voice and text data to understand their current emotional state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. The emotion data is used to adjust the importance of the advice and how it is displayed.

[0298] Output: Tailored advice based on sentiment data

[0299] Step 5: Advisory Output

[0300] server

[0301] Input: Tailored advice based on sentiment data

[0302] The server determines the format of notification to the agent based on the adjusted advice content. For example, if the user is feeling stressed, the advice will be brief and only important information will be highlighted.

[0303] Output: Adjusted advice notification

[0304] User

[0305] Input: Advice sent by the server

[0306] The user (person in charge) checks the advice sent from the server. For example, when implementing wireless equipment integration, they can plan countermeasures by referring to specific advice based on past bug information and problems that have occurred in other departments. Also, during disaster recovery, they can respond quickly based on the optimal recovery route suggested by the AI ​​model. Advice is provided based on the results of the emotion engine, reducing psychological burden.

[0307] Output: Specific measures and action plans

[0308] The above is the specific flow of the program processing of this system.

[0309] (Application example 2)

[0310] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0311] In traditional brick-and-mortar store operations, it is difficult to effectively utilize the large amounts of data obtained from POS systems, inventory management systems, customer feedback, etc., and advice for improving operations and measures based on employee emotions are not sufficiently implemented. In addition, busy work places a heavy psychological burden on employees, which can have a negative impact on the quality of customer service and sales effectiveness.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for analyzing the user's emotions and adjusting the content and presentation method of the advice, and means for notifying the person in charge of the generated advice. This makes it possible to effectively utilize digital data to provide advice for improving operations, and further to optimize the content and display method of the advice by taking employee emotions into consideration.

[0313] "Each department" refers to a division or section within a company or organization that has a different role or function.

[0314] "Digital data" means data that can be stored, transmitted, or processed electronically, including text, audio, images, and video.

[0315] "Means of collection" refers to the methods and technologies used to collect the necessary digital data, such as APIs, file uploads, and sensors.

[0316] "Preprocessing" refers to the basic processing and conversion work done on collected data to make it easier to analyze, and includes things like text extraction and data cleaning.

[0317] "Text information" refers to character string information written in natural language, and takes the form of documents, notes, comments, etc.

[0318] A "generative artificial intelligence model" refers to a model that uses machine learning algorithms and neural networks to automatically generate useful information and advice from input data.

[0319] "Advice" means suggestions or advice on problems or issues, including points for improvement and specific measures.

[0320] "Means of notification" refers to the methods and technologies used to deliver generated advice and information to the responsible party, including email, push notifications, and message displays.

[0321] "User emotions" refers to the current psychological state and emotional reactions of users using the system, including stress, fatigue, satisfaction, etc.

[0322] "Means for analyzing emotions" refers to technologies and methods for detecting and analyzing a user's emotions, including voice analysis, facial expression analysis, and text analysis.

[0323] "Presentation" refers to the format or method in which information or advice is displayed to the user, including textual, graphical, and animation displays.

[0324] This invention relates to a system that aims to optimize the operation of a physical store. The system is composed of a server, a terminal, and a user, and is implemented as follows.

[0325] 1. Data Collection

[0326] The server collects digital data from physical store POS systems, inventory management systems, and customer feedback systems. This includes methods such as API-based data acquisition, regular monitoring, and file upload triggers. For example, cloud storage can be monitored and new data can be automatically downloaded when detected. On the terminal side, employees use a smartphone app to upload the necessary data to the server, which then transmits the data to the server in real time.

[0327] 2. Data Preprocessing

[0328] The server preprocesses the collected digital data and converts it into text information. Specifically, it uses OCR (optical character recognition) technology to extract text from document data, and transcribes audio data using speech recognition technology (Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format and prepared for input into a generative artificial intelligence model.

[0329] 3. Collaboration with generative artificial intelligence models

[0330] The server inputs the preprocessed data into a generative artificial intelligence model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential problems. The analysis results of the AI ​​model generate recommendations for operational improvement.

[0331] 4. Introducing the Emotion Engine

[0332] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's (employee's) emotions. The emotion engine analyzes voice data and feedback collected from the device to understand the user's current psychological state. Emotional data is used to adjust the importance and presentation method of the generated advice.

[0333] 5. Advisory Output

[0334] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format for notification to the device and notifies the user (employee). For example, if the user is feeling stressed, the advice content will be simplified, emphasizing only the most important information. The user can review the advice notified to them and use it to improve operations and customer service.

[0335] Specific examples

[0336] Examples of employee stress reduction measures

[0337] When employees are tired, a "quick feedback check" is sufficient. In this case, the prompt would be "Generate a quick improvement suggestion to present to employees when they are tired."

[0338] Example of inventory management timing advice output

[0339] If there is a sudden increase in best-selling items, the system displays a message to "recommend the next order timing." In this case, the prompt is "Please suggest the next product to order based on sales and the timing."

[0340] This system will enable the use of digital data in physical store operations and the provision of optimal advice that takes user emotions into consideration, which is expected to improve operational efficiency and customer satisfaction.

[0341] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0342] Step 1:

[0343] The server collects digital data from the physical store's POS system, inventory management system, and customer feedback system. Specifically, it periodically retrieves data using APIs and monitors cloud storage to detect newly added data. The input is digital data from each system (e.g., sales data, inventory data, customer feedback), and the output is storing that data on the server.

[0344] Step 2:

[0345] At the terminal, employees use a smartphone app to upload the required data to the server. Specifically, they select a file from the app interface and upload it simply by dragging and dropping. The input is the file selected by the employee, and the output is that file is sent to the server in real time.

[0346] Step 3:

[0347] The server preprocesses the collected digital data. Specifically, it uses OCR (Optical Character Recognition) technology to extract text from document data and AudioFile to transcribe audio data. The input is the collected raw data, and the output is text information converted into a unified format.

[0348] Step 4:

[0349] The server inputs the preprocessed text information into a generative artificial intelligence model. The model uses NLP techniques to analyze the context of the data and identify relevant information and potential problems. The input is the preprocessed text data, and the output is recommendations for operational improvement.

[0350] Step 5:

[0351] The device sends voice data and feedback to a server to recognize the user's (employee's) emotions. Voice recognition technology is used to extract emotions from the voice, and text data is analyzed to determine the emotion. The input is voice data and text data, and the output is emotional data.

[0352] Step 6:

[0353] The server adjusts the advice content based on the advice obtained from the generative AI model and the emotional data obtained from the emotion engine. Specifically, it changes the importance and display method of the advice depending on the user's emotional state. The input is the advice from the generative AI model and the emotional data from the emotion engine, and the output is the adjusted advice content.

[0354] Step 7:

[0355] The server notifies the device of the adjusted advice. A push notification is sent to the smartphone app, which the employee confirms. Specific operations include using an API or push notification service to notify the employee. The input is the adjusted advice, and the output is the advice displayed on the employee's smartphone.

[0356] Step 8:

[0357] The user (employee) uses the received advice to improve operations and customer service. Specifically, they review their business processes based on the provided advice and take necessary measures. The input is the received advice, and the output is improvements to the store's operations and customer service.

[0358] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0359] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0360] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0361] [Second embodiment]

[0362] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0363] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0364] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0365] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0366] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0367] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0368] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0369] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0370] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0371] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0372] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0373] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0374] This system automatically collects digital data (slides, spreadsheets, conference audio data, etc.) generated by each department in a company in the course of their daily work, analyzes and advises using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention can be embodied in the following specific forms.

[0375] Data collection

[0376] server

[0377] The server automatically collects digital data from each department's file sharing system, cloud storage, and meeting tools. This can be done by directly retrieving data using APIs, periodically monitoring folders, or using file upload triggers. For example, it can monitor cloud storage such as S3 buckets and Google Drive and collect files when new files are added.

[0378] Terminal

[0379] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires the data in real time.

[0380] Data Preprocessing

[0381] server

[0382] The server preprocesses the various digital data collected. It extracts text information from slides and spreadsheets, and uses OCR (optical character recognition) technology to obtain text from image files. It converts meeting audio data into text using speech-to-text software. This allows all digital data to be integrated into a text format. The preprocessed data is integrated into a single data format, which can then be input into the subsequent generative artificial intelligence model.

[0383] Collaboration with generative artificial intelligence models

[0384] server

[0385] The preprocessed text data is fed into a generative artificial intelligence (AI) model, using natural language processing (NLP) for example, to understand the context of the data and identify relevant information. The AI ​​model then automatically analyzes relevant problems and solutions and generates specific recommendations.

[0386] Advisory Output

[0387] server

[0388] The server analyzes the advice obtained from the generative AI model and determines how to notify the person in charge. Notification methods include email notifications, messages sent to internal chat tools, or real-time display on a dashboard. The notification content is formatted and provided to the person in charge in a specific, easy-to-understand format.

[0389] User Utilization

[0390] User

[0391] The user (person in charge) then proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and issues that have occurred in other departments, allowing them to revise the integration plan for the target station and reduce the risk of malfunctions. Furthermore, during disaster recovery, they can refer to the optimal recovery route proposed by the AI ​​model to carry out efficient recovery activities.

[0392] Specific examples

[0393] Example 1: Radio integration

[0394] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the advice, who then uses it to revise the integration plan.

[0395] Example 2: Disaster recovery

[0396] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the person in charge of the generated advice, who then uses it to carry out efficient recovery activities.

[0397] The above-described embodiments enable the present invention to be effectively carried out.

[0398] The processing flow will be explained below.

[0399] Step 1:

[0400] server

[0401] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses direct acquisition using APIs, regular monitoring of specified directories, and file upload triggers. For example, it monitors cloud storage (e.g., Google Drive, S3 buckets) and downloads new files when they are detected.

[0402] Step 2:

[0403] Terminal

[0404] On the terminal side, the staff manually uploads the required digital data to the server. Through a dedicated interface, the staff can select files and upload them by dragging and dropping them. This data is sent to the server in real time and saved.

[0405] Step 3:

[0406] server

[0407] The server preprocesses the collected data. Specifically, it extracts text information from slide decks and spreadsheets, extracts text from image files using OCR (optical character recognition), and converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[0408] Step 4:

[0409] server

[0410] The preprocessed text data is fed into a generative artificial intelligence (AI) model. An API is called to send the data to the AI ​​model, which then performs the analysis task. The AI ​​model uses natural language processing (NLP) techniques to understand the context of the data and identify relevant information and potential issues.

[0411] Step 5:

[0412] server

[0413] Receive the response from the AI ​​model, analyze the generated advice, format the advice in an easy-to-understand format, and decide how to notify the responsible person. For example, select whether to notify the person via email, internal chat tool, or dashboard based on importance and urgency.

[0414] Step 6:

[0415] server

[0416] The system notifies the responsible person with formatted advice. In the case of email notification, the advice is sent to the responsible person's email address. In the case of using an internal chat tool, a message is sent to promote real-time communication. In the case of dashboard display, the responsible person can check the advice through a web interface.

[0417] Step 7:

[0418] User

[0419] The person in charge will review the advice provided. For example, when implementing wireless equipment integration, they will receive advice based on past bug information and problems that have occurred in other departments, and plan specific countermeasures.

[0420] Step 8:

[0421] User

[0422] The person in charge will proceed with their work based on the advice received. By modifying the integration plan and taking preventative measures against problems, they aim to improve work efficiency and reduce risks. In the event of a disaster, they will be able to respond quickly by referring to the optimal recovery route.

[0423] The above are the specific processing steps in this system.

[0424] Example 1

[0425] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0426] There is a need for a system that can efficiently collect a wide variety of digital data generated by each department within a company, centrally manage and analyze it, and provide personnel with specific advice that will help improve business operations and carry out their work. However, conventional methods require time-consuming data collection and preprocessing, and analyzing the data to obtain useful advice requires a great deal of time and effort. In addition, when personnel manually collect data, it often lacks real-time capabilities.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0428] In this invention, the server includes means for collecting digital data generated by each department, means for preprocessing the collected digital data and converting it into text information, and means for inputting the preprocessed data into a generative artificial intelligence model and generating advice. This makes it possible to efficiently collect and preprocess data generated within a company and quickly generate and provide useful advice from that data.

[0429] "Digital data" refers to information, records, or materials that are generated or stored electronically, including, for example, slides, spreadsheets, audio files, etc.

[0430] "Collection methods" refers to the methods, tools, or processes used to automatically or manually collect digital data generated from each department.

[0431] "Preprocessing means" refers to the process of converting collected digital data into a format that is easy to analyze, and specifically includes converting it into text information and removing noise.

[0432] "Generative artificial intelligence model" refers to an artificial intelligence algorithm or system used to generate useful information or advice from collected and pre-processed digital data.

[0433] "Advice generation means" refers to a method, tool, or process for inputting pre-processed data into a generative artificial intelligence model, analyzing it, and generating specific advice or suggestions.

[0434] "Notification means" refers to the methods, tools, or processes for effectively communicating generated advice and suggestions to relevant personnel, including, for example, email, chat tools, dashboards, etc.

[0435] This system automatically or manually collects digital data (e.g., slides, spreadsheets, audio files, etc.) generated by each department in a company in the course of their daily work, analyzes and provides advice using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention is embodied in the following specific forms.

[0436] Data collection

[0437] server

[0438] The server collects digital data from each department's file sharing system or cloud storage. Specifically, the server uses an API to monitor designated folders in cloud storage (e.g., Amazon S3 or Google Drive) and automatically retrieves newly uploaded files. This collection process can be performed periodically or in real time using a file upload trigger.

[0439] Terminal

[0440] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator simply accesses the interface on a browser and drags and drops the files they want to collect, which sends the files to the server, allowing the server to acquire data in real time.

[0441] Data Preprocessing

[0442] server

[0443] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition) technology. For example, it uses an OCR tool such as Tesseract. It converts the meeting audio data into text using transcription software (for example, Google Cloud Speech-to-Text API). The preprocessed data is then converted into a unified text format.

[0444] Collaboration with generative artificial intelligence models

[0445] server

[0446] The preprocessed text data is fed into a generative artificial intelligence (AI) model, which uses natural language processing (NLP) techniques to analyze the context of the data and extract relevant information. For example, by using an AI model such as OpenAI's GPT-3, useful advice and suggestions can be generated from each piece of data.

[0447] Advisory Output

[0448] server

[0449] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification methods include email notification, sending a message to an internal chat tool (such as Slack), or displaying the information in real time on a dashboard. The generated content is formatted in HTML or other formats and provided to the person in charge.

