system

Abstract

We provide the system. [Solution] A means for receiving time-series data acquired from a data collection device, A means for preprocessing received time-series data to generate an analyzable dataset, A means of generating analyzable datasets, inputting them into artificial intelligence models, and performing equipment operation optimization and failure prediction, A means for generating operational proposals based on the analysis results of the aforementioned artificial intelligence model, A means of notifying users of the generated operational proposals, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the operation of vehicles and industrial equipment, in order to achieve efficient management and cost reduction, it is required to grasp the state of equipment in real time and propose an optimal operation method. However, with conventional methods, it is difficult to effectively analyze a large amount of data, and there is a problem that the accuracy of failure prediction and operation optimization cannot be improved. For this reason, effective means for improving operation efficiency and preventive maintenance are required.

Means for Solving the Problems

[0005] This invention involves a server receiving time-series data acquired from a data collection device, preprocessing the data, and generating an analyzable dataset. Next, a generative artificial intelligence model is used with this dataset as input to optimize equipment operation and predict failures. This generative AI model generates operational suggestions based on the analysis results and a system is built to notify the user. Furthermore, the generative AI model continuously learns from newly acquired data to improve its analysis accuracy, and a means is provided to improve the model itself by storing user feedback in a database. This enables efficient equipment management and operational optimization.

[0006] A "data acquisition device" is a device used to acquire sensor information and operational status from vehicles and industrial equipment in real time.

[0007] "Time series data" refers to a collection of data acquired at regular time intervals, arranged in chronological order.

[0008] "Preprocessing" refers to the process of removing noise, correcting outliers, and so on, in order to convert data into an analyzable format.

[0009] An "analyzable dataset" is a collection of data that has been preprocessed and organized into a format that can be analyzed by generative artificial intelligence models, etc.

[0010] A "generative artificial intelligence model" is a model that uses machine learning and deep learning technologies to extract features from data and perform fault prediction and operational optimization.

[0011] "Operational suggestions" are recommendations generated by artificial intelligence models to improve the efficiency of equipment and systems and prevent failures.

[0012] "Feedback" refers to information used to improve the generated artificial intelligence model by reflecting the results of measures taken by users based on their suggestions.

[0013] "Analysis accuracy" is an indicator that represents the accuracy of the operational suggestions and predictions provided by generative artificial intelligence models. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] As an embodiment of the present invention, a system is described that efficiently collects and analyzes large amounts of data obtained from vehicles and industrial equipment, and provides optimal operational suggestions. This system mainly consists of terminals, servers, and users.

[0036] The terminals function as data collection devices installed in each vehicle and piece of equipment, collecting operational data in real time via multiple sensors. The collected data is then properly organized as time-series data and transmitted to a server via the network. The data collection devices monitor the equipment status at regular intervals and, as needed, collect information such as location, temperature, and vibration.

[0037] The server stores the received time-series data in a database and handles data preprocessing and analysis. During data preprocessing, noise is removed and outliers are corrected to generate an analyzable dataset, thereby improving data reliability. Next, the generated dataset is sent to an artificial intelligence model for analyzing equipment operating patterns and predicting failures. This model utilizes machine learning techniques to continuously improve its analysis accuracy by learning from new data.

[0038] Users receive operational suggestions based on analysis results provided by the server and use them to optimize operations and implement preventive maintenance. For example, this allows users to find driving methods that reduce fuel consumption while increasing vehicle uptime, or to plan maintenance in advance if an anomaly is detected. The results of the measures taken by the user are fed back to the server via the terminal, and this feedback information is used to improve the generated artificial intelligence model and enhance the analysis.

[0039] As a concrete example, consider the application of this system to a fleet of trucks operated by a logistics company. Each truck is equipped with a terminal, and various data such as engine operating time, coolant temperature, and vibration data are collected. The server analyzes this information and proposes specific driving plans and scheduled maintenance timings to optimize the trucks' fuel efficiency. In this way, logistics companies can reduce costs and improve operational efficiency. By using this system, operational reliability can be increased, and efficient management throughout the entire lifecycle of the equipment becomes possible.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The terminal collects data in real time from sensors attached to vehicles and industrial equipment. The terminal organizes the acquired data by sensor type and collection time, and then sends it to the server. The data includes information such as equipment temperature, vibration, location, and operating time.

[0043] Step 2:

[0044] The server collects data received from terminals via an API and stores it in a database. The server stores the data along with the time it was received and the sensor ID to maintain data integrity. The server also monitors for data loss and anomalies and performs initial error checks.

[0045] Step 3:

[0046] The server initiates preprocessing of the time-series data stored in the database. This preprocessing involves noise reduction and detection and correction of outliers to generate a dataset suitable for analysis. During this process, the server uses statistical methods to ensure reliable data formatting.

[0047] Step 4:

[0048] The server inputs pre-processed data into a generative artificial intelligence model. The generative AI model analyzes the operational patterns of the equipment from the collected data and performs analysis for anomaly detection and failure prediction. This model applies machine learning and deep learning algorithms to learn from the data and makes predictions based on the accumulated knowledge.

[0049] Step 5:

[0050] Based on the analysis results, the server generates optimal operational suggestions for the equipment. These suggestions include maintenance timing and specific operational improvement measures. The server displays this information in an easy-to-understand format on a dashboard and notifies the user. Alerts are also sent as needed.

[0051] Step 6:

[0052] Users receive suggestions from the server and use them to adjust operations and plan maintenance. Based on these suggestions, users review how they use their equipment, aiming to improve operational efficiency and reduce costs. Specifically, this includes implementing measures to improve fuel efficiency and conducting regular inspections.

[0053] Step 7:

[0054] Users report the results of the improvements and suggestions they have implemented as feedback. This feedback is sent back from the terminal to the server, which stores this information and uses it to further improve the generated artificial intelligence model. This improves the accuracy of subsequent analyses and enables more appropriate operational suggestions.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] The problem that this invention aims to solve is to efficiently collect and analyze large amounts of time-series data obtained from vehicles and industrial equipment, and to optimize operations and predict failures with high accuracy. Furthermore, it aims to improve operational efficiency and reliability by providing users with useful operational suggestions based on the obtained analysis results and continuously reflecting the feedback from their implementation into the system.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting and organizing time-series data from various sensors, means for transmitting the collected time-series data to the server via a network, and means for receiving the data and storing it in a database. This enables efficient processing of large amounts of data, improving analysis accuracy, optimizing operations, and enhancing availability.

[0060] "Time-series data" refers to data where data points are collected sequentially along a time axis, and each data point is associated with a specific time.

[0061] A "sensor" is a device that measures physical or environmental conditions and outputs the results as signals or data. This allows for the collection of information such as location, temperature, and vibration.

[0062] A "network" is a connected system for sending and receiving information, enabling data communication between terminals and servers.

[0063] A "server" is a computer system that provides data and services over a network, and has the functions of storing, processing, and analyzing received data.

[0064] A "database" is an electronic information storage system that systematically stores collected data, enabling efficient retrieval and management.

[0065] "Noise reduction" is a technique that improves data reliability by removing unnecessary information during the data processing process.

[0066] "Outlier correction" is the process of detecting, correcting, or removing data points that are considered anomalous in a dataset.

[0067] A "generative artificial intelligence model" is a program that uses machine learning techniques to analyze data and make specific patterns or predictions.

[0068] This system aims to optimize equipment operation by efficiently collecting and analyzing large amounts of time-series data acquired from vehicles and industrial equipment. Specifically, it consists of three main elements: terminals, servers, and users.

[0069] Terminal role

[0070] The terminals are installed in vehicles and industrial equipment and function as data collection devices. Specifically, they use GPS sensors, temperature sensors, acceleration sensors, etc., to collect operational data such as location information, temperature, and vibration in real time. This data is appropriately organized as time-series data and transmitted to a server via the network.

[0071] Server Role

[0072] The server receives time-series data transmitted from terminals and stores it in a database. The received data undergoes preprocessing, such as noise reduction and anomaly correction, and is converted into an analyzable format. This improves the reliability of the data. The preprocessed data is then input into a generative artificial intelligence model to analyze equipment operating patterns and predict failures. This generative AI model utilizes machine learning techniques and improves its analysis accuracy by continuously learning from new data.

[0073] User roles

[0074] Based on the analysis results provided by the server, users receive specific operational suggestions using prompts. For example, they might receive suggestions for driving plans to optimize vehicle fuel efficiency or schedules for regular maintenance. Users optimize their operations based on these suggestions and provide feedback to the server via their terminal. This feedback information is used to further train the generative artificial intelligence model.

[0075] Specific example

[0076] For example, when this system is applied to a fleet of trucks operated by a logistics company, a terminal is installed in each truck to collect data such as engine operating time, coolant temperature, and vibration. The server analyzes this information and proposes specific driving plans and maintenance timings to optimize fuel efficiency.

[0077] Example of a prompt

[0078] "Analyze diverse sensor data and propose a driving plan that optimizes the fuel efficiency of logistics vehicles."

[0079] In this way, users can improve operational efficiency and reliability.

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

[0081] Step 1:

[0082] The device collects data using various sensors. Specifically, it obtains location information from a GPS sensor, device temperature from a temperature sensor, and vibration from an accelerometer. This data is collected in real time and organized as time-series data. This organized data forms the basis for subsequent analysis.

[0083] Step 2:

[0084] The terminal sends organized time-series data to the server over the network. The network typically uses wired or wireless technology to ensure fast and secure data transfer. The server receives this data and logs the timing of its reception.

[0085] Step 3:

[0086] The server stores the received data in the database. During storage, a schema is used to structure the data, enabling quick queries and retrieval. This prepares the data for smooth subsequent processing.

[0087] Step 4:

[0088] The server retrieves data from the database and performs preprocessing to remove noise and correct for outliers. The input is raw data, and the output is a dataset with improved reliability and consistency. This process enhances data quality and improves accuracy in subsequent analysis.

[0089] Step 5:

[0090] The server inputs pre-processed data into a generating AI model. This model is based on machine learning techniques and detects operational patterns from the data to predict failures. Pre-processed data is used as input, and analysis results are generated as output.

[0091] Step 6:

[0092] The server generates operational suggestions using the analysis results obtained from the generated AI model. Using prompts, it creates specific operational methods and improvement suggestions for the user. This results in a more practical and actionable action plan.

[0093] Step 7:

[0094] Users receive operational suggestions from the server and implement operations based on those suggestions. They incorporate the suggestions into their on-site operations, observe the results, and evaluate them. This feedback becomes key data that will be used in subsequent model updates.

[0095] Step 8:

[0096] The device collects user feedback again and sends it to the server. The server stores the received feedback in a database and uses it as training data for the generated artificial intelligence model. This further improves the accuracy of the model's analysis and enables continuous system improvement.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] Modern factories are required to maximize the operational efficiency of machinery while simultaneously predicting breakdowns. However, conventional systems have not adequately achieved the analysis of vast amounts of data and improved prediction accuracy, leading to problems such as reduced machine utilization and delayed maintenance.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes a device for receiving time-series data acquired from a data acquisition device, a device for preprocessing the received time-series data to generate an analyzable data set, a device for inputting the analyzable data set into an artificial intelligence model to optimize equipment operation and predict failures, and a device for providing operation instructions and maintenance plans to optimize the operation of factory machinery. This makes it possible to maximize the operating rate of the machinery while enabling planned maintenance through proactive failure prediction.

[0102] A "data acquisition device" is a device that collects operational data in real time from machinery within a factory.

[0103] "Time-series data" refers to continuous data recorded at regular time intervals, which provides information about the state and operation of machinery.

[0104] "Preprocessing" is the process of removing noise from received raw data to generate a data set suitable for analysis.

[0105] An "analyzable data set" is a collection of data that has been prepared through preprocessing, making it possible to analyze it using artificial intelligence.

[0106] A "generative artificial intelligence model" is a model that uses machine learning techniques to predict the operating patterns and failures of equipment, and is a method of analysis using data.

[0107] "Operational proposals" refer to specific instructions and advice provided to users based on the analysis results of the generated artificial intelligence model, aimed at optimizing the operation of the equipment.

[0108] "Operation instructions" refer to information that provides specific instructions on how to operate equipment in order to optimize its operation.

[0109] A "maintenance plan" is a proposal for planning equipment maintenance schedules based on predicted failures.

[0110] To implement this invention, a data acquisition device is attached to a machine used in a factory, and machine operation data is collected in real time. A terminal organizes this data as time-series data and transmits it to a server via a network. The server removes noise from the received data and generates an analyzable data set. This makes it possible to understand the accurate state of machine operation.

[0111] The server inputs the generated data set into a generative artificial intelligence model to optimize equipment operation and predict failures. The generative artificial intelligence model continuously learns from new data, improving its analytical accuracy. This allows for detailed analysis of the operating patterns of the work machinery and the generation of efficient operating instructions.

[0112] Users receive operational suggestions based on analysis results provided by the server and use them to optimize machine operation. These suggestions include operating instructions to optimize the operation of the work equipment and maintenance plans aimed at preventative maintenance. This leads to improved machine uptime and accident prevention.

[0113] For example, by using a generative artificial intelligence model to make predictions based on vibration data from a robotic arm used in a factory, it is possible to detect minute errors in movement and recommend necessary adjustments. This makes it possible to carry out planned maintenance while maintaining product quality.

[0114] Example of a prompt:

[0115] "Detect abnormal values ​​based on the robot arm's motion data and output recommendations for necessary maintenance."

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The terminal collects operational data in real time from machinery within the factory. The data acquired through sensors includes temperature, vibration, and operating time, and this data is organized in a time-series format. The input is sensor data, and the output is organized time-series data.

[0119] Step 2:

[0120] The terminal sends organized time-series data to the server via the network. This process involves data transmission, and the server receives that data. The input is organized time-series data, and the output is the data arriving at the server.

[0121] Step 3:

[0122] The server denoises the received data and generates an analyzable data set. Specifically, it uses filtering techniques to remove outliers and unnecessary data, preparing the data for use. The input is the received time-series data, and the output is a denoised data set.

