system

Abstract

Provide a system. A method for collecting monitoring data of a base station includes: means for filtering data relating to the battery from the collected monitoring data; A means for obtaining past inspection result data; a means for analyzing the filtered data and past inspection result data to assess the lifespan of the battery; A means for listing base stations that require on-site inspection based on the evaluation results; a means for notifying a list of base stations that require on-site inspection; A system including:

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Base station batteries require regular maintenance, but conventional methods pose challenges in accurately predicting battery degradation and lifespan and replacing them in a timely manner. This can lead to sudden battery deterioration or failure, which can disrupt communication services. Frequent inspections of all base stations are also inefficient in terms of both human resources and costs. Therefore, a method is needed to accurately assess battery lifespan and efficiently conduct on-site inspections. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a means for collecting base station monitoring data, a means for filtering battery-related data from the collected monitoring data, a means for acquiring past inspection result data, a means for evaluating battery life by analyzing the filtered data and the past inspection result data, a means for listing base stations requiring on-site inspection based on the evaluation results, and a means for notifying the list of base stations requiring on-site inspection, thereby enabling accurate prediction of battery life, realizing timely maintenance, improving the stability of communication services, and optimizing human resources and costs.

[0006] A "base station" is a relay point or access point in a communication network for mobile communication or wireless communication.

[0007] "Monitoring data" refers to data collected from base stations, including communication status, power status, and device operating status.

[0008] "Collecting means" refers to a method or device for automatically or manually collecting monitoring data and inspection result data from base stations.

[0009] A "filtering means" is a method or device that extracts and selects only data that meets specific conditions from collected data.

[0010] "Inspection result data" refers to data recorded during maintenance inspections of base station equipment and batteries, and includes battery replacement history and inspection results.

[0011] "Means for analyzing" refers to a device or method that analyzes the collected data and evaluates the condition and lifespan of the battery based on certain rules or algorithms.

[0012] A "means for assessing battery life" is a device or method that estimates the remaining life of a battery based on collected and analyzed data.

[0013] The "means for listing base stations requiring on-site inspection" refers to a method or device for identifying base stations requiring prompt on-site inspection based on the results of battery life assessment, and creating a list of such base stations.

[0014] The "notification means" refers to a method or device for transmitting information about the listed base stations that require on-site inspection to the person in charge. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is described in detail below with reference to an embodiment thereof. The purpose of this system is to accurately evaluate the battery life of a base station and to realize timely on-site inspection and maintenance, thereby improving the stability of communication services and optimizing resources.

[0037] System Configuration

[0038] This system consists of a base station, a server, and a terminal. The base station is a relay point or access point for wireless communication in the communication network and provides the necessary monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal notifies the person in charge of the need for a field survey and is used by the person in charge to carry out the field survey.

[0039] Program Operation

[0040] 1. Data Collection

[0041] The server periodically collects monitoring data from each base station. For example, it receives data from base station ABC every day and stores it in a database.

[0042] The server also retrieves past inspection result data from the database, including battery replacement history and inspection results.

[0043] 2. Data Analysis

[0044] The server filters the monitoring data stored in the database and extracts only battery-related data, for example, "low voltage" alarm data for base station ABC.

[0045] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. It confirms that "low voltage" alarms have occurred five times in the past month.

[0046] The server analyzes the inspection result data and evaluates the battery replacement history and inspection results, for example, to verify that the last replacement was more than a year ago.

[0047] 3. Battery life evaluation

[0048] The server then runs an algorithm to assess battery life based on the analysis results, for example, if there is a high frequency of alarms or if inspection history indicates that the battery is deteriorating, and estimates the remaining battery life.

[0049] As a result of the evaluation, the server determines that the battery life is below a standard value (for example, less than three months remaining) and lists the base station as one that requires on-site inspection.

[0050] 4. Field survey list generation and notification

[0051] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies personnel of the need for an on-site inspection. For example, it creates a notification saying, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[0052] The terminal sends a notification to the person in charge, who then confirms it.

[0053] 5. Conducting on-site surveys

[0054] The user (person in charge) receives the notification, goes to base station ABC, and checks the actual battery condition on-site. If necessary, the battery is replaced to ensure the stability of the system.

[0055] Specific examples

[0056] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[0057] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] Data collection

[0061] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database.

[0062] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[0063] Step 2:

[0064] Data Filtering

[0065] The server filters the collected monitoring data for battery-related alarm data, for example, extracting only "low voltage" alarms.

[0066] Step 3:

[0067] Time Series Analysis

[0068] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0069] Step 4:

[0070] Inspection history analysis

[0071] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0072] Step 5:

[0073] Battery Life Rating

[0074] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0075] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[0076] Step 6:

[0077] Field survey list generation

[0078] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[0079] Step 7:

[0080] Notification generation

[0081] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it creates a notification with the content "Base station A has 3 months of battery life remaining. On-site inspection is required."

[0082] Step 8:

[0083] Send notifications

[0084] The terminal sends a notification message to the person in charge, who receives and confirms the notification on the terminal.

[0085] Step 9:

[0086] Preparation for field survey

[0087] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0088] Step 10:

[0089] Conducting on-site surveys

[0090] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the records in the database.

[0091] Through the above steps, the server, terminal, and user can cooperate to manage the battery life and perform maintenance at the appropriate time.

[0092] Example 1

[0093] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0094] There is a need to accurately assess the lifespan of power supply equipment (batteries) at base stations in communication networks and to carry out on-site inspections and maintenance when necessary. However, with conventional systems, it is difficult to predict the deterioration of power supply equipment and respond in a timely manner, which can result in a loss of stability in communication services. To address this, there is a need for more accurate and efficient methods to assess the lifespan of power supply equipment and notify the need for on-site inspections.

[0095] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0096] In this invention, the server includes means for collecting monitoring data, means for filtering the collected monitoring data to extract data related to the power supply devices, means for acquiring past operational inspection data, means for analyzing the filtered data and the past operational inspection data to evaluate the usable life of the power supply devices, means for selecting communication devices requiring on-site inspection based on the evaluation results, and means for notifying the list of communication devices requiring on-site inspection. This makes it possible to accurately evaluate the life of power supply devices in a communication network and to perform on-site inspections and maintenance in a timely manner.

[0097] "Monitoring data" refers to information relating to the operating status and performance of communication devices such as base stations.

[0098] "Filtering" is the process of extracting information that meets specific conditions from collected data and removing unnecessary information.

[0099] "Power Supply" means a battery or other power supply unit that provides power to a communications device.

[0100] "Operational inspection data" refers to records and history of inspection work carried out on communication devices in the past.

[0101] "Available life" refers to the estimated period of time that the power supply device can continue to function normally.

[0102] The term "communication device" refers to all devices, including base stations, for transmitting and receiving data in a communication network.

[0103] A "server" is a computer system that collects, analyzes, and notifies data.

[0104] The system of the present invention is designed to accurately assess the lifespan of base station power supplies (batteries) in communication networks and to perform on-site inspections and maintenance in a timely manner, thereby maintaining the stability of communication services and optimizing resources.

[0105] System Configuration

[0106] This system mainly consists of the following hardware and software:

[0107] Base Station: Acts as a relay or access point in the communication network and provides the necessary monitoring data.

[0108] Server: The main device that collects, analyzes, evaluates, and notifies data. Data is managed using a database system (e.g., MySQL (registered trademark)), and a programming language such as Python is used for analysis.

[0109] Terminal: A device used to notify personnel of the need for on-site inspections. It can be a smartphone, tablet, or PC.

[0110] Data collection

[0111] The server periodically collects monitoring data from each base station. For example, the server uses SNMP (Simple Network Management Protocol) to obtain data from the base station and stores it in a MySQL database. The collected data includes battery level, voltage value, alarm status, etc. The server also obtains inspection results and replacement history data from the same database. This is done using SQL queries.

[0112] Data analysis

[0113] The server analyzes the monitoring data stored in the database and filters it to extract battery-related data. For example, it executes the SQL query "SELECT FROM MonitoringData WHERE AlarmType='LowVoltage'" to extract only "low voltage" alarm data. The server then analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. The server then analyzes inspection result data and evaluates battery replacement history and inspection results.

[0114] Battery Life Rating

[0115] The server executes a battery life evaluation algorithm based on the analysis results. For example, it evaluates in Python "if alarm occurrence count > 5 or last replacement date > 365 days: remaining life = estimated value." Based on this evaluation result, if the battery life is below the standard value, the base station is listed as requiring an on-site inspection.

[0116] Field survey list generation and notification

[0117] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies the person in charge of the need for an on-site inspection. For example, it sends an email using the SMTP protocol stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required." In response, the terminal displays a notification to the person in charge.

[0118] Conducting on-site surveys

[0119] The user (person in charge) receives the notification, goes to the base station, checks the battery status on-site, and replaces the battery if necessary to ensure system stability.

[0120] Specific examples

[0121] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[0122] Prompt Sentence Examples

[0123] An example of a prompt to input to a generative AI model is as follows:

[0124] "Please prepare an analytical report on the battery life assessment for base station ABC. Based on the frequency of 'low voltage' alarms over the past month and inspection history, estimate the remaining life to be less than 3 months. Please also include a notice to the responsible party that an on-site inspection is required."

[0125] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1: Data collection

[0128] Input: Monitoring data from base stations and past inspection result data in the database.

[0129] Specific behavior:

[0130] The server acquires monitoring data from each base station using SNMP (Simple Network Management Protocol). For example, data is acquired from base station ABC at midnight every day and stored in a MySQL database.

[0131] The server retrieves the inspection results and battery replacement history data from the database using an SQL query, for example, "SELECT FROM BatteryCheckResults WHERE BaseStationID='ABC'".

[0132] Output: Collected monitoring data and historical inspection result data.

[0133] Step 2: Data filtering

[0134] Input: Collected monitoring data.

[0135] Specific behavior:

[0136] The server parses the monitoring data and extracts only the battery-related data, for example by executing the SQL query "SELECT FROM MonitoringData WHERE BaseStationID='ABC' AND AlarmType='LowVoltage'".

[0137] Filtered data includes voltage values, alarm conditions, battery levels, etc.

[0138] Output: Filtered monitoring data.

[0139] Step 3: Frequency analysis

[0140] Input: Filtered monitoring data.

[0141] Specific behavior:

[0142] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0143] Use a Python script to analyze the timestamps and tally the number of alarms that occurred.

[0144] Output: Alarm occurrence frequency data.

[0145] Step 4: Analyze the inspection results

[0146] Input: Past inspection result data.

[0147] Specific behavior:

[0148] The server analyzes past inspection data and evaluates battery replacement history and inspection results, for example, to verify that the last replacement date was more than one year ago.

[0149] Run an SQL query to retrieve inspection and replacement history (e.g., "SELECT LastInspectionDate FROM BatteryCheckResults WHERE BaseStationID='ABC'").

[0150] Output: Evaluation results of inspection result data.

[0151] Step 5: Battery Life Assessment

[0152] Input: Evaluation results of occurrence frequency data and inspection result data.

[0153] Specific behavior:

[0154] The server runs a battery life assessment algorithm, for example using the following logic: "if alarm count > 5 or last replacement date > 365 days: remaining life = < 3 months".

[0155] Implement conditional branching in a Python script and evaluate lifespan.

[0156] Output: Battery life evaluation results.

[0157] Step 6: Generate a site survey list

[0158] Input: Battery life assessment results.

[0159] Specific behavior:

[0160] The server generates a list of base stations that are evaluated as nearing the end of their life. For example, base station ABC is added to the list.

[0161] Export the list to a CSV file and save it as "surveylist.csv".

[0162] Output: Field survey list.

[0163] Step 7: Create and send a notification

[0164] Input: Field survey list.

[0165] Specific behavior:

[0166] The server creates a notification to the person in charge based on the generated list, for example, creating an email stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[0167] Use the SMTP protocol to send an email with the above content. Specifically, send an email with the following content: "From: server@company.com, To: user@company.com, Subject: On-site inspection notification, Body: Base station ABC has less than 3 months of battery life remaining."

[0168] Output: Notification of need for on-site investigation.

[0169] Step 8: Review the notification and conduct an on-site inspection

[0170] Input: Notification email.

[0171] Specific behavior:

[0172] The device displays a notification to the person in charge, who then checks the notification in the email app on their smartphone or tablet.

[0173] The user (person in charge) visits the base station, checks the battery condition on-site, and replaces the battery if necessary.

[0174] Output: Check battery condition and replace battery if necessary.

[0175] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[0176] (Application example 1)

[0177] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0178] In factories, there is a need to improve the operational efficiency of equipment by properly assessing the battery life of robots and machinery and performing timely maintenance. However, current systems make it difficult to monitor battery status in real time and respond appropriately, resulting in issues such as unplanned equipment shutdowns and repairs. In particular, maintenance personnel must individually check the battery status at each location in the factory, which is labor-intensive and time-consuming.

[0179] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0180] In this invention, the server includes means for collecting monitoring data from base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying devices that require on-site inspection based on the analysis results, and means for a person in charge to check the status of the devices on-site and perform maintenance as necessary. This enables the battery life of robots and machines in a factory to be appropriately evaluated, and enables maintenance personnel to take timely action.

[0181] "Monitoring Data" means information collected to verify the proper operation of a device.

[0182] "Battery-related data" refers to data including information necessary to indicate the performance and status of the battery, such as voltage, current, and temperature.

[0183] "Filtering" is the process of selecting only specific information that meets a purpose from collected data.

[0184] "Inspection result data" refers to information recorded as a result of past maintenance or inspections.

[0185] "Analysis" is the detailed examination of collected data to extract meaningful information and patterns.

[0186] "Battery life" refers to the period of time a battery can be used before it becomes unusable due to deterioration or wear.

[0187] "On-site inspection" refers to the process of visiting the actual installation site of the equipment to check its specific condition and carrying out maintenance as necessary.

[0188] "Listing" means compiling a list of objects based on specific criteria.

[0189] "Notification" is the act of conveying necessary information to relevant personnel or systems.

[0190] The system of the present invention is designed to monitor the battery status of robots and machines in a factory and appropriately evaluate their lifespan. The system is composed of a server, multiple terminals, and users.

[0191] System Configuration

[0192] server:

[0193] Battery monitoring data is collected from each robot and machine in the factory.

[0194] Filter the collected data to extract only the battery-related data.

[0195] The filtered data and past inspection result data are analyzed to assess the battery life.

[0196] Based on the evaluation results, a list of robots and machines that require on-site inspection will be made.

[0197] For listed devices, a notification is sent to the maintenance personnel.

[0198] Devices (smartphones, tablets, smart glasses, head-mounted displays):

[0199] Receive a notification from the server and notify the person in charge that an on-site inspection is required.

[0200] The person in charge will use the terminal to conduct an on-site inspection based on the received notification and perform maintenance such as battery replacement as necessary.

[0201] Hardware and Software

[0202] Hardware:

[0203] Robots and machines in factories: equipped with sensors to collect monitoring data.

[0204] Maintenance personnel's devices: smartphones, tablets, smart glasses, head-mounted displays.

[0205] software:

[0206] Data collection module: Uses Python, Node.js, etc.

[0207] Database management system: MySQL, PostgreSQL, etc.

[0208] Data analysis module: Uses Python's Pandas and NumPy libraries.

[0209] Notification system: Uses Firebase, etc.

[0210] Specific examples of processing

[0211] For example, a case where the battery status of a robot with ID "R001" is monitored will be described.

[0212] 1. Data Collection:

[0213] The server collects monitoring data from the robot "R001", and the collected data is stored in a database.

[0214] 2. Data filtering:

[0215] The server filters the collected data and extracts relevant data such as battery voltage and temperature.

[0216] 3. Data analysis and lifespan assessment:

[0217] The server analyzes the filtered data and past inspection results, and evaluates the remaining battery life based on battery deterioration patterns and low voltage.

[0218] 4. Generate and notify site inspection list:

[0219] The server adds the robot "R001" that is evaluated as nearing the end of its life to the on-site inspection list and notifies the person in charge.

[0220] 5. Site inspection and maintenance:

[0221] The person in charge will receive a notification and use a smartphone or tablet to inspect the robot "R001" on-site and replace the battery if necessary.

[0222] An example of a prompt to input to a generative AI model is as follows:

[0223] "Write Python code to assess the battery life of robots in a factory and notify them of required maintenance."

[0224] In this way, the system can properly assess the battery status of robots and machines in factories and achieve efficient maintenance.

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] Data collection

[0228] The server collects battery monitoring data from each robot and machine in the factory. Specifically, it periodically obtains data such as voltage, current, and temperature from sensors installed on each robot and machine and stores it in a database. The input is the monitoring data obtained from each robot and machine, and the output is the monitoring data stored in the database. The Python requests library is used to obtain the data.

[0229] Step 2:

[0230] Data Filtering

[0231] The server filters the collected monitoring data and extracts only battery-related data. For example, it selects only low-voltage data where the voltage is below a certain value. This filtering process uses the Python Pandas library. The input is the monitoring data stored in the database, and the output is the filtered battery-related data.

[0232] Step 3:

[0233] Obtaining past inspection result data

[0234] The server retrieves past inspection result data from the database. This includes past maintenance history and inspection evaluation results. The input is the past inspection result data stored in the database, and the output is the retrieved inspection result data. An SQL query is used to retrieve the data.