[0450] User Utilization

[0451] User

[0452] The user (person in charge) carries out their work based on the advice provided. For example, when integrating radio equipment, they can revise the integration plan by referring to past bug information and advice on problems in other departments. During disaster recovery, the optimal recovery route proposed by the AI ​​model is executed.

[0453] Specific examples

[0454] Example 1: Radio integration

[0455] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the generated advice, who then modifies the integration plan.

[0456] Example 2: Disaster recovery

[0457] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the responsible party of the generated advice, who then carries out efficient recovery activities.

[0458] Prompt Sentence Examples

[0459] Please analyze the slides and audio data for the radio integration and provide advice based on past bug information and issues. Please also include known bugs and workarounds for specific radio models.

[0460]

[0461] Analyze slide decks and meeting audio related to recent disasters to suggest optimal recovery routes and procedures. Generate recommendations taking into account relevant data.

[0462] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0463] Step 1: Data Collection (Server)

[0464] The server automatically collects digital data from cloud storage (Amazon S3 or Google Drive) or file sharing systems. Specifically, the server uses an API to monitor specified folders and collects any newly added files. The collected files are saved in local storage. The input is digital data obtained via the API, and the output is data saved in the server's local storage. For example, when a new file is uploaded to a specified S3 bucket, it detects it and downloads it.

[0465] Step 2: Data collection (device)

[0466] The person in charge manually uploads digital data to the server via a terminal. The file is sent to the server by dragging and dropping it into the interface on the browser and clicking the upload button. The input is the file uploaded by the person in charge, and the output is the file saved on the server. Specifically, the person in charge uploads the slide materials.

[0467] Step 3: Data Preprocessing (Server)

[0468] The collected digital data is preprocessed. The server extracts text information from slides and spreadsheets, and uses OCR technology to obtain text from image files. Audio files are also converted to text using speech-to-text software. The input is the collected raw data, and the output is data in a unified text format. Specifically, a Python script is used to extract text from PDFs, Tesseract is used to perform character recognition from images, and the speech is converted to text using the Google Cloud Speech-to-Text API.

[0469] Step 4: Input data into the generative AI model (server)

[0470] The preprocessed text data is input into a generative artificial intelligence model. The server converts the text data into JSON format and sends it to the AI ​​model. The input is the preprocessed text data, and the output is advice or suggestions generated by the AI ​​model. Specifically, the preprocessed data is input into an AI model such as OpenAI's GPT-3 via an API, and the analysis results are received in text format.

[0471] Step 5: Advisory Output and Notification (Server)

[0472] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification formats include email, internal chat tools, and dashboards, and notifications are sent in the most effective way for each. The input is the results generated by the AI ​​model, and the output is advice formatted in the notification format. Specifically, the generated advice is formatted into HTML and sent via email via an SMTP server, or a chat notification is sent using the Slack API.

[0473] Step 6: Use the advice (user)

[0474] The user (person in charge) proceeds with the work based on the advice notified. They utilize the advice, such as referring to past bug information when integrating radio equipment, or implementing the optimal recovery route when planning disaster recovery. The input is the notified advice, and the output is work improvement measures and plans based on that advice. Specifically, they check the advice received by email and revise the integration plan. Or they can respond quickly by referring to recovery routes in the event of a disaster.

[0475] (Application example 1)

[0476] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0477] Modern autonomous vehicles generate large amounts of sensor data and operational data, but there is a lack of systems that can analyze this data in real time and provide appropriate operational advice. This can result in insufficient operational efficiency and safety for autonomous vehicles. There is also a growing need for a system that integrates a series of processes for data collection, preprocessing, analysis using AI models, and appropriate notification of advice. This will enable drivers and supervisors to receive advice in a timely manner, enabling safer and more efficient management of autonomous vehicle operations.

[0478] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0479] In this invention, the server includes: means for collecting digital data generated by each department; means for preprocessing the collected digital data and converting it into text information; means for inputting the preprocessed data into a generative artificial intelligence model and generating advice; means for notifying a responsible person of the generated advice; means for collecting sensor data and operation data generated by autonomous vehicles and uploading it to cloud storage; means for preprocessing the collected autonomous vehicle data, removing unnecessary parts, and converting it into text and numerical data; means for inputting the preprocessed autonomous vehicle data into a generative artificial intelligence model and generating advice based on operating conditions and traffic conditions; and means for notifying a driver or supervisor of the generated advice via a smartphone application. This makes it possible to efficiently manage autonomous vehicle data through a series of processes and provide appropriate advice to drivers and supervisors in real time.

[0480] "Digital data" means data generated by electronic devices, including slide decks, spreadsheets, audio data, and autonomous vehicle sensor and operational data.

[0481] "Preprocessing" refers to the process of removing unnecessary parts and converting collected digital data into text information and numerical data in order to convert it into an analyzable format.

[0482] A "generative artificial intelligence model" refers to an algorithm or model that uses natural language processing and machine learning techniques to analyze data and generate advice.

[0483] "Sensor data" refers to data obtained from various sensors (cameras, lidar, radar, etc.) installed in autonomous vehicles.

[0484] "Operational data" refers to data related to the operational status of an autonomous vehicle, such as its speed, location, and driving conditions.

[0485] "Cloud storage" refers to a service or system that stores digital data on remote servers via the Internet.

[0486] "Smartphone application" refers to a software program that runs on a smartphone and provides specific functionality.

[0487] "Operation status" refers to information about the current operating status of an autonomous vehicle and the surrounding traffic conditions.

[0488] "Notification" refers to a means of communicating the generated advice to the driver or supervisor, and includes push notification, screen display, voice guidance, etc.

[0489] This invention is a system that efficiently collects and analyzes digital data generated within a company or in an autonomous vehicle, and provides useful advice using a generative artificial intelligence model. Specific embodiments for implementing the invention are described below.

[0490] Data collection

[0491] server

[0492] The server collects digital data generated by each department within a company and from autonomous vehicles. Within a company, the server automatically collects digital data from file sharing systems, cloud storage, and conferencing tools. For example, it monitors cloud storage and collects new files when they are added. In the case of autonomous vehicles, the server collects sensor data and operational data and uploads the data to cloud storage.

[0493] Terminal

[0494] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires data in real time.Data collection from autonomous vehicles involves acquiring data directly from the vehicle's ECU (Engine Control Unit) and other sensors.

[0495] Data Preprocessing

[0496] server

[0497] The server preprocesses the collected digital data. For internal company data, text information is extracted from slides and spreadsheets, and text is also obtained from image files using OCR (optical character recognition) technology. Voice data is converted into text using speech transcription technology. This unifies all digital data into text format. For autonomous vehicle data, sensor data and operational data are preprocessed into an analyzable format, unnecessary parts are removed, and the data is converted into text and numerical data.

[0498] Collaboration with generative artificial intelligence models

[0499] server

[0500] The preprocessed text data is fed into a generative AI model to understand the context of the data and generate relevant advice. For example, it can identify problems and improvements from a company's internal business data and generate advice based on the operation status and traffic conditions of autonomous vehicles.

[0501] Advisory Output

[0502] server

[0503] The server analyzes the advice obtained from the generative AI model and determines the format in which to notify the person in charge. Notification methods include email notification, sending a message to an internal chat tool, displaying the advice in real time on a dashboard, and notifying the person in charge via a smartphone application. The generated advice is formatted and provided in a specific and easy-to-understand format.

[0504] User Utilization

[0505] User

[0506] Users (staff and drivers) can then carry out their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. Drivers of autonomous vehicles receive advice based on operational and traffic conditions to optimize operations. Operations control centers also receive data and advice in the same way, enabling them to manage operations more efficiently.

[0507] Prompt Sentence Examples

[0508] For example, a prompt to input to a generative artificial intelligence model might look like this:

[0509] "October 6, 2023, 12:34, Vehicle ID: vehicle_123, Speed: 35km / h, Location: Latitude 35.6895, Longitude 139.6917, Environmental Data: Includes camera images and lidar points."

[0510] By sending this prompt sentence to a generative artificial intelligence model, appropriate advice is generated.

[0511] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0512] Step 1:

[0513] The server collects digital data generated by various departments within the company and from autonomous vehicles. Within the company, data is automatically acquired from file sharing systems, cloud storage, and conference tools. For example, new files are monitored and added using the cloud storage API. Meanwhile, in autonomous vehicles, sensor data and operational data are collected and uploaded to cloud storage. The input to this step is digital data from within the company and from autonomous vehicles, and the output is the collected data stored on the server.

[0514] Step 2:

[0515] The server preprocesses the collected digital data. For internal company data, this preprocessing involves using OCR technology to extract text information from slides and image files, and using speech-to-text technology to convert voice data into text. For autonomous vehicle data, unnecessary parts are removed and the data is converted into analyzable text and numerical data. The input for this step is the collected digital data, and the output is preprocessed text data.

[0516] Step 3:

[0517] The server inputs the preprocessed text data into a generative AI model. The generative AI model analyzes the context of the input data and generates appropriate advice. For example, it can identify problems and improvement measures from internal business data, or generate driving advice based on driving and traffic conditions from data on autonomous vehicles. The input for this step is the preprocessed text data, and the output is the generated advice.

[0518] Step 4:

[0519] The server analyzes the advice obtained from the generative artificial intelligence model and notifies the person in charge or the driver in an appropriate format. Specific notification methods include email notification, sending a message to an internal chat tool, displaying the information in real time on a dashboard, or notifying via a smartphone application. The input of this step is the generated advice, and the output is the information notified to the person in charge or the driver.

[0520] Step 5:

[0521] The user (person in charge or driver) proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. The driver of an autonomous vehicle receives advice based on operational and traffic conditions to optimize operation. The input to this step is the advice they receive, and the output is the result of the user taking action.

[0522] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0523] This system automatically collects and preprocesses digital data generated by each department within a company, analyzes and provides advice using a generative artificial intelligence (AI) model, and adjusts the importance and display method of the advice content by combining it with an emotion engine that recognizes the user's emotions. This invention is embodied in the following specific forms.

[0524] Data collection

[0525] server

[0526] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. This can be done by using APIs to obtain data, periodically monitoring designated directories, or triggering file uploads. For example, it can monitor cloud storage (e.g., Google Drive, S3 buckets) and automatically download new files when they are detected.

[0527] Terminal

[0528] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator can select the files from the interface and upload them easily with a drag-and-drop operation. This allows the data to be sent to the server in real time.

[0529] Data Preprocessing

[0530] server

[0531] The server preprocesses the collected digital data. Specifically, it extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. The preprocessed data is organized into a unified format and prepared for input into the generative AI model.

[0532] Collaboration with generative artificial intelligence models

[0533] server

[0534] The preprocessed text data is fed into a generative AI model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential issues. Recommendations are generated as a result of the analysis by the AI ​​model.

[0535] Introducing the Emotion Engine

[0536] server

[0537] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes emotions from the user's voice and text data to understand the user's current psychological state. The emotion data is used to dynamically adjust the importance and display method of the advice provided by the AI ​​model.

[0538] Advisory Output

[0539] server

[0540] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice content will be simplified and only the most important information will be emphasized.

[0541] User

[0542] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing the psychological burden on the person in charge and promoting effective decision-making.

[0543] Specific examples

[0544] Example 1: Radio integration

[0545] The server collects slides and conference audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which the server receives. At the same time, an emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the appropriate person.

[0546] Example 2: Disaster recovery

[0547] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. This data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model combines the relevant data to generate advice, which the server receives. An emotion engine analyzes the user's psychological state and adjusts the content and priorities of the advice. The server notifies the responsible party of the adjusted advice, and the user uses it to carry out efficient recovery activities.

[0548] The above-described embodiments enable the present invention to be effectively carried out.

[0549] The processing flow will be explained below.

[0550] Step 1:

[0551] server

[0552] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses APIs to retrieve files, regularly monitors designated directories, and automatically downloads new files when they are found. This process includes monitoring cloud storage such as Google Drive and S3 buckets.

[0553] Step 2:

[0554] Terminal

[0555] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator selects the files using a dedicated web interface and uploads them by dragging and dropping them. The files are then saved to the server in real time.

[0556] Step 3:

[0557] server

[0558] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[0559] Step 4:

[0560] server

[0561] The preprocessed text data is input into a generative artificial intelligence (AI) model. An API call is made to the AI ​​model to send the data. The AI ​​model uses NLP (natural language processing) techniques to analyze the context of the data and identify relevant information and potential issues. This processing results in the generation of appropriate advice.

[0562] Step 5:

[0563] server

[0564] After receiving the response from the AI ​​model, the generated advice is further processed by the emotion engine, which analyzes the user's voice and text data to recognize their emotional state. For example, if the user is feeling stressed, the content and presentation of the advice can be adjusted based on this information.

[0565] Step 6:

[0566] server

[0567] The adjusted advice is then sent to the person in charge. This is where the appropriate notification format is selected. For example, email notification, notification via an internal chat tool, or real-time display on the management dashboard may be selected. The advice is adjusted using an emotion engine, so the importance and display method are reflected according to the user's psychological state.

[0568] Step 7:

[0569] User

[0570] The user (person in charge) checks the notified advice. When implementing radio equipment integration, the user receives advice on past bugs and problems that have occurred in other departments, and plans specific countermeasures. In addition, when recovering from a disaster, the AI ​​model proposes optimal recovery routes, which can be used as a reference to quickly respond. At this time, the emotion engine provides advice in a way that reduces the user's psychological burden.

[0571] Step 8:

[0572] User

[0573] We proceed with the work based on the advice we receive. For example, we aim to improve operational efficiency and reduce risk by revising integration plans and taking preventative measures. In disaster recovery cases, we act quickly and efficiently based on the optimal recovery route.

[0574] The above steps ensure that the system is implemented effectively and efficiently.

[0575] Example 2

[0576] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0577] Many companies face challenges in efficiently collecting and preprocessing large amounts of digital data generated by various departments within a company and generating useful advice using generative artificial intelligence models. Furthermore, the generated advice must be optimally displayed for the staff member and adjusted to reduce the psychological burden. However, current systems lack the ability to recognize the user's emotions and dynamically adjust the advice content, and a system that solves this problem is needed.

[0578] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0579] In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for notifying a person in charge of the generated advice, and means for activating an emotion engine for recognizing the user's emotions and adjusting the advice content based on the emotion data. This makes it possible to efficiently collect and preprocess a wide variety of digital data within a company, generate advanced advice using a generative artificial intelligence model, and provide optimal advice that takes the user's emotions into consideration.