[0123] Step 4:

[0124] The server inputs the generated data set into an artificial intelligence model to analyze the equipment's operating patterns and predict failures. This process utilizes machine learning algorithms to continuously improve the model's accuracy. The input is a denoised data set, and the output includes operating patterns and failure prediction results.

[0125] Step 5:

[0126] The server generates operational suggestions based on the analysis results and notifies the user. These suggestions include optimal operating instructions and maintenance plans, providing the user with information for decision-making. The input is the analysis results, and the output is the generated operational suggestions.

[0127] Step 6:

[0128] Users receive and utilize notified operational suggestions to perform machine operation and maintenance activities. Specific actions include machine operation based on the operational suggestions and the implementation of planned maintenance. The input is the operational suggestions, and the output is feedback on the operations and maintenance activities performed.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] As an embodiment of the present invention, a system is described that provides efficient and effective operational suggestions while taking into account the user's emotions in the operation of vehicles and industrial equipment. The system consists of a terminal, a server, a user, and an emotion engine.

[0131] The terminal is responsible for sequentially acquiring operational data from multiple sensors attached to the equipment and transmitting it to the server. This includes sensor data such as equipment temperature, vibration, and operating time, which are organized as time-series data. The terminal also collects emotional data from the user's voice and facial expressions through the user interface and transmits it to the server as well.

[0132] The server stores received device data and user sentiment data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction to generate an analyzable dataset. These datasets are analyzed using a generative artificial intelligence model. The generative AI model optimizes device operation, predicts failures, and further incorporates the user's emotional state using an emotion engine to generate user-optimized operational suggestions.

[0133] The emotion engine analyzes the user's emotional data to identify the user's current emotional state. Based on this emotional state, it adjusts the operational suggestions derived from the generative artificial intelligence model. For example, if the user is stressed, the suggestions can be simplified for easier execution; if the user is relaxed, more detailed suggestions can be sent.

[0134] Users receive operational suggestions from the server and adjust equipment operation and schedules accordingly. These suggestions include maintenance needs, changes to operating patterns, and measures to improve energy efficiency. Users send feedback based on the results of their operations and their emotions through their terminals, and the server stores this feedback to further improve analysis accuracy and the accuracy of the emotion engine.

[0135] As a concrete example, consider a case where a manufacturing line supervisor uses the system. While operational status and error information are collected from manufacturing equipment, the supervisor's stress level (e.g., through voice analysis) is acquired as emotional data. The server integrates this information and provides emotionally sensitive and efficient equipment operation suggestions. Based on these suggestions, it becomes possible to maximize manufacturing quality and productivity while avoiding unnecessary human intervention.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The terminal collects operational data in real time from sensors installed in vehicles and industrial equipment. This includes temperature, vibration, and location information. It also collects user voice and facial expression data through microphones and cameras built into the user's device, acquiring emotional data to understand the user's emotional state.

[0139] Step 2:

[0140] The device transmits collected device data and emotional data to a server via the network. The data is organized as time-series data and timestamped to allow for detailed tracking of the device's operation.

[0141] Step 3:

[0142] The server stores the received data in a database and begins data preprocessing. This process involves detecting outliers, removing noise, and converting the data into a format suitable for analysis. The preprocessed data is then organized into datasets used for both equipment operation analysis and user sentiment analysis.

[0143] Step 4:

[0144] The server inputs the pre-processed dataset into a generative artificial intelligence model. The generative AI model uses machine learning algorithms to analyze the operating patterns of the equipment and perform failure prediction. It also uses an emotion engine to analyze user emotion data and incorporates the results into the analysis.

[0145] Step 5:

[0146] The server generates operational suggestions based on the analysis results. Based on the results of the emotion engine, it adjusts the suggestions to suit the user's emotional state. For example, if the user is feeling stressed, it prioritizes simpler and easier-to-implement suggestions.

[0147] Step 6:

[0148] The server notifies the user of the operational suggestions it has generated. The suggestions are displayed on the dashboard and, if necessary, are also sent via email or smartphone notification. Specific suggestions include maintenance requirements, operational improvement measures, and methods for improving energy efficiency.

[0149] Step 7:

[0150] Users adjust equipment operation and operational schedules based on suggestions from the server. They report the results of their improvements and feedback on their suggestions to the server by resending them through their terminal.

[0151] Step 8:

[0152] The server stores the received feedback in a database and uses it to further improve the accuracy of the generative artificial intelligence model and emotion engine. This continuous feedback loop improves the accuracy of operational suggestions and the user experience.

[0153] (Example 2)

[0154] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0155] Conventional machine operation management systems have difficulty taking user emotions into account when proposing operations, making it challenging to optimize operations efficiently or predict anomalies. Furthermore, there has been a lack of appropriate methods for improving the accuracy of data analysis.

[0156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0157] In this invention, the server includes means for receiving time-series information acquired from data collection means, means for preprocessing the received time-series information to generate an analyzable information set, and means for inputting the analyzable information set into an artificial intelligence means for optimizing the operation of the device and predicting anomalies. This enables the provision of operational suggestions that take into account the user's emotional state and continuous improvement of analysis accuracy.

[0158] A "data collection method" is a mechanism for collecting time-series information through sensors or interfaces attached to a device.

[0159] "Time-series information" refers to a set of data recorded at specific time intervals, where each data point is arranged chronologically.

[0160] "Preprocessing" is the process of removing noise and outliers from collected raw data and preparing it for analysis.

[0161] An "analyzable information set" is a dataset that has undergone preprocessing and been transformed into a format that can be analyzed by a machine.

[0162] "Generative artificial intelligence means" refers to models that use machine learning algorithms to analyze data and perform operational optimization and anomaly prediction.

[0163] "Optimizing equipment operation" is the process of determining the optimal settings and operating methods for equipment to function efficiently and effectively.

[0164] "Anomaly prediction" refers to the process of using equipment operating data to predict in advance the occurrence of abnormal situations such as failures or malfunctions.

[0165] "Emotional analysis means" refers to a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and extracts it as data.

[0166] An "operational proposal" is a specific suggestion or recommendation regarding the operation of the equipment and user actions, based on the collected data and its analysis results.

[0167] An "information storage system" is a mechanism for continuously accumulating and managing collected data and feedback.

[0168] The present invention provides suggestions that take user emotions into account in order to optimize the operation of the device efficiently and effectively. This system mainly comprises a terminal, a server, and an emotion engine.

[0169] The terminal collects time-series information in real time from various sensors connected to the device and transmits it to the server. Specifically, this includes information such as temperature, vibration, and operating time. In addition, the terminal uses a camera and microphone to capture the user's facial expressions and voice through the user interface and collects emotional data. This emotional data is also transmitted to the server.

[0170] The server has a database that centrally manages this data and performs preprocessing on the received time-series data, such as noise reduction and anomaly correction, to generate an analyzable information set. Using this information set, the generative artificial intelligence model executes a process to optimize operations and predict anomalies. For example, the generative AI model receives a prompt such as "Provide easy-to-follow operational suggestions when the user is feeling stressed" and generates appropriate suggestions.

[0171] The emotion engine analyzes the user's emotional data to identify their emotional state. Based on this analysis, the server dynamically adjusts operational suggestions to match the user's emotions and notifies the user of optimized information. In this way, it helps the user take the optimal action according to the situation.

[0172] As a concrete example, in a manufacturing environment, if users are experiencing stress, the system could lower the priority of less urgent maintenance tasks and suggest more necessary tasks with simplified procedures. In this way, the burden on users is reduced while enabling optimal equipment operation.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The terminal collects time-series information from various sensors connected to the device. Specifically, it acquires data from temperature sensors, vibration sensors, operating time meters, etc. This input data is transmitted to the server in real time. The output is the raw data transferred to the server.

[0176] Step 2:

[0177] The server stores the received time-series information in a database and performs noise reduction and outlier correction. This generates an analyzable data set. During this process, data integrity is checked and data processing such as smoothing outliers is performed. The output is an analyzable dataset.

[0178] Step 3:

[0179] The device uses a camera and microphone to capture the user's facial expressions and voice, collecting emotional data. This data is also sent to the server. The input is the captured audio and video data, and the output is the emotional data sent to the server.

[0180] Step 4:

[0181] The server analyzes emotional data and performs data calculations to identify the user's emotional state. It extracts emotional information as numerical data using an emotion engine. This output represents information about the user's emotional state.

[0182] Step 5:

[0183] The generative artificial intelligence model uses analyzable datasets and user emotional states to optimize device operation and predict anomalies. The input consists of analyzable information sets and emotional states, while the output is an initial proposal based on these.

[0184] Step 6:

[0185] The server dynamically adjusts initial suggestions based on the user's emotional state. For example, it generates simple, easy-to-follow suggestions for a stressed user and more detailed suggestions for a relaxed user. This output represents the adjusted operational suggestions.

[0186] Step 7:

[0187] The user receives optimized operational suggestions from the server and modifies the device operation and schedule based on them. The output of this step is the user's actions and their results.

[0188] Step 8:

[0189] Users send feedback on their actions and emotions to the server via their device. The server records this feedback in an information storage system and uses it for future data analysis and system improvements. The input is the user's feedback, and the output is the feedback data stored in the information storage system.

[0190] (Application Example 2)

[0191] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0192] In recent years, manufacturing and service industries have been required to improve worker productivity and efficiency while also considering workers' health and emotional states. However, conventional systems have struggled to provide operational suggestions that reflect workers' emotional states in real time, and have not adequately addressed the need to create an environment where individual workers can perform at their best. As a result, problems have arisen where workers' workloads increase and productivity declines.

[0193] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0194] In this invention, the server includes means for receiving time-series data acquired from a data acquisition device, means for preprocessing the received time-series data to generate an analyzable dataset, means for inputting the analyzable dataset into a generating artificial intelligence model to optimize equipment operation and predict failures, means for generating operational suggestions based on the analysis results of the generating artificial intelligence model, and means for analyzing the user's emotional state using an emotion engine and adjusting the operational suggestions based on that emotional state. This makes it possible to provide optimal operational suggestions in real time that are tailored to the emotional state of each individual worker.

[0195] A "data acquisition device" is a device used to acquire time-series data related to the operation of equipment.

[0196] "Time-series data" refers to data acquired over time, used to track various parameters of equipment.

[0197] "Preprocessing" refers to the process of removing noise and correcting outliers to transform data into a format suitable for data analysis.

[0198] An "analyzable dataset" is a collection of data that has been organized in a way that makes it applicable to data analysis tools and algorithms.

[0199] A "generative artificial intelligence model" is an algorithm or model used to optimize the operation of equipment and predict failures.

[0200] An "operational proposal" is a specific action plan for optimizing the operation of equipment.

[0201] An "emotion engine" is a software engine used to analyze and identify a user's emotional state.

[0202] A "user" is a person who adjusts the operation of the equipment based on the system's suggestions.

[0203] The system for implementing this invention consists of a terminal, a server, and an emotion engine. The terminal is placed in a work environment such as a factory and is responsible for sequentially acquiring operational data from multiple sensors attached to equipment and transmitting it to the server. The sensors collect data such as the temperature, vibration, and operating time of the equipment and organize this as time-series data. Furthermore, the terminal collects emotion data from the operator's voice and facial expressions and also transmits this to the server.

[0204] The server stores received equipment data and operator emotion data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction, and generates an analyzable dataset using text processing. These datasets are analyzed by a generative artificial intelligence model to optimize equipment operation and predict failures. Furthermore, an emotion engine is used to identify the operator's emotional state and generate operational suggestions optimized for the user.

[0205] For example, if the operator is stressed, the server can simplify the suggestions to make them easier to implement. Conversely, if the operator is relaxed, it can provide more detailed operational suggestions. Finally, the generated operational suggestions are communicated to the operator via the user interface. This allows the operator to optimize equipment operation and operational schedules based on the suggestions.

[0206] As a concrete example, in a factory setting, if the operator's fatigue level increases, the system can suggest break times based on operational recommendations or automatically adjust the machine's operating speed. This makes it possible to maintain productivity while protecting the operator's health.

[0207] An example of a prompt message might be: "Generate an optimal robot operation schedule to maximize the current emotional state and work efficiency. Suggest ways to reduce worker fatigue and improve productivity."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The terminal acquires operational data using multiple sensors. This includes equipment temperature, vibration, and operating time. The input is raw data obtained in real time from the sensors, but since it is difficult to analyze directly, it is first organized into time-series data. The output is time-series data in a format that can be sent to the server.

[0211] Step 2:

[0212] The terminal acquires the operator's voice and facial expressions using sensors and microphones, and transmits them to the server as emotion data. Audio and video data are used as input, and processing this data generates quantitatively representing emotions. An analyzable emotion dataset can be obtained as output.

[0213] Step 3:

[0214] The server receives operational and sentiment data transmitted from terminals and stores it in a database. The input consists of time-series data and sentiment data, which are then denoised and outlier corrected. The output is a clean dataset suitable for analysis.

[0215] Step 4:

[0216] The server generates an analyzable dataset, inputs it into an artificial intelligence model, and performs operational optimization and failure prediction for the equipment. The input is a cleaned dataset. Based on this, machine learning algorithms are used to generate operational optimization patterns and failure prediction data. The output is this analysis result data.

[0217] Step 5:

[0218] The server analyzes emotional states using analysis results and an emotion engine, and generates operational suggestions based on the results. Inputs are equipment operational analysis data and the operator's emotional state; these are combined to formulate optimal operational suggestions. The output generates operational suggestion data that is notified to the operator.

[0219] Step 6:

[0220] The user receives and executes operational suggestions generated by the server. The input is suggested data, which the user uses to adjust equipment operation and schedules. The output is a more efficient and emotionally responsive operational state.

[0221] Step 7:

[0222] Users send operational results and feedback to the server via their terminals. Inputs include data from newly executed operations and operator feedback. Outputs are improvement data to enhance the accuracy of the generated artificial intelligence model.