[0235] Step 4:

[0236] Data analysis and battery life evaluation

[0237] The server uses the filtered data and past inspection result data to perform analysis to evaluate the battery lifespan. Specifically, it analyzes voltage drop patterns and alarm occurrence frequency over time to evaluate the degree of battery deterioration. This analysis process uses Python's NumPy and SciPy libraries. The input is the filtered data and inspection result data, and the output is the estimated battery lifespan.

[0238] Step 5:

[0239] Generate and notify site survey list

[0240] Based on the analysis results, the server generates a list of robots and machines that are nearing the end of their lifespan and notifies the maintenance staff. For example, it creates a notification that reads, "Robot R001 has one month left of battery life, so an on-site inspection is required." The input is the analysis results, and the output is the notification sent to the maintenance staff. Firebase and Twilio are used to send the notifications.

[0241] Step 6:

[0242] Site inspection and maintenance

[0243] The user (maintenance personnel) receives the notification and uses a smartphone or tablet to conduct on-site inspections of the robots and machines. Specifically, they check the batteries of the designated robots and replace them if necessary. The input is the notified on-site inspection list, and the output is the on-site inspection results and the details of the maintenance performed.

[0244] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0245] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[0246] System Configuration

[0247] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[0248] Program Operation

[0249] Data collection

[0250] The server periodically collects monitoring data from each base station. The monitoring data includes information such as voltage, temperature, and current. For example, data is obtained from base station ABC every day and stored in a database.

[0251] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[0252] Data Filtering

[0253] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[0254] Time Series Analysis

[0255] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[0256] Inspection history analysis

[0257] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0258] Battery Life Rating

[0259] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0260] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[0261] Field survey list generation and notification

[0262] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[0263] The server generates a notification message based on the list of base stations that require site inspection, for example, "Base station ABC has 3 months of battery life remaining. Site inspection is required."

[0264] The terminal sends a notification message to the user (person in charge), who receives and confirms the notification on the terminal.

[0265] Emotion analysis using an emotion engine

[0266] The emotion engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion engine will recognize that.

[0267] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[0268] Preparation and implementation of on-site surveys

[0269] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0270] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the records.

[0271] Specific examples

[0272] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection results indicated battery degradation. The server determines that the battery has three months or less of life remaining and adds base station ABC to the site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time: "Base station ABC has three months of battery life remaining. Please schedule a site inspection."

[0273] The person in charge checks the notification, prepares for an on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing the battery if necessary, the stability of the system is ensured.

[0274] This embodiment enables accurate evaluation of battery life and timely maintenance, improving the stability of communication services. In addition, by combining it with an emotion engine, the burden on personnel is reduced and efficient business management is achieved.

[0275] The processing flow will be explained below.

[0276] Step 1:

[0277] Data collection

[0278] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database. It also retrieves past inspection result data from the database to create a comprehensive data set.

[0279] Step 2:

[0280] Data Filtering

[0281] The server filters the collected monitoring data for battery-related data, for example by extracting "low voltage" alarm data, thereby consolidating information about the battery's status.

[0282] Step 3:

[0283] Time Series Analysis

[0284] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0285] Step 4:

[0286] Inspection history analysis

[0287] The server analyzes past inspection data and evaluates battery replacement history and status, for example, checking to see if the battery has been replaced for more than a year since the last inspection and whether any deterioration was reported at the time of inspection.

[0288] Step 5:

[0289] Battery Life Rating

[0290] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. It estimates the remaining life based on the alarm frequency and inspection history. For example, if the evaluation result is below a reference value (e.g., less than 3 months remaining), it reports that fact.

[0291] Step 6:

[0292] Field survey list generation

[0293] The server generates a list of base stations that are assessed to be nearing the end of their lifespan, thereby clarifying which base stations require on-site inspection.

[0294] Step 7:

[0295] Notification generation

[0296] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it generates a notification saying, "Base station A has 3 months of battery life remaining. On-site inspection is required."

[0297] Step 8:

[0298] Send notifications

[0299] The terminal sends a notification message to the user's (person in charge) device, who receives and confirms the notification on the terminal.

[0300] Step 9:

[0301] Emotion analysis

[0302] The emotion engine analyzes the user's reaction when receiving a notification and extracts the user's emotions. For example, it analyzes the user's facial expressions when viewing the notification and the operation log to determine the user's emotions.

[0303] Step 10:

[0304] Notification content optimization

[0305] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if it determines that the user is busy, it will adjust the content of the next notification to be less tedious.

[0306] Step 11:

[0307] Field survey preparation

[0308] The user (person in charge) checks the notification and prepares for the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0309] Step 12:

[0310] Conducting on-site surveys

[0311] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the results.

[0312] Through the above steps, the server, terminal, user, and emotion engine cooperate to manage the battery life and perform maintenance at the appropriate time.

[0313] Example 2

[0314] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0315] There is a need to accurately assess the battery life of base stations and enable timely on-site inspections and maintenance. However, current systems often provide inaccurate battery life assessments and inappropriate notification content and timing, placing a heavy burden on personnel and potentially compromising the stability of communication services. Furthermore, notifications that do not take into account personnel's emotions or circumstances make efficient work management difficult, which is an issue.

[0316] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0317] In this invention, the server includes means for collecting monitoring data of base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying the user of the list of base stations that require on-site inspection, and means for analyzing the user's emotions and adjusting the content and transmission timing of notification messages based on the emotion data. This enables accurate evaluation of battery life, timely on-site inspections, and efficient business management while reducing the burden on personnel.

[0318] A "base station" is a device that functions as a relay point in a communication network and provides monitoring data such as voltage, temperature, and current.

[0319] "Server" refers to a computer system that processes and analyzes collected monitoring data, and evaluates, lists, and notifies users of battery life.

[0320] "Terminal" means a device that sends notification messages to a user and allows the user to receive and check notifications.

[0321] "User" refers to the person who receives the notification message and performs on-site inspections and maintenance.

[0322] The "emotion engine" is a system that analyzes the user's reaction to notifications received and extracts and evaluates the user's emotional data.

[0323] "Monitoring data" refers to data such as voltage, temperature, and current collected from a base station.

[0324] "Filtering" refers to the process of selecting data that meets specific conditions from collected data.

[0325] "Inspection result data" refers to data including the history of past battery inspections and replacements.

[0326] "Battery life" is a concept that evaluates the usable period of a battery and estimates its remaining life.

[0327] "Notification" refers to an information message sent from a server to a user through a terminal.

[0328] "On-site inspection" refers to the process in which the user actually goes to the site (base station) and inspects and evaluates the condition of the battery.

[0329] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[0330] System Configuration

[0331] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[0332] Program Operation

[0333] Data collection

[0334] The server periodically collects monitoring data from each base station. This includes information such as voltage, temperature, and current. For example, data is obtained from the base station on a daily basis and stored in a database. A relational database such as MySQL or PostgreSQL is used for this purpose. The server also obtains past inspection result data from the database. This includes battery replacement history and detailed inspection results.

[0335] Data Filtering

[0336] The server filters the collected monitoring data related to the battery. For example, to extract only "low voltage" alarms, it uses a SELECT statement to narrow down the data where the voltage is below a reference value.

[0337] Time Series Analysis

[0338] The server analyzes the filtered alarm data in time series to extract its frequency and patterns. It verifies that five "low voltage" alarms have occurred in the past month. It uses the Python pandas library to process time series data.

[0339] Inspection history analysis

[0340] The server analyzes the collected inspection data and evaluates the battery replacement history and status, for example using an SQL query to verify that the battery has not been replaced for more than a year since the last inspection.

[0341] Battery Life Rating

[0342] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. Machine learning models (e.g., regression models and random forests) are used to estimate the remaining battery life based on alarm frequency and inspection history. If the remaining battery life is determined to be below a certain threshold (e.g., less than three months), the server lists the base station as requiring an on-site inspection.

[0343] Field survey list generation and notification

[0344] The server generates a list of base stations that are evaluated as being nearing the end of their lifespan. It compiles information such as the ID and location of base stations that require an on-site inspection into a list and generates a notification message. For example, it creates a message stating, "Base station ABC has three months of battery life remaining. An on-site inspection is required," and the device sends this notification message to the user (person in charge). Notification methods include push notifications and SMS.

[0345] Emotion analysis using an emotion engine

[0346] The emotion engine analyzes the user's reaction to the notification they receive and extracts the user's emotion. By analyzing the time it takes the user to check the notification and their reaction speed, it evaluates whether the user is feeling stressed or has the time to tackle the task. Based on the analysis results, the emotion engine adjusts the content and sending timing of the notification message. For example, if the emotion engine determines that the user is busy, it will adjust the timing of the next notification to reduce the user's stress.

[0347] Preparation and implementation of on-site surveys

[0348] The user (person in charge) receives the notification and prepares for the on-site inspection. He / she sets the inspection schedule and prepares the necessary tools and equipment. The user (person in charge) then actually goes to the site (base station) and inspects the batteries of the listed base stations. If necessary, he / she replaces the batteries and updates the database with the results.

[0349] Specific examples

[0350] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has three months or less of remaining life and adds base station ABC to the on-site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Base station ABC's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing it if necessary, system stability can be ensured.

[0351] Example prompt sentence:

[0352] "Base station ABC has 3 months of battery life remaining. Please schedule a site inspection."

[0353] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0354] Step 1:

[0355] The server periodically collects monitoring data from each base station.

[0356] (Input) Monitoring data such as voltage, temperature, and current from each base station.

[0357] (Data processing / calculation) Obtain monitoring data via an interface and store it in a database. Specifically, collect data via API and insert it into a database (MongoDB, MySQL, etc.).

[0358] (Output) Monitoring data stored in a database.

[0359] Step 2:

[0360] The server retrieves past inspection result data from the database.

[0361] (Input) Inspection result data in the database.

[0362] (Data processing / calculation) Use SQL queries to extract the necessary inspection result data.

[0363] (Output) The inspection result data obtained.

[0364] Step 3:

[0365] The server filters data relating to the battery from the collected monitoring data.

[0366] (Input) Monitoring data collected in step 1.

[0367] (Data processing / calculation) Data with voltage below a standard value is sorted out using SQL queries and filtering algorithms.

[0368] (Output) Filtered low voltage alarm data.

[0369] Step 4:

[0370] The server analyzes the filtered alarm data in chronological order and extracts its frequency and patterns.

[0371] (Input) Low voltage alarm data obtained in step 3.

[0372] (Data processing / calculation) Use Python's pandas library to perform time series analysis of the data, for example, to count the number of low voltage alarms that occurred over the past month.

[0373] (Output) Time-series analyzed low voltage alarm data.

[0374] Step 5:

[0375] The server analyzes the collected inspection result data and evaluates the battery replacement history and condition.

[0376] (Input) Inspection result data obtained in Step 2.

[0377] (Data processing / calculation) Use SQL queries to examine exchange history and calculate time since last exchange.

[0378] (Output) Battery replacement history and evaluation results.

[0379] Step 6:

[0380] The server evaluates the battery life based on the results of time series analysis and inspection history analysis.

[0381] (Input) Data obtained in Steps 4 and 5.

[0382] (Data processing / calculation) Remaining lifespan is estimated using machine learning models (e.g., regression models and random forests).

[0383] (Output) Estimated remaining battery life.

[0384] Step 7:

[0385] The server generates a list of base stations that are assessed to be nearing the end of their life.

[0386] (Input) Estimated remaining battery life from step 6.

[0387] (Data processing / calculation) List base stations whose remaining lifespan is below a standard value (e.g., less than 3 months).

[0388] (Output) List of base stations that require site inspection.

[0389] Step 8:

[0390] The server generates a notification message based on the list of base stations that require on-site inspection.

[0391] (Input) The base station list generated in step 7.

[0392] (Data processing / calculation) A notification message is generated, for example, "Base station ABC has 3 months of battery life remaining. An on-site inspection is required."

[0393] (Output) The generated notification message.

[0394] Step 9:

[0395] The terminal sends a notification message to the user (person in charge).

[0396] (Input) The notification message generated in step 8.

[0397] (Data processing / calculation) Send messages to users using push notifications or SMS.

[0398] (Output) The notification message to be sent to the user.

[0399] Step 10:

[0400] The emotion engine analyzes the user's reaction to the notifications they receive.

[0401] (Input) User notification confirmation time and reaction speed.

[0402] (Data processing / computation) Use sentiment analysis algorithms to evaluate the emotions users have about notifications.

[0403] (Output) Parsed emotion data.

[0404] Step 11:

[0405] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotional data.

[0406] (Input) Emotion data parsed in step 10.

[0407] (Data processing / calculation) A prompt sentence is generated, and if the user feels busy, for example, the timing of the next notification is adjusted appropriately.

[0408] (Output) Adjusted notification message content and sending timing.

[0409] Step 12:

[0410] The user (person in charge) receives the notification and prepares for the on-site investigation.

[0411] (Input) The notification messages sent in Step 9 and Step 11.

[0412] (Data processing / calculation) Set the survey schedule and prepare the necessary tools and equipment.

[0413] (Output) The completed site survey plan.

[0414] Step 13:

[0415] The user (person in charge) goes to the site and checks the batteries of the listed base stations.

[0416] (Input) The site investigation plan prepared in step 12.

[0417] (Data processing / calculation) Inspection work is carried out, batteries are replaced if necessary, and the results are recorded in the database.

[0418] (Output) Updated inspection result data and replacement history.

[0419] (Application example 2)

[0420] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0421] The problem to be solved by this invention is a system for evaluating the battery life of robots in factories, improving the efficiency of their management, and providing maintenance notifications at appropriate times. In the past, it was difficult to effectively manage the battery life of robots in factories and perform appropriate maintenance, which could result in an impact on the operation of the robots. Furthermore, there was a need for a method for providing notifications efficiently while reducing the burden on maintenance personnel.

[0422] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0423] In this invention, the server includes means for collecting base station monitoring data, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations requiring on-site inspection based on the evaluation results, means for notifying the user of the list of base stations requiring on-site inspection, and means for analyzing the user's emotions and optimizing the content and transmission timing of the notification message. This enables accurate evaluation of the robot's battery life, optimal timing for on-site inspection, and efficient maintenance.

[0424] A "base station" is a device that is a relay point in a communication network and provides monitoring data.

[0425] "Monitoring data" refers to data such as voltage, temperature, and current collected from the base station.

[0426] "Battery-related data" refers to information from the monitoring data that relates to the state and lifespan of the battery.

[0427] "Filtering" refers to the process of extracting data that meets specific conditions from collected monitoring data.

[0428] "Inspection result data" refers to records of past inspections and data related to the results of those inspections.

[0429] "Analysis" refers to the process of performing calculations and evaluations based on data to predict the battery's condition and lifespan.

[0430] "Battery life assessment" refers to predicting the remaining life of a battery based on data analyzed by the server.

[0431] "On-site inspection" refers to actually visiting a base station to replace or perform maintenance on batteries.

[0432] "Emotion analysis" refers to extracting and analyzing the emotions of a user based on the user's emotional data.

[0433] An embodiment of the present invention is described in detail below. The present invention relates to a battery management system for robots in a factory. The system includes multiple robots, a server, a user, and an emotion analysis engine. This system can accurately evaluate the battery life of the robots and enable timely on-site inspection and maintenance.

[0434] System Configuration

[0435] This system consists of a robot, a server, a user, and a sentiment analysis engine. The robot operates in the factory and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The user receives notifications and performs on-site inspections. The sentiment analysis engine analyzes user emotions and optimizes the content and timing of notifications.

[0436] Program Operation

[0437] Data collection

[0438] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[0439] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[0440] Data Filtering

[0441] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[0442] Time Series Analysis

[0443] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[0444] Inspection history analysis

[0445] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0446] Battery Life Rating

[0447] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0448] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the robot as one that requires on-site inspection.

[0449] Field survey list generation and notification

[0450] The server generates a list of robots that are assessed as nearing the end of their lifespan, making it clear which robots need to be investigated.

[0451] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[0452] The user (person in charge) receives and confirms the notification message from the server.

[0453] Emotion analysis using an emotion analysis engine

[0454] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[0455] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[0456] Preparation and implementation of on-site surveys

[0457] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0458] The user (person in charge) visits the site, inspects the batteries of the listed robots, replaces the batteries as necessary, and updates the database with the results.

[0459] Specific examples

[0460] For example, the server collects and analyzes the following data for Robot A in a factory: Five "low voltage" alarms occurred in the past month, and the results of the last inspection indicated battery degradation. The server determines that the battery has three months or less of life left and adds Robot A to the on-site inspection list. The sentiment analysis engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Robot A's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects Robot A. System stability is ensured by checking the battery status on-site and replacing it if necessary.

[0461] Prompt Sentence Examples

[0462] prompt:

[0463] "Please describe a system that combines battery life assessment for factory robots and optimal notification timing. Please include the following elements: data collection, data analysis, life assessment, notification generation, notification delivery, and sentiment analysis."

[0464] Expected output:

[0465] "The robots in the factory use sensors to collect monitoring data on battery voltage, temperature, and current, and send it to a server. The server analyzes the collected data and evaluates battery life. When a robot's lifespan is shortened, an emotion analysis engine analyzes the emotions of the person in charge and sends a maintenance notification at the optimal time. Once the maintenance is completed, the results are updated in the database to ensure the stability of the system."

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Processing step flow

[0468] Step 1: Data collection

[0469] Specific behavior:

[0470] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[0471] Input: Monitoring data such as voltage, temperature, and current obtained from sensors inside the robot.

[0472] Output: Monitoring data stored in a database. The monitoring data is recorded in the database along with the date.