[0580] "Digital data" means information or data stored in electronic form.

[0581] "Preprocessing" refers to the process of converting and shaping digital data to make it easier to analyze and use.

[0582] "Text information" refers to information expressed in characters or symbols.

[0583] A "generative artificial intelligence model" is an algorithm or system that analyzes patterns and trends from given data and generates predictions and suggestions.

[0584] An "emotion engine" is an analysis system for recognizing a user's emotional state, and is a technology for grasping a user's psychological state from voice and text.

[0585] "Advice" is information intended to provide solutions or guidance to a particular situation or problem.

[0586] A "notification" is a method or action for informing a user of specific information.

[0587] This invention is a system that efficiently collects and preprocesses digital data generated by each department within a company and provides analysis and advice using a generative artificial intelligence (AI) model. Furthermore, it aims to reduce psychological burden by combining an emotion engine that recognizes the user's emotions and adjusting the importance and display method of advice. Below, we will explain how to specifically implement this invention.

[0588] Data collection

[0589] server

[0590] The server automatically collects digital data generated by each department within the company. The system obtains data using API access to file sharing systems and cloud storage (e.g., Google Drive, Amazon S3 buckets). It also uses periodic monitoring of designated directories and file upload triggers. For example, it monitors Google Drive and automatically downloads new files when they are uploaded.

[0591] Terminal

[0592] The terminal provides an interface for the person in charge to manually upload the necessary files to the server. Using this interface, users can upload files with a simple drag-and-drop operation, and the resulting data is sent to the server in real time.

[0593] Data Preprocessing

[0594] server

[0595] The server preprocesses the collected digital data. It uses OCR technology (e.g., Tesseract OCR) to extract text information from slides and spreadsheets. It also converts the meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format, ready to be fed into the generative AI model in the next step.

[0596] Collaboration with generative artificial intelligence models

[0597] server

[0598] The server inputs the preprocessed text data into a generative AI model. The AI ​​model uses NLP techniques to understand the context of the data and identify relevant information and potential problems. For example, it analyzes past meeting notes and technical documents to extract trends and risk factors. Specific advice is generated as a result of the analysis.

[0599] Introducing the Emotion Engine

[0600] server

[0601] The server receives advice from the AI ​​model and simultaneously activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and text data to understand their current psychological state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. This dynamically adjusts the importance of the advice and how it is displayed.

[0602] Advisory Output

[0603] server

[0604] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice will be brief and only the important information will be highlighted.

[0605] User

[0606] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing psychological burden and promoting effective decision-making.

[0607] Specific examples

[0608] Example 1: Radio integration

[0609] The server collects and preprocesses the slides and meeting audio data generated for the radio integration. It extracts text information from the slides and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which is received by the server. At the same time, the emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the person in charge. An example of a prompt is, "Please generate advice on future measures based on the bug information and meeting audio data for the past year regarding the radio integration."

[0610] Example 2: Disaster recovery

[0611] When a disaster occurs, the server automatically collects and pre-processes relevant documents and conference audio data. This data is pre-processed and input into a generative AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with the relevant data to generate advice, which the server receives. The emotion engine analyzes the user's psychological state and adjusts the advice content and priorities. The adjusted advice content is notified to the person in charge, who then uses it to carry out efficient recovery activities. An example of a prompt is, "Please provide advice on the optimal recovery routes and procedures based on the conference audio data and related documents from the most recent disaster."

[0612] The above is a specific embodiment for carrying out the present invention.

[0613] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0614] Step 1: Data collection

[0615] server

[0616] Input: Digital data generated by each department (e.g., electronic documents, spreadsheet data, audio data)

[0617] The server collects digital data using API access to each department's file sharing system and cloud storage. It automatically imports data when a file is added by using periodic monitoring of designated directories or file upload triggers. For example, it can detect new files from cloud storage and automatically download them to the server.

[0618] Output: Collected digital data (electronic file)

[0619] Terminal

[0620] Input: Necessary files held by the person in charge

[0621] The terminal provides an interface for the staff member to manually upload files, allowing them to select files and send them by dragging and dropping them.

[0622] Output: The file uploaded to the server.

[0623] Step 2: Data Preprocessing

[0624] server

[0625] Input: Collected digital data

[0626] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, extracts text information from image files using OCR technology (e.g., Tesseract OCR), and converts meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The resulting text data is then organized into a unified format.

[0627] Output: Preprocessed text data

[0628] Step 3: Collaboration with generative AI models

[0629] server

[0630] Input: Preprocessed text data

[0631] The server inputs the preprocessed data into a generative artificial intelligence model (e.g., GPT-3). This AI model uses NLP techniques to understand the context of the data and analyze it for relevant information and potential problems. The AI ​​model analyzes the data and generates specific advice, such as extracting trends and risk factors based on past meeting notes and technical documents.

[0632] Output: Generated advice

[0633] Step 4: Implementing the Emotion Engine

[0634] server

[0635] Input: Advice from the generative AI model, user emotional data (voice data, text data)

[0636] The server activates an emotion engine based on the advice received from the generative AI model. The emotion engine analyzes the user's voice and text data to understand their current emotional state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. The emotion data is used to adjust the importance of the advice and how it is displayed.

[0637] Output: Tailored advice based on sentiment data

[0638] Step 5: Advisory Output

[0639] server

[0640] Input: Tailored advice based on sentiment data

[0641] The server determines the format of notification to the agent based on the adjusted advice content. For example, if the user is feeling stressed, the advice will be brief and only important information will be highlighted.

[0642] Output: Adjusted advice notification

[0643] User

[0644] Input: Advice sent by the server

[0645] The user (person in charge) checks the advice sent from the server. For example, when implementing wireless equipment integration, they can plan countermeasures by referring to specific advice based on past bug information and problems that have occurred in other departments. Also, during disaster recovery, they can respond quickly based on the optimal recovery route suggested by the AI ​​model. Advice is provided based on the results of the emotion engine, reducing psychological burden.

[0646] Output: Specific measures and action plans

[0647] The above is the specific flow of the program processing of this system.

[0648] (Application example 2)

[0649] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0650] In traditional brick-and-mortar store operations, it is difficult to effectively utilize the large amounts of data obtained from POS systems, inventory management systems, customer feedback, etc., and advice for improving operations and measures based on employee emotions are not sufficiently implemented. In addition, busy work places a heavy psychological burden on employees, which can have a negative impact on the quality of customer service and sales effectiveness.

[0651] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for analyzing the user's emotions and adjusting the content and presentation method of the advice, and means for notifying the person in charge of the generated advice. This makes it possible to effectively utilize digital data to provide advice for improving operations, and further to optimize the content and display method of the advice by taking employee emotions into consideration.

[0652] "Each department" refers to a division or section within a company or organization that has a different role or function.

[0653] "Digital data" means data that can be stored, transmitted, or processed electronically, including text, audio, images, and video.

[0654] "Means of collection" refers to the methods and technologies used to collect the necessary digital data, such as APIs, file uploads, and sensors.

[0655] "Preprocessing" refers to the basic processing and conversion work done on collected data to make it easier to analyze, and includes things like text extraction and data cleaning.

[0656] "Text information" refers to character string information written in natural language, and takes the form of documents, notes, comments, etc.

[0657] A "generative artificial intelligence model" refers to a model that uses machine learning algorithms and neural networks to automatically generate useful information and advice from input data.

[0658] "Advice" means suggestions or advice on problems or issues, including points for improvement and specific measures.

[0659] "Means of notification" refers to the methods and technologies used to deliver generated advice and information to the responsible party, including email, push notifications, and message displays.

[0660] "User emotions" refers to the current psychological state and emotional reactions of users using the system, including stress, fatigue, satisfaction, etc.

[0661] "Means for analyzing emotions" refers to technologies and methods for detecting and analyzing a user's emotions, including voice analysis, facial expression analysis, and text analysis.

[0662] "Presentation" refers to the format or method in which information or advice is displayed to the user, including textual, graphical, and animation displays.

[0663] This invention relates to a system that aims to optimize the operation of a physical store. The system is composed of a server, a terminal, and a user, and is implemented as follows.

[0664] 1. Data Collection

[0665] The server collects digital data from physical store POS systems, inventory management systems, and customer feedback systems. This includes methods such as API-based data acquisition, regular monitoring, and file upload triggers. For example, cloud storage can be monitored and new data can be automatically downloaded when detected. On the terminal side, employees use a smartphone app to upload the necessary data to the server, which then transmits the data to the server in real time.

[0666] 2. Data Preprocessing

[0667] The server preprocesses the collected digital data and converts it into text information. Specifically, it uses OCR (optical character recognition) technology to extract text from document data, and transcribes audio data using speech recognition technology (Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format and prepared for input into a generative artificial intelligence model.

[0668] 3. Collaboration with generative artificial intelligence models

[0669] The server inputs the preprocessed data into a generative artificial intelligence model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential problems. The analysis results of the AI ​​model generate recommendations for operational improvement.

[0670] 4. Introducing the Emotion Engine

[0671] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's (employee's) emotions. The emotion engine analyzes voice data and feedback collected from the device to understand the user's current psychological state. Emotional data is used to adjust the importance and presentation method of the generated advice.

[0672] 5. Advisory Output

[0673] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format for notification to the device and notifies the user (employee). For example, if the user is feeling stressed, the advice content will be simplified, emphasizing only the most important information. The user can review the advice notified to them and use it to improve operations and customer service.

[0674] Specific examples

[0675] Examples of employee stress reduction measures

[0676] When employees are tired, a "quick feedback check" is sufficient. In this case, the prompt would be "Generate a quick improvement suggestion to present to employees when they are tired."

[0677] Example of inventory management timing advice output

[0678] If there is a sudden increase in best-selling items, the system displays a message to "recommend the next order timing." In this case, the prompt is "Please suggest the next product to order based on sales and the timing."

[0679] This system will enable the use of digital data in physical store operations and the provision of optimal advice that takes user emotions into consideration, which is expected to improve operational efficiency and customer satisfaction.

[0680] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0681] Step 1:

[0682] The server collects digital data from the physical store's POS system, inventory management system, and customer feedback system. Specifically, it periodically retrieves data using APIs and monitors cloud storage to detect newly added data. The input is digital data from each system (e.g., sales data, inventory data, customer feedback), and the output is storing that data on the server.

[0683] Step 2:

[0684] At the terminal, employees use a smartphone app to upload the required data to the server. Specifically, they select a file from the app interface and upload it simply by dragging and dropping. The input is the file selected by the employee, and the output is that file is sent to the server in real time.

[0685] Step 3:

[0686] The server preprocesses the collected digital data. Specifically, it uses OCR (Optical Character Recognition) technology to extract text from document data and AudioFile to transcribe audio data. The input is the collected raw data, and the output is text information converted into a unified format.

[0687] Step 4:

[0688] The server inputs the preprocessed text information into a generative artificial intelligence model. The model uses NLP techniques to analyze the context of the data and identify relevant information and potential problems. The input is the preprocessed text data, and the output is recommendations for operational improvement.

[0689] Step 5:

[0690] The device sends voice data and feedback to a server to recognize the user's (employee's) emotions. Voice recognition technology is used to extract emotions from the voice, and text data is analyzed to determine the emotion. The input is voice data and text data, and the output is emotional data.

[0691] Step 6:

[0692] The server adjusts the advice content based on the advice obtained from the generative AI model and the emotional data obtained from the emotion engine. Specifically, it changes the importance and display method of the advice depending on the user's emotional state. The input is the advice from the generative AI model and the emotional data from the emotion engine, and the output is the adjusted advice content.

[0693] Step 7:

[0694] The server notifies the device of the adjusted advice. A push notification is sent to the smartphone app, which the employee confirms. Specific operations include using an API or push notification service to notify the employee. The input is the adjusted advice, and the output is the advice displayed on the employee's smartphone.

[0695] Step 8:

[0696] The user (employee) uses the received advice to improve operations and customer service. Specifically, they review their business processes based on the provided advice and take necessary measures. The input is the received advice, and the output is improvements to the store's operations and customer service.

[0697] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0698] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0699] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0700] [Third embodiment]

[0701] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0702] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0703] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0704] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0705] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0706] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0707] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0708] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0709] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0710] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0711] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0712] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0713] This system automatically collects digital data (slides, spreadsheets, conference audio data, etc.) generated by each department in a company in the course of their daily work, analyzes and advises using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention can be embodied in the following specific forms.

[0714] Data collection

[0715] server

[0716] The server automatically collects digital data from each department's file sharing system, cloud storage, and meeting tools. This can be done by directly retrieving data using APIs, periodically monitoring folders, or using file upload triggers. For example, it can monitor cloud storage such as S3 buckets and Google Drive and collect files when new files are added.

[0717] Terminal

[0718] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires the data in real time.

[0719] Data Preprocessing

[0720] server

[0721] The server preprocesses the various digital data collected. It extracts text information from slides and spreadsheets, and uses OCR (optical character recognition) technology to obtain text from image files. It converts meeting audio data into text using speech-to-text software. This allows all digital data to be integrated into a text format. The preprocessed data is integrated into a single data format, which can then be input into the subsequent generative artificial intelligence model.

[0722] Collaboration with generative artificial intelligence models

[0723] server

[0724] The preprocessed text data is fed into a generative artificial intelligence (AI) model, using natural language processing (NLP) for example, to understand the context of the data and identify relevant information. The AI ​​model then automatically analyzes relevant problems and solutions and generates specific recommendations.

[0725] Advisory Output

[0726] server

[0727] The server analyzes the advice obtained from the generative AI model and determines how to notify the person in charge. Notification methods include email notifications, messages sent to internal chat tools, or real-time display on a dashboard. The notification content is formatted and provided to the person in charge in a specific, easy-to-understand format.

[0728] User Utilization

[0729] User

[0730] The user (person in charge) then proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and issues that have occurred in other departments, allowing them to revise the integration plan for the target station and reduce the risk of malfunctions. Furthermore, during disaster recovery, they can refer to the optimal recovery route proposed by the AI ​​model to carry out efficient recovery activities.

[0731] Specific examples

[0732] Example 1: Radio integration

[0733] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the advice, who then uses it to revise the integration plan.

[0734] Example 2: Disaster recovery

[0735] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the person in charge of the generated advice, who then uses it to carry out efficient recovery activities.

[0736] The above-described embodiments enable the present invention to be effectively carried out.

[0737] The processing flow will be explained below.

[0738] Step 1:

[0739] server

[0740] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses direct acquisition using APIs, regular monitoring of specified directories, and file upload triggers. For example, it monitors cloud storage (e.g., Google Drive, S3 buckets) and downloads new files when they are detected.