[0223] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0224] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0225] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0229] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0230] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0231] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0232] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0233] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0234] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0235] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0236] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0237] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0238] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0239] As an embodiment of the present invention, a system is described that efficiently collects and analyzes large amounts of data obtained from vehicles and industrial equipment, and provides optimal operational suggestions. This system mainly consists of terminals, servers, and users.

[0240] The terminals function as data collection devices installed in each vehicle and piece of equipment, collecting operational data in real time via multiple sensors. The collected data is then properly organized as time-series data and transmitted to a server via the network. The data collection devices monitor the equipment status at regular intervals and, as needed, collect information such as location, temperature, and vibration.

[0241] The server stores the received time-series data in a database and handles data preprocessing and analysis. During data preprocessing, noise is removed and outliers are corrected to generate an analyzable dataset, thereby improving data reliability. Next, the generated dataset is sent to an artificial intelligence model for analyzing equipment operating patterns and predicting failures. This model utilizes machine learning techniques to continuously improve its analysis accuracy by learning from new data.

[0242] Users receive operational suggestions based on analysis results provided by the server and use them to optimize operations and implement preventive maintenance. For example, this allows users to find driving methods that reduce fuel consumption while increasing vehicle uptime, or to plan maintenance in advance if an anomaly is detected. The results of the measures taken by the user are fed back to the server via the terminal, and this feedback information is used to improve the generated artificial intelligence model and enhance the analysis.

[0243] As a concrete example, consider the application of this system to a fleet of trucks operated by a logistics company. Each truck is equipped with a terminal, and various data such as engine operating time, coolant temperature, and vibration data are collected. The server analyzes this information and proposes specific driving plans and scheduled maintenance timings to optimize the trucks' fuel efficiency. In this way, logistics companies can reduce costs and improve operational efficiency. By using this system, operational reliability can be increased, and efficient management throughout the entire lifecycle of the equipment becomes possible.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The terminal collects data in real time from sensors attached to vehicles and industrial equipment. The terminal organizes the acquired data by sensor type and collection time, and then sends it to the server. The data includes information such as equipment temperature, vibration, location, and operating time.

[0247] Step 2:

[0248] The server collects data received from terminals via an API and stores it in a database. The server stores the data along with the time it was received and the sensor ID to maintain data integrity. The server also monitors for data loss and anomalies and performs initial error checks.

[0249] Step 3:

[0250] The server initiates preprocessing of the time-series data stored in the database. This preprocessing involves noise reduction and detection and correction of outliers to generate a dataset suitable for analysis. During this process, the server uses statistical methods to ensure reliable data formatting.

[0251] Step 4:

[0252] The server inputs pre-processed data into a generative artificial intelligence model. The generative AI model analyzes the operational patterns of the equipment from the collected data and performs analysis for anomaly detection and failure prediction. This model applies machine learning and deep learning algorithms to learn from the data and makes predictions based on the accumulated knowledge.

[0253] Step 5:

[0254] Based on the analysis results, the server generates optimal operational suggestions for the equipment. These suggestions include maintenance timing and specific operational improvement measures. The server displays this information in an easy-to-understand format on a dashboard and notifies the user. Alerts are also sent as needed.

[0255] Step 6:

[0256] Users receive suggestions from the server and use them to adjust operations and plan maintenance. Based on these suggestions, users review how they use their equipment, aiming to improve operational efficiency and reduce costs. Specifically, this includes implementing measures to improve fuel efficiency and conducting regular inspections.

[0257] Step 7:

[0258] Users report the results of the improvements and suggestions they have implemented as feedback. This feedback is sent back from the terminal to the server, which stores this information and uses it to further improve the generated artificial intelligence model. This improves the accuracy of subsequent analyses and enables more appropriate operational suggestions.

[0259] (Example 1)

[0260] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0261] The problem that this invention aims to solve is to efficiently collect and analyze large amounts of time-series data obtained from vehicles and industrial equipment, and to optimize operations and predict failures with high accuracy. Furthermore, it aims to improve operational efficiency and reliability by providing users with useful operational suggestions based on the obtained analysis results and continuously reflecting the feedback from their implementation into the system.

[0262] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0263] In this invention, the server includes means for collecting and organizing time-series data from various sensors, means for transmitting the collected time-series data to the server via a network, and means for receiving the data and storing it in a database. This enables efficient processing of large amounts of data, improving analysis accuracy, optimizing operations, and enhancing availability.

[0264] "Time-series data" refers to data where data points are collected sequentially along a time axis, and each data point is associated with a specific time.

[0265] A "sensor" is a device that measures physical or environmental conditions and outputs the results as signals or data. This allows for the collection of information such as location, temperature, and vibration.

[0266] A "network" is a connected system for sending and receiving information, enabling data communication between terminals and servers.

[0267] A "server" is a computer system that provides data and services over a network, and has the functions of storing, processing, and analyzing received data.

[0268] A "database" is an electronic information storage system that systematically stores collected data, enabling efficient retrieval and management.

[0269] "Noise reduction" is a technique that improves data reliability by removing unnecessary information during the data processing process.

[0270] "Outlier correction" is the process of detecting, correcting, or removing data points that are considered anomalous in a dataset.

[0271] A "generative artificial intelligence model" is a program that uses machine learning techniques to analyze data and make specific patterns or predictions.

[0272] This system aims to optimize equipment operation by efficiently collecting and analyzing large amounts of time-series data acquired from vehicles and industrial equipment. Specifically, it consists of three main elements: terminals, servers, and users.

[0273] Terminal role

[0274] The terminals are installed in vehicles and industrial equipment and function as data collection devices. Specifically, they use GPS sensors, temperature sensors, acceleration sensors, etc., to collect operational data such as location information, temperature, and vibration in real time. This data is appropriately organized as time-series data and transmitted to a server via the network.

[0275] Server Role

[0276] The server receives time-series data transmitted from terminals and stores it in a database. The received data undergoes preprocessing, such as noise reduction and anomaly correction, and is converted into an analyzable format. This improves the reliability of the data. The preprocessed data is then input into a generative artificial intelligence model to analyze equipment operating patterns and predict failures. This generative AI model utilizes machine learning techniques and improves its analysis accuracy by continuously learning from new data.

[0277] User roles

[0278] Based on the analysis results provided by the server, users receive specific operational suggestions using prompts. For example, they might receive suggestions for driving plans to optimize vehicle fuel efficiency or schedules for regular maintenance. Users optimize their operations based on these suggestions and provide feedback to the server via their terminal. This feedback information is used to further train the generative artificial intelligence model.

[0279] Specific example

[0280] For example, in the case of applying this system to a fleet of trucks operated by a logistics company, terminals are attached to each truck, and engine operation time, coolant temperature, vibration data, etc. are collected. The server analyzes this information and proposes specific driving plans and maintenance timings to optimize fuel consumption.

[0281] Example of a prompt sentence

[0282] "Please analyze various sensor data and propose a driving plan to optimize the fuel consumption of logistics vehicles."

[0283] In this way, the user can improve operational efficiency and reliability.

[0284] The flow of the specific process in Example 1 will be described using FIG. 11.

[0285] Step 1:

[0286] The terminal collects data using various sensors. Specifically, it obtains location information from a GPS sensor, the temperature of the device from a temperature sensor, and vibration from an acceleration sensor, and collects these data in real time and organizes them as time-series data. This organized data serves as the basis for subsequent analysis.

[0287] Step 2:

[0288] The terminal transmits the organized time-series data to the server via the network. The network usually uses wired or wireless communication technology to ensure fast and secure data transfer. The server receives this data and records the reception timing in a log.

[0289] Step 3:

[0290] The server stores the received data in the database. During storage, a schema is used to structure the data, enabling quick queries and retrieval. This prepares the data for smooth subsequent processing.

[0291] Step 4:

[0292] The server retrieves data from the database and performs preprocessing to remove noise and correct for outliers. The input is raw data, and the output is a dataset with improved reliability and consistency. This process enhances data quality and improves accuracy in subsequent analysis.

[0293] Step 5:

[0294] The server inputs pre-processed data into a generating AI model. This model is based on machine learning techniques and detects operational patterns from the data to predict failures. Pre-processed data is used as input, and analysis results are generated as output.

[0295] Step 6:

[0296] The server generates operational suggestions using the analysis results obtained from the generated AI model. Using prompts, it creates specific operational methods and improvement suggestions for the user. This results in a more practical and actionable action plan.

[0297] Step 7:

[0298] Users receive operational suggestions from the server and implement operations based on those suggestions. They incorporate the suggestions into their on-site operations, observe the results, and evaluate them. This feedback becomes key data that will be used in subsequent model updates.

[0299] Step 8:

[0300] The terminal collects the user's feedback again and sends it to the server. The server stores the received feedback in a database and uses it as learning data for generating an artificial intelligence model. As a result, the analysis accuracy of the model is further improved, enabling continuous system improvement.

[0301] (Application Example 1)

[0302] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0303] In modern factories, it is required to maximize the operation efficiency of working machines while predicting failures in advance. However, in conventional systems, the analysis of a huge amount of data and the improvement of prediction accuracy have not been sufficiently achieved, and problems such as a decrease in the operating rate of machines and a delay in maintenance have occurred.

[0304] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0305] In this invention, the server includes a device that receives time-series data acquired from a data collection device, a device that preprocesses the received time-series data to generate an analyzable data set, a device that inputs the analyzable data set into a generative artificial intelligence model to optimize the operation of equipment and predict failures, and a device that provides operation instructions and maintenance plans for optimizing the operation of working machines in a factory. As a result, it is possible to maximize the operating rate of working machines and perform planned maintenance through pre-failure prediction.

[0306] The "data collection device" is a device that collects operation data from working machines in a factory in real time.

[0307] The "time-series data" is continuous data recorded at regular time intervals and is information indicating the state and operation of a working machine.

[0308] "Preprocessing" is the process of removing noise from received raw data to generate a data set suitable for analysis.

[0309] An "analyzable data set" is a collection of data that has been prepared through preprocessing, making it possible to analyze it using artificial intelligence.

[0310] A "generative artificial intelligence model" is a model that uses machine learning techniques to predict the operating patterns and failures of equipment, and is a method of analysis using data.

[0311] "Operational proposals" refer to specific instructions and advice provided to users based on the analysis results of the generated artificial intelligence model, aimed at optimizing the operation of the equipment.

[0312] "Operation instructions" refer to information that provides specific instructions on how to operate equipment in order to optimize its operation.

[0313] A "maintenance plan" is a proposal for planning equipment maintenance schedules based on predicted failures.

[0314] To implement this invention, a data acquisition device is attached to a machine used in a factory, and machine operation data is collected in real time. A terminal organizes this data as time-series data and transmits it to a server via a network. The server removes noise from the received data and generates an analyzable data set. This makes it possible to understand the accurate state of machine operation.

[0315] The server inputs the generated data set into a generative artificial intelligence model to optimize equipment operation and predict failures. The generative artificial intelligence model continuously learns from new data, improving its analytical accuracy. This allows for detailed analysis of the operating patterns of the work machinery and the generation of efficient operating instructions.

[0316] Users receive operational suggestions based on analysis results provided by the server and use them to optimize machine operation. These suggestions include operating instructions to optimize the operation of the work equipment and maintenance plans aimed at preventative maintenance. This leads to improved machine uptime and accident prevention.

[0317] For example, by using a generative artificial intelligence model to make predictions based on vibration data from a robotic arm used in a factory, it is possible to detect minute errors in movement and recommend necessary adjustments. This makes it possible to carry out planned maintenance while maintaining product quality.

[0318] Example of a prompt:

[0319] "Detect abnormal values ​​based on the robot arm's motion data and output recommendations for necessary maintenance."

[0320] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0321] Step 1:

[0322] The terminal collects operational data in real time from machinery within the factory. The data acquired through sensors includes temperature, vibration, and operating time, and this data is organized in a time-series format. The input is sensor data, and the output is organized time-series data.

[0323] Step 2:

[0324] The terminal sends organized time-series data to the server via the network. This process involves data transmission, and the server receives that data. The input is organized time-series data, and the output is the data arriving at the server.

[0325] Step 3:

[0326] The server denoises the received data and generates an analyzable data set. Specifically, it uses filtering techniques to remove outliers and unnecessary data, preparing the data for use. The input is the received time-series data, and the output is a denoised data set.

[0327] Step 4:

[0328] The server inputs the generated data set into an artificial intelligence model to analyze the equipment's operating patterns and predict failures. This process utilizes machine learning algorithms to continuously improve the model's accuracy. The input is a denoised data set, and the output includes operating patterns and failure prediction results.

[0329] Step 5:

[0330] The server generates operational suggestions based on the analysis results and notifies the user. These suggestions include optimal operating instructions and maintenance plans, providing the user with information for decision-making. The input is the analysis results, and the output is the generated operational suggestions.

[0331] Step 6:

[0332] Users receive and utilize notified operational suggestions to perform machine operation and maintenance activities. Specific actions include machine operation based on the operational suggestions and the implementation of planned maintenance. The input is the operational suggestions, and the output is feedback on the operations and maintenance activities performed.

[0333] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0334] As an embodiment of the present invention, a system is described that provides efficient and effective operational suggestions while taking into account the user's emotions in the operation of vehicles and industrial equipment. The system consists of a terminal, a server, a user, and an emotion engine.

[0335] The terminal is responsible for sequentially acquiring operational data from multiple sensors attached to the equipment and transmitting it to the server. This includes sensor data such as equipment temperature, vibration, and operating time, which are organized as time-series data. The terminal also collects emotional data from the user's voice and facial expressions through the user interface and transmits it to the server as well.

[0336] The server stores received device data and user sentiment data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction to generate an analyzable dataset. These datasets are analyzed using a generative artificial intelligence model. The generative AI model optimizes device operation, predicts failures, and further incorporates the user's emotional state using an emotion engine to generate user-optimized operational suggestions.

[0337] The emotion engine analyzes the user's emotional data to identify the user's current emotional state. Based on this emotional state, it adjusts the operational suggestions derived from the generative artificial intelligence model. For example, if the user is stressed, the suggestions can be simplified for easier execution; if the user is relaxed, more detailed suggestions can be sent.