[0473] Step 2: Data filtering

[0474] Specific behavior:

[0475] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[0476] Input: All monitoring data stored in the database.

[0477] Output: Filtered battery related data. Data for "low voltage" alarms is extracted.

[0478] Step 3: Obtaining inspection result data

[0479] Specific behavior:

[0480] The server retrieves past inspection result data from a database, including battery replacement history and detailed inspection results.

[0481] Input: Inspection result data stored in the database.

[0482] Output: Obtained past inspection result data. The server reads the inspection result information into memory.

[0483] Step 4: Time series analysis

[0484] Specific behavior:

[0485] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0486] Input: Filtered alarm data.

[0487] Output: Analysis results (alarm occurrence frequency and pattern). The server records the result that a "low voltage" alarm has occurred five times in the past month.

[0488] Step 5: Inspection history analysis

[0489] Specific behavior:

[0490] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0491] Input: Obtained inspection result data.

[0492] Output: Analysis results (battery replacement history and status). Information that the battery has not been replaced for over a year is recorded.

[0493] Step 6: Evaluate battery life

[0494] Specific behavior:

[0495] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0496] Input: Time series analysis results and inspection history analysis results.

[0497] Output: Battery life assessment result. Information indicating that the remaining battery life is less than 3 months is recorded.

[0498] Step 7: Generate a site inspection list

[0499] Specific behavior:

[0500] The server generates a list of robots that are assessed to be nearing the end of their lifespan, making it clear which robots need to be investigated.

[0501] Input: Battery life assessment results.

[0502] Output: List of robots that require on-site investigation. A list of robots that require investigation is generated.

[0503] Step 8: Generate and send a notification message

[0504] Specific behavior:

[0505] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[0506] Input: List of robots that require on-site inspection.

[0507] Output: Notification message. A notification message is sent to the user's terminal.

[0508] Step 9: Sentiment analysis using a sentiment analysis engine

[0509] Specific behavior:

[0510] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[0511] Input: User response data.

[0512] Output: Parsed emotion data. Information that the user is feeling stressed is recorded.

[0513] Step 10: Optimize notification timing

[0514] Specific behavior:

[0515] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[0516] Input: Parsed emotion data.

[0517] Output: Optimized notification timing. Notifications are sent at the best possible time for the user.

[0518] Step 11: Prepare and conduct the site survey

[0519] Specific behavior:

[0520] The user (person in charge) receives the notification and prepares for the on-site inspection. They set up an inspection schedule and prepare the necessary tools and equipment. The user then goes to the site and checks the batteries of the listed robots. They replace the batteries as necessary and update the database with the records.

[0521] Input: Notification message and required investigation tools.

[0522] Output: Updated inspection result data. The results of the on-site inspection and battery replacement are recorded in the database.

[0523] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0524] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0525] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0526] [Second embodiment]

[0527] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0528] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0529] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0530] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0531] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0532] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0533] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0534] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0535] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0536] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0537] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0538] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0539] The present invention is described in detail below with reference to an embodiment thereof. The purpose of this system is to accurately evaluate the battery life of a base station and to realize timely on-site inspection and maintenance, thereby improving the stability of communication services and optimizing resources.

[0540] System Configuration

[0541] This system consists of a base station, a server, and a terminal. The base station is a relay point or access point for wireless communication in the communication network and provides the necessary monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal notifies the person in charge of the need for a field survey and is used by the person in charge to carry out the field survey.

[0542] Program Operation

[0543] 1. Data Collection

[0544] The server periodically collects monitoring data from each base station. For example, it receives data from base station ABC every day and stores it in a database.

[0545] The server also retrieves past inspection result data from the database, including battery replacement history and inspection results.

[0546] 2. Data Analysis

[0547] The server filters the monitoring data stored in the database and extracts only battery-related data, for example, "low voltage" alarm data for base station ABC.

[0548] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. It confirms that "low voltage" alarms have occurred five times in the past month.

[0549] The server analyzes the inspection result data and evaluates the battery replacement history and inspection results, for example, to verify that the last replacement was more than a year ago.

[0550] 3. Battery life evaluation

[0551] The server then runs an algorithm to assess battery life based on the analysis results, for example, if there is a high frequency of alarms or if inspection history indicates that the battery is deteriorating, and estimates the remaining battery life.

[0552] As a result of the evaluation, the server determines that the battery life is below a standard value (for example, less than three months remaining) and lists the base station as one that requires on-site inspection.

[0553] 4. Field survey list generation and notification

[0554] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies personnel of the need for an on-site inspection. For example, it creates a notification saying, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[0555] The terminal sends a notification to the person in charge, who then confirms it.

[0556] 5. Conducting on-site surveys

[0557] The user (person in charge) receives the notification, goes to base station ABC, and checks the actual battery condition on-site. If necessary, the battery is replaced to ensure the stability of the system.

[0558] Specific examples

[0559] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[0560] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] Data collection

[0564] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database.

[0565] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[0566] Step 2:

[0567] Data Filtering

[0568] The server filters the collected monitoring data for battery-related alarm data, for example, extracting only "low voltage" alarms.

[0569] Step 3:

[0570] Time Series Analysis

[0571] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0572] Step 4:

[0573] Inspection history analysis

[0574] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0575] Step 5:

[0576] Battery Life Rating

[0577] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0578] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[0579] Step 6:

[0580] Field survey list generation

[0581] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[0582] Step 7:

[0583] Notification generation

[0584] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it creates a notification with the content "Base station A has 3 months of battery life remaining. On-site inspection is required."

[0585] Step 8:

[0586] Send notifications

[0587] The terminal sends a notification message to the person in charge, who receives and confirms the notification on the terminal.

[0588] Step 9:

[0589] Preparation for field survey

[0590] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0591] Step 10:

[0592] Conducting on-site surveys

[0593] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the records in the database.

[0594] Through the above steps, the server, terminal, and user can cooperate to manage the battery life and perform maintenance at the appropriate time.

[0595] Example 1

[0596] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0597] There is a need to accurately assess the lifespan of power supply equipment (batteries) at base stations in communication networks and to carry out on-site inspections and maintenance when necessary. However, with conventional systems, it is difficult to predict the deterioration of power supply equipment and respond in a timely manner, which can result in a loss of stability in communication services. To address this, there is a need for more accurate and efficient methods to assess the lifespan of power supply equipment and notify the need for on-site inspections.

[0598] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0599] In this invention, the server includes means for collecting monitoring data, means for filtering the collected monitoring data to extract data related to the power supply devices, means for acquiring past operational inspection data, means for analyzing the filtered data and the past operational inspection data to evaluate the usable life of the power supply devices, means for selecting communication devices requiring on-site inspection based on the evaluation results, and means for notifying the list of communication devices requiring on-site inspection. This makes it possible to accurately evaluate the life of power supply devices in a communication network and to perform on-site inspections and maintenance in a timely manner.

[0600] "Monitoring data" refers to information relating to the operating status and performance of communication devices such as base stations.

[0601] "Filtering" is the process of extracting information that meets specific conditions from collected data and removing unnecessary information.

[0602] "Power Supply" means a battery or other power supply unit that provides power to a communications device.

[0603] "Operational inspection data" refers to records and history of inspection work carried out on communication devices in the past.

[0604] "Available life" refers to the estimated period of time that the power supply device can continue to function normally.

[0605] The term "communication device" refers to all devices, including base stations, for transmitting and receiving data in a communication network.

[0606] A "server" is a computer system that collects, analyzes, and notifies data.

[0607] The system of the present invention is designed to accurately assess the lifespan of base station power supplies (batteries) in communication networks and to perform on-site inspections and maintenance in a timely manner, thereby maintaining the stability of communication services and optimizing resources.

[0608] System Configuration

[0609] This system mainly consists of the following hardware and software:

[0610] Base Station: Acts as a relay or access point in the communication network and provides the necessary monitoring data.

[0611] Server: The main device that collects, analyzes, evaluates, and notifies data. Data is managed using a database system (e.g., MySQL), and analysis is performed using a programming language such as Python.

[0612] Terminal: A device used to notify personnel of the need for on-site inspections. It can be a smartphone, tablet, or PC.

[0613] Data collection

[0614] The server periodically collects monitoring data from each base station. For example, the server uses SNMP (Simple Network Management Protocol) to obtain data from the base station and stores it in a MySQL database. The collected data includes battery level, voltage value, alarm status, etc. The server also obtains inspection results and replacement history data from the same database. This is done using SQL queries.

[0615] Data analysis

[0616] The server analyzes the monitoring data stored in the database and filters it to extract battery-related data. For example, it executes the SQL query "SELECT FROM MonitoringData WHERE AlarmType='LowVoltage'" to extract only "low voltage" alarm data. The server then analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. The server then analyzes inspection result data and evaluates battery replacement history and inspection results.

[0617] Battery Life Rating

[0618] The server executes a battery life evaluation algorithm based on the analysis results. For example, it evaluates in Python "if alarm occurrence count > 5 or last replacement date > 365 days: remaining life = estimated value." Based on this evaluation result, if the battery life is below the standard value, the base station is listed as requiring an on-site inspection.

[0619] Field survey list generation and notification

[0620] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies the person in charge of the need for an on-site inspection. For example, it sends an email using the SMTP protocol stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required." In response, the terminal displays a notification to the person in charge.

[0621] Conducting on-site surveys

[0622] The user (person in charge) receives the notification, goes to the base station, checks the battery status on-site, and replaces the battery if necessary to ensure system stability.

[0623] Specific examples

[0624] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[0625] Prompt Sentence Examples

[0626] An example of a prompt to input to a generative AI model is as follows:

[0627] "Please prepare an analytical report on the battery life assessment for base station ABC. Based on the frequency of 'low voltage' alarms over the past month and inspection history, estimate the remaining life to be less than 3 months. Please also include a notice to the responsible party that an on-site inspection is required."

[0628] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[0629] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0630] Step 1: Data collection

[0631] Input: Monitoring data from base stations and past inspection result data in the database.

[0632] Specific behavior:

[0633] The server acquires monitoring data from each base station using SNMP (Simple Network Management Protocol). For example, data is acquired from base station ABC at midnight every day and stored in a MySQL database.

[0634] The server retrieves the inspection results and battery replacement history data from the database using an SQL query, for example, "SELECT FROM BatteryCheckResults WHERE BaseStationID='ABC'".

[0635] Output: Collected monitoring data and historical inspection result data.

[0636] Step 2: Data filtering

[0637] Input: Collected monitoring data.

[0638] Specific behavior:

[0639] The server parses the monitoring data and extracts only the battery-related data, for example by executing the SQL query "SELECT FROM MonitoringData WHERE BaseStationID='ABC' AND AlarmType='LowVoltage'".

[0640] Filtered data includes voltage values, alarm conditions, battery levels, etc.

[0641] Output: Filtered monitoring data.

[0642] Step 3: Frequency analysis

[0643] Input: Filtered monitoring data.

[0644] Specific behavior:

[0645] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0646] Use a Python script to analyze the timestamps and tally the number of alarms that occurred.

[0647] Output: Alarm occurrence frequency data.

[0648] Step 4: Analyze the inspection results

[0649] Input: Past inspection result data.

[0650] Specific behavior:

[0651] The server analyzes past inspection data and evaluates battery replacement history and inspection results, for example, to verify that the last replacement date was more than one year ago.

[0652] Run an SQL query to retrieve inspection and replacement history (e.g., "SELECT LastInspectionDate FROM BatteryCheckResults WHERE BaseStationID='ABC'").

[0653] Output: Evaluation results of inspection result data.

[0654] Step 5: Battery Life Assessment

[0655] Input: Evaluation results of occurrence frequency data and inspection result data.

[0656] Specific behavior:

[0657] The server runs a battery life assessment algorithm, for example using the following logic: "if alarm count > 5 or last replacement date > 365 days: remaining life = < 3 months".

[0658] Implement conditional branching in a Python script and evaluate lifespan.

[0659] Output: Battery life evaluation results.

[0660] Step 6: Generate a site survey list

[0661] Input: Battery life assessment results.

[0662] Specific behavior:

[0663] The server generates a list of base stations that are evaluated as nearing the end of their life. For example, base station ABC is added to the list.

[0664] Export the list to a CSV file and save it as "surveylist.csv".

[0665] Output: Field survey list.

[0666] Step 7: Create and send a notification

[0667] Input: Field survey list.

[0668] Specific behavior:

[0669] The server creates a notification to the person in charge based on the generated list, for example, creating an email stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[0670] Use the SMTP protocol to send an email with the above content. Specifically, send an email with the following content: "From: server@company.com, To: user@company.com, Subject: On-site inspection notification, Body: Base station ABC has less than 3 months of battery life remaining."

[0671] Output: Notification of need for on-site investigation.

[0672] Step 8: Review the notification and conduct an on-site inspection

[0673] Input: Notification email.

[0674] Specific behavior:

[0675] The device displays a notification to the person in charge, who then checks the notification in the email app on their smartphone or tablet.

[0676] The user (person in charge) visits the base station, checks the battery condition on-site, and replaces the battery if necessary.

[0677] Output: Check battery condition and replace battery if necessary.

[0678] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[0679] (Application example 1)

[0680] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0681] In factories, there is a need to improve the operational efficiency of equipment by properly assessing the battery life of robots and machinery and performing timely maintenance. However, current systems make it difficult to monitor battery status in real time and respond appropriately, resulting in issues such as unplanned equipment shutdowns and repairs. In particular, maintenance personnel must individually check the battery status at each location in the factory, which is labor-intensive and time-consuming.

[0682] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0683] In this invention, the server includes means for collecting monitoring data from base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying devices that require on-site inspection based on the analysis results, and means for a person in charge to check the status of the devices on-site and perform maintenance as necessary. This enables the battery life of robots and machines in a factory to be appropriately evaluated, and enables maintenance personnel to take timely action.

[0684] "Monitoring Data" means information collected to verify the proper operation of a device.

[0685] "Battery-related data" refers to data including information necessary to indicate the performance and status of the battery, such as voltage, current, and temperature.

[0686] "Filtering" is the process of selecting only specific information that meets a purpose from collected data.

[0687] "Inspection result data" refers to information recorded as a result of past maintenance or inspections.

[0688] "Analysis" is the detailed examination of collected data to extract meaningful information and patterns.

[0689] "Battery life" refers to the period of time a battery can be used before it becomes unusable due to deterioration or wear.

[0690] "On-site inspection" refers to the process of visiting the actual installation site of the equipment to check its specific condition and carrying out maintenance as necessary.

[0691] "Listing" means compiling a list of objects based on specific criteria.

[0692] "Notification" is the act of conveying necessary information to relevant personnel or systems.

[0693] The system of the present invention is designed to monitor the battery status of robots and machines in a factory and appropriately evaluate their lifespan. The system is composed of a server, multiple terminals, and users.

[0694] System Configuration

[0695] server:

[0696] Battery monitoring data is collected from each robot and machine in the factory.

[0697] Filter the collected data to extract only the battery-related data.

[0698] The filtered data and past inspection result data are analyzed to assess the battery life.

[0699] Based on the evaluation results, a list of robots and machines that require on-site inspection will be made.

[0700] For listed devices, a notification is sent to the maintenance personnel.

[0701] Devices (smartphones, tablets, smart glasses, head-mounted displays):

[0702] Receive a notification from the server and notify the person in charge that an on-site inspection is required.

[0703] The person in charge will use the terminal to conduct an on-site inspection based on the received notification and perform maintenance such as battery replacement as necessary.

[0704] Hardware and Software

[0705] Hardware:

[0706] Robots and machines in factories: equipped with sensors to collect monitoring data.

[0707] Maintenance personnel's devices: smartphones, tablets, smart glasses, head-mounted displays.

[0708] software:

[0709] Data collection module: Uses Python, Node.js, etc.

[0710] Database management system: MySQL, PostgreSQL, etc.

[0711] Data analysis module: Uses Python's Pandas and NumPy libraries.

[0712] Notification system: Uses Firebase, etc.

[0713] Specific examples of processing

[0714] For example, a case where the battery status of a robot with ID "R001" is monitored will be described.

[0715] 1. Data Collection:

[0716] The server collects monitoring data from the robot "R001", and the collected data is stored in a database.

[0717] 2. Data filtering:

[0718] The server filters the collected data and extracts relevant data such as battery voltage and temperature.

[0719] 3. Data analysis and lifespan assessment:

[0720] The server analyzes the filtered data and past inspection results, and evaluates the remaining battery life based on battery deterioration patterns and low voltage.

[0721] 4. Generate and notify site inspection list:

[0722] The server adds the robot "R001" that is evaluated as nearing the end of its life to the on-site inspection list and notifies the person in charge.

[0723] 5. Site inspection and maintenance:

[0724] The person in charge will receive a notification and use a smartphone or tablet to inspect the robot "R001" on-site and replace the battery if necessary.

[0725] An example of a prompt to input to a generative AI model is as follows:

[0726] "Write Python code to assess the battery life of robots in a factory and notify them of required maintenance."

[0727] In this way, the system can properly assess the battery status of robots and machines in factories and achieve efficient maintenance.

[0728] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0729] Step 1:

[0730] Data collection

[0731] The server collects battery monitoring data from each robot and machine in the factory. Specifically, it periodically obtains data such as voltage, current, and temperature from sensors installed on each robot and machine and stores it in a database. The input is the monitoring data obtained from each robot and machine, and the output is the monitoring data stored in the database. The Python requests library is used to obtain the data.