[0741] Step 2:

[0742] Terminal

[0743] On the terminal side, the staff manually uploads the required digital data to the server. Through a dedicated interface, the staff can select files and upload them by dragging and dropping them. This data is sent to the server in real time and saved.

[0744] Step 3:

[0745] server

[0746] The server preprocesses the collected data. Specifically, it extracts text information from slide decks and spreadsheets, extracts text from image files using OCR (optical character recognition), and converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[0747] Step 4:

[0748] server

[0749] The preprocessed text data is fed into a generative artificial intelligence (AI) model. An API is called to send the data to the AI ​​model, which then performs the analysis task. The AI ​​model uses natural language processing (NLP) techniques to understand the context of the data and identify relevant information and potential issues.

[0750] Step 5:

[0751] server

[0752] Receive the response from the AI ​​model, analyze the generated advice, format the advice in an easy-to-understand format, and decide how to notify the responsible person. For example, select whether to notify the person via email, internal chat tool, or dashboard based on importance and urgency.

[0753] Step 6:

[0754] server

[0755] The system notifies the responsible person with formatted advice. In the case of email notification, the advice is sent to the responsible person's email address. In the case of using an internal chat tool, a message is sent to promote real-time communication. In the case of dashboard display, the responsible person can check the advice through a web interface.

[0756] Step 7:

[0757] User

[0758] The person in charge will review the advice provided. For example, when implementing wireless equipment integration, they will receive advice based on past bug information and problems that have occurred in other departments, and plan specific countermeasures.

[0759] Step 8:

[0760] User

[0761] The person in charge will proceed with their work based on the advice received. By modifying the integration plan and taking preventative measures against problems, they aim to improve work efficiency and reduce risks. In the event of a disaster, they will be able to respond quickly by referring to the optimal recovery route.

[0762] The above are the specific processing steps in this system.

[0763] Example 1

[0764] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0765] There is a need for a system that can efficiently collect a wide variety of digital data generated by each department within a company, centrally manage and analyze it, and provide personnel with specific advice that will help improve business operations and carry out their work. However, conventional methods require time-consuming data collection and preprocessing, and analyzing the data to obtain useful advice requires a great deal of time and effort. In addition, when personnel manually collect data, it often lacks real-time capabilities.

[0766] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0767] In this invention, the server includes means for collecting digital data generated by each department, means for preprocessing the collected digital data and converting it into text information, and means for inputting the preprocessed data into a generative artificial intelligence model and generating advice. This makes it possible to efficiently collect and preprocess data generated within a company and quickly generate and provide useful advice from that data.

[0768] "Digital data" refers to information, records, or materials that are generated or stored electronically, including, for example, slides, spreadsheets, audio files, etc.

[0769] "Collection methods" refers to the methods, tools, or processes used to automatically or manually collect digital data generated from each department.

[0770] "Preprocessing means" refers to the process of converting collected digital data into a format that is easy to analyze, and specifically includes converting it into text information and removing noise.

[0771] "Generative artificial intelligence model" refers to an artificial intelligence algorithm or system used to generate useful information or advice from collected and pre-processed digital data.

[0772] "Advice generation means" refers to a method, tool, or process for inputting pre-processed data into a generative artificial intelligence model, analyzing it, and generating specific advice or suggestions.

[0773] "Notification means" refers to the methods, tools, or processes for effectively communicating generated advice and suggestions to relevant personnel, including, for example, email, chat tools, dashboards, etc.

[0774] This system automatically or manually collects digital data (e.g., slides, spreadsheets, audio files, etc.) generated by each department in a company in the course of their daily work, analyzes and provides advice using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention is embodied in the following specific forms.

[0775] Data collection

[0776] server

[0777] The server collects digital data from each department's file sharing system or cloud storage. Specifically, the server uses an API to monitor designated folders in cloud storage (e.g., Amazon S3 or Google Drive) and automatically retrieves newly uploaded files. This collection process can be performed periodically or in real time using a file upload trigger.

[0778] Terminal

[0779] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator simply accesses the interface on a browser and drags and drops the files they want to collect, which sends the files to the server, allowing the server to acquire data in real time.

[0780] Data Preprocessing

[0781] server

[0782] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition) technology. For example, it uses an OCR tool such as Tesseract. It converts the meeting audio data into text using transcription software (for example, Google Cloud Speech-to-Text API). The preprocessed data is then converted into a unified text format.

[0783] Collaboration with generative artificial intelligence models

[0784] server

[0785] The preprocessed text data is fed into a generative artificial intelligence (AI) model, which uses natural language processing (NLP) techniques to analyze the context of the data and extract relevant information. For example, by using an AI model such as OpenAI's GPT-3, useful advice and suggestions can be generated from each piece of data.

[0786] Advisory Output

[0787] server

[0788] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification methods include email notification, sending a message to an internal chat tool (such as Slack), or displaying the information in real time on a dashboard. The generated content is formatted in HTML or other formats and provided to the person in charge.

[0789] User Utilization

[0790] User

[0791] The user (person in charge) carries out their work based on the advice provided. For example, when integrating radio equipment, they can revise the integration plan by referring to past bug information and advice on problems in other departments. During disaster recovery, the optimal recovery route proposed by the AI ​​model is executed.

[0792] Specific examples

[0793] Example 1: Radio integration

[0794] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the generated advice, who then modifies the integration plan.

[0795] Example 2: Disaster recovery

[0796] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the responsible party of the generated advice, who then carries out efficient recovery activities.

[0797] Prompt Sentence Examples

[0798] Please analyze the slides and audio data for the radio integration and provide advice based on past bug information and issues. Please also include known bugs and workarounds for specific radio models.

[0799]

[0800] Analyze slide decks and meeting audio related to recent disasters to suggest optimal recovery routes and procedures. Generate recommendations taking into account relevant data.

[0801] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0802] Step 1: Data Collection (Server)

[0803] The server automatically collects digital data from cloud storage (Amazon S3 or Google Drive) or file sharing systems. Specifically, the server uses an API to monitor specified folders and collects any newly added files. The collected files are saved in local storage. The input is digital data obtained via the API, and the output is data saved in the server's local storage. For example, when a new file is uploaded to a specified S3 bucket, it detects it and downloads it.

[0804] Step 2: Data collection (device)

[0805] The person in charge manually uploads digital data to the server via a terminal. The file is sent to the server by dragging and dropping it into the interface on the browser and clicking the upload button. The input is the file uploaded by the person in charge, and the output is the file saved on the server. Specifically, the person in charge uploads the slide materials.

[0806] Step 3: Data Preprocessing (Server)

[0807] The collected digital data is preprocessed. The server extracts text information from slides and spreadsheets, and uses OCR technology to obtain text from image files. Audio files are also converted to text using speech-to-text software. The input is the collected raw data, and the output is data in a unified text format. Specifically, a Python script is used to extract text from PDFs, Tesseract is used to perform character recognition from images, and the speech is converted to text using the Google Cloud Speech-to-Text API.

[0808] Step 4: Input data into the generative AI model (server)

[0809] The preprocessed text data is input into a generative artificial intelligence model. The server converts the text data into JSON format and sends it to the AI ​​model. The input is the preprocessed text data, and the output is advice or suggestions generated by the AI ​​model. Specifically, the preprocessed data is input into an AI model such as OpenAI's GPT-3 via an API, and the analysis results are received in text format.

[0810] Step 5: Advisory Output and Notification (Server)

[0811] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification formats include email, internal chat tools, and dashboards, and notifications are sent in the most effective way for each. The input is the results generated by the AI ​​model, and the output is advice formatted in the notification format. Specifically, the generated advice is formatted into HTML and sent via email via an SMTP server, or a chat notification is sent using the Slack API.

[0812] Step 6: Use the advice (user)

[0813] The user (person in charge) proceeds with the work based on the advice notified. They utilize the advice, such as referring to past bug information when integrating radio equipment, or implementing the optimal recovery route when planning disaster recovery. The input is the notified advice, and the output is work improvement measures and plans based on that advice. Specifically, they check the advice received by email and revise the integration plan. Or they can respond quickly by referring to recovery routes in the event of a disaster.

[0814] (Application example 1)

[0815] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0816] Modern autonomous vehicles generate large amounts of sensor data and operational data, but there is a lack of systems that can analyze this data in real time and provide appropriate operational advice. This can result in insufficient operational efficiency and safety for autonomous vehicles. There is also a growing need for a system that integrates a series of processes for data collection, preprocessing, analysis using AI models, and appropriate notification of advice. This will enable drivers and supervisors to receive advice in a timely manner, enabling safer and more efficient management of autonomous vehicle operations.

[0817] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0818] In this invention, the server includes: means for collecting digital data generated by each department; means for preprocessing the collected digital data and converting it into text information; means for inputting the preprocessed data into a generative artificial intelligence model and generating advice; means for notifying a responsible person of the generated advice; means for collecting sensor data and operation data generated by autonomous vehicles and uploading it to cloud storage; means for preprocessing the collected autonomous vehicle data, removing unnecessary parts, and converting it into text and numerical data; means for inputting the preprocessed autonomous vehicle data into a generative artificial intelligence model and generating advice based on operating conditions and traffic conditions; and means for notifying a driver or supervisor of the generated advice via a smartphone application. This makes it possible to efficiently manage autonomous vehicle data through a series of processes and provide appropriate advice to drivers and supervisors in real time.

[0819] "Digital data" means data generated by electronic devices, including slide decks, spreadsheets, audio data, and autonomous vehicle sensor and operational data.

[0820] "Preprocessing" refers to the process of removing unnecessary parts and converting collected digital data into text information and numerical data in order to convert it into an analyzable format.

[0821] A "generative artificial intelligence model" refers to an algorithm or model that uses natural language processing and machine learning techniques to analyze data and generate advice.

[0822] "Sensor data" refers to data obtained from various sensors (cameras, lidar, radar, etc.) installed in autonomous vehicles.

[0823] "Operational data" refers to data related to the operational status of an autonomous vehicle, such as its speed, location, and driving conditions.

[0824] "Cloud storage" refers to a service or system that stores digital data on remote servers via the Internet.

[0825] "Smartphone application" refers to a software program that runs on a smartphone and provides specific functionality.

[0826] "Operation status" refers to information about the current operating status of an autonomous vehicle and the surrounding traffic conditions.

[0827] "Notification" refers to a means of communicating the generated advice to the driver or supervisor, and includes push notification, screen display, voice guidance, etc.

[0828] This invention is a system that efficiently collects and analyzes digital data generated within a company or in an autonomous vehicle, and provides useful advice using a generative artificial intelligence model. Specific embodiments for implementing the invention are described below.

[0829] Data collection

[0830] server

[0831] The server collects digital data generated by each department within a company and from autonomous vehicles. Within a company, the server automatically collects digital data from file sharing systems, cloud storage, and conferencing tools. For example, it monitors cloud storage and collects new files when they are added. In the case of autonomous vehicles, the server collects sensor data and operational data and uploads the data to cloud storage.

[0832] Terminal

[0833] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires data in real time.Data collection from autonomous vehicles involves acquiring data directly from the vehicle's ECU (Engine Control Unit) and other sensors.

[0834] Data Preprocessing

[0835] server

[0836] The server preprocesses the collected digital data. For internal company data, text information is extracted from slides and spreadsheets, and text is also obtained from image files using OCR (optical character recognition) technology. Voice data is converted into text using speech transcription technology. This unifies all digital data into text format. For autonomous vehicle data, sensor data and operational data are preprocessed into an analyzable format, unnecessary parts are removed, and the data is converted into text and numerical data.

[0837] Collaboration with generative artificial intelligence models

[0838] server

[0839] The preprocessed text data is fed into a generative AI model to understand the context of the data and generate relevant advice. For example, it can identify problems and improvements from a company's internal business data and generate advice based on the operation status and traffic conditions of autonomous vehicles.

[0840] Advisory Output

[0841] server

[0842] The server analyzes the advice obtained from the generative AI model and determines the format in which to notify the person in charge. Notification methods include email notification, sending a message to an internal chat tool, displaying the advice in real time on a dashboard, and notifying the person in charge via a smartphone application. The generated advice is formatted and provided in a specific and easy-to-understand format.

[0843] User Utilization

[0844] User

[0845] Users (staff and drivers) can then carry out their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. Drivers of autonomous vehicles receive advice based on operational and traffic conditions to optimize operations. Operations control centers also receive data and advice in the same way, enabling them to manage operations more efficiently.

[0846] Prompt Sentence Examples

[0847] For example, a prompt to input to a generative artificial intelligence model might look like this:

[0848] "October 6, 2023, 12:34, Vehicle ID: vehicle_123, Speed: 35km / h, Location: Latitude 35.6895, Longitude 139.6917, Environmental Data: Includes camera images and lidar points."

[0849] By sending this prompt sentence to a generative artificial intelligence model, appropriate advice is generated.

[0850] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0851] Step 1:

[0852] The server collects digital data generated by various departments within the company and from autonomous vehicles. Within the company, data is automatically acquired from file sharing systems, cloud storage, and conference tools. For example, new files are monitored and added using the cloud storage API. Meanwhile, in autonomous vehicles, sensor data and operational data are collected and uploaded to cloud storage. The input to this step is digital data from within the company and from autonomous vehicles, and the output is the collected data stored on the server.

[0853] Step 2:

[0854] The server preprocesses the collected digital data. For internal company data, this preprocessing involves using OCR technology to extract text information from slides and image files, and using speech-to-text technology to convert voice data into text. For autonomous vehicle data, unnecessary parts are removed and the data is converted into analyzable text and numerical data. The input for this step is the collected digital data, and the output is preprocessed text data.

[0855] Step 3:

[0856] The server inputs the preprocessed text data into a generative AI model. The generative AI model analyzes the context of the input data and generates appropriate advice. For example, it can identify problems and improvement measures from internal business data, or generate driving advice based on driving and traffic conditions from data on autonomous vehicles. The input for this step is the preprocessed text data, and the output is the generated advice.

[0857] Step 4:

[0858] The server analyzes the advice obtained from the generative artificial intelligence model and notifies the person in charge or the driver in an appropriate format. Specific notification methods include email notification, sending a message to an internal chat tool, displaying the information in real time on a dashboard, or notifying via a smartphone application. The input of this step is the generated advice, and the output is the information notified to the person in charge or the driver.