[0338] Users receive operational suggestions from the server and adjust equipment operation and schedules accordingly. These suggestions include maintenance needs, changes to operating patterns, and measures to improve energy efficiency. Users send feedback based on the results of their operations and their emotions through their terminals, and the server stores this feedback to further improve analysis accuracy and the accuracy of the emotion engine.

[0339] As a concrete example, consider a case where a manufacturing line supervisor uses the system. While operational status and error information are collected from manufacturing equipment, the supervisor's stress level (e.g., through voice analysis) is acquired as emotional data. The server integrates this information and provides emotionally sensitive and efficient equipment operation suggestions. Based on these suggestions, it becomes possible to maximize manufacturing quality and productivity while avoiding unnecessary human intervention.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The terminal collects operational data in real time from sensors installed in vehicles and industrial equipment. This includes temperature, vibration, and location information. It also collects user voice and facial expression data through microphones and cameras built into the user's device, acquiring emotional data to understand the user's emotional state.

[0343] Step 2:

[0344] The device transmits collected device data and emotional data to a server via the network. The data is organized as time-series data and timestamped to allow for detailed tracking of the device's operation.

[0345] Step 3:

[0346] The server stores the received data in a database and begins data preprocessing. This process involves detecting outliers, removing noise, and converting the data into a format suitable for analysis. The preprocessed data is then organized into datasets used for both equipment operation analysis and user sentiment analysis.

[0347] Step 4:

[0348] The server inputs the pre-processed dataset into a generative artificial intelligence model. The generative AI model uses machine learning algorithms to analyze the operating patterns of the equipment and perform failure prediction. It also uses an emotion engine to analyze user emotion data and incorporates the results into the analysis.

[0349] Step 5:

[0350] The server generates operational suggestions based on the analysis results. Based on the results of the emotion engine, it adjusts the suggestions to suit the user's emotional state. For example, if the user is feeling stressed, it prioritizes simpler and easier-to-implement suggestions.

[0351] Step 6:

[0352] The server notifies the user of the operational suggestions it has generated. The suggestions are displayed on the dashboard and, if necessary, are also sent via email or smartphone notification. Specific suggestions include maintenance requirements, operational improvement measures, and methods for improving energy efficiency.

[0353] Step 7:

[0354] Users adjust equipment operation and operational schedules based on suggestions from the server. They report the results of their improvements and feedback on their suggestions to the server by resending them through their terminal.

[0355] Step 8:

[0356] The server stores the received feedback in a database and uses it to further improve the accuracy of the generative artificial intelligence model and emotion engine. This continuous feedback loop improves the accuracy of operational suggestions and the user experience.

[0357] (Example 2)

[0358] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0359] Conventional machine operation management systems have difficulty taking user emotions into account when proposing operations, making it challenging to optimize operations efficiently or predict anomalies. Furthermore, there has been a lack of appropriate methods for improving the accuracy of data analysis.

[0360] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0361] In this invention, the server includes means for receiving time-series information acquired from data collection means, means for preprocessing the received time-series information to generate an analyzable information set, and means for inputting the analyzable information set into an artificial intelligence means for optimizing the operation of the device and predicting anomalies. This enables the provision of operational suggestions that take into account the user's emotional state and continuous improvement of analysis accuracy.

[0362] A "data collection method" is a mechanism for collecting time-series information through sensors or interfaces attached to a device.

[0363] "Time-series information" refers to a set of data recorded at specific time intervals, where each data point is arranged chronologically.

[0364] "Preprocessing" is the process of removing noise and outliers from collected raw data and preparing it for analysis.

[0365] An "analyzable information set" is a dataset that has undergone preprocessing and been transformed into a format that can be analyzed by a machine.

[0366] "Generative artificial intelligence means" refers to models that use machine learning algorithms to analyze data and perform operational optimization and anomaly prediction.

[0367] "Optimizing equipment operation" is the process of determining the optimal settings and operating methods for equipment to function efficiently and effectively.

[0368] "Anomaly prediction" refers to the process of using equipment operating data to predict in advance the occurrence of abnormal situations such as failures or malfunctions.

[0369] "Emotional analysis means" refers to a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and extracts it as data.

[0370] An "operational proposal" is a specific suggestion or recommendation regarding the operation of the equipment and user actions, based on the collected data and its analysis results.

[0371] An "information storage system" is a mechanism for continuously accumulating and managing collected data and feedback.

[0372] The present invention provides suggestions that take user emotions into account in order to optimize the operation of the device efficiently and effectively. This system mainly comprises a terminal, a server, and an emotion engine.

[0373] The terminal collects time-series information in real time from various sensors connected to the device and transmits it to the server. Specifically, this includes information such as temperature, vibration, and operating time. In addition, the terminal uses a camera and microphone to capture the user's facial expressions and voice through the user interface and collects emotional data. This emotional data is also transmitted to the server.

[0374] The server has a database that centrally manages this data and performs preprocessing on the received time-series data, such as noise reduction and anomaly correction, to generate an analyzable information set. Using this information set, the generative artificial intelligence model executes a process to optimize operations and predict anomalies. For example, the generative AI model receives a prompt such as "Provide easy-to-follow operational suggestions when the user is feeling stressed" and generates appropriate suggestions.

[0375] The emotion engine analyzes the user's emotional data to identify their emotional state. Based on this analysis, the server dynamically adjusts operational suggestions to match the user's emotions and notifies the user of optimized information. In this way, it helps the user take the optimal action according to the situation.

[0376] As a concrete example, in a manufacturing environment, if users are experiencing stress, the system could lower the priority of less urgent maintenance tasks and suggest more necessary tasks with simplified procedures. In this way, the burden on users is reduced while enabling optimal equipment operation.

[0377] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0378] Step 1:

[0379] The terminal collects time-series information from various sensors connected to the device. Specifically, it acquires data from temperature sensors, vibration sensors, operating time meters, etc. This input data is transmitted to the server in real time. The output is the raw data transferred to the server.

[0380] Step 2:

[0381] The server stores the received time-series information in a database and performs noise reduction and outlier correction. This generates an analyzable data set. During this process, data integrity is checked and data processing such as smoothing outliers is performed. The output is an analyzable dataset.

[0382] Step 3:

[0383] The device uses a camera and microphone to capture the user's facial expressions and voice, collecting emotional data. This data is also sent to the server. The input is the captured audio and video data, and the output is the emotional data sent to the server.

[0384] Step 4:

[0385] The server analyzes emotional data and performs data calculations to identify the user's emotional state. It extracts emotional information as numerical data using an emotion engine. This output represents information about the user's emotional state.

[0386] Step 5:

[0387] The generative artificial intelligence model uses analyzable datasets and user emotional states to optimize device operation and predict anomalies. The input consists of analyzable information sets and emotional states, while the output is an initial proposal based on these.

[0388] Step 6:

[0389] The server dynamically adjusts initial suggestions based on the user's emotional state. For example, it generates simple, easy-to-follow suggestions for a stressed user and more detailed suggestions for a relaxed user. This output represents the adjusted operational suggestions.

[0390] Step 7:

[0391] The user receives optimized operational suggestions from the server and modifies the device operation and schedule based on them. The output of this step is the user's actions and their results.

[0392] Step 8:

[0393] Users send feedback on their actions and emotions to the server via their device. The server records this feedback in an information storage system and uses it for future data analysis and system improvements. The input is the user's feedback, and the output is the feedback data stored in the information storage system.

[0394] (Application Example 2)

[0395] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0396] In recent years, manufacturing and service industries have been required to improve worker productivity and efficiency while also considering workers' health and emotional states. However, conventional systems have struggled to provide operational suggestions that reflect workers' emotional states in real time, and have not adequately addressed the need to create an environment where individual workers can perform at their best. As a result, problems have arisen where workers' workloads increase and productivity declines.

[0397] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0398] In this invention, the server includes means for receiving time-series data acquired from a data acquisition device, means for preprocessing the received time-series data to generate an analyzable dataset, means for inputting the analyzable dataset into a generating artificial intelligence model to optimize equipment operation and predict failures, means for generating operational suggestions based on the analysis results of the generating artificial intelligence model, and means for analyzing the user's emotional state using an emotion engine and adjusting the operational suggestions based on that emotional state. This makes it possible to provide optimal operational suggestions in real time that are tailored to the emotional state of each individual worker.

[0399] A "data acquisition device" is a device used to acquire time-series data related to the operation of equipment.

[0400] "Time-series data" refers to data acquired over time, used to track various parameters of equipment.

[0401] "Preprocessing" refers to the process of removing noise and correcting outliers to transform data into a format suitable for data analysis.

[0402] An "analyzable dataset" is a collection of data that has been organized in a way that makes it applicable to data analysis tools and algorithms.

[0403] A "generative artificial intelligence model" is an algorithm or model used to optimize the operation of equipment and predict failures.

[0404] An "operational proposal" is a specific action plan for optimizing the operation of equipment.

[0405] An "emotion engine" is a software engine used to analyze and identify a user's emotional state.

[0406] A "user" is a person who adjusts the operation of the equipment based on the system's suggestions.

[0407] The system for implementing this invention consists of a terminal, a server, and an emotion engine. The terminal is placed in a work environment such as a factory and is responsible for sequentially acquiring operational data from multiple sensors attached to equipment and transmitting it to the server. The sensors collect data such as the temperature, vibration, and operating time of the equipment and organize this as time-series data. Furthermore, the terminal collects emotion data from the operator's voice and facial expressions and also transmits this to the server.

[0408] The server stores received equipment data and operator emotion data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction, and generates an analyzable dataset using text processing. These datasets are analyzed by a generative artificial intelligence model to optimize equipment operation and predict failures. Furthermore, an emotion engine is used to identify the operator's emotional state and generate operational suggestions optimized for the user.

[0409] For example, if the operator is stressed, the server can simplify the suggestions to make them easier to implement. Conversely, if the operator is relaxed, it can provide more detailed operational suggestions. Finally, the generated operational suggestions are communicated to the operator via the user interface. This allows the operator to optimize equipment operation and operational schedules based on the suggestions.

[0410] As a concrete example, in a factory setting, if the operator's fatigue level increases, the system can suggest break times based on operational recommendations or automatically adjust the machine's operating speed. This makes it possible to maintain productivity while protecting the operator's health.

[0411] An example of a prompt message might be: "Generate an optimal robot operation schedule to maximize the current emotional state and work efficiency. Suggest ways to reduce worker fatigue and improve productivity."

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The terminal acquires operational data using multiple sensors. This includes equipment temperature, vibration, and operating time. The input is raw data obtained in real time from the sensors, but since it is difficult to analyze directly, it is first organized into time-series data. The output is time-series data in a format that can be sent to the server.

[0415] Step 2:

[0416] The terminal acquires the operator's voice and facial expressions using sensors and microphones, and transmits them to the server as emotion data. Audio and video data are used as input, and processing this data generates quantitatively representing emotions. An analyzable emotion dataset can be obtained as output.

[0417] Step 3:

[0418] The server receives operational and sentiment data transmitted from terminals and stores it in a database. The input consists of time-series data and sentiment data, which are then denoised and outlier corrected. The output is a clean dataset suitable for analysis.

[0419] Step 4:

[0420] The server generates an analyzable dataset, inputs it into an artificial intelligence model, and performs operational optimization and failure prediction for the equipment. The input is a cleaned dataset. Based on this, machine learning algorithms are used to generate operational optimization patterns and failure prediction data. The output is this analysis result data.

[0421] Step 5:

[0422] The server analyzes emotional states using analysis results and an emotion engine, and generates operational suggestions based on the results. Inputs are equipment operational analysis data and the operator's emotional state; these are combined to formulate optimal operational suggestions. The output generates operational suggestion data that is notified to the operator.

[0423] Step 6:

[0424] The user receives and executes operational suggestions generated by the server. The input is suggested data, which the user uses to adjust equipment operation and schedules. The output is a more efficient and emotionally responsive operational state.

[0425] Step 7:

[0426] Users send operational results and feedback to the server via their terminals. Inputs include data from newly executed operations and operator feedback. Outputs are improvement data to enhance the accuracy of the generated artificial intelligence model.

[0427] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0428] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0429] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0430] [Third Embodiment]

[0431] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0432] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0433] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0434] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0435] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0436] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0437] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0438] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0439] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0440] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0441] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0442] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0443] As an embodiment of the present invention, a system is described that efficiently collects and analyzes large amounts of data obtained from vehicles and industrial equipment, and provides optimal operational suggestions. This system mainly consists of terminals, servers, and users.

[0444] The terminals function as data collection devices installed in each vehicle and piece of equipment, collecting operational data in real time via multiple sensors. The collected data is then properly organized as time-series data and transmitted to a server via the network. The data collection devices monitor the equipment status at regular intervals and, as needed, collect information such as location, temperature, and vibration.

[0445] The server stores the received time-series data in a database and handles data preprocessing and analysis. During data preprocessing, noise is removed and outliers are corrected to generate an analyzable dataset, thereby improving data reliability. Next, the generated dataset is sent to an artificial intelligence model for analyzing equipment operating patterns and predicting failures. This model utilizes machine learning techniques to continuously improve its analysis accuracy by learning from new data.

[0446] Users receive operational suggestions based on analysis results provided by the server and use them to optimize operations and implement preventive maintenance. For example, this allows users to find driving methods that reduce fuel consumption while increasing vehicle uptime, or to plan maintenance in advance if an anomaly is detected. The results of the measures taken by the user are fed back to the server via the terminal, and this feedback information is used to improve the generated artificial intelligence model and enhance the analysis.

[0447] As a concrete example, consider the application of this system to a fleet of trucks operated by a logistics company. Each truck is equipped with a terminal, and various data such as engine operating time, coolant temperature, and vibration data are collected. The server analyzes this information and proposes specific driving plans and scheduled maintenance timings to optimize the trucks' fuel efficiency. In this way, logistics companies can reduce costs and improve operational efficiency. By using this system, operational reliability can be increased, and efficient management throughout the entire lifecycle of the equipment becomes possible.