[0732] Step 2:

[0733] Data Filtering

[0734] The server filters the collected monitoring data and extracts only battery-related data. For example, it selects only low-voltage data where the voltage is below a certain value. This filtering process uses the Python Pandas library. The input is the monitoring data stored in the database, and the output is the filtered battery-related data.

[0735] Step 3:

[0736] Obtaining past inspection result data

[0737] The server retrieves past inspection result data from the database. This includes past maintenance history and inspection evaluation results. The input is the past inspection result data stored in the database, and the output is the retrieved inspection result data. An SQL query is used to retrieve the data.

[0738] Step 4:

[0739] Data analysis and battery life evaluation

[0740] The server uses the filtered data and past inspection result data to perform analysis to evaluate the battery lifespan. Specifically, it analyzes voltage drop patterns and alarm occurrence frequency over time to evaluate the degree of battery deterioration. This analysis process uses Python's NumPy and SciPy libraries. The input is the filtered data and inspection result data, and the output is the estimated battery lifespan.

[0741] Step 5:

[0742] Generate and notify site survey list

[0743] Based on the analysis results, the server generates a list of robots and machines that are nearing the end of their lifespan and notifies the maintenance staff. For example, it creates a notification that reads, "Robot R001 has one month left of battery life, so an on-site inspection is required." The input is the analysis results, and the output is the notification sent to the maintenance staff. Firebase and Twilio are used to send the notifications.

[0744] Step 6:

[0745] Site inspection and maintenance

[0746] The user (maintenance personnel) receives the notification and uses a smartphone or tablet to conduct on-site inspections of the robots and machines. Specifically, they check the batteries of the designated robots and replace them if necessary. The input is the notified on-site inspection list, and the output is the on-site inspection results and the details of the maintenance performed.

[0747] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0748] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[0749] System Configuration

[0750] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[0751] Program Operation

[0752] Data collection

[0753] The server periodically collects monitoring data from each base station. The monitoring data includes information such as voltage, temperature, and current. For example, data is obtained from base station ABC every day and stored in a database.

[0754] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[0755] Data Filtering

[0756] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[0757] Time Series Analysis

[0758] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[0759] Inspection history analysis

[0760] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0761] Battery Life Rating

[0762] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0763] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[0764] Field survey list generation and notification

[0765] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[0766] The server generates a notification message based on the list of base stations that require site inspection, for example, "Base station ABC has 3 months of battery life remaining. Site inspection is required."

[0767] The terminal sends a notification message to the user (person in charge), who receives and confirms the notification on the terminal.

[0768] Emotion analysis using an emotion engine

[0769] The emotion engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion engine will recognize that.

[0770] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[0771] Preparation and implementation of on-site surveys

[0772] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0773] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the records.

[0774] Specific examples

[0775] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection results indicated battery degradation. The server determines that the battery has three months or less of life remaining and adds base station ABC to the site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time: "Base station ABC has three months of battery life remaining. Please schedule a site inspection."

[0776] The person in charge checks the notification, prepares for an on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing the battery if necessary, the stability of the system is ensured.

[0777] This embodiment enables accurate evaluation of battery life and timely maintenance, improving the stability of communication services. In addition, by combining it with an emotion engine, the burden on personnel is reduced and efficient business management is achieved.

[0778] The processing flow will be explained below.

[0779] Step 1:

[0780] Data collection

[0781] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database. It also retrieves past inspection result data from the database to create a comprehensive data set.

[0782] Step 2:

[0783] Data Filtering

[0784] The server filters the collected monitoring data for battery-related data, for example by extracting "low voltage" alarm data, thereby consolidating information about the battery's status.

[0785] Step 3:

[0786] Time Series Analysis

[0787] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0788] Step 4:

[0789] Inspection history analysis

[0790] The server analyzes past inspection data and evaluates battery replacement history and status, for example, checking to see if the battery has been replaced for more than a year since the last inspection and whether any deterioration was reported at the time of inspection.

[0791] Step 5:

[0792] Battery Life Rating

[0793] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. It estimates the remaining life based on the alarm frequency and inspection history. For example, if the evaluation result is below a reference value (e.g., less than 3 months remaining), it reports that fact.

[0794] Step 6:

[0795] Field survey list generation

[0796] The server generates a list of base stations that are assessed to be nearing the end of their lifespan, thereby clarifying which base stations require on-site inspection.

[0797] Step 7:

[0798] Notification generation

[0799] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it generates a notification saying, "Base station A has 3 months of battery life remaining. On-site inspection is required."

[0800] Step 8:

[0801] Send notifications

[0802] The terminal sends a notification message to the user's (person in charge) device, who receives and confirms the notification on the terminal.

[0803] Step 9:

[0804] Emotion analysis

[0805] The emotion engine analyzes the user's reaction when receiving a notification and extracts the user's emotions. For example, it analyzes the user's facial expressions when viewing the notification and the operation log to determine the user's emotions.

[0806] Step 10:

[0807] Notification content optimization

[0808] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if it determines that the user is busy, it will adjust the content of the next notification to be less tedious.

[0809] Step 11:

[0810] Field survey preparation

[0811] The user (person in charge) checks the notification and prepares for the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0812] Step 12:

[0813] Conducting on-site surveys

[0814] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the results.

[0815] Through the above steps, the server, terminal, user, and emotion engine cooperate to manage the battery life and perform maintenance at the appropriate time.

[0816] Example 2

[0817] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0818] There is a need to accurately assess the battery life of base stations and enable timely on-site inspections and maintenance. However, current systems often provide inaccurate battery life assessments and inappropriate notification content and timing, placing a heavy burden on personnel and potentially compromising the stability of communication services. Furthermore, notifications that do not take into account personnel's emotions or circumstances make efficient work management difficult, which is an issue.

[0819] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0820] In this invention, the server includes means for collecting monitoring data of base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying the user of the list of base stations that require on-site inspection, and means for analyzing the user's emotions and adjusting the content and transmission timing of notification messages based on the emotion data. This enables accurate evaluation of battery life, timely on-site inspections, and efficient business management while reducing the burden on personnel.

[0821] A "base station" is a device that functions as a relay point in a communication network and provides monitoring data such as voltage, temperature, and current.

[0822] "Server" refers to a computer system that processes and analyzes collected monitoring data, and evaluates, lists, and notifies users of battery life.

[0823] "Terminal" means a device that sends notification messages to a user and allows the user to receive and check notifications.

[0824] "User" refers to the person who receives the notification message and performs on-site inspections and maintenance.

[0825] The "emotion engine" is a system that analyzes the user's reaction to notifications received and extracts and evaluates the user's emotional data.

[0826] "Monitoring data" refers to data such as voltage, temperature, and current collected from a base station.

[0827] "Filtering" refers to the process of selecting data that meets specific conditions from collected data.

[0828] "Inspection result data" refers to data including the history of past battery inspections and replacements.

[0829] "Battery life" is a concept that evaluates the usable period of a battery and estimates its remaining life.

[0830] "Notification" refers to an information message sent from a server to a user through a terminal.

[0831] "On-site inspection" refers to the process in which the user actually goes to the site (base station) and inspects and evaluates the condition of the battery.

[0832] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[0833] System Configuration

[0834] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[0835] Program Operation

[0836] Data collection

[0837] The server periodically collects monitoring data from each base station. This includes information such as voltage, temperature, and current. For example, data is obtained from the base station on a daily basis and stored in a database. A relational database such as MySQL or PostgreSQL is used for this purpose. The server also obtains past inspection result data from the database. This includes battery replacement history and detailed inspection results.

[0838] Data Filtering

[0839] The server filters the collected monitoring data related to the battery. For example, to extract only "low voltage" alarms, it uses a SELECT statement to narrow down the data where the voltage is below a reference value.

[0840] Time Series Analysis

[0841] The server analyzes the filtered alarm data in time series to extract its frequency and patterns. It verifies that five "low voltage" alarms have occurred in the past month. It uses the Python pandas library to process time series data.

[0842] Inspection history analysis

[0843] The server analyzes the collected inspection data and evaluates the battery replacement history and status, for example using an SQL query to verify that the battery has not been replaced for more than a year since the last inspection.

[0844] Battery Life Rating

[0845] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. Machine learning models (e.g., regression models and random forests) are used to estimate the remaining battery life based on alarm frequency and inspection history. If the remaining battery life is determined to be below a certain threshold (e.g., less than three months), the server lists the base station as requiring an on-site inspection.

[0846] Field survey list generation and notification

[0847] The server generates a list of base stations that are evaluated as being nearing the end of their lifespan. It compiles information such as the ID and location of base stations that require an on-site inspection into a list and generates a notification message. For example, it creates a message stating, "Base station ABC has three months of battery life remaining. An on-site inspection is required," and the device sends this notification message to the user (person in charge). Notification methods include push notifications and SMS.

[0848] Emotion analysis using an emotion engine

[0849] The emotion engine analyzes the user's reaction to the notification they receive and extracts the user's emotion. By analyzing the time it takes the user to check the notification and their reaction speed, it evaluates whether the user is feeling stressed or has the time to tackle the task. Based on the analysis results, the emotion engine adjusts the content and sending timing of the notification message. For example, if the emotion engine determines that the user is busy, it will adjust the timing of the next notification to reduce the user's stress.

[0850] Preparation and implementation of on-site surveys

[0851] The user (person in charge) receives the notification and prepares for the on-site inspection. He / she sets the inspection schedule and prepares the necessary tools and equipment. The user (person in charge) then actually goes to the site (base station) and inspects the batteries of the listed base stations. If necessary, he / she replaces the batteries and updates the database with the results.

[0852] Specific examples

[0853] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has three months or less of remaining life and adds base station ABC to the on-site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Base station ABC's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing it if necessary, system stability can be ensured.

[0854] Example prompt sentence:

[0855] "Base station ABC has 3 months of battery life remaining. Please schedule a site inspection."

[0856] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0857] Step 1:

[0858] The server periodically collects monitoring data from each base station.

[0859] (Input) Monitoring data such as voltage, temperature, and current from each base station.

[0860] (Data processing / calculation) Obtain monitoring data via an interface and store it in a database. Specifically, collect data via API and insert it into a database (MongoDB, MySQL, etc.).

[0861] (Output) Monitoring data stored in a database.

[0862] Step 2:

[0863] The server retrieves past inspection result data from the database.

[0864] (Input) Inspection result data in the database.

[0865] (Data processing / calculation) Use SQL queries to extract the necessary inspection result data.

[0866] (Output) The inspection result data obtained.

[0867] Step 3:

[0868] The server filters data relating to the battery from the collected monitoring data.

[0869] (Input) Monitoring data collected in step 1.

[0870] (Data processing / calculation) Data with voltage below a standard value is sorted out using SQL queries and filtering algorithms.

[0871] (Output) Filtered low voltage alarm data.

[0872] Step 4:

[0873] The server analyzes the filtered alarm data in chronological order and extracts its frequency and patterns.

[0874] (Input) Low voltage alarm data obtained in step 3.

[0875] (Data processing / calculation) Use Python's pandas library to perform time series analysis of the data, for example, to count the number of low voltage alarms that occurred over the past month.

[0876] (Output) Time-series analyzed low voltage alarm data.

[0877] Step 5:

[0878] The server analyzes the collected inspection result data and evaluates the battery replacement history and condition.

[0879] (Input) Inspection result data obtained in Step 2.

[0880] (Data processing / calculation) Use SQL queries to examine exchange history and calculate time since last exchange.

[0881] (Output) Battery replacement history and evaluation results.

[0882] Step 6:

[0883] The server evaluates the battery life based on the results of time series analysis and inspection history analysis.

[0884] (Input) Data obtained in Steps 4 and 5.

[0885] (Data processing / calculation) Remaining lifespan is estimated using machine learning models (e.g., regression models and random forests).

[0886] (Output) Estimated remaining battery life.

[0887] Step 7:

[0888] The server generates a list of base stations that are assessed to be nearing the end of their life.

[0889] (Input) Estimated remaining battery life from step 6.

[0890] (Data processing / calculation) List base stations whose remaining lifespan is below a standard value (e.g., less than 3 months).

[0891] (Output) List of base stations that require site inspection.

[0892] Step 8:

[0893] The server generates a notification message based on the list of base stations that require on-site inspection.

[0894] (Input) The base station list generated in step 7.

[0895] (Data processing / calculation) A notification message is generated, for example, "Base station ABC has 3 months of battery life remaining. An on-site inspection is required."

[0896] (Output) The generated notification message.

[0897] Step 9:

[0898] The terminal sends a notification message to the user (person in charge).

[0899] (Input) The notification message generated in step 8.

[0900] (Data processing / calculation) Send messages to users using push notifications or SMS.

[0901] (Output) The notification message to be sent to the user.

[0902] Step 10:

[0903] The emotion engine analyzes the user's reaction to the notifications they receive.

[0904] (Input) User notification confirmation time and reaction speed.

[0905] (Data processing / computation) Use sentiment analysis algorithms to evaluate the emotions users have about notifications.

[0906] (Output) Parsed emotion data.

[0907] Step 11:

[0908] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotional data.

[0909] (Input) Emotion data parsed in step 10.

[0910] (Data processing / calculation) A prompt sentence is generated, and if the user feels busy, for example, the timing of the next notification is adjusted appropriately.

[0911] (Output) Adjusted notification message content and sending timing.

[0912] Step 12:

[0913] The user (person in charge) receives the notification and prepares for the on-site investigation.

[0914] (Input) The notification messages sent in Step 9 and Step 11.

[0915] (Data processing / calculation) Set the survey schedule and prepare the necessary tools and equipment.

[0916] (Output) The completed site survey plan.

[0917] Step 13:

[0918] The user (person in charge) goes to the site and checks the batteries of the listed base stations.

[0919] (Input) The site investigation plan prepared in step 12.

[0920] (Data processing / calculation) Inspection work is carried out, batteries are replaced if necessary, and the results are recorded in the database.

[0921] (Output) Updated inspection result data and replacement history.

[0922] (Application example 2)

[0923] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0924] The problem to be solved by this invention is a system for evaluating the battery life of robots in factories, improving the efficiency of their management, and providing maintenance notifications at appropriate times. In the past, it was difficult to effectively manage the battery life of robots in factories and perform appropriate maintenance, which could result in an impact on the operation of the robots. Furthermore, there was a need for a method for providing notifications efficiently while reducing the burden on maintenance personnel.

[0925] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0926] In this invention, the server includes means for collecting base station monitoring data, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations requiring on-site inspection based on the evaluation results, means for notifying the user of the list of base stations requiring on-site inspection, and means for analyzing the user's emotions and optimizing the content and transmission timing of the notification message. This enables accurate evaluation of the robot's battery life, optimal timing for on-site inspection, and efficient maintenance.

[0927] A "base station" is a device that is a relay point in a communication network and provides monitoring data.

[0928] "Monitoring data" refers to data such as voltage, temperature, and current collected from the base station.

[0929] "Battery-related data" refers to information from the monitoring data that relates to the state and lifespan of the battery.

[0930] "Filtering" refers to the process of extracting data that meets specific conditions from collected monitoring data.

[0931] "Inspection result data" refers to records of past inspections and data related to the results of those inspections.

[0932] "Analysis" refers to the process of performing calculations and evaluations based on data to predict the battery's condition and lifespan.

[0933] "Battery life assessment" refers to predicting the remaining life of a battery based on data analyzed by the server.

[0934] "On-site inspection" refers to actually visiting a base station to replace or perform maintenance on batteries.

[0935] "Emotion analysis" refers to extracting and analyzing the emotions of a user based on the user's emotional data.

[0936] An embodiment of the present invention is described in detail below. The present invention relates to a battery management system for robots in a factory. The system includes multiple robots, a server, a user, and an emotion analysis engine. This system can accurately evaluate the battery life of the robots and enable timely on-site inspection and maintenance.

[0937] System Configuration

[0938] This system consists of a robot, a server, a user, and a sentiment analysis engine. The robot operates in the factory and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The user receives notifications and performs on-site inspections. The sentiment analysis engine analyzes user emotions and optimizes the content and timing of notifications.

[0939] Program Operation

[0940] Data collection

[0941] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[0942] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[0943] Data Filtering

[0944] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[0945] Time Series Analysis

[0946] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[0947] Inspection history analysis

[0948] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0949] Battery Life Rating

[0950] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0951] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the robot as one that requires on-site inspection.

[0952] Field survey list generation and notification

[0953] The server generates a list of robots that are assessed as nearing the end of their lifespan, making it clear which robots need to be investigated.

[0954] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[0955] The user (person in charge) receives and confirms the notification message from the server.

[0956] Emotion analysis using an emotion analysis engine

[0957] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[0958] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[0959] Preparation and implementation of on-site surveys

[0960] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[0961] The user (person in charge) visits the site, inspects the batteries of the listed robots, replaces the batteries as necessary, and updates the database with the results.

[0962] Specific examples

[0963] For example, the server collects and analyzes the following data for Robot A in a factory: Five "low voltage" alarms occurred in the past month, and the results of the last inspection indicated battery degradation. The server determines that the battery has three months or less of life left and adds Robot A to the on-site inspection list. The sentiment analysis engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Robot A's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects Robot A. System stability is ensured by checking the battery status on-site and replacing it if necessary.

[0964] Prompt Sentence Examples

[0965] prompt:

[0966] "Please describe a system that combines battery life assessment for factory robots and optimal notification timing. Please include the following elements: data collection, data analysis, life assessment, notification generation, notification delivery, and sentiment analysis."