[0859] Step 5:

[0860] The user (person in charge or driver) proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. The driver of an autonomous vehicle receives advice based on operational and traffic conditions to optimize operation. The input to this step is the advice they receive, and the output is the result of the user taking action.

[0861] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0862] This system automatically collects and preprocesses digital data generated by each department within a company, analyzes and provides advice using a generative artificial intelligence (AI) model, and adjusts the importance and display method of the advice content by combining it with an emotion engine that recognizes the user's emotions. This invention is embodied in the following specific forms.

[0863] Data collection

[0864] server

[0865] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. This can be done by using APIs to obtain data, periodically monitoring designated directories, or triggering file uploads. For example, it can monitor cloud storage (e.g., Google Drive, S3 buckets) and automatically download new files when they are detected.

[0866] Terminal

[0867] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator can select the files from the interface and upload them easily with a drag-and-drop operation. This allows the data to be sent to the server in real time.

[0868] Data Preprocessing

[0869] server

[0870] The server preprocesses the collected digital data. Specifically, it extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. The preprocessed data is organized into a unified format and prepared for input into the generative AI model.

[0871] Collaboration with generative artificial intelligence models

[0872] server

[0873] The preprocessed text data is fed into a generative AI model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential issues. Recommendations are generated as a result of the analysis by the AI ​​model.

[0874] Introducing the Emotion Engine

[0875] server

[0876] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes emotions from the user's voice and text data to understand the user's current psychological state. The emotion data is used to dynamically adjust the importance and display method of the advice provided by the AI ​​model.

[0877] Advisory Output

[0878] server

[0879] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice content will be simplified and only the most important information will be emphasized.

[0880] User

[0881] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing the psychological burden on the person in charge and promoting effective decision-making.

[0882] Specific examples

[0883] Example 1: Radio integration

[0884] The server collects slides and conference audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which the server receives. At the same time, an emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the appropriate person.

[0885] Example 2: Disaster recovery

[0886] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. This data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model combines the relevant data to generate advice, which the server receives. An emotion engine analyzes the user's psychological state and adjusts the content and priorities of the advice. The server notifies the responsible party of the adjusted advice, and the user uses it to carry out efficient recovery activities.

[0887] The above-described embodiments enable the present invention to be effectively carried out.

[0888] The processing flow will be explained below.

[0889] Step 1:

[0890] server

[0891] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses APIs to retrieve files, regularly monitors designated directories, and automatically downloads new files when they are found. This process includes monitoring cloud storage such as Google Drive and S3 buckets.

[0892] Step 2:

[0893] Terminal

[0894] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator selects the files using a dedicated web interface and uploads them by dragging and dropping them. The files are then saved to the server in real time.

[0895] Step 3:

[0896] server

[0897] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[0898] Step 4:

[0899] server

[0900] The preprocessed text data is input into a generative artificial intelligence (AI) model. An API call is made to the AI ​​model to send the data. The AI ​​model uses NLP (natural language processing) techniques to analyze the context of the data and identify relevant information and potential issues. This processing results in the generation of appropriate advice.

[0901] Step 5:

[0902] server

[0903] After receiving the response from the AI ​​model, the generated advice is further processed by the emotion engine, which analyzes the user's voice and text data to recognize their emotional state. For example, if the user is feeling stressed, the content and presentation of the advice can be adjusted based on this information.

[0904] Step 6:

[0905] server

[0906] The adjusted advice is then sent to the person in charge. This is where the appropriate notification format is selected. For example, email notification, notification via an internal chat tool, or real-time display on the management dashboard may be selected. The advice is adjusted using an emotion engine, so the importance and display method are reflected according to the user's psychological state.

[0907] Step 7:

[0908] User

[0909] The user (person in charge) checks the notified advice. When implementing radio equipment integration, the user receives advice on past bugs and problems that have occurred in other departments, and plans specific countermeasures. In addition, when recovering from a disaster, the AI ​​model proposes optimal recovery routes, which can be used as a reference to quickly respond. At this time, the emotion engine provides advice in a way that reduces the user's psychological burden.

[0910] Step 8:

[0911] User

[0912] We proceed with the work based on the advice we receive. For example, we aim to improve operational efficiency and reduce risk by revising integration plans and taking preventative measures. In disaster recovery cases, we act quickly and efficiently based on the optimal recovery route.

[0913] The above steps ensure that the system is implemented effectively and efficiently.

[0914] Example 2

[0915] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0916] Many companies face challenges in efficiently collecting and preprocessing large amounts of digital data generated by various departments within a company and generating useful advice using generative artificial intelligence models. Furthermore, the generated advice must be optimally displayed for the staff member and adjusted to reduce the psychological burden. However, current systems lack the ability to recognize the user's emotions and dynamically adjust the advice content, and a system that solves this problem is needed.

[0917] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0918] In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for notifying a person in charge of the generated advice, and means for activating an emotion engine for recognizing the user's emotions and adjusting the advice content based on the emotion data. This makes it possible to efficiently collect and preprocess a wide variety of digital data within a company, generate advanced advice using a generative artificial intelligence model, and provide optimal advice that takes the user's emotions into consideration.

[0919] "Digital data" means information or data stored in electronic form.

[0920] "Preprocessing" refers to the process of converting and shaping digital data to make it easier to analyze and use.

[0921] "Text information" refers to information expressed in characters or symbols.

[0922] A "generative artificial intelligence model" is an algorithm or system that analyzes patterns and trends from given data and generates predictions and suggestions.

[0923] An "emotion engine" is an analysis system for recognizing a user's emotional state, and is a technology for grasping a user's psychological state from voice and text.

[0924] "Advice" is information intended to provide solutions or guidance to a particular situation or problem.

[0925] A "notification" is a method or action for informing a user of specific information.

[0926] This invention is a system that efficiently collects and preprocesses digital data generated by each department within a company and provides analysis and advice using a generative artificial intelligence (AI) model. Furthermore, it aims to reduce psychological burden by combining an emotion engine that recognizes the user's emotions and adjusting the importance and display method of advice. Below, we will explain how to specifically implement this invention.

[0927] Data collection

[0928] server

[0929] The server automatically collects digital data generated by each department within the company. The system obtains data using API access to file sharing systems and cloud storage (e.g., Google Drive, Amazon S3 buckets). It also uses periodic monitoring of designated directories and file upload triggers. For example, it monitors Google Drive and automatically downloads new files when they are uploaded.

[0930] Terminal

[0931] The terminal provides an interface for the person in charge to manually upload the necessary files to the server. Using this interface, users can upload files with a simple drag-and-drop operation, and the resulting data is sent to the server in real time.

[0932] Data Preprocessing

[0933] server

[0934] The server preprocesses the collected digital data. It uses OCR technology (e.g., Tesseract OCR) to extract text information from slides and spreadsheets. It also converts the meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format, ready to be fed into the generative AI model in the next step.

[0935] Collaboration with generative artificial intelligence models

[0936] server

[0937] The server inputs the preprocessed text data into a generative AI model. The AI ​​model uses NLP techniques to understand the context of the data and identify relevant information and potential problems. For example, it analyzes past meeting notes and technical documents to extract trends and risk factors. Specific advice is generated as a result of the analysis.

[0938] Introducing the Emotion Engine

[0939] server

[0940] The server receives advice from the AI ​​model and simultaneously activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and text data to understand their current psychological state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. This dynamically adjusts the importance of the advice and how it is displayed.

[0941] Advisory Output

[0942] server

[0943] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice will be brief and only the important information will be highlighted.

[0944] User

[0945] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing psychological burden and promoting effective decision-making.

[0946] Specific examples

[0947] Example 1: Radio integration

[0948] The server collects and preprocesses the slides and meeting audio data generated for the radio integration. It extracts text information from the slides and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which is received by the server. At the same time, the emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the person in charge. An example of a prompt is, "Please generate advice on future measures based on the bug information and meeting audio data for the past year regarding the radio integration."

[0949] Example 2: Disaster recovery

[0950] When a disaster occurs, the server automatically collects and pre-processes relevant documents and conference audio data. This data is pre-processed and input into a generative AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with the relevant data to generate advice, which the server receives. The emotion engine analyzes the user's psychological state and adjusts the advice content and priorities. The adjusted advice content is notified to the person in charge, who then uses it to carry out efficient recovery activities. An example of a prompt is, "Please provide advice on the optimal recovery routes and procedures based on the conference audio data and related documents from the most recent disaster."

[0951] The above is a specific embodiment for carrying out the present invention.

[0952] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0953] Step 1: Data collection

[0954] server

[0955] Input: Digital data generated by each department (e.g., electronic documents, spreadsheet data, audio data)

[0956] The server collects digital data using API access to each department's file sharing system and cloud storage. It automatically imports data when a file is added by using periodic monitoring of designated directories or file upload triggers. For example, it can detect new files from cloud storage and automatically download them to the server.

[0957] Output: Collected digital data (electronic file)

[0958] Terminal

[0959] Input: Necessary files held by the person in charge

[0960] The terminal provides an interface for the staff member to manually upload files, allowing them to select files and send them by dragging and dropping them.

[0961] Output: The file uploaded to the server.

[0962] Step 2: Data Preprocessing

[0963] server

[0964] Input: Collected digital data

[0965] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, extracts text information from image files using OCR technology (e.g., Tesseract OCR), and converts meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The resulting text data is then organized into a unified format.

[0966] Output: Preprocessed text data

[0967] Step 3: Collaboration with generative AI models

[0968] server

[0969] Input: Preprocessed text data

[0970] The server inputs the preprocessed data into a generative artificial intelligence model (e.g., GPT-3). This AI model uses NLP techniques to understand the context of the data and analyze it for relevant information and potential problems. The AI ​​model analyzes the data and generates specific advice, such as extracting trends and risk factors based on past meeting notes and technical documents.

[0971] Output: Generated advice

[0972] Step 4: Implementing the Emotion Engine

[0973] server

[0974] Input: Advice from the generative AI model, user emotional data (voice data, text data)

[0975] The server activates an emotion engine based on the advice received from the generative AI model. The emotion engine analyzes the user's voice and text data to understand their current emotional state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. The emotion data is used to adjust the importance of the advice and how it is displayed.

[0976] Output: Tailored advice based on sentiment data

[0977] Step 5: Advisory Output

[0978] server

[0979] Input: Tailored advice based on sentiment data

[0980] The server determines the format of notification to the agent based on the adjusted advice content. For example, if the user is feeling stressed, the advice will be brief and only important information will be highlighted.

[0981] Output: Adjusted advice notification

[0982] User

[0983] Input: Advice sent by the server

[0984] The user (person in charge) checks the advice sent from the server. For example, when implementing wireless equipment integration, they can plan countermeasures by referring to specific advice based on past bug information and problems that have occurred in other departments. Also, during disaster recovery, they can respond quickly based on the optimal recovery route suggested by the AI ​​model. Advice is provided based on the results of the emotion engine, reducing psychological burden.

[0985] Output: Specific measures and action plans

[0986] The above is the specific flow of the program processing of this system.

[0987] (Application example 2)

[0988] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0989] In traditional brick-and-mortar store operations, it is difficult to effectively utilize the large amounts of data obtained from POS systems, inventory management systems, customer feedback, etc., and advice for improving operations and measures based on employee emotions are not sufficiently implemented. In addition, busy work places a heavy psychological burden on employees, which can have a negative impact on the quality of customer service and sales effectiveness.

[0990] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for analyzing the user's emotions and adjusting the content and presentation method of the advice, and means for notifying the person in charge of the generated advice. This makes it possible to effectively utilize digital data to provide advice for improving operations, and further to optimize the content and display method of the advice by taking employee emotions into consideration.

[0991] "Each department" refers to a division or section within a company or organization that has a different role or function.

[0992] "Digital data" means data that can be stored, transmitted, or processed electronically, including text, audio, images, and video.

[0993] "Means of collection" refers to the methods and technologies used to collect the necessary digital data, such as APIs, file uploads, and sensors.

[0994] "Preprocessing" refers to the basic processing and conversion work done on collected data to make it easier to analyze, and includes things like text extraction and data cleaning.

[0995] "Text information" refers to character string information written in natural language, and takes the form of documents, notes, comments, etc.

[0996] A "generative artificial intelligence model" refers to a model that uses machine learning algorithms and neural networks to automatically generate useful information and advice from input data.

[0997] "Advice" means suggestions or advice on problems or issues, including points for improvement and specific measures.

[0998] "Means of notification" refers to the methods and technologies used to deliver generated advice and information to the responsible party, including email, push notifications, and message displays.

[0999] "User emotions" refers to the current psychological state and emotional reactions of users using the system, including stress, fatigue, satisfaction, etc.

[1000] "Means for analyzing emotions" refers to technologies and methods for detecting and analyzing a user's emotions, including voice analysis, facial expression analysis, and text analysis.

[1001] "Presentation" refers to the format or method in which information or advice is displayed to the user, including textual, graphical, and animation displays.

[1002] This invention relates to a system that aims to optimize the operation of a physical store. The system is composed of a server, a terminal, and a user, and is implemented as follows.

[1003] 1. Data Collection

[1004] The server collects digital data from physical store POS systems, inventory management systems, and customer feedback systems. This includes methods such as API-based data acquisition, regular monitoring, and file upload triggers. For example, cloud storage can be monitored and new data can be automatically downloaded when detected. On the terminal side, employees use a smartphone app to upload the necessary data to the server, which then transmits the data to the server in real time.

[1005] 2. Data Preprocessing

[1006] The server preprocesses the collected digital data and converts it into text information. Specifically, it uses OCR (optical character recognition) technology to extract text from document data, and transcribes audio data using speech recognition technology (Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format and prepared for input into a generative artificial intelligence model.

[1007] 3. Collaboration with generative artificial intelligence models

[1008] The server inputs the preprocessed data into a generative artificial intelligence model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential problems. The analysis results of the AI ​​model generate recommendations for operational improvement.

[1009] 4. Introducing the Emotion Engine

[1010] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's (employee's) emotions. The emotion engine analyzes voice data and feedback collected from the device to understand the user's current psychological state. Emotional data is used to adjust the importance and presentation method of the generated advice.

[1011] 5. Advisory Output

[1012] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format for notification to the device and notifies the user (employee). For example, if the user is feeling stressed, the advice content will be simplified, emphasizing only the most important information. The user can review the advice notified to them and use it to improve operations and customer service.

[1013] Specific examples

[1014] Examples of employee stress reduction measures

[1015] When employees are tired, a "quick feedback check" is sufficient. In this case, the prompt would be "Generate a quick improvement suggestion to present to employees when they are tired."