[0448] The following describes the processing flow.

[0449] Step 1:

[0450] The terminal collects data in real time from sensors attached to vehicles and industrial equipment. The terminal organizes the acquired data by sensor type and collection time, and then sends it to the server. The data includes information such as equipment temperature, vibration, location, and operating time.

[0451] Step 2:

[0452] The server collects data received from terminals via an API and stores it in a database. The server stores the data along with the time it was received and the sensor ID to maintain data integrity. The server also monitors for data loss and anomalies and performs initial error checks.

[0453] Step 3:

[0454] The server initiates preprocessing of the time-series data stored in the database. This preprocessing involves noise reduction and detection and correction of outliers to generate a dataset suitable for analysis. During this process, the server uses statistical methods to ensure reliable data formatting.

[0455] Step 4:

[0456] The server inputs pre-processed data into a generative artificial intelligence model. The generative AI model analyzes the operational patterns of the equipment from the collected data and performs analysis for anomaly detection and failure prediction. This model applies machine learning and deep learning algorithms to learn from the data and makes predictions based on the accumulated knowledge.

[0457] Step 5:

[0458] Based on the analysis results, the server generates optimal operational suggestions for the equipment. These suggestions include maintenance timing and specific operational improvement measures. The server displays this information in an easy-to-understand format on a dashboard and notifies the user. Alerts are also sent as needed.

[0459] Step 6:

[0460] Users receive suggestions from the server and use them to adjust operations and plan maintenance. Based on these suggestions, users review how they use their equipment, aiming to improve operational efficiency and reduce costs. Specifically, this includes implementing measures to improve fuel efficiency and conducting regular inspections.

[0461] Step 7:

[0462] Users report the results of the improvements and suggestions they have implemented as feedback. This feedback is sent back from the terminal to the server, which stores this information and uses it to further improve the generated artificial intelligence model. This improves the accuracy of subsequent analyses and enables more appropriate operational suggestions.

[0463] (Example 1)

[0464] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0465] The problem that this invention aims to solve is to efficiently collect and analyze large amounts of time-series data obtained from vehicles and industrial equipment, and to optimize operations and predict failures with high accuracy. Furthermore, it aims to improve operational efficiency and reliability by providing users with useful operational suggestions based on the obtained analysis results and continuously reflecting the feedback from their implementation into the system.

[0466] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0467] In this invention, the server includes means for collecting and organizing time-series data from various sensors, means for transmitting the collected time-series data to the server via a network, and means for receiving the data and storing it in a database. This enables efficient processing of large amounts of data, improving analysis accuracy, optimizing operations, and enhancing availability.

[0468] "Time-series data" refers to data where data points are collected sequentially along a time axis, and each data point is associated with a specific time.

[0469] A "sensor" is a device that measures physical or environmental conditions and outputs the results as signals or data. This allows for the collection of information such as location, temperature, and vibration.

[0470] A "network" is a connected system for sending and receiving information, enabling data communication between terminals and servers.

[0471] A "server" is a computer system that provides data and services over a network, and has the functions of storing, processing, and analyzing received data.

[0472] A "database" is an electronic information storage system that systematically stores collected data, enabling efficient retrieval and management.

[0473] "Noise reduction" is a technique that improves data reliability by removing unnecessary information during the data processing process.

[0474] "Outlier correction" is the process of detecting, correcting, or removing data points that are considered anomalous in a dataset.

[0475] A "generative artificial intelligence model" is a program that uses machine learning techniques to analyze data and make specific patterns or predictions.

[0476] This system aims to optimize equipment operation by efficiently collecting and analyzing large amounts of time-series data acquired from vehicles and industrial equipment. Specifically, it consists of three main elements: terminals, servers, and users.

[0477] Terminal role

[0478] The terminals are installed in vehicles and industrial equipment and function as data collection devices. Specifically, they use GPS sensors, temperature sensors, acceleration sensors, etc., to collect operational data such as location information, temperature, and vibration in real time. This data is appropriately organized as time-series data and transmitted to a server via the network.

[0479] Server Role

[0480] The server receives time-series data transmitted from terminals and stores it in a database. The received data undergoes preprocessing, such as noise reduction and anomaly correction, and is converted into an analyzable format. This improves the reliability of the data. The preprocessed data is then input into a generative artificial intelligence model to analyze equipment operating patterns and predict failures. This generative AI model utilizes machine learning techniques and improves its analysis accuracy by continuously learning from new data.

[0481] User roles

[0482] Based on the analysis results provided by the server, users receive specific operational suggestions using prompts. For example, they might receive suggestions for driving plans to optimize vehicle fuel efficiency or schedules for regular maintenance. Users optimize their operations based on these suggestions and provide feedback to the server via their terminal. This feedback information is used to further train the generative artificial intelligence model.

[0483] Specific example

[0484] For example, when this system is applied to a fleet of trucks operated by a logistics company, a terminal is installed in each truck to collect data such as engine operating time, coolant temperature, and vibration. The server analyzes this information and proposes specific driving plans and maintenance timings to optimize fuel efficiency.

[0485] Example of a prompt

[0486] "Analyze diverse sensor data and propose a driving plan that optimizes the fuel efficiency of logistics vehicles."

[0487] In this way, users can improve operational efficiency and reliability.

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] The device collects data using various sensors. Specifically, it obtains location information from a GPS sensor, device temperature from a temperature sensor, and vibration from an accelerometer. This data is collected in real time and organized as time-series data. This organized data forms the basis for subsequent analysis.

[0491] Step 2:

[0492] The terminal sends organized time-series data to the server over the network. The network typically uses wired or wireless technology to ensure fast and secure data transfer. The server receives this data and logs the timing of its reception.

[0493] Step 3:

[0494] The server stores the received data in the database. During storage, a schema is used to structure the data, enabling quick queries and retrieval. This prepares the data for smooth subsequent processing.

[0495] Step 4:

[0496] The server retrieves data from the database and performs preprocessing to remove noise and correct for outliers. The input is raw data, and the output is a dataset with improved reliability and consistency. This process enhances data quality and improves accuracy in subsequent analysis.

[0497] Step 5:

[0498] The server inputs pre-processed data into a generating AI model. This model is based on machine learning techniques and detects operational patterns from the data to predict failures. Pre-processed data is used as input, and analysis results are generated as output.

[0499] Step 6:

[0500] The server generates operational suggestions using the analysis results obtained from the generated AI model. Using prompts, it creates specific operational methods and improvement suggestions for the user. This results in a more practical and actionable action plan.

[0501] Step 7:

[0502] Users receive operational suggestions from the server and implement operations based on those suggestions. They incorporate the suggestions into their on-site operations, observe the results, and evaluate them. This feedback becomes key data that will be used in subsequent model updates.

[0503] Step 8:

[0504] The device collects user feedback again and sends it to the server. The server stores the received feedback in a database and uses it as training data for the generated artificial intelligence model. This further improves the accuracy of the model's analysis and enables continuous system improvement.

[0505] (Application Example 1)

[0506] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0507] Modern factories are required to maximize the operational efficiency of machinery while simultaneously predicting breakdowns. However, conventional systems have not adequately achieved the analysis of vast amounts of data and improved prediction accuracy, leading to problems such as reduced machine utilization and delayed maintenance.

[0508] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0509] In this invention, the server includes a device for receiving time-series data acquired from a data acquisition device, a device for preprocessing the received time-series data to generate an analyzable data set, a device for inputting the analyzable data set into an artificial intelligence model to optimize equipment operation and predict failures, and a device for providing operation instructions and maintenance plans to optimize the operation of factory machinery. This makes it possible to maximize the operating rate of the machinery while enabling planned maintenance through proactive failure prediction.

[0510] A "data acquisition device" is a device that collects operational data in real time from machinery within a factory.

[0511] "Time-series data" refers to continuous data recorded at regular time intervals, which provides information about the state and operation of machinery.

[0512] "Preprocessing" is the process of removing noise from received raw data to generate a data set suitable for analysis.

[0513] An "analyzable data set" is a collection of data that has been prepared through preprocessing, making it possible to analyze it using artificial intelligence.

[0514] A "generative artificial intelligence model" is a model that uses machine learning techniques to predict the operating patterns and failures of equipment, and is a method of analysis using data.

[0515] "Operational proposals" refer to specific instructions and advice provided to users based on the analysis results of the generated artificial intelligence model, aimed at optimizing the operation of the equipment.

[0516] "Operation instructions" refer to information that provides specific instructions on how to operate equipment in order to optimize its operation.

[0517] A "maintenance plan" is a proposal for planning equipment maintenance schedules based on predicted failures.

[0518] To implement this invention, a data acquisition device is attached to a machine used in a factory, and machine operation data is collected in real time. A terminal organizes this data as time-series data and transmits it to a server via a network. The server removes noise from the received data and generates an analyzable data set. This makes it possible to understand the accurate state of machine operation.

[0519] The server inputs the generated data set into a generative artificial intelligence model to optimize equipment operation and predict failures. The generative artificial intelligence model continuously learns from new data, improving its analytical accuracy. This allows for detailed analysis of the operating patterns of the work machinery and the generation of efficient operating instructions.

[0520] Users receive operational suggestions based on analysis results provided by the server and use them to optimize machine operation. These suggestions include operating instructions to optimize the operation of the work equipment and maintenance plans aimed at preventative maintenance. This leads to improved machine uptime and accident prevention.

[0521] For example, by using a generative artificial intelligence model to make predictions based on vibration data from a robotic arm used in a factory, it is possible to detect minute errors in movement and recommend necessary adjustments. This makes it possible to carry out planned maintenance while maintaining product quality.

[0522] Example of a prompt:

[0523] "Detect abnormal values ​​based on the robot arm's motion data and output recommendations for necessary maintenance."

[0524] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0525] Step 1:

[0526] The terminal collects operational data in real time from machinery within the factory. The data acquired through sensors includes temperature, vibration, and operating time, and this data is organized in a time-series format. The input is sensor data, and the output is organized time-series data.

[0527] Step 2:

[0528] The terminal sends organized time-series data to the server via the network. This process involves data transmission, and the server receives that data. The input is organized time-series data, and the output is the data arriving at the server.

[0529] Step 3:

[0530] The server denoises the received data and generates an analyzable data set. Specifically, it uses filtering techniques to remove outliers and unnecessary data, preparing the data for use. The input is the received time-series data, and the output is a denoised data set.

[0531] Step 4:

[0532] The server inputs the generated data set into an artificial intelligence model to analyze the equipment's operating patterns and predict failures. This process utilizes machine learning algorithms to continuously improve the model's accuracy. The input is a denoised data set, and the output includes operating patterns and failure prediction results.

[0533] Step 5:

[0534] The server generates operational suggestions based on the analysis results and notifies the user. These suggestions include optimal operating instructions and maintenance plans, providing the user with information for decision-making. The input is the analysis results, and the output is the generated operational suggestions.

[0535] Step 6:

[0536] Users receive and utilize notified operational suggestions to perform machine operation and maintenance activities. Specific actions include machine operation based on the operational suggestions and the implementation of planned maintenance. The input is the operational suggestions, and the output is feedback on the operations and maintenance activities performed.

[0537] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0538] As an embodiment of the present invention, a system is described that provides efficient and effective operational suggestions while taking into account the user's emotions in the operation of vehicles and industrial equipment. The system consists of a terminal, a server, a user, and an emotion engine.

[0539] The terminal is responsible for sequentially acquiring operational data from multiple sensors attached to the equipment and transmitting it to the server. This includes sensor data such as equipment temperature, vibration, and operating time, which are organized as time-series data. The terminal also collects emotional data from the user's voice and facial expressions through the user interface and transmits it to the server as well.

[0540] The server stores received device data and user sentiment data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction to generate an analyzable dataset. These datasets are analyzed using a generative artificial intelligence model. The generative AI model optimizes device operation, predicts failures, and further incorporates the user's emotional state using an emotion engine to generate user-optimized operational suggestions.

[0541] The emotion engine analyzes the user's emotional data to identify the user's current emotional state. Based on this emotional state, it adjusts the operational suggestions derived from the generative artificial intelligence model. For example, if the user is stressed, the suggestions can be simplified for easier execution; if the user is relaxed, more detailed suggestions can be sent.

[0542] Users receive operational suggestions from the server and adjust equipment operation and schedules accordingly. These suggestions include maintenance needs, changes to operating patterns, and measures to improve energy efficiency. Users send feedback based on the results of their operations and their emotions through their terminals, and the server stores this feedback to further improve analysis accuracy and the accuracy of the emotion engine.

[0543] As a concrete example, consider a case where a manufacturing line supervisor uses the system. While operational status and error information are collected from manufacturing equipment, the supervisor's stress level (e.g., through voice analysis) is acquired as emotional data. The server integrates this information and provides emotionally sensitive and efficient equipment operation suggestions. Based on these suggestions, it becomes possible to maximize manufacturing quality and productivity while avoiding unnecessary human intervention.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The terminal collects operational data in real time from sensors installed in vehicles and industrial equipment. This includes temperature, vibration, and location information. It also collects user voice and facial expression data through microphones and cameras built into the user's device, acquiring emotional data to understand the user's emotional state.

[0547] Step 2:

[0548] The device transmits collected device data and emotional data to a server via the network. The data is organized as time-series data and timestamped to allow for detailed tracking of the device's operation.

[0549] Step 3:

[0550] The server stores the received data in a database and begins data preprocessing. This process involves detecting outliers, removing noise, and converting the data into a format suitable for analysis. The preprocessed data is then organized into datasets used for both equipment operation analysis and user sentiment analysis.

[0551] Step 4:

[0552] The server inputs the pre-processed dataset into a generative artificial intelligence model. The generative AI model uses machine learning algorithms to analyze the operating patterns of the equipment and perform failure prediction. It also uses an emotion engine to analyze user emotion data and incorporates the results into the analysis.

[0553] Step 5:

[0554] The server generates operational suggestions based on the analysis results. Based on the results of the emotion engine, it adjusts the suggestions to suit the user's emotional state. For example, if the user is feeling stressed, it prioritizes simpler and easier-to-implement suggestions.