[0967] Expected output:

[0968] "The robots in the factory use sensors to collect monitoring data on battery voltage, temperature, and current, and send it to a server. The server analyzes the collected data and evaluates battery life. When a robot's lifespan is shortened, an emotion analysis engine analyzes the emotions of the person in charge and sends a maintenance notification at the optimal time. Once the maintenance is completed, the results are updated in the database to ensure the stability of the system."

[0969] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0970] Processing step flow

[0971] Step 1: Data collection

[0972] Specific behavior:

[0973] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[0974] Input: Monitoring data such as voltage, temperature, and current obtained from sensors inside the robot.

[0975] Output: Monitoring data stored in a database. The monitoring data is recorded in the database along with the date.

[0976] Step 2: Data filtering

[0977] Specific behavior:

[0978] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[0979] Input: All monitoring data stored in the database.

[0980] Output: Filtered battery related data. Data for "low voltage" alarms is extracted.

[0981] Step 3: Obtaining inspection result data

[0982] Specific behavior:

[0983] The server retrieves past inspection result data from a database, including battery replacement history and detailed inspection results.

[0984] Input: Inspection result data stored in the database.

[0985] Output: Obtained past inspection result data. The server reads the inspection result information into memory.

[0986] Step 4: Time series analysis

[0987] Specific behavior:

[0988] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[0989] Input: Filtered alarm data.

[0990] Output: Analysis results (alarm occurrence frequency and pattern). The server records the result that a "low voltage" alarm has occurred five times in the past month.

[0991] Step 5: Inspection history analysis

[0992] Specific behavior:

[0993] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[0994] Input: Obtained inspection result data.

[0995] Output: Analysis results (battery replacement history and status). Information that the battery has not been replaced for over a year is recorded.

[0996] Step 6: Evaluate battery life

[0997] Specific behavior:

[0998] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[0999] Input: Time series analysis results and inspection history analysis results.

[1000] Output: Battery life assessment result. Information indicating that the remaining battery life is less than 3 months is recorded.

[1001] Step 7: Generate a site inspection list

[1002] Specific behavior:

[1003] The server generates a list of robots that are assessed to be nearing the end of their lifespan, making it clear which robots need to be investigated.

[1004] Input: Battery life assessment results.

[1005] Output: List of robots that require on-site investigation. A list of robots that require investigation is generated.

[1006] Step 8: Generate and send a notification message

[1007] Specific behavior:

[1008] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[1009] Input: List of robots that require on-site inspection.

[1010] Output: Notification message. A notification message is sent to the user's terminal.

[1011] Step 9: Sentiment analysis using a sentiment analysis engine

[1012] Specific behavior:

[1013] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[1014] Input: User response data.

[1015] Output: Parsed emotion data. Information that the user is feeling stressed is recorded.

[1016] Step 10: Optimize notification timing

[1017] Specific behavior:

[1018] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[1019] Input: Parsed emotion data.

[1020] Output: Optimized notification timing. Notifications are sent at the best possible time for the user.

[1021] Step 11: Prepare and conduct the site survey

[1022] Specific behavior:

[1023] The user (person in charge) receives the notification and prepares for the on-site inspection. They set up an inspection schedule and prepare the necessary tools and equipment. The user then goes to the site and checks the batteries of the listed robots. They replace the batteries as necessary and update the database with the records.

[1024] Input: Notification message and required investigation tools.

[1025] Output: Updated inspection result data. The results of the on-site inspection and battery replacement are recorded in the database.

[1026] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1027] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1028] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1029] [Third embodiment]

[1030] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1031] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1033] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1034] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1035] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1037] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1038] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1040] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1041] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1042] The present invention is described in detail below with reference to an embodiment thereof. The purpose of this system is to accurately evaluate the battery life of a base station and to realize timely on-site inspection and maintenance, thereby improving the stability of communication services and optimizing resources.

[1043] System Configuration

[1044] This system consists of a base station, a server, and a terminal. The base station is a relay point or access point for wireless communication in the communication network and provides the necessary monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal notifies the person in charge of the need for a field survey and is used by the person in charge to carry out the field survey.

[1045] Program Operation

[1046] 1. Data Collection

[1047] The server periodically collects monitoring data from each base station. For example, it receives data from base station ABC every day and stores it in a database.

[1048] The server also retrieves past inspection result data from the database, including battery replacement history and inspection results.

[1049] 2. Data Analysis

[1050] The server filters the monitoring data stored in the database and extracts only battery-related data, for example, "low voltage" alarm data for base station ABC.

[1051] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. It confirms that "low voltage" alarms have occurred five times in the past month.

[1052] The server analyzes the inspection result data and evaluates the battery replacement history and inspection results, for example, to verify that the last replacement was more than a year ago.

[1053] 3. Battery life evaluation

[1054] The server then runs an algorithm to assess battery life based on the analysis results, for example, if there is a high frequency of alarms or if inspection history indicates that the battery is deteriorating, and estimates the remaining battery life.

[1055] As a result of the evaluation, the server determines that the battery life is below a standard value (for example, less than three months remaining) and lists the base station as one that requires on-site inspection.

[1056] 4. Field survey list generation and notification

[1057] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies personnel of the need for an on-site inspection. For example, it creates a notification saying, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[1058] The terminal sends a notification to the person in charge, who then confirms it.

[1059] 5. Conducting on-site surveys

[1060] The user (person in charge) receives the notification, goes to base station ABC, and checks the actual battery condition on-site. If necessary, the battery is replaced to ensure the stability of the system.

[1061] Specific examples

[1062] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[1063] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[1064] The processing flow will be explained below.

[1065] Step 1:

[1066] Data collection

[1067] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database.

[1068] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[1069] Step 2:

[1070] Data Filtering

[1071] The server filters the collected monitoring data for battery-related alarm data, for example, extracting only "low voltage" alarms.

[1072] Step 3:

[1073] Time Series Analysis

[1074] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1075] Step 4:

[1076] Inspection history analysis

[1077] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[1078] Step 5:

[1079] Battery Life Rating

[1080] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[1081] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[1082] Step 6:

[1083] Field survey list generation

[1084] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[1085] Step 7:

[1086] Notification generation

[1087] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it creates a notification with the content "Base station A has 3 months of battery life remaining. On-site inspection is required."

[1088] Step 8:

[1089] Send notifications

[1090] The terminal sends a notification message to the person in charge, who receives and confirms the notification on the terminal.

[1091] Step 9:

[1092] Preparation for field survey

[1093] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1094] Step 10:

[1095] Conducting on-site surveys

[1096] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the records in the database.

[1097] Through the above steps, the server, terminal, and user can cooperate to manage the battery life and perform maintenance at the appropriate time.

[1098] Example 1

[1099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1100] There is a need to accurately assess the lifespan of power supply equipment (batteries) at base stations in communication networks and to carry out on-site inspections and maintenance when necessary. However, with conventional systems, it is difficult to predict the deterioration of power supply equipment and respond in a timely manner, which can result in a loss of stability in communication services. To address this, there is a need for more accurate and efficient methods to assess the lifespan of power supply equipment and notify the need for on-site inspections.

[1101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1102] In this invention, the server includes means for collecting monitoring data, means for filtering the collected monitoring data to extract data related to the power supply devices, means for acquiring past operational inspection data, means for analyzing the filtered data and the past operational inspection data to evaluate the usable life of the power supply devices, means for selecting communication devices requiring on-site inspection based on the evaluation results, and means for notifying the list of communication devices requiring on-site inspection. This makes it possible to accurately evaluate the life of power supply devices in a communication network and to perform on-site inspections and maintenance in a timely manner.

[1103] "Monitoring data" refers to information relating to the operating status and performance of communication devices such as base stations.

[1104] "Filtering" is the process of extracting information that meets specific conditions from collected data and removing unnecessary information.

[1105] "Power Supply" means a battery or other power supply unit that provides power to a communications device.

[1106] "Operational inspection data" refers to records and history of inspection work carried out on communication devices in the past.

[1107] "Available life" refers to the estimated period of time that the power supply device can continue to function normally.

[1108] The term "communication device" refers to all devices, including base stations, for transmitting and receiving data in a communication network.

[1109] A "server" is a computer system that collects, analyzes, and notifies data.

[1110] The system of the present invention is designed to accurately assess the lifespan of base station power supplies (batteries) in communication networks and to perform on-site inspections and maintenance in a timely manner, thereby maintaining the stability of communication services and optimizing resources.

[1111] System Configuration

[1112] This system mainly consists of the following hardware and software:

[1113] Base Station: Acts as a relay or access point in the communication network and provides the necessary monitoring data.

[1114] Server: The main device that collects, analyzes, evaluates, and notifies data. Data is managed using a database system (e.g., MySQL), and analysis is performed using a programming language such as Python.

[1115] Terminal: A device used to notify personnel of the need for on-site inspections. It can be a smartphone, tablet, or PC.

[1116] Data collection

[1117] The server periodically collects monitoring data from each base station. For example, the server uses SNMP (Simple Network Management Protocol) to obtain data from the base station and stores it in a MySQL database. The collected data includes battery level, voltage value, alarm status, etc. The server also obtains inspection results and replacement history data from the same database. This is done using SQL queries.

[1118] Data analysis

[1119] The server analyzes the monitoring data stored in the database and filters it to extract battery-related data. For example, it executes the SQL query "SELECT FROM MonitoringData WHERE AlarmType='LowVoltage'" to extract only "low voltage" alarm data. The server then analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. The server then analyzes inspection result data and evaluates battery replacement history and inspection results.

[1120] Battery Life Rating

[1121] The server executes a battery life evaluation algorithm based on the analysis results. For example, it evaluates in Python "if alarm occurrence count > 5 or last replacement date > 365 days: remaining life = estimated value." Based on this evaluation result, if the battery life is below the standard value, the base station is listed as requiring an on-site inspection.

[1122] Field survey list generation and notification

[1123] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies the person in charge of the need for an on-site inspection. For example, it sends an email using the SMTP protocol stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required." In response, the terminal displays a notification to the person in charge.

[1124] Conducting on-site surveys

[1125] The user (person in charge) receives the notification, goes to the base station, checks the battery status on-site, and replaces the battery if necessary to ensure system stability.

[1126] Specific examples

[1127] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[1128] Prompt Sentence Examples

[1129] An example of a prompt to input to a generative AI model is as follows:

[1130] "Please prepare an analytical report on the battery life assessment for base station ABC. Based on the frequency of 'low voltage' alarms over the past month and inspection history, estimate the remaining life to be less than 3 months. Please also include a notice to the responsible party that an on-site inspection is required."

[1131] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[1132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1133] Step 1: Data collection

[1134] Input: Monitoring data from base stations and past inspection result data in the database.

[1135] Specific behavior:

[1136] The server acquires monitoring data from each base station using SNMP (Simple Network Management Protocol). For example, data is acquired from base station ABC at midnight every day and stored in a MySQL database.

[1137] The server retrieves the inspection results and battery replacement history data from the database using an SQL query, for example, "SELECT FROM BatteryCheckResults WHERE BaseStationID='ABC'".

[1138] Output: Collected monitoring data and historical inspection result data.

[1139] Step 2: Data filtering

[1140] Input: Collected monitoring data.

[1141] Specific behavior:

[1142] The server parses the monitoring data and extracts only the battery-related data, for example by executing the SQL query "SELECT FROM MonitoringData WHERE BaseStationID='ABC' AND AlarmType='LowVoltage'".

[1143] Filtered data includes voltage values, alarm conditions, battery levels, etc.

[1144] Output: Filtered monitoring data.

[1145] Step 3: Frequency analysis

[1146] Input: Filtered monitoring data.

[1147] Specific behavior:

[1148] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1149] Use a Python script to analyze the timestamps and tally the number of alarms that occurred.

[1150] Output: Alarm occurrence frequency data.

[1151] Step 4: Analyze the inspection results

[1152] Input: Past inspection result data.

[1153] Specific behavior:

[1154] The server analyzes past inspection data and evaluates battery replacement history and inspection results, for example, to verify that the last replacement date was more than one year ago.

[1155] Run an SQL query to retrieve inspection and replacement history (e.g., "SELECT LastInspectionDate FROM BatteryCheckResults WHERE BaseStationID='ABC'").

[1156] Output: Evaluation results of inspection result data.

[1157] Step 5: Battery Life Assessment

[1158] Input: Evaluation results of occurrence frequency data and inspection result data.

[1159] Specific behavior:

[1160] The server runs a battery life assessment algorithm, for example using the following logic: "if alarm count > 5 or last replacement date > 365 days: remaining life = < 3 months".

[1161] Implement conditional branching in a Python script and evaluate lifespan.

[1162] Output: Battery life evaluation results.

[1163] Step 6: Generate a site survey list

[1164] Input: Battery life assessment results.

[1165] Specific behavior:

[1166] The server generates a list of base stations that are evaluated as nearing the end of their life. For example, base station ABC is added to the list.

[1167] Export the list to a CSV file and save it as "surveylist.csv".

[1168] Output: Field survey list.

[1169] Step 7: Create and send a notification

[1170] Input: Field survey list.

[1171] Specific behavior:

[1172] The server creates a notification to the person in charge based on the generated list, for example, creating an email stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[1173] Use the SMTP protocol to send an email with the above content. Specifically, send an email with the following content: "From: server@company.com, To: user@company.com, Subject: On-site inspection notification, Body: Base station ABC has less than 3 months of battery life remaining."

[1174] Output: Notification of need for on-site investigation.

[1175] Step 8: Review the notification and conduct an on-site inspection

[1176] Input: Notification email.

[1177] Specific behavior:

[1178] The device displays a notification to the person in charge, who then checks the notification in the email app on their smartphone or tablet.

[1179] The user (person in charge) visits the base station, checks the battery condition on-site, and replaces the battery if necessary.

[1180] Output: Check battery condition and replace battery if necessary.

[1181] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[1182] (Application example 1)

[1183] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1184] In factories, there is a need to improve the operational efficiency of equipment by properly assessing the battery life of robots and machinery and performing timely maintenance. However, current systems make it difficult to monitor battery status in real time and respond appropriately, resulting in issues such as unplanned equipment shutdowns and repairs. In particular, maintenance personnel must individually check the battery status at each location in the factory, which is labor-intensive and time-consuming.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1186] In this invention, the server includes means for collecting monitoring data from base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying devices that require on-site inspection based on the analysis results, and means for a person in charge to check the status of the devices on-site and perform maintenance as necessary. This enables the battery life of robots and machines in a factory to be appropriately evaluated, and enables maintenance personnel to take timely action.

[1187] "Monitoring Data" means information collected to verify the proper operation of a device.

[1188] "Battery-related data" refers to data including information necessary to indicate the performance and status of the battery, such as voltage, current, and temperature.

[1189] "Filtering" is the process of selecting only specific information that meets a purpose from collected data.

[1190] "Inspection result data" refers to information recorded as a result of past maintenance or inspections.

[1191] "Analysis" is the detailed examination of collected data to extract meaningful information and patterns.

[1192] "Battery life" refers to the period of time a battery can be used before it becomes unusable due to deterioration or wear.

[1193] "On-site inspection" refers to the process of visiting the actual installation site of the equipment to check its specific condition and carrying out maintenance as necessary.

[1194] "Listing" means compiling a list of objects based on specific criteria.

[1195] "Notification" is the act of conveying necessary information to relevant personnel or systems.

[1196] The system of the present invention is designed to monitor the battery status of robots and machines in a factory and appropriately evaluate their lifespan. The system is composed of a server, multiple terminals, and users.

[1197] System Configuration

[1198] server:

[1199] Battery monitoring data is collected from each robot and machine in the factory.

[1200] Filter the collected data to extract only the battery-related data.

[1201] The filtered data and past inspection result data are analyzed to assess the battery life.

[1202] Based on the evaluation results, a list of robots and machines that require on-site inspection will be made.

[1203] For listed devices, a notification is sent to the maintenance personnel.

[1204] Devices (smartphones, tablets, smart glasses, head-mounted displays):

[1205] Receive a notification from the server and notify the person in charge that an on-site inspection is required.

[1206] The person in charge will use the terminal to conduct an on-site inspection based on the received notification and perform maintenance such as battery replacement as necessary.

[1207] Hardware and Software

[1208] Hardware:

[1209] Robots and machines in factories: equipped with sensors to collect monitoring data.

[1210] Maintenance personnel's devices: smartphones, tablets, smart glasses, head-mounted displays.

[1211] software:

[1212] Data collection module: Uses Python, Node.js, etc.

[1213] Database management system: MySQL, PostgreSQL, etc.

[1214] Data analysis module: Uses Python's Pandas and NumPy libraries.

[1215] Notification system: Uses Firebase, etc.

[1216] Specific examples of processing

[1217] For example, a case where the battery status of a robot with ID "R001" is monitored will be described.

[1218] 1. Data Collection:

[1219] The server collects monitoring data from the robot "R001", and the collected data is stored in a database.

[1220] 2. Data filtering:

[1221] The server filters the collected data and extracts relevant data such as battery voltage and temperature.

[1222] 3. Data analysis and lifespan assessment:

[1223] The server analyzes the filtered data and past inspection results, and evaluates the remaining battery life based on battery deterioration patterns and low voltage.

[1224] 4. Generate and notify site inspection list:

[1225] The server adds the robot "R001" that is evaluated as nearing the end of its life to the on-site inspection list and notifies the person in charge.