[1016] Example of inventory management timing advice output

[1017] If there is a sudden increase in best-selling items, the system displays a message to "recommend the next order timing." In this case, the prompt is "Please suggest the next product to order based on sales and the timing."

[1018] This system will enable the use of digital data in physical store operations and the provision of optimal advice that takes user emotions into consideration, which is expected to improve operational efficiency and customer satisfaction.

[1019] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1020] Step 1:

[1021] The server collects digital data from the physical store's POS system, inventory management system, and customer feedback system. Specifically, it periodically retrieves data using APIs and monitors cloud storage to detect newly added data. The input is digital data from each system (e.g., sales data, inventory data, customer feedback), and the output is storing that data on the server.

[1022] Step 2:

[1023] At the terminal, employees use a smartphone app to upload the required data to the server. Specifically, they select a file from the app interface and upload it simply by dragging and dropping. The input is the file selected by the employee, and the output is that file is sent to the server in real time.

[1024] Step 3:

[1025] The server preprocesses the collected digital data. Specifically, it uses OCR (Optical Character Recognition) technology to extract text from document data and AudioFile to transcribe audio data. The input is the collected raw data, and the output is text information converted into a unified format.

[1026] Step 4:

[1027] The server inputs the preprocessed text information into a generative artificial intelligence model. The model uses NLP techniques to analyze the context of the data and identify relevant information and potential problems. The input is the preprocessed text data, and the output is recommendations for operational improvement.

[1028] Step 5:

[1029] The device sends voice data and feedback to a server to recognize the user's (employee's) emotions. Voice recognition technology is used to extract emotions from the voice, and text data is analyzed to determine the emotion. The input is voice data and text data, and the output is emotional data.

[1030] Step 6:

[1031] The server adjusts the advice content based on the advice obtained from the generative AI model and the emotional data obtained from the emotion engine. Specifically, it changes the importance and display method of the advice depending on the user's emotional state. The input is the advice from the generative AI model and the emotional data from the emotion engine, and the output is the adjusted advice content.

[1032] Step 7:

[1033] The server notifies the device of the adjusted advice. A push notification is sent to the smartphone app, which the employee confirms. Specific operations include using an API or push notification service to notify the employee. The input is the adjusted advice, and the output is the advice displayed on the employee's smartphone.

[1034] Step 8:

[1035] The user (employee) uses the received advice to improve operations and customer service. Specifically, they review their business processes based on the provided advice and take necessary measures. The input is the received advice, and the output is improvements to the store's operations and customer service.

[1036] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1037] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1038] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1039] [Fourth embodiment]

[1040] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1041] 7, a 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.

[1042] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1043] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1044] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1045] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1046] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1047] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1048] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1049] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1050] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1051] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1052] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1053] This system automatically collects digital data (slides, spreadsheets, conference audio data, etc.) generated by each department in a company in the course of their daily work, analyzes and advises using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention can be embodied in the following specific forms.

[1054] Data collection

[1055] server

[1056] The server automatically collects digital data from each department's file sharing system, cloud storage, and meeting tools. This can be done by directly retrieving data using APIs, periodically monitoring folders, or using file upload triggers. For example, it can monitor cloud storage such as S3 buckets and Google Drive and collect files when new files are added.

[1057] Terminal

[1058] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires the data in real time.

[1059] Data Preprocessing

[1060] server

[1061] The server preprocesses the various digital data collected. It extracts text information from slides and spreadsheets, and uses OCR (optical character recognition) technology to obtain text from image files. It converts meeting audio data into text using speech-to-text software. This allows all digital data to be integrated into a text format. The preprocessed data is integrated into a single data format, which can then be input into the subsequent generative artificial intelligence model.

[1062] Collaboration with generative artificial intelligence models

[1063] server

[1064] The preprocessed text data is fed into a generative artificial intelligence (AI) model, using natural language processing (NLP) for example, to understand the context of the data and identify relevant information. The AI ​​model then automatically analyzes relevant problems and solutions and generates specific recommendations.

[1065] Advisory Output

[1066] server

[1067] The server analyzes the advice obtained from the generative AI model and determines how to notify the person in charge. Notification methods include email notifications, messages sent to internal chat tools, or real-time display on a dashboard. The notification content is formatted and provided to the person in charge in a specific, easy-to-understand format.

[1068] User Utilization

[1069] User

[1070] The user (person in charge) then proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and issues that have occurred in other departments, allowing them to revise the integration plan for the target station and reduce the risk of malfunctions. Furthermore, during disaster recovery, they can refer to the optimal recovery route proposed by the AI ​​model to carry out efficient recovery activities.

[1071] Specific examples

[1072] Example 1: Radio integration

[1073] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the advice, who then uses it to revise the integration plan.

[1074] Example 2: Disaster recovery

[1075] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the person in charge of the generated advice, who then uses it to carry out efficient recovery activities.

[1076] The above-described embodiments enable the present invention to be effectively carried out.

[1077] The processing flow will be explained below.

[1078] Step 1:

[1079] server

[1080] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses direct acquisition using APIs, regular monitoring of specified directories, and file upload triggers. For example, it monitors cloud storage (e.g., Google Drive, S3 buckets) and downloads new files when they are detected.

[1081] Step 2:

[1082] Terminal

[1083] On the terminal side, the staff manually uploads the required digital data to the server. Through a dedicated interface, the staff can select files and upload them by dragging and dropping them. This data is sent to the server in real time and saved.

[1084] Step 3:

[1085] server

[1086] The server preprocesses the collected data. Specifically, it extracts text information from slide decks and spreadsheets, extracts text from image files using OCR (optical character recognition), and converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[1087] Step 4:

[1088] server

[1089] The preprocessed text data is fed into a generative artificial intelligence (AI) model. An API is called to send the data to the AI ​​model, which then performs the analysis task. The AI ​​model uses natural language processing (NLP) techniques to understand the context of the data and identify relevant information and potential issues.

[1090] Step 5:

[1091] server

[1092] Receive the response from the AI ​​model, analyze the generated advice, format the advice in an easy-to-understand format, and decide how to notify the responsible person. For example, select whether to notify the person via email, internal chat tool, or dashboard based on importance and urgency.

[1093] Step 6:

[1094] server

[1095] The system notifies the responsible person with formatted advice. In the case of email notification, the advice is sent to the responsible person's email address. In the case of using an internal chat tool, a message is sent to promote real-time communication. In the case of dashboard display, the responsible person can check the advice through a web interface.

[1096] Step 7:

[1097] User

[1098] The person in charge will review the advice provided. For example, when implementing wireless equipment integration, they will receive advice based on past bug information and problems that have occurred in other departments, and plan specific countermeasures.

[1099] Step 8:

[1100] User

[1101] The person in charge will proceed with their work based on the advice received. By modifying the integration plan and taking preventative measures against problems, they aim to improve work efficiency and reduce risks. In the event of a disaster, they will be able to respond quickly by referring to the optimal recovery route.

[1102] The above are the specific processing steps in this system.

[1103] Example 1

[1104] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1105] There is a need for a system that can efficiently collect a wide variety of digital data generated by each department within a company, centrally manage and analyze it, and provide personnel with specific advice that will help improve business operations and carry out their work. However, conventional methods require time-consuming data collection and preprocessing, and analyzing the data to obtain useful advice requires a great deal of time and effort. In addition, when personnel manually collect data, it often lacks real-time capabilities.

[1106] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1107] In this invention, the server includes means for collecting digital data generated by each department, means for preprocessing the collected digital data and converting it into text information, and means for inputting the preprocessed data into a generative artificial intelligence model and generating advice. This makes it possible to efficiently collect and preprocess data generated within a company and quickly generate and provide useful advice from that data.

[1108] "Digital data" refers to information, records, or materials that are generated or stored electronically, including, for example, slides, spreadsheets, audio files, etc.

[1109] "Collection methods" refers to the methods, tools, or processes used to automatically or manually collect digital data generated from each department.

[1110] "Preprocessing means" refers to the process of converting collected digital data into a format that is easy to analyze, and specifically includes converting it into text information and removing noise.

[1111] "Generative artificial intelligence model" refers to an artificial intelligence algorithm or system used to generate useful information or advice from collected and pre-processed digital data.

[1112] "Advice generation means" refers to a method, tool, or process for inputting pre-processed data into a generative artificial intelligence model, analyzing it, and generating specific advice or suggestions.

[1113] "Notification means" refers to the methods, tools, or processes for effectively communicating generated advice and suggestions to relevant personnel, including, for example, email, chat tools, dashboards, etc.

[1114] This system automatically or manually collects digital data (e.g., slides, spreadsheets, audio files, etc.) generated by each department in a company in the course of their daily work, analyzes and provides advice using a generative artificial intelligence (AI) model, and notifies the person in charge. This invention is embodied in the following specific forms.

[1115] Data collection

[1116] server

[1117] The server collects digital data from each department's file sharing system or cloud storage. Specifically, the server uses an API to monitor designated folders in cloud storage (e.g., Amazon S3 or Google Drive) and automatically retrieves newly uploaded files. This collection process can be performed periodically or in real time using a file upload trigger.

[1118] Terminal

[1119] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator simply accesses the interface on a browser and drags and drops the files they want to collect, which sends the files to the server, allowing the server to acquire data in real time.

[1120] Data Preprocessing

[1121] server

[1122] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition) technology. For example, it uses an OCR tool such as Tesseract. It converts the meeting audio data into text using transcription software (for example, Google Cloud Speech-to-Text API). The preprocessed data is then converted into a unified text format.

[1123] Collaboration with generative artificial intelligence models

[1124] server

[1125] The preprocessed text data is fed into a generative artificial intelligence (AI) model, which uses natural language processing (NLP) techniques to analyze the context of the data and extract relevant information. For example, by using an AI model such as OpenAI's GPT-3, useful advice and suggestions can be generated from each piece of data.

[1126] Advisory Output

[1127] server

[1128] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification methods include email notification, sending a message to an internal chat tool (such as Slack), or displaying the information in real time on a dashboard. The generated content is formatted in HTML or other formats and provided to the person in charge.

[1129] User Utilization

[1130] User

[1131] The user (person in charge) carries out their work based on the advice provided. For example, when integrating radio equipment, they can revise the integration plan by referring to past bug information and advice on problems in other departments. During disaster recovery, the optimal recovery route proposed by the AI ​​model is executed.

[1132] Specific examples

[1133] Example 1: Radio integration

[1134] The server collects slides and meeting audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates advice on known bugs and solutions for specific radio models. The server notifies the person in charge of the generated advice, who then modifies the integration plan.

[1135] Example 2: Disaster recovery

[1136] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. The collected data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with related data to propose optimal recovery routes. The server notifies the responsible party of the generated advice, who then carries out efficient recovery activities.

[1137] Prompt Sentence Examples

[1138] Please analyze the slides and audio data for the radio integration and provide advice based on past bug information and issues. Please also include known bugs and workarounds for specific radio models.

[1139]

[1140] Analyze slide decks and meeting audio related to recent disasters to suggest optimal recovery routes and procedures. Generate recommendations taking into account relevant data.

[1141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1142] Step 1: Data Collection (Server)

[1143] The server automatically collects digital data from cloud storage (Amazon S3 or Google Drive) or file sharing systems. Specifically, the server uses an API to monitor specified folders and collects any newly added files. The collected files are saved in local storage. The input is digital data obtained via the API, and the output is data saved in the server's local storage. For example, when a new file is uploaded to a specified S3 bucket, it detects it and downloads it.

[1144] Step 2: Data collection (device)

[1145] The person in charge manually uploads digital data to the server via a terminal. The file is sent to the server by dragging and dropping it into the interface on the browser and clicking the upload button. The input is the file uploaded by the person in charge, and the output is the file saved on the server. Specifically, the person in charge uploads the slide materials.

[1146] Step 3: Data Preprocessing (Server)

[1147] The collected digital data is preprocessed. The server extracts text information from slides and spreadsheets, and uses OCR technology to obtain text from image files. Audio files are also converted to text using speech-to-text software. The input is the collected raw data, and the output is data in a unified text format. Specifically, a Python script is used to extract text from PDFs, Tesseract is used to perform character recognition from images, and the speech is converted to text using the Google Cloud Speech-to-Text API.

[1148] Step 4: Input data into the generative AI model (server)

[1149] The preprocessed text data is input into a generative artificial intelligence model. The server converts the text data into JSON format and sends it to the AI ​​model. The input is the preprocessed text data, and the output is advice or suggestions generated by the AI ​​model. Specifically, the preprocessed data is input into an AI model such as OpenAI's GPT-3 via an API, and the analysis results are received in text format.

[1150] Step 5: Advisory Output and Notification (Server)

[1151] The server analyzes the advice obtained from the generative AI model and determines the appropriate notification format. Notification formats include email, internal chat tools, and dashboards, and notifications are sent in the most effective way for each. The input is the results generated by the AI ​​model, and the output is advice formatted in the notification format. Specifically, the generated advice is formatted into HTML and sent via email via an SMTP server, or a chat notification is sent using the Slack API.

[1152] Step 6: Use the advice (user)

[1153] The user (person in charge) proceeds with the work based on the advice notified. They utilize the advice, such as referring to past bug information when integrating radio equipment, or implementing the optimal recovery route when planning disaster recovery. The input is the notified advice, and the output is work improvement measures and plans based on that advice. Specifically, they check the advice received by email and revise the integration plan. Or they can respond quickly by referring to recovery routes in the event of a disaster.

[1154] (Application example 1)

[1155] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1156] Modern autonomous vehicles generate large amounts of sensor data and operational data, but there is a lack of systems that can analyze this data in real time and provide appropriate operational advice. This can result in insufficient operational efficiency and safety for autonomous vehicles. There is also a growing need for a system that integrates a series of processes for data collection, preprocessing, analysis using AI models, and appropriate notification of advice. This will enable drivers and supervisors to receive advice in a timely manner, enabling safer and more efficient management of autonomous vehicle operations.

[1157] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1158] In this invention, the server includes: means for collecting digital data generated by each department; means for preprocessing the collected digital data and converting it into text information; means for inputting the preprocessed data into a generative artificial intelligence model and generating advice; means for notifying a responsible person of the generated advice; means for collecting sensor data and operation data generated by autonomous vehicles and uploading it to cloud storage; means for preprocessing the collected autonomous vehicle data, removing unnecessary parts, and converting it into text and numerical data; means for inputting the preprocessed autonomous vehicle data into a generative artificial intelligence model and generating advice based on operating conditions and traffic conditions; and means for notifying a driver or supervisor of the generated advice via a smartphone application. This makes it possible to efficiently manage autonomous vehicle data through a series of processes and provide appropriate advice to drivers and supervisors in real time.