[0555] Step 6:

[0556] The server notifies the user of the operational suggestions it has generated. The suggestions are displayed on the dashboard and, if necessary, are also sent via email or smartphone notification. Specific suggestions include maintenance requirements, operational improvement measures, and methods for improving energy efficiency.

[0557] Step 7:

[0558] Users adjust equipment operation and operational schedules based on suggestions from the server. They report the results of their improvements and feedback on their suggestions to the server by resending them through their terminal.

[0559] Step 8:

[0560] The server stores the received feedback in a database and uses it to further improve the accuracy of the generative artificial intelligence model and emotion engine. This continuous feedback loop improves the accuracy of operational suggestions and the user experience.

[0561] (Example 2)

[0562] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0563] Conventional machine operation management systems have difficulty taking user emotions into account when proposing operations, making it challenging to optimize operations efficiently or predict anomalies. Furthermore, there has been a lack of appropriate methods for improving the accuracy of data analysis.

[0564] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0565] In this invention, the server includes means for receiving time-series information acquired from data collection means, means for preprocessing the received time-series information to generate an analyzable information set, and means for inputting the analyzable information set into an artificial intelligence means for optimizing the operation of the device and predicting anomalies. This enables the provision of operational suggestions that take into account the user's emotional state and continuous improvement of analysis accuracy.

[0566] A "data collection method" is a mechanism for collecting time-series information through sensors or interfaces attached to a device.

[0567] "Time-series information" refers to a set of data recorded at specific time intervals, where each data point is arranged chronologically.

[0568] "Preprocessing" is the process of removing noise and outliers from collected raw data and preparing it for analysis.

[0569] An "analyzable information set" is a dataset that has undergone preprocessing and been transformed into a format that can be analyzed by a machine.

[0570] "Generative artificial intelligence means" refers to models that use machine learning algorithms to analyze data and perform operational optimization and anomaly prediction.

[0571] "Optimizing equipment operation" is the process of determining the optimal settings and operating methods for equipment to function efficiently and effectively.

[0572] "Anomaly prediction" refers to the process of using equipment operating data to predict in advance the occurrence of abnormal situations such as failures or malfunctions.

[0573] "Emotional analysis means" refers to a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and extracts it as data.

[0574] An "operational proposal" is a specific suggestion or recommendation regarding the operation of the equipment and user actions, based on the collected data and its analysis results.

[0575] An "information storage system" is a mechanism for continuously accumulating and managing collected data and feedback.

[0576] The present invention provides suggestions that take user emotions into account in order to optimize the operation of the device efficiently and effectively. This system mainly comprises a terminal, a server, and an emotion engine.

[0577] The terminal collects time-series information in real time from various sensors connected to the device and transmits it to the server. Specifically, this includes information such as temperature, vibration, and operating time. In addition, the terminal uses a camera and microphone to capture the user's facial expressions and voice through the user interface and collects emotional data. This emotional data is also transmitted to the server.

[0578] The server has a database that centrally manages this data and performs preprocessing on the received time-series data, such as noise reduction and anomaly correction, to generate an analyzable information set. Using this information set, the generative artificial intelligence model executes a process to optimize operations and predict anomalies. For example, the generative AI model receives a prompt such as "Provide easy-to-follow operational suggestions when the user is feeling stressed" and generates appropriate suggestions.

[0579] The emotion engine analyzes the user's emotional data to identify their emotional state. Based on this analysis, the server dynamically adjusts operational suggestions to match the user's emotions and notifies the user of optimized information. In this way, it helps the user take the optimal action according to the situation.

[0580] As a concrete example, in a manufacturing environment, if users are experiencing stress, the system could lower the priority of less urgent maintenance tasks and suggest more necessary tasks with simplified procedures. In this way, the burden on users is reduced while enabling optimal equipment operation.

[0581] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0582] Step 1:

[0583] The terminal collects time-series information from various sensors connected to the device. Specifically, it acquires data from temperature sensors, vibration sensors, operating time meters, etc. This input data is transmitted to the server in real time. The output is the raw data transferred to the server.

[0584] Step 2:

[0585] The server stores the received time-series information in a database and performs noise reduction and outlier correction. This generates an analyzable data set. During this process, data integrity is checked and data processing such as smoothing outliers is performed. The output is an analyzable dataset.

[0586] Step 3:

[0587] The device uses a camera and microphone to capture the user's facial expressions and voice, collecting emotional data. This data is also sent to the server. The input is the captured audio and video data, and the output is the emotional data sent to the server.

[0588] Step 4:

[0589] The server analyzes emotional data and performs data calculations to identify the user's emotional state. It extracts emotional information as numerical data using an emotion engine. This output represents information about the user's emotional state.

[0590] Step 5:

[0591] The generative artificial intelligence model uses analyzable datasets and user emotional states to optimize device operation and predict anomalies. The input consists of analyzable information sets and emotional states, while the output is an initial proposal based on these.

[0592] Step 6:

[0593] The server dynamically adjusts initial suggestions based on the user's emotional state. For example, it generates simple, easy-to-follow suggestions for a stressed user and more detailed suggestions for a relaxed user. This output represents the adjusted operational suggestions.

[0594] Step 7:

[0595] The user receives optimized operational suggestions from the server and modifies the device operation and schedule based on them. The output of this step is the user's actions and their results.

[0596] Step 8:

[0597] Users send feedback on their actions and emotions to the server via their device. The server records this feedback in an information storage system and uses it for future data analysis and system improvements. The input is the user's feedback, and the output is the feedback data stored in the information storage system.

[0598] (Application Example 2)

[0599] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0600] In recent years, manufacturing and service industries have been required to improve worker productivity and efficiency while also considering workers' health and emotional states. However, conventional systems have struggled to provide operational suggestions that reflect workers' emotional states in real time, and have not adequately addressed the need to create an environment where individual workers can perform at their best. As a result, problems have arisen where workers' workloads increase and productivity declines.

[0601] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0602] In this invention, the server includes means for receiving time-series data acquired from a data acquisition device, means for preprocessing the received time-series data to generate an analyzable dataset, means for inputting the analyzable dataset into a generating artificial intelligence model to optimize equipment operation and predict failures, means for generating operational suggestions based on the analysis results of the generating artificial intelligence model, and means for analyzing the user's emotional state using an emotion engine and adjusting the operational suggestions based on that emotional state. This makes it possible to provide optimal operational suggestions in real time that are tailored to the emotional state of each individual worker.

[0603] A "data acquisition device" is a device used to acquire time-series data related to the operation of equipment.

[0604] "Time-series data" refers to data acquired over time, used to track various parameters of equipment.

[0605] "Preprocessing" refers to the process of removing noise and correcting outliers to transform data into a format suitable for data analysis.

[0606] An "analyzable dataset" is a collection of data that has been organized in a way that makes it applicable to data analysis tools and algorithms.

[0607] A "generative artificial intelligence model" is an algorithm or model used to optimize the operation of equipment and predict failures.

[0608] An "operational proposal" is a specific action plan for optimizing the operation of equipment.

[0609] An "emotion engine" is a software engine used to analyze and identify a user's emotional state.

[0610] A "user" is a person who adjusts the operation of the equipment based on the system's suggestions.

[0611] The system for implementing this invention consists of a terminal, a server, and an emotion engine. The terminal is placed in a work environment such as a factory and is responsible for sequentially acquiring operational data from multiple sensors attached to equipment and transmitting it to the server. The sensors collect data such as the temperature, vibration, and operating time of the equipment and organize this as time-series data. Furthermore, the terminal collects emotion data from the operator's voice and facial expressions and also transmits this to the server.

[0612] The server stores received equipment data and operator emotion data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction, and generates an analyzable dataset using text processing. These datasets are analyzed by a generative artificial intelligence model to optimize equipment operation and predict failures. Furthermore, an emotion engine is used to identify the operator's emotional state and generate operational suggestions optimized for the user.

[0613] For example, if the operator is stressed, the server can simplify the suggestions to make them easier to implement. Conversely, if the operator is relaxed, it can provide more detailed operational suggestions. Finally, the generated operational suggestions are communicated to the operator via the user interface. This allows the operator to optimize equipment operation and operational schedules based on the suggestions.

[0614] As a concrete example, in a factory setting, if the operator's fatigue level increases, the system can suggest break times based on operational recommendations or automatically adjust the machine's operating speed. This makes it possible to maintain productivity while protecting the operator's health.

[0615] An example of a prompt message might be: "Generate an optimal robot operation schedule to maximize the current emotional state and work efficiency. Suggest ways to reduce worker fatigue and improve productivity."

[0616] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0617] Step 1:

[0618] The terminal acquires operational data using multiple sensors. This includes equipment temperature, vibration, and operating time. The input is raw data obtained in real time from the sensors, but since it is difficult to analyze directly, it is first organized into time-series data. The output is time-series data in a format that can be sent to the server.

[0619] Step 2:

[0620] The terminal acquires the operator's voice and facial expressions using sensors and microphones, and transmits them to the server as emotion data. Audio and video data are used as input, and processing this data generates quantitatively representing emotions. An analyzable emotion dataset can be obtained as output.

[0621] Step 3:

[0622] The server receives operational and sentiment data transmitted from terminals and stores it in a database. The input consists of time-series data and sentiment data, which are then denoised and outlier corrected. The output is a clean dataset suitable for analysis.

[0623] Step 4:

[0624] The server generates an analyzable dataset, inputs it into an artificial intelligence model, and performs operational optimization and failure prediction for the equipment. The input is a cleaned dataset. Based on this, machine learning algorithms are used to generate operational optimization patterns and failure prediction data. The output is this analysis result data.

[0625] Step 5:

[0626] The server analyzes emotional states using analysis results and an emotion engine, and generates operational suggestions based on the results. Inputs are equipment operational analysis data and the operator's emotional state; these are combined to formulate optimal operational suggestions. The output generates operational suggestion data that is notified to the operator.

[0627] Step 6:

[0628] The user receives and executes operational suggestions generated by the server. The input is suggested data, which the user uses to adjust equipment operation and schedules. The output is a more efficient and emotionally responsive operational state.

[0629] Step 7:

[0630] Users send operational results and feedback to the server via their terminals. Inputs include data from newly executed operations and operator feedback. Outputs are improvement data to enhance the accuracy of the generated artificial intelligence model.

[0631] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0632] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0633] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0634] [Fourth Embodiment]

[0635] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0636] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0637] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0638] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0639] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0640] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0641] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0642] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0643] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0644] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0645] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0646] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0647] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0648] As an embodiment of the present invention, a system is described that efficiently collects and analyzes large amounts of data obtained from vehicles and industrial equipment, and provides optimal operational suggestions. This system mainly consists of terminals, servers, and users.

[0649] The terminals function as data collection devices installed in each vehicle and piece of equipment, collecting operational data in real time via multiple sensors. The collected data is then properly organized as time-series data and transmitted to a server via the network. The data collection devices monitor the equipment status at regular intervals and, as needed, collect information such as location, temperature, and vibration.

[0650] The server stores the received time-series data in a database and handles data preprocessing and analysis. During data preprocessing, noise is removed and outliers are corrected to generate an analyzable dataset, thereby improving data reliability. Next, the generated dataset is sent to an artificial intelligence model for analyzing equipment operating patterns and predicting failures. This model utilizes machine learning techniques to continuously improve its analysis accuracy by learning from new data.

[0651] Users receive operational suggestions based on analysis results provided by the server and use them to optimize operations and implement preventive maintenance. For example, this allows users to find driving methods that reduce fuel consumption while increasing vehicle uptime, or to plan maintenance in advance if an anomaly is detected. The results of the measures taken by the user are fed back to the server via the terminal, and this feedback information is used to improve the generated artificial intelligence model and enhance the analysis.

[0652] As a concrete example, consider the application of this system to a fleet of trucks operated by a logistics company. Each truck is equipped with a terminal, and various data such as engine operating time, coolant temperature, and vibration data are collected. The server analyzes this information and proposes specific driving plans and scheduled maintenance timings to optimize the trucks' fuel efficiency. In this way, logistics companies can reduce costs and improve operational efficiency. By using this system, operational reliability can be increased, and efficient management throughout the entire lifecycle of the equipment becomes possible.

[0653] The following describes the processing flow.

[0654] Step 1:

[0655] The terminal collects data in real time from sensors attached to vehicles and industrial equipment. The terminal organizes the acquired data by sensor type and collection time, and then sends it to the server. The data includes information such as equipment temperature, vibration, location, and operating time.

[0656] Step 2:

[0657] The server collects data received from terminals via an API and stores it in a database. The server stores the data along with the time it was received and the sensor ID to maintain data integrity. The server also monitors for data loss and anomalies and performs initial error checks.

[0658] Step 3:

[0659] The server initiates preprocessing of the time-series data stored in the database. This preprocessing involves noise reduction and detection and correction of outliers to generate a dataset suitable for analysis. During this process, the server uses statistical methods to ensure reliable data formatting.

[0660] Step 4:

[0661] The server inputs pre-processed data into a generative artificial intelligence model. The generative AI model analyzes the operational patterns of the equipment from the collected data and performs analysis for anomaly detection and failure prediction. This model applies machine learning and deep learning algorithms to learn from the data and makes predictions based on the accumulated knowledge.

[0662] Step 5:

[0663] Based on the analysis results, the server generates optimal operational suggestions for the equipment. These suggestions include maintenance timing and specific operational improvement measures. The server displays this information in an easy-to-understand format on a dashboard and notifies the user. Alerts are also sent as needed.

[0664] Step 6:

[0665] Users receive suggestions from the server and use them to adjust operations and plan maintenance. Based on these suggestions, users review how they use their equipment, aiming to improve operational efficiency and reduce costs. Specifically, this includes implementing measures to improve fuel efficiency and conducting regular inspections.

[0666] Step 7:

[0667] Users report the results of the improvements and suggestions they have implemented as feedback. This feedback is sent back from the terminal to the server, which stores this information and uses it to further improve the generated artificial intelligence model. This improves the accuracy of subsequent analyses and enables more appropriate operational suggestions.