[1226] 5. Site inspection and maintenance:

[1227] The person in charge will receive a notification and use a smartphone or tablet to inspect the robot "R001" on-site and replace the battery if necessary.

[1228] An example of a prompt to input to a generative AI model is as follows:

[1229] "Write Python code to assess the battery life of robots in a factory and notify them of required maintenance."

[1230] In this way, the system can properly assess the battery status of robots and machines in factories and achieve efficient maintenance.

[1231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1232] Step 1:

[1233] Data collection

[1234] The server collects battery monitoring data from each robot and machine in the factory. Specifically, it periodically obtains data such as voltage, current, and temperature from sensors installed on each robot and machine and stores it in a database. The input is the monitoring data obtained from each robot and machine, and the output is the monitoring data stored in the database. The Python requests library is used to obtain the data.

[1235] Step 2:

[1236] Data Filtering

[1237] The server filters the collected monitoring data and extracts only battery-related data. For example, it selects only low-voltage data where the voltage is below a certain value. This filtering process uses the Python Pandas library. The input is the monitoring data stored in the database, and the output is the filtered battery-related data.

[1238] Step 3:

[1239] Obtaining past inspection result data

[1240] The server retrieves past inspection result data from the database. This includes past maintenance history and inspection evaluation results. The input is the past inspection result data stored in the database, and the output is the retrieved inspection result data. An SQL query is used to retrieve the data.

[1241] Step 4:

[1242] Data analysis and battery life evaluation

[1243] The server uses the filtered data and past inspection result data to perform analysis to evaluate the battery lifespan. Specifically, it analyzes voltage drop patterns and alarm occurrence frequency over time to evaluate the degree of battery deterioration. This analysis process uses Python's NumPy and SciPy libraries. The input is the filtered data and inspection result data, and the output is the estimated battery lifespan.

[1244] Step 5:

[1245] Generate and notify site survey list

[1246] Based on the analysis results, the server generates a list of robots and machines that are nearing the end of their lifespan and notifies the maintenance staff. For example, it creates a notification that reads, "Robot R001 has one month left of battery life, so an on-site inspection is required." The input is the analysis results, and the output is the notification sent to the maintenance staff. Firebase and Twilio are used to send the notifications.

[1247] Step 6:

[1248] Site inspection and maintenance

[1249] The user (maintenance personnel) receives the notification and uses a smartphone or tablet to conduct on-site inspections of the robots and machines. Specifically, they check the batteries of the designated robots and replace them if necessary. The input is the notified on-site inspection list, and the output is the on-site inspection results and the details of the maintenance performed.

[1250] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1251] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[1252] System Configuration

[1253] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[1254] Program Operation

[1255] Data collection

[1256] The server periodically collects monitoring data from each base station. The monitoring data includes information such as voltage, temperature, and current. For example, data is obtained from base station ABC every day and stored in a database.

[1257] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[1258] Data Filtering

[1259] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[1260] Time Series Analysis

[1261] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[1262] Inspection history analysis

[1263] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[1264] Battery Life Rating

[1265] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[1266] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[1267] Field survey list generation and notification

[1268] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[1269] The server generates a notification message based on the list of base stations that require site inspection, for example, "Base station ABC has 3 months of battery life remaining. Site inspection is required."

[1270] The terminal sends a notification message to the user (person in charge), who receives and confirms the notification on the terminal.

[1271] Emotion analysis using an emotion engine

[1272] The emotion engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion engine will recognize that.

[1273] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[1274] Preparation and implementation of on-site surveys

[1275] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1276] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the records.

[1277] Specific examples

[1278] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection results indicated battery degradation. The server determines that the battery has three months or less of life remaining and adds base station ABC to the site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time: "Base station ABC has three months of battery life remaining. Please schedule a site inspection."

[1279] The person in charge checks the notification, prepares for an on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing the battery if necessary, the stability of the system is ensured.

[1280] This embodiment enables accurate evaluation of battery life and timely maintenance, improving the stability of communication services. In addition, by combining it with an emotion engine, the burden on personnel is reduced and efficient business management is achieved.

[1281] The processing flow will be explained below.

[1282] Step 1:

[1283] Data collection

[1284] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database. It also retrieves past inspection result data from the database to create a comprehensive data set.

[1285] Step 2:

[1286] Data Filtering

[1287] The server filters the collected monitoring data for battery-related data, for example by extracting "low voltage" alarm data, thereby consolidating information about the battery's status.

[1288] Step 3:

[1289] Time Series Analysis

[1290] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1291] Step 4:

[1292] Inspection history analysis

[1293] The server analyzes past inspection data and evaluates battery replacement history and status, for example, checking to see if the battery has been replaced for more than a year since the last inspection and whether any deterioration was reported at the time of inspection.

[1294] Step 5:

[1295] Battery Life Rating

[1296] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. It estimates the remaining life based on the alarm frequency and inspection history. For example, if the evaluation result is below a reference value (e.g., less than 3 months remaining), it reports that fact.

[1297] Step 6:

[1298] Field survey list generation

[1299] The server generates a list of base stations that are assessed to be nearing the end of their lifespan, thereby clarifying which base stations require on-site inspection.

[1300] Step 7:

[1301] Notification generation

[1302] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it generates a notification saying, "Base station A has 3 months of battery life remaining. On-site inspection is required."

[1303] Step 8:

[1304] Send notifications

[1305] The terminal sends a notification message to the user's (person in charge) device, who receives and confirms the notification on the terminal.

[1306] Step 9:

[1307] Emotion analysis

[1308] The emotion engine analyzes the user's reaction when receiving a notification and extracts the user's emotions. For example, it analyzes the user's facial expressions when viewing the notification and the operation log to determine the user's emotions.

[1309] Step 10:

[1310] Notification content optimization

[1311] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if it determines that the user is busy, it will adjust the content of the next notification to be less tedious.

[1312] Step 11:

[1313] Field survey preparation

[1314] The user (person in charge) checks the notification and prepares for the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1315] Step 12:

[1316] Conducting on-site surveys

[1317] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the results.

[1318] Through the above steps, the server, terminal, user, and emotion engine cooperate to manage the battery life and perform maintenance at the appropriate time.

[1319] Example 2

[1320] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1321] There is a need to accurately assess the battery life of base stations and enable timely on-site inspections and maintenance. However, current systems often provide inaccurate battery life assessments and inappropriate notification content and timing, placing a heavy burden on personnel and potentially compromising the stability of communication services. Furthermore, notifications that do not take into account personnel's emotions or circumstances make efficient work management difficult, which is an issue.

[1322] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1323] In this invention, the server includes means for collecting monitoring data of base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying the user of the list of base stations that require on-site inspection, and means for analyzing the user's emotions and adjusting the content and transmission timing of notification messages based on the emotion data. This enables accurate evaluation of battery life, timely on-site inspections, and efficient business management while reducing the burden on personnel.

[1324] A "base station" is a device that functions as a relay point in a communication network and provides monitoring data such as voltage, temperature, and current.

[1325] "Server" refers to a computer system that processes and analyzes collected monitoring data, and evaluates, lists, and notifies users of battery life.

[1326] "Terminal" means a device that sends notification messages to a user and allows the user to receive and check notifications.

[1327] "User" refers to the person who receives the notification message and performs on-site inspections and maintenance.

[1328] The "emotion engine" is a system that analyzes the user's reaction to notifications received and extracts and evaluates the user's emotional data.

[1329] "Monitoring data" refers to data such as voltage, temperature, and current collected from a base station.

[1330] "Filtering" refers to the process of selecting data that meets specific conditions from collected data.

[1331] "Inspection result data" refers to data including the history of past battery inspections and replacements.

[1332] "Battery life" is a concept that evaluates the usable period of a battery and estimates its remaining life.

[1333] "Notification" refers to an information message sent from a server to a user through a terminal.

[1334] "On-site inspection" refers to the process in which the user actually goes to the site (base station) and inspects and evaluates the condition of the battery.

[1335] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[1336] System Configuration

[1337] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[1338] Program Operation

[1339] Data collection

[1340] The server periodically collects monitoring data from each base station. This includes information such as voltage, temperature, and current. For example, data is obtained from the base station on a daily basis and stored in a database. A relational database such as MySQL or PostgreSQL is used for this purpose. The server also obtains past inspection result data from the database. This includes battery replacement history and detailed inspection results.

[1341] Data Filtering

[1342] The server filters the collected monitoring data related to the battery. For example, to extract only "low voltage" alarms, it uses a SELECT statement to narrow down the data where the voltage is below a reference value.

[1343] Time Series Analysis

[1344] The server analyzes the filtered alarm data in time series to extract its frequency and patterns. It verifies that five "low voltage" alarms have occurred in the past month. It uses the Python pandas library to process time series data.

[1345] Inspection history analysis

[1346] The server analyzes the collected inspection data and evaluates the battery replacement history and status, for example using an SQL query to verify that the battery has not been replaced for more than a year since the last inspection.

[1347] Battery Life Rating

[1348] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. Machine learning models (e.g., regression models and random forests) are used to estimate the remaining battery life based on alarm frequency and inspection history. If the remaining battery life is determined to be below a certain threshold (e.g., less than three months), the server lists the base station as requiring an on-site inspection.

[1349] Field survey list generation and notification

[1350] The server generates a list of base stations that are evaluated as being nearing the end of their lifespan. It compiles information such as the ID and location of base stations that require an on-site inspection into a list and generates a notification message. For example, it creates a message stating, "Base station ABC has three months of battery life remaining. An on-site inspection is required," and the device sends this notification message to the user (person in charge). Notification methods include push notifications and SMS.

[1351] Emotion analysis using an emotion engine

[1352] The emotion engine analyzes the user's reaction to the notification they receive and extracts the user's emotion. By analyzing the time it takes the user to check the notification and their reaction speed, it evaluates whether the user is feeling stressed or has the time to tackle the task. Based on the analysis results, the emotion engine adjusts the content and sending timing of the notification message. For example, if the emotion engine determines that the user is busy, it will adjust the timing of the next notification to reduce the user's stress.

[1353] Preparation and implementation of on-site surveys

[1354] The user (person in charge) receives the notification and prepares for the on-site inspection. He / she sets the inspection schedule and prepares the necessary tools and equipment. The user (person in charge) then actually goes to the site (base station) and inspects the batteries of the listed base stations. If necessary, he / she replaces the batteries and updates the database with the results.

[1355] Specific examples

[1356] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has three months or less of remaining life and adds base station ABC to the on-site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Base station ABC's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing it if necessary, system stability can be ensured.

[1357] Example prompt sentence:

[1358] "Base station ABC has 3 months of battery life remaining. Please schedule a site inspection."

[1359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1360] Step 1:

[1361] The server periodically collects monitoring data from each base station.

[1362] (Input) Monitoring data such as voltage, temperature, and current from each base station.

[1363] (Data processing / calculation) Obtain monitoring data via an interface and store it in a database. Specifically, collect data via API and insert it into a database (MongoDB, MySQL, etc.).

[1364] (Output) Monitoring data stored in a database.

[1365] Step 2:

[1366] The server retrieves past inspection result data from the database.

[1367] (Input) Inspection result data in the database.

[1368] (Data processing / calculation) Use SQL queries to extract the necessary inspection result data.

[1369] (Output) The inspection result data obtained.

[1370] Step 3:

[1371] The server filters data relating to the battery from the collected monitoring data.

[1372] (Input) Monitoring data collected in step 1.

[1373] (Data processing / calculation) Data with voltage below a standard value is sorted out using SQL queries and filtering algorithms.

[1374] (Output) Filtered low voltage alarm data.

[1375] Step 4:

[1376] The server analyzes the filtered alarm data in chronological order and extracts its frequency and patterns.

[1377] (Input) Low voltage alarm data obtained in step 3.

[1378] (Data processing / calculation) Use Python's pandas library to perform time series analysis of the data, for example, to count the number of low voltage alarms that occurred over the past month.

[1379] (Output) Time-series analyzed low voltage alarm data.

[1380] Step 5:

[1381] The server analyzes the collected inspection result data and evaluates the battery replacement history and condition.

[1382] (Input) Inspection result data obtained in Step 2.

[1383] (Data processing / calculation) Use SQL queries to examine exchange history and calculate time since last exchange.

[1384] (Output) Battery replacement history and evaluation results.

[1385] Step 6:

[1386] The server evaluates the battery life based on the results of time series analysis and inspection history analysis.

[1387] (Input) Data obtained in Steps 4 and 5.

[1388] (Data processing / calculation) Remaining lifespan is estimated using machine learning models (e.g., regression models and random forests).

[1389] (Output) Estimated remaining battery life.

[1390] Step 7:

[1391] The server generates a list of base stations that are assessed to be nearing the end of their life.

[1392] (Input) Estimated remaining battery life from step 6.

[1393] (Data processing / calculation) List base stations whose remaining lifespan is below a standard value (e.g., less than 3 months).

[1394] (Output) List of base stations that require site inspection.

[1395] Step 8:

[1396] The server generates a notification message based on the list of base stations that require on-site inspection.

[1397] (Input) The base station list generated in step 7.

[1398] (Data processing / calculation) A notification message is generated, for example, "Base station ABC has 3 months of battery life remaining. An on-site inspection is required."

[1399] (Output) The generated notification message.

[1400] Step 9:

[1401] The terminal sends a notification message to the user (person in charge).

[1402] (Input) The notification message generated in step 8.

[1403] (Data processing / calculation) Send messages to users using push notifications or SMS.

[1404] (Output) The notification message to be sent to the user.

[1405] Step 10:

[1406] The emotion engine analyzes the user's reaction to the notifications they receive.

[1407] (Input) User notification confirmation time and reaction speed.

[1408] (Data processing / computation) Use sentiment analysis algorithms to evaluate the emotions users have about notifications.

[1409] (Output) Parsed emotion data.

[1410] Step 11:

[1411] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotional data.

[1412] (Input) Emotion data parsed in step 10.

[1413] (Data processing / calculation) A prompt sentence is generated, and if the user feels busy, for example, the timing of the next notification is adjusted appropriately.

[1414] (Output) Adjusted notification message content and sending timing.

[1415] Step 12:

[1416] The user (person in charge) receives the notification and prepares for the on-site investigation.

[1417] (Input) The notification messages sent in Step 9 and Step 11.

[1418] (Data processing / calculation) Set the survey schedule and prepare the necessary tools and equipment.

[1419] (Output) The completed site survey plan.

[1420] Step 13:

[1421] The user (person in charge) goes to the site and checks the batteries of the listed base stations.

[1422] (Input) The site investigation plan prepared in step 12.

[1423] (Data processing / calculation) Inspection work is carried out, batteries are replaced if necessary, and the results are recorded in the database.

[1424] (Output) Updated inspection result data and replacement history.

[1425] (Application example 2)

[1426] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1427] The problem to be solved by this invention is a system for evaluating the battery life of robots in factories, improving the efficiency of their management, and providing maintenance notifications at appropriate times. In the past, it was difficult to effectively manage the battery life of robots in factories and perform appropriate maintenance, which could result in an impact on the operation of the robots. Furthermore, there was a need for a method for providing notifications efficiently while reducing the burden on maintenance personnel.

[1428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1429] In this invention, the server includes means for collecting base station monitoring data, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations requiring on-site inspection based on the evaluation results, means for notifying the user of the list of base stations requiring on-site inspection, and means for analyzing the user's emotions and optimizing the content and transmission timing of the notification message. This enables accurate evaluation of the robot's battery life, optimal timing for on-site inspection, and efficient maintenance.

[1430] A "base station" is a device that is a relay point in a communication network and provides monitoring data.

[1431] "Monitoring data" refers to data such as voltage, temperature, and current collected from the base station.

[1432] "Battery-related data" refers to information from the monitoring data that relates to the state and lifespan of the battery.

[1433] "Filtering" refers to the process of extracting data that meets specific conditions from collected monitoring data.

[1434] "Inspection result data" refers to records of past inspections and data related to the results of those inspections.

[1435] "Analysis" refers to the process of performing calculations and evaluations based on data to predict the battery's condition and lifespan.

[1436] "Battery life assessment" refers to predicting the remaining life of a battery based on data analyzed by the server.

[1437] "On-site inspection" refers to actually visiting a base station to replace or perform maintenance on batteries.

[1438] "Emotion analysis" refers to extracting and analyzing the emotions of a user based on the user's emotional data.

[1439] An embodiment of the present invention is described in detail below. The present invention relates to a battery management system for robots in a factory. The system includes multiple robots, a server, a user, and an emotion analysis engine. This system can accurately evaluate the battery life of the robots and enable timely on-site inspection and maintenance.

[1440] System Configuration

[1441] This system consists of a robot, a server, a user, and a sentiment analysis engine. The robot operates in the factory and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The user receives notifications and performs on-site inspections. The sentiment analysis engine analyzes user emotions and optimizes the content and timing of notifications.

[1442] Program Operation

[1443] Data collection

[1444] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[1445] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[1446] Data Filtering

[1447] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[1448] Time Series Analysis

[1449] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[1450] Inspection history analysis

[1451] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[1452] Battery Life Rating

[1453] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[1454] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the robot as one that requires on-site inspection.

[1455] Field survey list generation and notification

[1456] The server generates a list of robots that are assessed as nearing the end of their lifespan, making it clear which robots need to be investigated.

[1457] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[1458] The user (person in charge) receives and confirms the notification message from the server.