[1159] "Digital data" means data generated by electronic devices, including slide decks, spreadsheets, audio data, and autonomous vehicle sensor and operational data.

[1160] "Preprocessing" refers to the process of removing unnecessary parts and converting collected digital data into text information and numerical data in order to convert it into an analyzable format.

[1161] A "generative artificial intelligence model" refers to an algorithm or model that uses natural language processing and machine learning techniques to analyze data and generate advice.

[1162] "Sensor data" refers to data obtained from various sensors (cameras, lidar, radar, etc.) installed in autonomous vehicles.

[1163] "Operational data" refers to data related to the operational status of an autonomous vehicle, such as its speed, location, and driving conditions.

[1164] "Cloud storage" refers to a service or system that stores digital data on remote servers via the Internet.

[1165] "Smartphone application" refers to a software program that runs on a smartphone and provides specific functionality.

[1166] "Operation status" refers to information about the current operating status of an autonomous vehicle and the surrounding traffic conditions.

[1167] "Notification" refers to a means of communicating the generated advice to the driver or supervisor, and includes push notification, screen display, voice guidance, etc.

[1168] This invention is a system that efficiently collects and analyzes digital data generated within a company or in an autonomous vehicle, and provides useful advice using a generative artificial intelligence model. Specific embodiments for implementing the invention are described below.

[1169] Data collection

[1170] server

[1171] The server collects digital data generated by each department within a company and from autonomous vehicles. Within a company, the server automatically collects digital data from file sharing systems, cloud storage, and conferencing tools. For example, it monitors cloud storage and collects new files when they are added. In the case of autonomous vehicles, the server collects sensor data and operational data and uploads the data to cloud storage.

[1172] Terminal

[1173] The terminal provides an interface for the operator to manually upload the necessary files to the server, which then acquires data in real time.Data collection from autonomous vehicles involves acquiring data directly from the vehicle's ECU (Engine Control Unit) and other sensors.

[1174] Data Preprocessing

[1175] server

[1176] The server preprocesses the collected digital data. For internal company data, text information is extracted from slides and spreadsheets, and text is also obtained from image files using OCR (optical character recognition) technology. Voice data is converted into text using speech transcription technology. This unifies all digital data into text format. For autonomous vehicle data, sensor data and operational data are preprocessed into an analyzable format, unnecessary parts are removed, and the data is converted into text and numerical data.

[1177] Collaboration with generative artificial intelligence models

[1178] server

[1179] The preprocessed text data is fed into a generative AI model to understand the context of the data and generate relevant advice. For example, it can identify problems and improvements from a company's internal business data and generate advice based on the operation status and traffic conditions of autonomous vehicles.

[1180] Advisory Output

[1181] server

[1182] The server analyzes the advice obtained from the generative AI model and determines the format in which to notify the person in charge. Notification methods include email notification, sending a message to an internal chat tool, displaying the advice in real time on a dashboard, and notifying the person in charge via a smartphone application. The generated advice is formatted and provided in a specific and easy-to-understand format.

[1183] User Utilization

[1184] User

[1185] Users (staff and drivers) can then carry out their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. Drivers of autonomous vehicles receive advice based on operational and traffic conditions to optimize operations. Operations control centers also receive data and advice in the same way, enabling them to manage operations more efficiently.

[1186] Prompt Sentence Examples

[1187] For example, a prompt to input to a generative artificial intelligence model might look like this:

[1188] "October 6, 2023, 12:34, Vehicle ID: vehicle_123, Speed: 35km / h, Location: Latitude 35.6895, Longitude 139.6917, Environmental Data: Includes camera images and lidar points."

[1189] By sending this prompt sentence to a generative artificial intelligence model, appropriate advice is generated.

[1190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1191] Step 1:

[1192] The server collects digital data generated by various departments within the company and from autonomous vehicles. Within the company, data is automatically acquired from file sharing systems, cloud storage, and conference tools. For example, new files are monitored and added using the cloud storage API. Meanwhile, in autonomous vehicles, sensor data and operational data are collected and uploaded to cloud storage. The input to this step is digital data from within the company and from autonomous vehicles, and the output is the collected data stored on the server.

[1193] Step 2:

[1194] The server preprocesses the collected digital data. For internal company data, this preprocessing involves using OCR technology to extract text information from slides and image files, and using speech-to-text technology to convert voice data into text. For autonomous vehicle data, unnecessary parts are removed and the data is converted into analyzable text and numerical data. The input for this step is the collected digital data, and the output is preprocessed text data.

[1195] Step 3:

[1196] The server inputs the preprocessed text data into a generative AI model. The generative AI model analyzes the context of the input data and generates appropriate advice. For example, it can identify problems and improvement measures from internal business data, or generate driving advice based on driving and traffic conditions from data on autonomous vehicles. The input for this step is the preprocessed text data, and the output is the generated advice.

[1197] Step 4:

[1198] The server analyzes the advice obtained from the generative artificial intelligence model and notifies the person in charge or the driver in an appropriate format. Specific notification methods include email notification, sending a message to an internal chat tool, displaying the information in real time on a dashboard, or notifying via a smartphone application. The input of this step is the generated advice, and the output is the information notified to the person in charge or the driver.

[1199] Step 5:

[1200] The user (person in charge or driver) proceeds with their work based on the advice they receive. For example, when implementing radio equipment integration, they can receive advice on past bug information and problems that have occurred in other departments. The driver of an autonomous vehicle receives advice based on operational and traffic conditions to optimize operation. The input to this step is the advice they receive, and the output is the result of the user taking action.

[1201] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1202] This system automatically collects and preprocesses digital data generated by each department within a company, analyzes and provides advice using a generative artificial intelligence (AI) model, and adjusts the importance and display method of the advice content by combining it with an emotion engine that recognizes the user's emotions. This invention is embodied in the following specific forms.

[1203] Data collection

[1204] server

[1205] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. This can be done by using APIs to obtain data, periodically monitoring designated directories, or triggering file uploads. For example, it can monitor cloud storage (e.g., Google Drive, S3 buckets) and automatically download new files when they are detected.

[1206] Terminal

[1207] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator can select the files from the interface and upload them easily with a drag-and-drop operation. This allows the data to be sent to the server in real time.

[1208] Data Preprocessing

[1209] server

[1210] The server preprocesses the collected digital data. Specifically, it extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. The preprocessed data is organized into a unified format and prepared for input into the generative AI model.

[1211] Collaboration with generative artificial intelligence models

[1212] server

[1213] The preprocessed text data is fed into a generative AI model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential issues. Recommendations are generated as a result of the analysis by the AI ​​model.

[1214] Introducing the Emotion Engine

[1215] server

[1216] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes emotions from the user's voice and text data to understand the user's current psychological state. The emotion data is used to dynamically adjust the importance and display method of the advice provided by the AI ​​model.

[1217] Advisory Output

[1218] server

[1219] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice content will be simplified and only the most important information will be emphasized.

[1220] User

[1221] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing the psychological burden on the person in charge and promoting effective decision-making.

[1222] Specific examples

[1223] Example 1: Radio integration

[1224] The server collects slides and conference audio data generated for radio integration. It preprocesses this data, extracts text information from the slides, and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which the server receives. At the same time, an emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the appropriate person.

[1225] Example 2: Disaster recovery

[1226] When a disaster occurs, the server automatically collects relevant slides, spreadsheets, and the latest conference audio data. This data is preprocessed and input into an AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model combines the relevant data to generate advice, which the server receives. An emotion engine analyzes the user's psychological state and adjusts the content and priorities of the advice. The server notifies the responsible party of the adjusted advice, and the user uses it to carry out efficient recovery activities.

[1227] The above-described embodiments enable the present invention to be effectively carried out.

[1228] The processing flow will be explained below.

[1229] Step 1:

[1230] server

[1231] The server collects digital data from each department's file sharing system, cloud storage, and conference tools. Specifically, it uses APIs to retrieve files, regularly monitors designated directories, and automatically downloads new files when they are found. This process includes monitoring cloud storage such as Google Drive and S3 buckets.

[1232] Step 2:

[1233] Terminal

[1234] The terminal provides an interface for the operator to manually upload the necessary files to the server. The operator selects the files using a dedicated web interface and uploads them by dragging and dropping them. The files are then saved to the server in real time.

[1235] Step 3:

[1236] server

[1237] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, and extracts text from image files using OCR (optical character recognition). It also converts meeting audio data into text using speech-to-text software. This ensures that all digital data is formatted into a unified text format.

[1238] Step 4:

[1239] server

[1240] The preprocessed text data is input into a generative artificial intelligence (AI) model. An API call is made to the AI ​​model to send the data. The AI ​​model uses NLP (natural language processing) techniques to analyze the context of the data and identify relevant information and potential issues. This processing results in the generation of appropriate advice.

[1241] Step 5:

[1242] server

[1243] After receiving the response from the AI ​​model, the generated advice is further processed by the emotion engine, which analyzes the user's voice and text data to recognize their emotional state. For example, if the user is feeling stressed, the content and presentation of the advice can be adjusted based on this information.

[1244] Step 6:

[1245] server

[1246] The adjusted advice is then sent to the person in charge. This is where the appropriate notification format is selected. For example, email notification, notification via an internal chat tool, or real-time display on the management dashboard may be selected. The advice is adjusted using an emotion engine, so the importance and display method are reflected according to the user's psychological state.

[1247] Step 7:

[1248] User

[1249] The user (person in charge) checks the notified advice. When implementing radio equipment integration, the user receives advice on past bugs and problems that have occurred in other departments, and plans specific countermeasures. In addition, when recovering from a disaster, the AI ​​model proposes optimal recovery routes, which can be used as a reference to quickly respond. At this time, the emotion engine provides advice in a way that reduces the user's psychological burden.

[1250] Step 8:

[1251] User

[1252] We proceed with the work based on the advice we receive. For example, we aim to improve operational efficiency and reduce risk by revising integration plans and taking preventative measures. In disaster recovery cases, we act quickly and efficiently based on the optimal recovery route.

[1253] The above steps ensure that the system is implemented effectively and efficiently.

[1254] Example 2

[1255] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1256] Many companies face challenges in efficiently collecting and preprocessing large amounts of digital data generated by various departments within a company and generating useful advice using generative artificial intelligence models. Furthermore, the generated advice must be optimally displayed for the staff member and adjusted to reduce the psychological burden. However, current systems lack the ability to recognize the user's emotions and dynamically adjust the advice content, and a system that solves this problem is needed.

[1257] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1258] In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for notifying a person in charge of the generated advice, and means for activating an emotion engine for recognizing the user's emotions and adjusting the advice content based on the emotion data. This makes it possible to efficiently collect and preprocess a wide variety of digital data within a company, generate advanced advice using a generative artificial intelligence model, and provide optimal advice that takes the user's emotions into consideration.

[1259] "Digital data" means information or data stored in electronic form.

[1260] "Preprocessing" refers to the process of converting and shaping digital data to make it easier to analyze and use.

[1261] "Text information" refers to information expressed in characters or symbols.

[1262] A "generative artificial intelligence model" is an algorithm or system that analyzes patterns and trends from given data and generates predictions and suggestions.

[1263] An "emotion engine" is an analysis system for recognizing a user's emotional state, and is a technology for grasping a user's psychological state from voice and text.

[1264] "Advice" is information intended to provide solutions or guidance to a particular situation or problem.

[1265] A "notification" is a method or action for informing a user of specific information.

[1266] This invention is a system that efficiently collects and preprocesses digital data generated by each department within a company and provides analysis and advice using a generative artificial intelligence (AI) model. Furthermore, it aims to reduce psychological burden by combining an emotion engine that recognizes the user's emotions and adjusting the importance and display method of advice. Below, we will explain how to specifically implement this invention.

[1267] Data collection

[1268] server

[1269] The server automatically collects digital data generated by each department within the company. The system obtains data using API access to file sharing systems and cloud storage (e.g., Google Drive, Amazon S3 buckets). It also uses periodic monitoring of designated directories and file upload triggers. For example, it monitors Google Drive and automatically downloads new files when they are uploaded.

[1270] Terminal

[1271] The terminal provides an interface for the person in charge to manually upload the necessary files to the server. Using this interface, users can upload files with a simple drag-and-drop operation, and the resulting data is sent to the server in real time.

[1272] Data Preprocessing

[1273] server

[1274] The server preprocesses the collected digital data. It uses OCR technology (e.g., Tesseract OCR) to extract text information from slides and spreadsheets. It also converts the meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format, ready to be fed into the generative AI model in the next step.

[1275] Collaboration with generative artificial intelligence models

[1276] server

[1277] The server inputs the preprocessed text data into a generative AI model. The AI ​​model uses NLP techniques to understand the context of the data and identify relevant information and potential problems. For example, it analyzes past meeting notes and technical documents to extract trends and risk factors. Specific advice is generated as a result of the analysis.

[1278] Introducing the Emotion Engine

[1279] server

[1280] The server receives advice from the AI ​​model and simultaneously activates an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and text data to understand their current psychological state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. This dynamically adjusts the importance of the advice and how it is displayed.

[1281] Advisory Output

[1282] server

[1283] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format in which to notify the person in charge. For example, if the user is feeling stressed, the advice will be brief and only the important information will be highlighted.

[1284] User

[1285] The user (person in charge) checks the advice provided. For example, when implementing wireless equipment integration, the user receives advice based on past bug information and problems that have occurred in other departments, and plans specific countermeasures. During disaster recovery, the user can respond quickly by referring to the optimal recovery route proposed by the AI ​​model. In this case, advice is provided based on the analysis results of the emotion engine, reducing psychological burden and promoting effective decision-making.

[1286] Specific examples

[1287] Example 1: Radio integration

[1288] The server collects and preprocesses the slides and meeting audio data generated for the radio integration. It extracts text information from the slides and transcribes the audio data. The preprocessed data is input into an AI model, which analyzes past bug information and issues in other departments. The AI ​​model generates appropriate advice, which is received by the server. At the same time, the emotion engine analyzes the user's emotional data, adjusts the content of the notification, and sends it to the person in charge. An example of a prompt is, "Please generate advice on future measures based on the bug information and meeting audio data for the past year regarding the radio integration."