[0668] (Example 1)

[0669] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0670] The problem that this invention aims to solve is to efficiently collect and analyze large amounts of time-series data obtained from vehicles and industrial equipment, and to optimize operations and predict failures with high accuracy. Furthermore, it aims to improve operational efficiency and reliability by providing users with useful operational suggestions based on the obtained analysis results and continuously reflecting the feedback from their implementation into the system.

[0671] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0672] In this invention, the server includes means for collecting and organizing time-series data from various sensors, means for transmitting the collected time-series data to the server via a network, and means for receiving the data and storing it in a database. This enables efficient processing of large amounts of data, improving analysis accuracy, optimizing operations, and enhancing availability.

[0673] "Time-series data" refers to data where data points are collected sequentially along a time axis, and each data point is associated with a specific time.

[0674] A "sensor" is a device that measures physical or environmental conditions and outputs the results as signals or data. This allows for the collection of information such as location, temperature, and vibration.

[0675] A "network" is a connected system for sending and receiving information, enabling data communication between terminals and servers.

[0676] A "server" is a computer system that provides data and services over a network, and has the functions of storing, processing, and analyzing received data.

[0677] A "database" is an electronic information storage system that systematically stores collected data, enabling efficient retrieval and management.

[0678] "Noise reduction" is a technique that improves data reliability by removing unnecessary information during the data processing process.

[0679] "Outlier correction" is the process of detecting, correcting, or removing data points that are considered anomalous in a dataset.

[0680] A "generative artificial intelligence model" is a program that uses machine learning techniques to analyze data and make specific patterns or predictions.

[0681] This system aims to optimize equipment operation by efficiently collecting and analyzing large amounts of time-series data acquired from vehicles and industrial equipment. Specifically, it consists of three main elements: terminals, servers, and users.

[0682] Terminal role

[0683] The terminals are installed in vehicles and industrial equipment and function as data collection devices. Specifically, they use GPS sensors, temperature sensors, acceleration sensors, etc., to collect operational data such as location information, temperature, and vibration in real time. This data is appropriately organized as time-series data and transmitted to a server via the network.

[0684] Server Role

[0685] The server receives time-series data transmitted from terminals and stores it in a database. The received data undergoes preprocessing, such as noise reduction and anomaly correction, and is converted into an analyzable format. This improves the reliability of the data. The preprocessed data is then input into a generative artificial intelligence model to analyze equipment operating patterns and predict failures. This generative AI model utilizes machine learning techniques and improves its analysis accuracy by continuously learning from new data.

[0686] User roles

[0687] Based on the analysis results provided by the server, users receive specific operational suggestions using prompts. For example, they might receive suggestions for driving plans to optimize vehicle fuel efficiency or schedules for regular maintenance. Users optimize their operations based on these suggestions and provide feedback to the server via their terminal. This feedback information is used to further train the generative artificial intelligence model.

[0688] Specific example

[0689] For example, when this system is applied to a fleet of trucks operated by a logistics company, a terminal is installed in each truck to collect data such as engine operating time, coolant temperature, and vibration. The server analyzes this information and proposes specific driving plans and maintenance timings to optimize fuel efficiency.

[0690] Example of a prompt

[0691] "Analyze diverse sensor data and propose a driving plan that optimizes the fuel efficiency of logistics vehicles."

[0692] In this way, users can improve operational efficiency and reliability.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] The device collects data using various sensors. Specifically, it obtains location information from a GPS sensor, device temperature from a temperature sensor, and vibration from an accelerometer. This data is collected in real time and organized as time-series data. This organized data forms the basis for subsequent analysis.

[0696] Step 2:

[0697] The terminal sends organized time-series data to the server over the network. The network typically uses wired or wireless technology to ensure fast and secure data transfer. The server receives this data and logs the timing of its reception.

[0698] Step 3:

[0699] The server stores the received data in the database. During storage, a schema is used to structure the data, enabling quick queries and retrieval. This prepares the data for smooth subsequent processing.

[0700] Step 4:

[0701] The server retrieves data from the database and performs preprocessing to remove noise and correct for outliers. The input is raw data, and the output is a dataset with improved reliability and consistency. This process enhances data quality and improves accuracy in subsequent analysis.

[0702] Step 5:

[0703] The server inputs pre-processed data into a generating AI model. This model is based on machine learning techniques and detects operational patterns from the data to predict failures. Pre-processed data is used as input, and analysis results are generated as output.

[0704] Step 6:

[0705] The server generates operational suggestions using the analysis results obtained from the generated AI model. Using prompts, it creates specific operational methods and improvement suggestions for the user. This results in a more practical and actionable action plan.

[0706] Step 7:

[0707] Users receive operational suggestions from the server and implement operations based on those suggestions. They incorporate the suggestions into their on-site operations, observe the results, and evaluate them. This feedback becomes key data that will be used in subsequent model updates.

[0708] Step 8:

[0709] The device collects user feedback again and sends it to the server. The server stores the received feedback in a database and uses it as training data for the generated artificial intelligence model. This further improves the accuracy of the model's analysis and enables continuous system improvement.

[0710] (Application Example 1)

[0711] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0712] Modern factories are required to maximize the operational efficiency of machinery while simultaneously predicting breakdowns. However, conventional systems have not adequately achieved the analysis of vast amounts of data and improved prediction accuracy, leading to problems such as reduced machine utilization and delayed maintenance.

[0713] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0714] In this invention, the server includes a device for receiving time-series data acquired from a data acquisition device, a device for preprocessing the received time-series data to generate an analyzable data set, a device for inputting the analyzable data set into an artificial intelligence model to optimize equipment operation and predict failures, and a device for providing operation instructions and maintenance plans to optimize the operation of factory machinery. This makes it possible to maximize the operating rate of the machinery while enabling planned maintenance through proactive failure prediction.

[0715] A "data acquisition device" is a device that collects operational data in real time from machinery within a factory.

[0716] "Time-series data" refers to continuous data recorded at regular time intervals, which provides information about the state and operation of machinery.

[0717] "Preprocessing" is the process of removing noise from received raw data to generate a data set suitable for analysis.

[0718] An "analyzable data set" is a collection of data that has been prepared through preprocessing, making it possible to analyze it using artificial intelligence.

[0719] A "generative artificial intelligence model" is a model that uses machine learning techniques to predict the operating patterns and failures of equipment, and is a method of analysis using data.

[0720] "Operational proposals" refer to specific instructions and advice provided to users based on the analysis results of the generated artificial intelligence model, aimed at optimizing the operation of the equipment.

[0721] "Operation instructions" refer to information that provides specific instructions on how to operate equipment in order to optimize its operation.

[0722] A "maintenance plan" is a proposal for planning equipment maintenance schedules based on predicted failures.

[0723] To implement this invention, a data acquisition device is attached to a machine used in a factory, and machine operation data is collected in real time. A terminal organizes this data as time-series data and transmits it to a server via a network. The server removes noise from the received data and generates an analyzable data set. This makes it possible to understand the accurate state of machine operation.

[0724] The server inputs the generated data set into a generative artificial intelligence model to optimize equipment operation and predict failures. The generative artificial intelligence model continuously learns from new data, improving its analytical accuracy. This allows for detailed analysis of the operating patterns of the work machinery and the generation of efficient operating instructions.

[0725] Users receive operational suggestions based on analysis results provided by the server and use them to optimize machine operation. These suggestions include operating instructions to optimize the operation of the work equipment and maintenance plans aimed at preventative maintenance. This leads to improved machine uptime and accident prevention.

[0726] For example, by using a generative artificial intelligence model to make predictions based on vibration data from a robotic arm used in a factory, it is possible to detect minute errors in movement and recommend necessary adjustments. This makes it possible to carry out planned maintenance while maintaining product quality.

[0727] Example of a prompt:

[0728] "Detect abnormal values ​​based on the robot arm's motion data and output recommendations for necessary maintenance."

[0729] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0730] Step 1:

[0731] The terminal collects operational data in real time from machinery within the factory. The data acquired through sensors includes temperature, vibration, and operating time, and this data is organized in a time-series format. The input is sensor data, and the output is organized time-series data.

[0732] Step 2:

[0733] The terminal sends organized time-series data to the server via the network. This process involves data transmission, and the server receives that data. The input is organized time-series data, and the output is the data arriving at the server.

[0734] Step 3:

[0735] The server denoises the received data and generates an analyzable data set. Specifically, it uses filtering techniques to remove outliers and unnecessary data, preparing the data for use. The input is the received time-series data, and the output is a denoised data set.

[0736] Step 4:

[0737] The server inputs the generated data set into an artificial intelligence model to analyze the equipment's operating patterns and predict failures. This process utilizes machine learning algorithms to continuously improve the model's accuracy. The input is a denoised data set, and the output includes operating patterns and failure prediction results.

[0738] Step 5:

[0739] The server generates operational suggestions based on the analysis results and notifies the user. These suggestions include optimal operating instructions and maintenance plans, providing the user with information for decision-making. The input is the analysis results, and the output is the generated operational suggestions.

[0740] Step 6:

[0741] Users receive and utilize notified operational suggestions to perform machine operation and maintenance activities. Specific actions include machine operation based on the operational suggestions and the implementation of planned maintenance. The input is the operational suggestions, and the output is feedback on the operations and maintenance activities performed.

[0742] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0743] As an embodiment of the present invention, a system is described that provides efficient and effective operational suggestions while taking into account the user's emotions in the operation of vehicles and industrial equipment. The system consists of a terminal, a server, a user, and an emotion engine.

[0744] The terminal is responsible for sequentially acquiring operational data from multiple sensors attached to the equipment and transmitting it to the server. This includes sensor data such as equipment temperature, vibration, and operating time, which are organized as time-series data. The terminal also collects emotional data from the user's voice and facial expressions through the user interface and transmits it to the server as well.

[0745] The server stores received device data and user sentiment data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction to generate an analyzable dataset. These datasets are analyzed using a generative artificial intelligence model. The generative AI model optimizes device operation, predicts failures, and further incorporates the user's emotional state using an emotion engine to generate user-optimized operational suggestions.

[0746] The emotion engine analyzes the user's emotional data to identify the user's current emotional state. Based on this emotional state, it adjusts the operational suggestions derived from the generative artificial intelligence model. For example, if the user is stressed, the suggestions can be simplified for easier execution; if the user is relaxed, more detailed suggestions can be sent.

[0747] Users receive operational suggestions from the server and adjust equipment operation and schedules accordingly. These suggestions include maintenance needs, changes to operating patterns, and measures to improve energy efficiency. Users send feedback based on the results of their operations and their emotions through their terminals, and the server stores this feedback to further improve analysis accuracy and the accuracy of the emotion engine.

[0748] As a concrete example, consider a case where a manufacturing line supervisor uses the system. While operational status and error information are collected from manufacturing equipment, the supervisor's stress level (e.g., through voice analysis) is acquired as emotional data. The server integrates this information and provides emotionally sensitive and efficient equipment operation suggestions. Based on these suggestions, it becomes possible to maximize manufacturing quality and productivity while avoiding unnecessary human intervention.

[0749] The following describes the processing flow.

[0750] Step 1:

[0751] The terminal collects operational data in real time from sensors installed in vehicles and industrial equipment. This includes temperature, vibration, and location information. It also collects user voice and facial expression data through microphones and cameras built into the user's device, acquiring emotional data to understand the user's emotional state.

[0752] Step 2:

[0753] The device transmits collected device data and emotional data to a server via the network. The data is organized as time-series data and timestamped to allow for detailed tracking of the device's operation.

[0754] Step 3:

[0755] The server stores the received data in a database and begins data preprocessing. This process involves detecting outliers, removing noise, and converting the data into a format suitable for analysis. The preprocessed data is then organized into datasets used for both equipment operation analysis and user sentiment analysis.

[0756] Step 4:

[0757] The server inputs the pre-processed dataset into a generative artificial intelligence model. The generative AI model uses machine learning algorithms to analyze the operating patterns of the equipment and perform failure prediction. It also uses an emotion engine to analyze user emotion data and incorporates the results into the analysis.

[0758] Step 5:

[0759] The server generates operational suggestions based on the analysis results. Based on the results of the emotion engine, it adjusts the suggestions to suit the user's emotional state. For example, if the user is feeling stressed, it prioritizes simpler and easier-to-implement suggestions.

[0760] Step 6:

[0761] The server notifies the user of the operational suggestions it has generated. The suggestions are displayed on the dashboard and, if necessary, are also sent via email or smartphone notification. Specific suggestions include maintenance requirements, operational improvement measures, and methods for improving energy efficiency.

[0762] Step 7:

[0763] Users adjust equipment operation and operational schedules based on suggestions from the server. They report the results of their improvements and feedback on their suggestions to the server by resending them through their terminal.

[0764] Step 8:

[0765] The server stores the received feedback in a database and uses it to further improve the accuracy of the generative artificial intelligence model and emotion engine. This continuous feedback loop improves the accuracy of operational suggestions and the user experience.

[0766] (Example 2)

[0767] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0768] Conventional machine operation management systems have difficulty taking user emotions into account when proposing operations, making it challenging to optimize operations efficiently or predict anomalies. Furthermore, there has been a lack of appropriate methods for improving the accuracy of data analysis.

[0769] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0770] In this invention, the server includes means for receiving time-series information acquired from data collection means, means for preprocessing the received time-series information to generate an analyzable information set, and means for inputting the analyzable information set into an artificial intelligence means for optimizing the operation of the device and predicting anomalies. This enables the provision of operational suggestions that take into account the user's emotional state and continuous improvement of analysis accuracy.

[0771] A "data collection method" is a mechanism for collecting time-series information through sensors or interfaces attached to a device.

[0772] "Time-series information" refers to a set of data recorded at specific time intervals, where each data point is arranged chronologically.

[0773] "Preprocessing" is the process of removing noise and outliers from collected raw data and preparing it for analysis.