[1459] Emotion analysis using an emotion analysis engine

[1460] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[1461] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[1462] Preparation and implementation of on-site surveys

[1463] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1464] The user (person in charge) visits the site, inspects the batteries of the listed robots, replaces the batteries as necessary, and updates the database with the results.

[1465] Specific examples

[1466] For example, the server collects and analyzes the following data for Robot A in a factory: Five "low voltage" alarms occurred in the past month, and the results of the last inspection indicated battery degradation. The server determines that the battery has three months or less of life left and adds Robot A to the on-site inspection list. The sentiment analysis engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Robot A's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects Robot A. System stability is ensured by checking the battery status on-site and replacing it if necessary.

[1467] Prompt Sentence Examples

[1468] prompt:

[1469] "Please describe a system that combines battery life assessment for factory robots and optimal notification timing. Please include the following elements: data collection, data analysis, life assessment, notification generation, notification delivery, and sentiment analysis."

[1470] Expected output:

[1471] "The robots in the factory use sensors to collect monitoring data on battery voltage, temperature, and current, and send it to a server. The server analyzes the collected data and evaluates battery life. When a robot's lifespan is shortened, an emotion analysis engine analyzes the emotions of the person in charge and sends a maintenance notification at the optimal time. Once the maintenance is completed, the results are updated in the database to ensure the stability of the system."

[1472] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1473] Processing step flow

[1474] Step 1: Data collection

[1475] Specific behavior:

[1476] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[1477] Input: Monitoring data such as voltage, temperature, and current obtained from sensors inside the robot.

[1478] Output: Monitoring data stored in a database. The monitoring data is recorded in the database along with the date.

[1479] Step 2: Data filtering

[1480] Specific behavior:

[1481] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[1482] Input: All monitoring data stored in the database.

[1483] Output: Filtered battery related data. Data for "low voltage" alarms is extracted.

[1484] Step 3: Obtaining inspection result data

[1485] Specific behavior:

[1486] The server retrieves past inspection result data from a database, including battery replacement history and detailed inspection results.

[1487] Input: Inspection result data stored in the database.

[1488] Output: Obtained past inspection result data. The server reads the inspection result information into memory.

[1489] Step 4: Time series analysis

[1490] Specific behavior:

[1491] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1492] Input: Filtered alarm data.

[1493] Output: Analysis results (alarm occurrence frequency and pattern). The server records the result that a "low voltage" alarm has occurred five times in the past month.

[1494] Step 5: Inspection history analysis

[1495] Specific behavior:

[1496] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[1497] Input: Obtained inspection result data.

[1498] Output: Analysis results (battery replacement history and status). Information that the battery has not been replaced for over a year is recorded.

[1499] Step 6: Evaluate battery life

[1500] Specific behavior:

[1501] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[1502] Input: Time series analysis results and inspection history analysis results.

[1503] Output: Battery life assessment result. Information indicating that the remaining battery life is less than 3 months is recorded.

[1504] Step 7: Generate a site inspection list

[1505] Specific behavior:

[1506] The server generates a list of robots that are assessed to be nearing the end of their lifespan, making it clear which robots need to be investigated.

[1507] Input: Battery life assessment results.

[1508] Output: List of robots that require on-site investigation. A list of robots that require investigation is generated.

[1509] Step 8: Generate and send a notification message

[1510] Specific behavior:

[1511] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[1512] Input: List of robots that require on-site inspection.

[1513] Output: Notification message. A notification message is sent to the user's terminal.

[1514] Step 9: Sentiment analysis using a sentiment analysis engine

[1515] Specific behavior:

[1516] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[1517] Input: User response data.

[1518] Output: Parsed emotion data. Information that the user is feeling stressed is recorded.

[1519] Step 10: Optimize notification timing

[1520] Specific behavior:

[1521] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[1522] Input: Parsed emotion data.

[1523] Output: Optimized notification timing. Notifications are sent at the best possible time for the user.

[1524] Step 11: Prepare and conduct the site survey

[1525] Specific behavior:

[1526] The user (person in charge) receives the notification and prepares for the on-site inspection. They set up an inspection schedule and prepare the necessary tools and equipment. The user then goes to the site and checks the batteries of the listed robots. They replace the batteries as necessary and update the database with the records.

[1527] Input: Notification message and required investigation tools.

[1528] Output: Updated inspection result data. The results of the on-site inspection and battery replacement are recorded in the database.

[1529] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1530] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1531] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1532] [Fourth embodiment]

[1533] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1534] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1535] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1536] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1537] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1538] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1539] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1540] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1541] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1542] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1543] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1544] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1545] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1546] The present invention is described in detail below with reference to an embodiment thereof. The purpose of this system is to accurately evaluate the battery life of a base station and to realize timely on-site inspection and maintenance, thereby improving the stability of communication services and optimizing resources.

[1547] System Configuration

[1548] This system consists of a base station, a server, and a terminal. The base station is a relay point or access point for wireless communication in the communication network and provides the necessary monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal notifies the person in charge of the need for a field survey and is used by the person in charge to carry out the field survey.

[1549] Program Operation

[1550] 1. Data Collection

[1551] The server periodically collects monitoring data from each base station. For example, it receives data from base station ABC every day and stores it in a database.

[1552] The server also retrieves past inspection result data from the database, including battery replacement history and inspection results.

[1553] 2. Data Analysis

[1554] The server filters the monitoring data stored in the database and extracts only battery-related data, for example, "low voltage" alarm data for base station ABC.

[1555] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. It confirms that "low voltage" alarms have occurred five times in the past month.

[1556] The server analyzes the inspection result data and evaluates the battery replacement history and inspection results, for example, to verify that the last replacement was more than a year ago.

[1557] 3. Battery life evaluation

[1558] The server then runs an algorithm to assess battery life based on the analysis results, for example, if there is a high frequency of alarms or if inspection history indicates that the battery is deteriorating, and estimates the remaining battery life.

[1559] As a result of the evaluation, the server determines that the battery life is below a standard value (for example, less than three months remaining) and lists the base station as one that requires on-site inspection.

[1560] 4. Field survey list generation and notification

[1561] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies personnel of the need for an on-site inspection. For example, it creates a notification saying, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[1562] The terminal sends a notification to the person in charge, who then confirms it.

[1563] 5. Conducting on-site surveys

[1564] The user (person in charge) receives the notification, goes to base station ABC, and checks the actual battery condition on-site. If necessary, the battery is replaced to ensure the stability of the system.

[1565] Specific examples

[1566] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[1567] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[1568] The processing flow will be explained below.

[1569] Step 1:

[1570] Data collection

[1571] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database.

[1572] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[1573] Step 2:

[1574] Data Filtering

[1575] The server filters the collected monitoring data for battery-related alarm data, for example, extracting only "low voltage" alarms.

[1576] Step 3:

[1577] Time Series Analysis

[1578] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1579] Step 4:

[1580] Inspection history analysis

[1581] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[1582] Step 5:

[1583] Battery Life Rating

[1584] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[1585] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[1586] Step 6:

[1587] Field survey list generation

[1588] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[1589] Step 7:

[1590] Notification generation

[1591] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it creates a notification with the content "Base station A has 3 months of battery life remaining. On-site inspection is required."

[1592] Step 8:

[1593] Send notifications

[1594] The terminal sends a notification message to the person in charge, who receives and confirms the notification on the terminal.

[1595] Step 9:

[1596] Preparation for field survey

[1597] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1598] Step 10:

[1599] Conducting on-site surveys

[1600] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the records in the database.

[1601] Through the above steps, the server, terminal, and user can cooperate to manage the battery life and perform maintenance at the appropriate time.

[1602] Example 1

[1603] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1604] There is a need to accurately assess the lifespan of power supply equipment (batteries) at base stations in communication networks and to carry out on-site inspections and maintenance when necessary. However, with conventional systems, it is difficult to predict the deterioration of power supply equipment and respond in a timely manner, which can result in a loss of stability in communication services. To address this, there is a need for more accurate and efficient methods to assess the lifespan of power supply equipment and notify the need for on-site inspections.

[1605] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1606] In this invention, the server includes means for collecting monitoring data, means for filtering the collected monitoring data to extract data related to the power supply devices, means for acquiring past operational inspection data, means for analyzing the filtered data and the past operational inspection data to evaluate the usable life of the power supply devices, means for selecting communication devices requiring on-site inspection based on the evaluation results, and means for notifying the list of communication devices requiring on-site inspection. This makes it possible to accurately evaluate the life of power supply devices in a communication network and to perform on-site inspections and maintenance in a timely manner.

[1607] "Monitoring data" refers to information relating to the operating status and performance of communication devices such as base stations.

[1608] "Filtering" is the process of extracting information that meets specific conditions from collected data and removing unnecessary information.

[1609] "Power Supply" means a battery or other power supply unit that provides power to a communications device.

[1610] "Operational inspection data" refers to records and history of inspection work carried out on communication devices in the past.

[1611] "Available life" refers to the estimated period of time that the power supply device can continue to function normally.

[1612] The term "communication device" refers to all devices, including base stations, for transmitting and receiving data in a communication network.

[1613] A "server" is a computer system that collects, analyzes, and notifies data.

[1614] The system of the present invention is designed to accurately assess the lifespan of base station power supplies (batteries) in communication networks and to perform on-site inspections and maintenance in a timely manner, thereby maintaining the stability of communication services and optimizing resources.

[1615] System Configuration

[1616] This system mainly consists of the following hardware and software:

[1617] Base Station: Acts as a relay or access point in the communication network and provides the necessary monitoring data.

[1618] Server: The main device that collects, analyzes, evaluates, and notifies data. Data is managed using a database system (e.g., MySQL), and analysis is performed using a programming language such as Python.

[1619] Terminal: A device used to notify personnel of the need for on-site inspections. It can be a smartphone, tablet, or PC.

[1620] Data collection

[1621] The server periodically collects monitoring data from each base station. For example, the server uses SNMP (Simple Network Management Protocol) to obtain data from the base station and stores it in a MySQL database. The collected data includes battery level, voltage value, alarm status, etc. The server also obtains inspection results and replacement history data from the same database. This is done using SQL queries.

[1622] Data analysis

[1623] The server analyzes the monitoring data stored in the database and filters it to extract battery-related data. For example, it executes the SQL query "SELECT FROM MonitoringData WHERE AlarmType='LowVoltage'" to extract only "low voltage" alarm data. The server then analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns. The server then analyzes inspection result data and evaluates battery replacement history and inspection results.

[1624] Battery Life Rating

[1625] The server executes a battery life evaluation algorithm based on the analysis results. For example, it evaluates in Python "if alarm occurrence count > 5 or last replacement date > 365 days: remaining life = estimated value." Based on this evaluation result, if the battery life is below the standard value, the base station is listed as requiring an on-site inspection.

[1626] Field survey list generation and notification

[1627] The server generates a list of base stations that are evaluated as nearing the end of their lifespan and notifies the person in charge of the need for an on-site inspection. For example, it sends an email using the SMTP protocol stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required." In response, the terminal displays a notification to the person in charge.

[1628] Conducting on-site surveys

[1629] The user (person in charge) receives the notification, goes to the base station, checks the battery status on-site, and replaces the battery if necessary to ensure system stability.

[1630] Specific examples

[1631] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has less than three months of remaining life and adds base station ABC to the on-site inspection list. The person in charge receives the notification, conducts an on-site inspection of base station ABC, and replaces the battery if necessary.

[1632] Prompt Sentence Examples

[1633] An example of a prompt to input to a generative AI model is as follows:

[1634] "Please prepare an analytical report on the battery life assessment for base station ABC. Based on the frequency of 'low voltage' alarms over the past month and inspection history, estimate the remaining life to be less than 3 months. Please also include a notice to the responsible party that an on-site inspection is required."

[1635] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[1636] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1637] Step 1: Data collection

[1638] Input: Monitoring data from base stations and past inspection result data in the database.

[1639] Specific behavior:

[1640] The server acquires monitoring data from each base station using SNMP (Simple Network Management Protocol). For example, data is acquired from base station ABC at midnight every day and stored in a MySQL database.

[1641] The server retrieves the inspection results and battery replacement history data from the database using an SQL query, for example, "SELECT FROM BatteryCheckResults WHERE BaseStationID='ABC'".

[1642] Output: Collected monitoring data and historical inspection result data.

[1643] Step 2: Data filtering

[1644] Input: Collected monitoring data.

[1645] Specific behavior:

[1646] The server parses the monitoring data and extracts only the battery-related data, for example by executing the SQL query "SELECT FROM MonitoringData WHERE BaseStationID='ABC' AND AlarmType='LowVoltage'".

[1647] Filtered data includes voltage values, alarm conditions, battery levels, etc.

[1648] Output: Filtered monitoring data.

[1649] Step 3: Frequency analysis

[1650] Input: Filtered monitoring data.

[1651] Specific behavior:

[1652] The server analyzes the filtered data in chronological order to extract alarm occurrence frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1653] Use a Python script to analyze the timestamps and tally the number of alarms that occurred.

[1654] Output: Alarm occurrence frequency data.

[1655] Step 4: Analyze the inspection results

[1656] Input: Past inspection result data.

[1657] Specific behavior:

[1658] The server analyzes past inspection data and evaluates battery replacement history and inspection results, for example, to verify that the last replacement date was more than one year ago.

[1659] Run an SQL query to retrieve inspection and replacement history (e.g., "SELECT LastInspectionDate FROM BatteryCheckResults WHERE BaseStationID='ABC'").

[1660] Output: Evaluation results of inspection result data.

[1661] Step 5: Battery Life Assessment

[1662] Input: Evaluation results of occurrence frequency data and inspection result data.

[1663] Specific behavior:

[1664] The server runs a battery life assessment algorithm, for example using the following logic: "if alarm count > 5 or last replacement date > 365 days: remaining life = < 3 months".

[1665] Implement conditional branching in a Python script and evaluate lifespan.

[1666] Output: Battery life evaluation results.

[1667] Step 6: Generate a site survey list

[1668] Input: Battery life assessment results.

[1669] Specific behavior:

[1670] The server generates a list of base stations that are evaluated as nearing the end of their life. For example, base station ABC is added to the list.

[1671] Export the list to a CSV file and save it as "surveylist.csv".

[1672] Output: Field survey list.

[1673] Step 7: Create and send a notification

[1674] Input: Field survey list.

[1675] Specific behavior:

[1676] The server creates a notification to the person in charge based on the generated list, for example, creating an email stating, "Base station ABC has three months of battery life remaining, so an on-site inspection is required."

[1677] Use the SMTP protocol to send an email with the above content. Specifically, send an email with the following content: "From: server@company.com, To: user@company.com, Subject: On-site inspection notification, Body: Base station ABC has less than 3 months of battery life remaining."

[1678] Output: Notification of need for on-site investigation.

[1679] Step 8: Review the notification and conduct an on-site inspection

[1680] Input: Notification email.

[1681] Specific behavior:

[1682] The device displays a notification to the person in charge, who then checks the notification in the email app on their smartphone or tablet.

[1683] The user (person in charge) visits the base station, checks the battery condition on-site, and replaces the battery if necessary.

[1684] Output: Check battery condition and replace battery if necessary.

[1685] This allows the system to accurately evaluate the battery life of base stations and achieve efficient maintenance.

[1686] (Application example 1)

[1687] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1688] In factories, there is a need to improve the operational efficiency of equipment by properly assessing the battery life of robots and machinery and performing timely maintenance. However, current systems make it difficult to monitor battery status in real time and respond appropriately, resulting in issues such as unplanned equipment shutdowns and repairs. In particular, maintenance personnel must individually check the battery status at each location in the factory, which is labor-intensive and time-consuming.

[1689] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1690] In this invention, the server includes means for collecting monitoring data from base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying devices that require on-site inspection based on the analysis results, and means for a person in charge to check the status of the devices on-site and perform maintenance as necessary. This enables the battery life of robots and machines in a factory to be appropriately evaluated, and enables maintenance personnel to take timely action.

[1691] "Monitoring Data" means information collected to verify the proper operation of a device.

[1692] "Battery-related data" refers to data including information necessary to indicate the performance and status of the battery, such as voltage, current, and temperature.

[1693] "Filtering" is the process of selecting only specific information that meets a purpose from collected data.

[1694] "Inspection result data" refers to information recorded as a result of past maintenance or inspections.

[1695] "Analysis" is the detailed examination of collected data to extract meaningful information and patterns.

[1696] "Battery life" refers to the period of time a battery can be used before it becomes unusable due to deterioration or wear.

[1697] "On-site inspection" refers to the process of visiting the actual installation site of the equipment to check its specific condition and carrying out maintenance as necessary.

[1698] "Listing" means compiling a list of objects based on specific criteria.

[1699] "Notification" is the act of conveying necessary information to relevant personnel or systems.

[1700] The system of the present invention is designed to monitor the battery status of robots and machines in a factory and appropriately evaluate their lifespan. The system is composed of a server, multiple terminals, and users.

[1701] System Configuration

[1702] server:

[1703] Battery monitoring data is collected from each robot and machine in the factory.

[1704] Filter the collected data to extract only the battery-related data.

[1705] The filtered data and past inspection result data are analyzed to assess the battery life.

[1706] Based on the evaluation results, a list of robots and machines that require on-site inspection will be made.

[1707] For listed devices, a notification is sent to the maintenance personnel.

[1708] Devices (smartphones, tablets, smart glasses, head-mounted displays):

[1709] Receive a notification from the server and notify the person in charge that an on-site inspection is required.