[1289] Example 2: Disaster recovery

[1290] When a disaster occurs, the server automatically collects and pre-processes relevant documents and conference audio data. This data is pre-processed and input into a generative AI model to generate optimal recovery routes and procedures in the event of a disaster. The AI ​​model works with the relevant data to generate advice, which the server receives. The emotion engine analyzes the user's psychological state and adjusts the advice content and priorities. The adjusted advice content is notified to the person in charge, who then uses it to carry out efficient recovery activities. An example of a prompt is, "Please provide advice on the optimal recovery routes and procedures based on the conference audio data and related documents from the most recent disaster."

[1291] The above is a specific embodiment for carrying out the present invention.

[1292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1293] Step 1: Data collection

[1294] server

[1295] Input: Digital data generated by each department (e.g., electronic documents, spreadsheet data, audio data)

[1296] The server collects digital data using API access to each department's file sharing system and cloud storage. It automatically imports data when a file is added by using periodic monitoring of designated directories or file upload triggers. For example, it can detect new files from cloud storage and automatically download them to the server.

[1297] Output: Collected digital data (electronic file)

[1298] Terminal

[1299] Input: Necessary files held by the person in charge

[1300] The terminal provides an interface for the staff member to manually upload files, allowing them to select files and send them by dragging and dropping them.

[1301] Output: The file uploaded to the server.

[1302] Step 2: Data Preprocessing

[1303] server

[1304] Input: Collected digital data

[1305] The server preprocesses the collected digital data. It extracts text information from slides and spreadsheets, extracts text information from image files using OCR technology (e.g., Tesseract OCR), and converts meeting audio data into text using transcription software (e.g., Google Cloud Speech-to-Text). The resulting text data is then organized into a unified format.

[1306] Output: Preprocessed text data

[1307] Step 3: Collaboration with generative AI models

[1308] server

[1309] Input: Preprocessed text data

[1310] The server inputs the preprocessed data into a generative artificial intelligence model (e.g., GPT-3). This AI model uses NLP techniques to understand the context of the data and analyze it for relevant information and potential problems. The AI ​​model analyzes the data and generates specific advice, such as extracting trends and risk factors based on past meeting notes and technical documents.

[1311] Output: Generated advice

[1312] Step 4: Implementing the Emotion Engine

[1313] server

[1314] Input: Advice from the generative AI model, user emotional data (voice data, text data)

[1315] The server activates an emotion engine based on the advice received from the generative AI model. The emotion engine analyzes the user's voice and text data to understand their current emotional state. For example, it uses voice analysis software (e.g., IBM Watson Tone Analyzer) to detect stress or impatience from the way the user speaks. The emotion data is used to adjust the importance of the advice and how it is displayed.

[1316] Output: Tailored advice based on sentiment data

[1317] Step 5: Advisory Output

[1318] server

[1319] Input: Tailored advice based on sentiment data

[1320] The server determines the format of notification to the agent based on the adjusted advice content. For example, if the user is feeling stressed, the advice will be brief and only important information will be highlighted.

[1321] Output: Adjusted advice notification

[1322] User

[1323] Input: Advice sent by the server

[1324] The user (person in charge) checks the advice sent from the server. For example, when implementing wireless equipment integration, they can plan countermeasures by referring to specific advice based on past bug information and problems that have occurred in other departments. Also, during disaster recovery, they can respond quickly based on the optimal recovery route suggested by the AI ​​model. Advice is provided based on the results of the emotion engine, reducing psychological burden.

[1325] Output: Specific measures and action plans

[1326] The above is the specific flow of the program processing of this system.

[1327] (Application example 2)

[1328] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1329] In traditional brick-and-mortar store operations, it is difficult to effectively utilize the large amounts of data obtained from POS systems, inventory management systems, customer feedback, etc., and advice for improving operations and measures based on employee emotions are not sufficiently implemented. In addition, busy work places a heavy psychological burden on employees, which can have a negative impact on the quality of customer service and sales effectiveness.

[1330] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting digital data generated from each department, means for preprocessing the collected digital data and converting it into text information, means for inputting the preprocessed data into a generative artificial intelligence model and generating advice, means for analyzing the user's emotions and adjusting the content and presentation method of the advice, and means for notifying the person in charge of the generated advice. This makes it possible to effectively utilize digital data to provide advice for improving operations, and further to optimize the content and display method of the advice by taking employee emotions into consideration.

[1331] "Each department" refers to a division or section within a company or organization that has a different role or function.

[1332] "Digital data" means data that can be stored, transmitted, or processed electronically, including text, audio, images, and video.

[1333] "Means of collection" refers to the methods and technologies used to collect the necessary digital data, such as APIs, file uploads, and sensors.

[1334] "Preprocessing" refers to the basic processing and conversion work done on collected data to make it easier to analyze, and includes things like text extraction and data cleaning.

[1335] "Text information" refers to character string information written in natural language, and takes the form of documents, notes, comments, etc.

[1336] A "generative artificial intelligence model" refers to a model that uses machine learning algorithms and neural networks to automatically generate useful information and advice from input data.

[1337] "Advice" means suggestions or advice on problems or issues, including points for improvement and specific measures.

[1338] "Means of notification" refers to the methods and technologies used to deliver generated advice and information to the responsible party, including email, push notifications, and message displays.

[1339] "User emotions" refers to the current psychological state and emotional reactions of users using the system, including stress, fatigue, satisfaction, etc.

[1340] "Means for analyzing emotions" refers to technologies and methods for detecting and analyzing a user's emotions, including voice analysis, facial expression analysis, and text analysis.

[1341] "Presentation" refers to the format or method in which information or advice is displayed to the user, including textual, graphical, and animation displays.

[1342] This invention relates to a system that aims to optimize the operation of a physical store. The system is composed of a server, a terminal, and a user, and is implemented as follows.

[1343] 1. Data Collection

[1344] The server collects digital data from physical store POS systems, inventory management systems, and customer feedback systems. This includes methods such as API-based data acquisition, regular monitoring, and file upload triggers. For example, cloud storage can be monitored and new data can be automatically downloaded when detected. On the terminal side, employees use a smartphone app to upload the necessary data to the server, which then transmits the data to the server in real time.

[1345] 2. Data Preprocessing

[1346] The server preprocesses the collected digital data and converts it into text information. Specifically, it uses OCR (optical character recognition) technology to extract text from document data, and transcribes audio data using speech recognition technology (Google Cloud Speech-to-Text). The preprocessed data is organized into a unified format and prepared for input into a generative artificial intelligence model.

[1347] 3. Collaboration with generative artificial intelligence models

[1348] The server inputs the preprocessed data into a generative artificial intelligence model, which uses NLP (natural language processing) techniques to understand the context of the data and identify relevant information and potential problems. The analysis results of the AI ​​model generate recommendations for operational improvement.

[1349] 4. Introducing the Emotion Engine

[1350] The server receives advice from the AI ​​model and simultaneously activates an emotion engine that recognizes the user's (employee's) emotions. The emotion engine analyzes voice data and feedback collected from the device to understand the user's current psychological state. Emotional data is used to adjust the importance and presentation method of the generated advice.

[1351] 5. Advisory Output

[1352] The server adjusts the advice content based on the advice received from the AI ​​model and the emotion data obtained from the emotion engine. After adjusting the content, it decides the format for notification to the device and notifies the user (employee). For example, if the user is feeling stressed, the advice content will be simplified, emphasizing only the most important information. The user can review the advice notified to them and use it to improve operations and customer service.

[1353] Specific examples

[1354] Examples of employee stress reduction measures

[1355] When employees are tired, a "quick feedback check" is sufficient. In this case, the prompt would be "Generate a quick improvement suggestion to present to employees when they are tired."

[1356] Example of inventory management timing advice output

[1357] If there is a sudden increase in best-selling items, the system displays a message to "recommend the next order timing." In this case, the prompt is "Please suggest the next product to order based on sales and the timing."

[1358] This system will enable the use of digital data in physical store operations and the provision of optimal advice that takes user emotions into consideration, which is expected to improve operational efficiency and customer satisfaction.

[1359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1360] Step 1:

[1361] The server collects digital data from the physical store's POS system, inventory management system, and customer feedback system. Specifically, it periodically retrieves data using APIs and monitors cloud storage to detect newly added data. The input is digital data from each system (e.g., sales data, inventory data, customer feedback), and the output is storing that data on the server.

[1362] Step 2:

[1363] At the terminal, employees use a smartphone app to upload the required data to the server. Specifically, they select a file from the app interface and upload it simply by dragging and dropping. The input is the file selected by the employee, and the output is that file is sent to the server in real time.

[1364] Step 3:

[1365] The server preprocesses the collected digital data. Specifically, it uses OCR (Optical Character Recognition) technology to extract text from document data and AudioFile to transcribe audio data. The input is the collected raw data, and the output is text information converted into a unified format.

[1366] Step 4:

[1367] The server inputs the preprocessed text information into a generative artificial intelligence model. The model uses NLP techniques to analyze the context of the data and identify relevant information and potential problems. The input is the preprocessed text data, and the output is recommendations for operational improvement.

[1368] Step 5:

[1369] The device sends voice data and feedback to a server to recognize the user's (employee's) emotions. Voice recognition technology is used to extract emotions from the voice, and text data is analyzed to determine the emotion. The input is voice data and text data, and the output is emotional data.

[1370] Step 6:

[1371] The server adjusts the advice content based on the advice obtained from the generative AI model and the emotional data obtained from the emotion engine. Specifically, it changes the importance and display method of the advice depending on the user's emotional state. The input is the advice from the generative AI model and the emotional data from the emotion engine, and the output is the adjusted advice content.

[1372] Step 7:

[1373] The server notifies the device of the adjusted advice. A push notification is sent to the smartphone app, which the employee confirms. Specific operations include using an API or push notification service to notify the employee. The input is the adjusted advice, and the output is the advice displayed on the employee's smartphone.

[1374] Step 8:

[1375] The user (employee) uses the received advice to improve operations and customer service. Specifically, they review their business processes based on the provided advice and take necessary measures. The input is the received advice, and the output is improvements to the store's operations and customer service.

[1376] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1377] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1378] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1379] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1380] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1381] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1382] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1383] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1384] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1385] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1386] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1387] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1388] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1389] 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.

[1390] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1391] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1392] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1393] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1394] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1395] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1396] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1397] The following is further disclosed regarding the above embodiment.

[1398] (Claim 1)

[1399] A means of collecting digital data generated by each department, and

[1400] means for preprocessing the collected digital data and converting it into text information;

[1401] means for inputting the preprocessed data into a generative artificial intelligence model to generate advice;

[1402] means for notifying a person of the generated advice;

[1403] A system including:

[1404] (Claim 2)

[1405] 10. The system of claim 1, wherein the digital data includes slides, spreadsheets, and audio data.

[1406] (Claim 3)

[1407] 10. The system of claim 1, wherein the preprocessing means uses optical character recognition and speech-to-text techniques.

[1408] "Example 1"

[1409] (Claim 1)

[1410] A means of collecting digital data generated by each department, and

[1411] means for preprocessing the collected digital data and converting it into text information;

[1412] means for inputting the preprocessed data into a generative artificial intelligence model to generate advice;

[1413] means for notifying a person of the generated advice;

[1414] A means for personnel to manually upload data to the server through an interface;

[1415] means for analyzing the generated advice and determining a notification format;

[1416] A system including:

[1417] (Claim 2)

[1418] 10. The system of claim 1, wherein the digital data includes electronic documents, spreadsheet files, and audio files.

[1419] (Claim 3)

[1420] 10. The system of claim 1, wherein the preprocessing means uses optical character recognition and speech-to-text techniques.

[1421] "Application Example 1"

[1422] (Claim 1)

[1423] A means of collecting digital data generated by each department, and

[1424] means for preprocessing the collected digital data and converting it into text information;

[1425] means for inputting the preprocessed data into a generative artificial intelligence model to generate advice;

[1426] means for notifying a person of the generated advice;

[1427] a means for collecting sensor data and operational data generated by the autonomous vehicle and uploading the data to cloud storage;

[1428] a means for preprocessing the collected autonomous vehicle data, cleaning it, and converting it into text and numeric data;

[1429] means for inputting the preprocessed autonomous vehicle data into a generative artificial intelligence model to generate recommendations based on operational and traffic conditions;

[1430] a means for notifying the driver or supervisor of the generated advice via a smartphone application;

[1431] A system including:

[1432] (Claim 2)

[1433] 10. The system of claim 1, wherein the digital data includes slides, spreadsheets, audio data, and autonomous vehicle sensor and operational data.

[1434] (Claim 3)

[1435] 10. The system of claim 1, wherein the preprocessing means converts the collected autonomous vehicle data into text and numeric data using optical character recognition and speech-to-text techniques.

[1436] "Example 2: Combining Emotion Engines"

[1437] (Claim 1)

[1438] A means of collecting digital data generated by each department, and

[1439] means for preprocessing the collected digital data and converting it into text information;

[1440] means for inputting the preprocessed data into a generative artificial intelligence model to generate advice;

[1441] means for notifying a person of the generated advice;

[1442] means for activating an emotion engine for recognizing the user's emotion and adjusting advice content based on the emotion data;

[1443] A system including:

[1444] (Claim 2)

[1445] 10. The system of claim 1, wherein the digital data includes electronic documents, spreadsheet data, and audio data.

[1446] (Claim 3)

[1447] 10. The system of claim 1, wherein the preprocessing means uses optical character recognition and speech recognition techniques.

[1448] "Application example 2 when combining emotion engines"

[1449] (Claim 1)

[1450] A means of collecting digital data generated by each department, and

[1451] means for preprocessing the collected digital data and converting it into text information;

[1452] means for inputting the preprocessed data into a generative artificial intelligence model to generate advice;

[1453] A means for analyzing user emotions and adjusting the content and presentation of advice;

[1454] means for notifying a person of the generated advice;

[1455] A system including:

[1456] (Claim 2)

[1457] 10. The system of claim 1, wherein the digital data includes presentations, spreadsheets, and audio recordings.

[1458] (Claim 3)

[1459] 10. The system of claim 1, wherein the preprocessing means uses optical character recognition and speech recognition techniques. [Explanation of symbols]

[1460] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting digital data generated by each department, and means for preprocessing the collected digital data and converting it into text information; means for inputting the preprocessed data into a generative artificial intelligence model to generate advice; means for notifying a person of the generated advice; A system including:

2. 10. The system of claim 1, wherein the digital data includes slides, spreadsheets, and audio data.

3. The system of claim 1 , wherein the preprocessing means uses optical character recognition and speech-to-text techniques.

Images