[0774] An "analyzable information set" is a dataset that has undergone preprocessing and been transformed into a format that can be analyzed by a machine.

[0775] "Generative artificial intelligence means" refers to models that use machine learning algorithms to analyze data and perform operational optimization and anomaly prediction.

[0776] "Optimizing equipment operation" is the process of determining the optimal settings and operating methods for equipment to function efficiently and effectively.

[0777] "Anomaly prediction" refers to the process of using equipment operating data to predict in advance the occurrence of abnormal situations such as failures or malfunctions.

[0778] "Emotional analysis means" refers to a technology that analyzes a user's emotional state from their voice, facial expressions, etc., and extracts it as data.

[0779] An "operational proposal" is a specific suggestion or recommendation regarding the operation of the equipment and user actions, based on the collected data and its analysis results.

[0780] An "information storage system" is a mechanism for continuously accumulating and managing collected data and feedback.

[0781] The present invention provides suggestions that take user emotions into account in order to optimize the operation of the device efficiently and effectively. This system mainly comprises a terminal, a server, and an emotion engine.

[0782] The terminal collects time-series information in real time from various sensors connected to the device and transmits it to the server. Specifically, this includes information such as temperature, vibration, and operating time. In addition, the terminal uses a camera and microphone to capture the user's facial expressions and voice through the user interface and collects emotional data. This emotional data is also transmitted to the server.

[0783] The server has a database that centrally manages this data and performs preprocessing on the received time-series data, such as noise reduction and anomaly correction, to generate an analyzable information set. Using this information set, the generative artificial intelligence model executes a process to optimize operations and predict anomalies. For example, the generative AI model receives a prompt such as "Provide easy-to-follow operational suggestions when the user is feeling stressed" and generates appropriate suggestions.

[0784] The emotion engine analyzes the user's emotional data to identify their emotional state. Based on this analysis, the server dynamically adjusts operational suggestions to match the user's emotions and notifies the user of optimized information. In this way, it helps the user take the optimal action according to the situation.

[0785] As a concrete example, in a manufacturing environment, if users are experiencing stress, the system could lower the priority of less urgent maintenance tasks and suggest more necessary tasks with simplified procedures. In this way, the burden on users is reduced while enabling optimal equipment operation.

[0786] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0787] Step 1:

[0788] The terminal collects time-series information from various sensors connected to the device. Specifically, it acquires data from temperature sensors, vibration sensors, operating time meters, etc. This input data is transmitted to the server in real time. The output is the raw data transferred to the server.

[0789] Step 2:

[0790] The server stores the received time-series information in a database and performs noise reduction and outlier correction. This generates an analyzable data set. During this process, data integrity is checked and data processing such as smoothing outliers is performed. The output is an analyzable dataset.

[0791] Step 3:

[0792] The device uses a camera and microphone to capture the user's facial expressions and voice, collecting emotional data. This data is also sent to the server. The input is the captured audio and video data, and the output is the emotional data sent to the server.

[0793] Step 4:

[0794] The server analyzes emotional data and performs data calculations to identify the user's emotional state. It extracts emotional information as numerical data using an emotion engine. This output represents information about the user's emotional state.

[0795] Step 5:

[0796] The generative artificial intelligence model uses analyzable datasets and user emotional states to optimize device operation and predict anomalies. The input consists of analyzable information sets and emotional states, while the output is an initial proposal based on these.

[0797] Step 6:

[0798] The server dynamically adjusts initial suggestions based on the user's emotional state. For example, it generates simple, easy-to-follow suggestions for a stressed user and more detailed suggestions for a relaxed user. This output represents the adjusted operational suggestions.

[0799] Step 7:

[0800] The user receives optimized operational suggestions from the server and modifies the device operation and schedule based on them. The output of this step is the user's actions and their results.

[0801] Step 8:

[0802] Users send feedback on their actions and emotions to the server via their device. The server records this feedback in an information storage system and uses it for future data analysis and system improvements. The input is the user's feedback, and the output is the feedback data stored in the information storage system.

[0803] (Application Example 2)

[0804] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0805] In recent years, manufacturing and service industries have been required to improve worker productivity and efficiency while also considering workers' health and emotional states. However, conventional systems have struggled to provide operational suggestions that reflect workers' emotional states in real time, and have not adequately addressed the need to create an environment where individual workers can perform at their best. As a result, problems have arisen where workers' workloads increase and productivity declines.

[0806] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0807] In this invention, the server includes means for receiving time-series data acquired from a data acquisition device, means for preprocessing the received time-series data to generate an analyzable dataset, means for inputting the analyzable dataset into a generating artificial intelligence model to optimize equipment operation and predict failures, means for generating operational suggestions based on the analysis results of the generating artificial intelligence model, and means for analyzing the user's emotional state using an emotion engine and adjusting the operational suggestions based on that emotional state. This makes it possible to provide optimal operational suggestions in real time that are tailored to the emotional state of each individual worker.

[0808] A "data acquisition device" is a device used to acquire time-series data related to the operation of equipment.

[0809] "Time-series data" refers to data acquired over time, used to track various parameters of equipment.

[0810] "Preprocessing" refers to the process of removing noise and correcting outliers to transform data into a format suitable for data analysis.

[0811] An "analyzable dataset" is a collection of data that has been organized in a way that makes it applicable to data analysis tools and algorithms.

[0812] A "generative artificial intelligence model" is an algorithm or model used to optimize the operation of equipment and predict failures.

[0813] An "operational proposal" is a specific action plan for optimizing the operation of equipment.

[0814] An "emotion engine" is a software engine used to analyze and identify a user's emotional state.

[0815] A "user" is a person who adjusts the operation of the equipment based on the system's suggestions.

[0816] The system for implementing this invention consists of a terminal, a server, and an emotion engine. The terminal is placed in a work environment such as a factory and is responsible for sequentially acquiring operational data from multiple sensors attached to equipment and transmitting it to the server. The sensors collect data such as the temperature, vibration, and operating time of the equipment and organize this as time-series data. Furthermore, the terminal collects emotion data from the operator's voice and facial expressions and also transmits this to the server.

[0817] The server stores received equipment data and operator emotion data in a database. As a data preprocessing step, the server performs noise reduction and anomaly correction, and generates an analyzable dataset using text processing. These datasets are analyzed by a generative artificial intelligence model to optimize equipment operation and predict failures. Furthermore, an emotion engine is used to identify the operator's emotional state and generate operational suggestions optimized for the user.

[0818] For example, if the operator is stressed, the server can simplify the suggestions to make them easier to implement. Conversely, if the operator is relaxed, it can provide more detailed operational suggestions. Finally, the generated operational suggestions are communicated to the operator via the user interface. This allows the operator to optimize equipment operation and operational schedules based on the suggestions.

[0819] As a concrete example, in a factory setting, if the operator's fatigue level increases, the system can suggest break times based on operational recommendations or automatically adjust the machine's operating speed. This makes it possible to maintain productivity while protecting the operator's health.

[0820] An example of a prompt message might be: "Generate an optimal robot operation schedule to maximize the current emotional state and work efficiency. Suggest ways to reduce worker fatigue and improve productivity."

[0821] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0822] Step 1:

[0823] The terminal acquires operational data using multiple sensors. This includes equipment temperature, vibration, and operating time. The input is raw data obtained in real time from the sensors, but since it is difficult to analyze directly, it is first organized into time-series data. The output is time-series data in a format that can be sent to the server.

[0824] Step 2:

[0825] The terminal acquires the operator's voice and facial expressions using sensors and microphones, and transmits them to the server as emotion data. Audio and video data are used as input, and processing this data generates quantitatively representing emotions. An analyzable emotion dataset can be obtained as output.

[0826] Step 3:

[0827] The server receives operational and sentiment data transmitted from terminals and stores it in a database. The input consists of time-series data and sentiment data, which are then denoised and outlier corrected. The output is a clean dataset suitable for analysis.

[0828] Step 4:

[0829] The server generates an analyzable dataset, inputs it into an artificial intelligence model, and performs operational optimization and failure prediction for the equipment. The input is a cleaned dataset. Based on this, machine learning algorithms are used to generate operational optimization patterns and failure prediction data. The output is this analysis result data.

[0830] Step 5:

[0831] The server analyzes emotional states using analysis results and an emotion engine, and generates operational suggestions based on the results. Inputs are equipment operational analysis data and the operator's emotional state; these are combined to formulate optimal operational suggestions. The output generates operational suggestion data that is notified to the operator.

[0832] Step 6:

[0833] The user receives and executes operational suggestions generated by the server. The input is suggested data, which the user uses to adjust equipment operation and schedules. The output is a more efficient and emotionally responsive operational state.

[0834] Step 7:

[0835] Users send operational results and feedback to the server via their terminals. Inputs include data from newly executed operations and operator feedback. Outputs are improvement data to enhance the accuracy of the generated artificial intelligence model.

[0836] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0837] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0838] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0839] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0840] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0841] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0842] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0843] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0844] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0845] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0846] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0847] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0848] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0849] 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.

[0850] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0851] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0852] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0853] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0854] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0855] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0856] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0857] The following is further disclosed regarding the embodiments described above.

[0858] (Claim 1)

[0859] A means for receiving time-series data acquired from a data collection device,

[0860] A means for preprocessing received time-series data to generate an analyzable dataset,

[0861] A means of generating analyzable datasets, inputting them into artificial intelligence models, and performing equipment operation optimization and failure prediction,

[0862] A means for generating operational proposals based on the analysis results of the aforementioned artificial intelligence model,

[0863] A means of notifying users of the generated operational proposals,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, wherein the generative artificial intelligence model continuously learns based on newly acquired data and improves the accuracy of the analysis.

[0867] (Claim 3)

[0868] The system according to claim 1, which stores user feedback based on analysis results and operational proposals in a database and improves the generated artificial intelligence model.

[0869] "Example 1"

[0870] (Claim 1)

[0871] A means of collecting and organizing time-series data from various sensors,

[0872] A means of transmitting collected time-series data to a server via a network,

[0873] A means of receiving data and storing it in a database,

[0874] A means of preprocessing the stored data by removing noise and correcting outliers,

[0875] A means for analyzing pre-processed data and inputting it into a generative artificial intelligence model that generates operational patterns and failure predictions,

[0876] A means for generating specific operational suggestions using prompt sentences based on analysis results from a generative artificial intelligence model,

[0877] A means of notifying users of the generated operational proposals and collecting the results of their implementation again,

[0878] A method for utilizing the re-collected results as feedback to train a generative artificial intelligence model,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, wherein the generative artificial intelligence model continuously learns based on newly collected data and user feedback to improve the accuracy of the analysis.

[0882] (Claim 3)

[0883] The system according to claim 1, which generates specific operation plans and maintenance schedules based on analysis results and proposes them to users in order to improve the operational efficiency of logistics and industrial equipment.

[0884] "Application Example 1"

[0885] (Claim 1)

[0886] A device that receives time-series data acquired from a data collection device,

[0887] A device that preprocesses received time-series data to generate an analyzable data set,

[0888] A device that generates an analyzable data set, inputs it into an artificial intelligence model, and performs optimization of equipment operation and fault prediction,

[0889] A device that generates operational proposals based on the analysis results of a generated artificial intelligence model,

[0890] A device that notifies the user of the generated operational proposal,

[0891] A device that provides operating instructions and maintenance plans to optimize the operation of machinery in a factory,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, wherein the generative artificial intelligence model continuously learns based on newly acquired information and improves the accuracy of the analysis.

[0895] (Claim 3)

[0896] The system according to claim 1, which stores user feedback based on analysis results and operational proposals in an information infrastructure and improves the generated artificial intelligence model.

[0897] "Example 2 of combining an emotion engine"

[0898] (Claim 1)

[0899] A means for receiving time-series information acquired from data collection means,

[0900] A means for preprocessing received time-series information to generate an analyzable information set,

[0901] A means for generating an analyzable set of information, inputting it into an artificial intelligence means, and performing optimization of device operation and anomaly prediction,

[0902] A means for generating operational proposals based on the analysis results of the aforementioned artificial intelligence generation means,

[0903] A means of notifying users of the generated operational proposals,

[0904] A means for analyzing the user's emotional state using an emotional analysis tool and adjusting operational proposals based on that emotion,

[0905] A means of receiving user feedback based on operation results and emotions, and using it for improvement,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, wherein the generating artificial intelligence means continuously learns based on newly acquired information and improves the accuracy of the analysis.

[0909] (Claim 3)

[0910] The system according to claim 1, which stores user feedback based on analysis results and operational proposals in an information storage means and improves the generating artificial intelligence means.

[0911] "Application example 2 when combining with an emotional engine"

[0912] (Claim 1)

[0913] A means for receiving time-series data acquired from a data collection device,

[0914] A means for preprocessing received time-series data to generate an analyzable dataset,

[0915] A means of generating analyzable datasets, inputting them into artificial intelligence models, and performing equipment operation optimization and failure prediction,

[0916] A means for generating operational proposals based on the analysis results of the aforementioned artificial intelligence model,

[0917] A means of analyzing the user's emotional state using an emotion engine and adjusting operational proposals based on that emotional state,

[0918] A means of notifying users of the generated operational proposals,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, wherein the generative artificial intelligence model continuously learns based on newly acquired data and improves the accuracy of the analysis.

[0922] (Claim 3)

[0923] The system according to claim 1, which stores user feedback based on analysis results and operational proposals in a database and improves the generated artificial intelligence model. [Explanation of symbols]

[0924] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving time-series data acquired from a data collection device, A means for preprocessing received time-series data to generate an analyzable dataset, A means of generating analyzable datasets, inputting them into artificial intelligence models, and performing equipment operation optimization and failure prediction, A means for generating operational proposals based on the analysis results of the aforementioned artificial intelligence model, A means of notifying users of the generated operational proposals, A system that includes this.

2. The system according to claim 1, wherein the generative artificial intelligence model continuously learns based on newly acquired data and improves the accuracy of the analysis.

3. The system according to claim 1, which stores user feedback based on analysis results and operational proposals in a database and improves the generated artificial intelligence model.

Images