[1710] The person in charge will use the terminal to conduct an on-site inspection based on the received notification and perform maintenance such as battery replacement as necessary.

[1711] Hardware and Software

[1712] Hardware:

[1713] Robots and machines in factories: equipped with sensors to collect monitoring data.

[1714] Maintenance personnel's devices: smartphones, tablets, smart glasses, head-mounted displays.

[1715] software:

[1716] Data collection module: Uses Python, Node.js, etc.

[1717] Database management system: MySQL, PostgreSQL, etc.

[1718] Data analysis module: Uses Python's Pandas and NumPy libraries.

[1719] Notification system: Uses Firebase, etc.

[1720] Specific examples of processing

[1721] For example, a case where the battery status of a robot with ID "R001" is monitored will be described.

[1722] 1. Data Collection:

[1723] The server collects monitoring data from the robot "R001", and the collected data is stored in a database.

[1724] 2. Data filtering:

[1725] The server filters the collected data and extracts relevant data such as battery voltage and temperature.

[1726] 3. Data analysis and lifespan assessment:

[1727] The server analyzes the filtered data and past inspection results, and evaluates the remaining battery life based on battery deterioration patterns and low voltage.

[1728] 4. Generate and notify site inspection list:

[1729] The server adds the robot "R001" that is evaluated as nearing the end of its life to the on-site inspection list and notifies the person in charge.

[1730] 5. Site inspection and maintenance:

[1731] The person in charge will receive a notification and use a smartphone or tablet to inspect the robot "R001" on-site and replace the battery if necessary.

[1732] An example of a prompt to input to a generative AI model is as follows:

[1733] "Write Python code to assess the battery life of robots in a factory and notify them of required maintenance."

[1734] In this way, the system can properly assess the battery status of robots and machines in factories and achieve efficient maintenance.

[1735] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1736] Step 1:

[1737] Data collection

[1738] The server collects battery monitoring data from each robot and machine in the factory. Specifically, it periodically obtains data such as voltage, current, and temperature from sensors installed on each robot and machine and stores it in a database. The input is the monitoring data obtained from each robot and machine, and the output is the monitoring data stored in the database. The Python requests library is used to obtain the data.

[1739] Step 2:

[1740] Data Filtering

[1741] The server filters the collected monitoring data and extracts only battery-related data. For example, it selects only low-voltage data where the voltage is below a certain value. This filtering process uses the Python Pandas library. The input is the monitoring data stored in the database, and the output is the filtered battery-related data.

[1742] Step 3:

[1743] Obtaining past inspection result data

[1744] The server retrieves past inspection result data from the database. This includes past maintenance history and inspection evaluation results. The input is the past inspection result data stored in the database, and the output is the retrieved inspection result data. An SQL query is used to retrieve the data.

[1745] Step 4:

[1746] Data analysis and battery life evaluation

[1747] The server uses the filtered data and past inspection result data to perform analysis to evaluate the battery lifespan. Specifically, it analyzes voltage drop patterns and alarm occurrence frequency over time to evaluate the degree of battery deterioration. This analysis process uses Python's NumPy and SciPy libraries. The input is the filtered data and inspection result data, and the output is the estimated battery lifespan.

[1748] Step 5:

[1749] Generate and notify site survey list

[1750] Based on the analysis results, the server generates a list of robots and machines that are nearing the end of their lifespan and notifies the maintenance staff. For example, it creates a notification that reads, "Robot R001 has one month left of battery life, so an on-site inspection is required." The input is the analysis results, and the output is the notification sent to the maintenance staff. Firebase and Twilio are used to send the notifications.

[1751] Step 6:

[1752] Site inspection and maintenance

[1753] The user (maintenance personnel) receives the notification and uses a smartphone or tablet to conduct on-site inspections of the robots and machines. Specifically, they check the batteries of the designated robots and replace them if necessary. The input is the notified on-site inspection list, and the output is the on-site inspection results and the details of the maintenance performed.

[1754] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1755] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[1756] System Configuration

[1757] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[1758] Program Operation

[1759] Data collection

[1760] The server periodically collects monitoring data from each base station. The monitoring data includes information such as voltage, temperature, and current. For example, data is obtained from base station ABC every day and stored in a database.

[1761] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[1762] Data Filtering

[1763] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[1764] Time Series Analysis

[1765] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[1766] Inspection history analysis

[1767] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[1768] Battery Life Rating

[1769] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[1770] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the base station as one that requires on-site inspection.

[1771] Field survey list generation and notification

[1772] The server generates a list of base stations that are evaluated as approaching the end of their service life, which identifies base stations that need to be investigated.

[1773] The server generates a notification message based on the list of base stations that require site inspection, for example, "Base station ABC has 3 months of battery life remaining. Site inspection is required."

[1774] The terminal sends a notification message to the user (person in charge), who receives and confirms the notification on the terminal.

[1775] Emotion analysis using an emotion engine

[1776] The emotion engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion engine will recognize that.

[1777] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[1778] Preparation and implementation of on-site surveys

[1779] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1780] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the records.

[1781] Specific examples

[1782] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection results indicated battery degradation. The server determines that the battery has three months or less of life remaining and adds base station ABC to the site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time: "Base station ABC has three months of battery life remaining. Please schedule a site inspection."

[1783] The person in charge checks the notification, prepares for an on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing the battery if necessary, the stability of the system is ensured.

[1784] This embodiment enables accurate evaluation of battery life and timely maintenance, improving the stability of communication services. In addition, by combining it with an emotion engine, the burden on personnel is reduced and efficient business management is achieved.

[1785] The processing flow will be explained below.

[1786] Step 1:

[1787] Data collection

[1788] The server periodically collects monitoring data from each base station, for example, daily, and stores the information in a database. It also retrieves past inspection result data from the database to create a comprehensive data set.

[1789] Step 2:

[1790] Data Filtering

[1791] The server filters the collected monitoring data for battery-related data, for example by extracting "low voltage" alarm data, thereby consolidating information about the battery's status.

[1792] Step 3:

[1793] Time Series Analysis

[1794] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1795] Step 4:

[1796] Inspection history analysis

[1797] The server analyzes past inspection data and evaluates battery replacement history and status, for example, checking to see if the battery has been replaced for more than a year since the last inspection and whether any deterioration was reported at the time of inspection.

[1798] Step 5:

[1799] Battery Life Rating

[1800] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. It estimates the remaining life based on the alarm frequency and inspection history. For example, if the evaluation result is below a reference value (e.g., less than 3 months remaining), it reports that fact.

[1801] Step 6:

[1802] Field survey list generation

[1803] The server generates a list of base stations that are assessed to be nearing the end of their lifespan, thereby clarifying which base stations require on-site inspection.

[1804] Step 7:

[1805] Notification generation

[1806] The server generates a notification message based on the list of base stations that require on-site inspection. For example, it generates a notification saying, "Base station A has 3 months of battery life remaining. On-site inspection is required."

[1807] Step 8:

[1808] Send notifications

[1809] The terminal sends a notification message to the user's (person in charge) device, who receives and confirms the notification on the terminal.

[1810] Step 9:

[1811] Emotion analysis

[1812] The emotion engine analyzes the user's reaction when receiving a notification and extracts the user's emotions. For example, it analyzes the user's facial expressions when viewing the notification and the operation log to determine the user's emotions.

[1813] Step 10:

[1814] Notification content optimization

[1815] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if it determines that the user is busy, it will adjust the content of the next notification to be less tedious.

[1816] Step 11:

[1817] Field survey preparation

[1818] The user (person in charge) checks the notification and prepares for the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1819] Step 12:

[1820] Conducting on-site surveys

[1821] The user (person in charge) visits the site, inspects the batteries of the listed base stations, replaces the batteries as necessary, and updates the database with the results.

[1822] Through the above steps, the server, terminal, user, and emotion engine cooperate to manage the battery life and perform maintenance at the appropriate time.

[1823] Example 2

[1824] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1825] There is a need to accurately assess the battery life of base stations and enable timely on-site inspections and maintenance. However, current systems often provide inaccurate battery life assessments and inappropriate notification content and timing, placing a heavy burden on personnel and potentially compromising the stability of communication services. Furthermore, notifications that do not take into account personnel's emotions or circumstances make efficient work management difficult, which is an issue.

[1826] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1827] In this invention, the server includes means for collecting monitoring data of base stations, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations that require on-site inspection based on the evaluation results, means for notifying the user of the list of base stations that require on-site inspection, and means for analyzing the user's emotions and adjusting the content and transmission timing of notification messages based on the emotion data. This enables accurate evaluation of battery life, timely on-site inspections, and efficient business management while reducing the burden on personnel.

[1828] A "base station" is a device that functions as a relay point in a communication network and provides monitoring data such as voltage, temperature, and current.

[1829] "Server" refers to a computer system that processes and analyzes collected monitoring data, and evaluates, lists, and notifies users of battery life.

[1830] "Terminal" means a device that sends notification messages to a user and allows the user to receive and check notifications.

[1831] "User" refers to the person who receives the notification message and performs on-site inspections and maintenance.

[1832] The "emotion engine" is a system that analyzes the user's reaction to notifications received and extracts and evaluates the user's emotional data.

[1833] "Monitoring data" refers to data such as voltage, temperature, and current collected from a base station.

[1834] "Filtering" refers to the process of selecting data that meets specific conditions from collected data.

[1835] "Inspection result data" refers to data including the history of past battery inspections and replacements.

[1836] "Battery life" is a concept that evaluates the usable period of a battery and estimates its remaining life.

[1837] "Notification" refers to an information message sent from a server to a user through a terminal.

[1838] "On-site inspection" refers to the process in which the user actually goes to the site (base station) and inspects and evaluates the condition of the battery.

[1839] An embodiment of the present invention will be described in detail below. The purpose of this system is to accurately evaluate the battery life of base stations and realize timely on-site inspections and maintenance. To achieve this, the system is constructed by combining a server, terminals, users, and an emotion engine.

[1840] System Configuration

[1841] This system consists of a base station, a server, a terminal, a user, and an emotion engine. The base station is a relay point in the communication network and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The terminal is responsible for sending notifications to personnel. The user receives the notification and performs a field survey. Furthermore, the emotion engine analyzes the user's emotions and optimizes the content and timing of notifications.

[1842] Program Operation

[1843] Data collection

[1844] The server periodically collects monitoring data from each base station. This includes information such as voltage, temperature, and current. For example, data is obtained from the base station on a daily basis and stored in a database. A relational database such as MySQL or PostgreSQL is used for this purpose. The server also obtains past inspection result data from the database. This includes battery replacement history and detailed inspection results.

[1845] Data Filtering

[1846] The server filters the collected monitoring data related to the battery. For example, to extract only "low voltage" alarms, it uses a SELECT statement to narrow down the data where the voltage is below a reference value.

[1847] Time Series Analysis

[1848] The server analyzes the filtered alarm data in time series to extract its frequency and patterns. It verifies that five "low voltage" alarms have occurred in the past month. It uses the Python pandas library to process time series data.

[1849] Inspection history analysis

[1850] The server analyzes the collected inspection data and evaluates the battery replacement history and status, for example using an SQL query to verify that the battery has not been replaced for more than a year since the last inspection.

[1851] Battery Life Rating

[1852] The server evaluates the battery life based on the results of time series analysis and inspection history analysis. Machine learning models (e.g., regression models and random forests) are used to estimate the remaining battery life based on alarm frequency and inspection history. If the remaining battery life is determined to be below a certain threshold (e.g., less than three months), the server lists the base station as requiring an on-site inspection.

[1853] Field survey list generation and notification

[1854] The server generates a list of base stations that are evaluated as being nearing the end of their lifespan. It compiles information such as the ID and location of base stations that require an on-site inspection into a list and generates a notification message. For example, it creates a message stating, "Base station ABC has three months of battery life remaining. An on-site inspection is required," and the device sends this notification message to the user (person in charge). Notification methods include push notifications and SMS.

[1855] Emotion analysis using an emotion engine

[1856] The emotion engine analyzes the user's reaction to the notification they receive and extracts the user's emotion. By analyzing the time it takes the user to check the notification and their reaction speed, it evaluates whether the user is feeling stressed or has the time to tackle the task. Based on the analysis results, the emotion engine adjusts the content and sending timing of the notification message. For example, if the emotion engine determines that the user is busy, it will adjust the timing of the next notification to reduce the user's stress.

[1857] Preparation and implementation of on-site surveys

[1858] The user (person in charge) receives the notification and prepares for the on-site inspection. He / she sets the inspection schedule and prepares the necessary tools and equipment. The user (person in charge) then actually goes to the site (base station) and inspects the batteries of the listed base stations. If necessary, he / she replaces the batteries and updates the database with the results.

[1859] Specific examples

[1860] For example, for base station ABC, the server collects and analyzes the following data: Five "low voltage" alarms occurred in the past month, and the last inspection result indicated battery degradation. The server determines that the battery has three months or less of remaining life and adds base station ABC to the on-site inspection list. The emotion engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Base station ABC's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects base station ABC. By checking the battery status on-site and replacing it if necessary, system stability can be ensured.

[1861] Example prompt sentence:

[1862] "Base station ABC has 3 months of battery life remaining. Please schedule a site inspection."

[1863] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1864] Step 1:

[1865] The server periodically collects monitoring data from each base station.

[1866] (Input) Monitoring data such as voltage, temperature, and current from each base station.

[1867] (Data processing / calculation) Obtain monitoring data via an interface and store it in a database. Specifically, collect data via API and insert it into a database (MongoDB, MySQL, etc.).

[1868] (Output) Monitoring data stored in a database.

[1869] Step 2:

[1870] The server retrieves past inspection result data from the database.

[1871] (Input) Inspection result data in the database.

[1872] (Data processing / calculation) Use SQL queries to extract the necessary inspection result data.

[1873] (Output) The inspection result data obtained.

[1874] Step 3:

[1875] The server filters data relating to the battery from the collected monitoring data.

[1876] (Input) Monitoring data collected in step 1.

[1877] (Data processing / calculation) Data with voltage below a standard value is sorted out using SQL queries and filtering algorithms.

[1878] (Output) Filtered low voltage alarm data.

[1879] Step 4:

[1880] The server analyzes the filtered alarm data in chronological order and extracts its frequency and patterns.

[1881] (Input) Low voltage alarm data obtained in step 3.

[1882] (Data processing / calculation) Use Python's pandas library to perform time series analysis of the data, for example, to count the number of low voltage alarms that occurred over the past month.

[1883] (Output) Time-series analyzed low voltage alarm data.

[1884] Step 5:

[1885] The server analyzes the collected inspection result data and evaluates the battery replacement history and condition.

[1886] (Input) Inspection result data obtained in Step 2.

[1887] (Data processing / calculation) Use SQL queries to examine exchange history and calculate time since last exchange.

[1888] (Output) Battery replacement history and evaluation results.

[1889] Step 6:

[1890] The server evaluates the battery life based on the results of time series analysis and inspection history analysis.

[1891] (Input) Data obtained in Steps 4 and 5.

[1892] (Data processing / calculation) Remaining lifespan is estimated using machine learning models (e.g., regression models and random forests).

[1893] (Output) Estimated remaining battery life.

[1894] Step 7:

[1895] The server generates a list of base stations that are assessed to be nearing the end of their life.

[1896] (Input) Estimated remaining battery life from step 6.

[1897] (Data processing / calculation) List base stations whose remaining lifespan is below a standard value (e.g., less than 3 months).

[1898] (Output) List of base stations that require site inspection.

[1899] Step 8:

[1900] The server generates a notification message based on the list of base stations that require on-site inspection.

[1901] (Input) The base station list generated in step 7.

[1902] (Data processing / calculation) A notification message is generated, for example, "Base station ABC has 3 months of battery life remaining. An on-site inspection is required."

[1903] (Output) The generated notification message.

[1904] Step 9:

[1905] The terminal sends a notification message to the user (person in charge).

[1906] (Input) The notification message generated in step 8.

[1907] (Data processing / calculation) Send messages to users using push notifications or SMS.

[1908] (Output) The notification message to be sent to the user.

[1909] Step 10:

[1910] The emotion engine analyzes the user's reaction to the notifications they receive.

[1911] (Input) User notification confirmation time and reaction speed.

[1912] (Data processing / computation) Use sentiment analysis algorithms to evaluate the emotions users have about notifications.

[1913] (Output) Parsed emotion data.

[1914] Step 11:

[1915] The emotion engine adjusts the content and timing of notification messages based on the analyzed emotional data.

[1916] (Input) Emotion data parsed in step 10.

[1917] (Data processing / calculation) A prompt sentence is generated, and if the user feels busy, for example, the timing of the next notification is adjusted appropriately.

[1918] (Output) Adjusted notification message content and sending timing.

[1919] Step 12:

[1920] The user (person in charge) receives the notification and prepares for the on-site investigation.

[1921] (Input) The notification messages sent in Step 9 and Step 11.

[1922] (Data processing / calculation) Set the survey schedule and prepare the necessary tools and equipment.

[1923] (Output) The completed site survey plan.

[1924] Step 13:

[1925] The user (person in charge) goes to the site and checks the batteries of the listed base stations.

[1926] (Input) The site investigation plan prepared in step 12.

[1927] (Data processing / calculation) Inspection work is carried out, batteries are replaced if necessary, and the results are recorded in the database.

[1928] (Output) Updated inspection result data and replacement history.

[1929] (Application example 2)

[1930] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1931] The problem to be solved by this invention is a system for evaluating the battery life of robots in factories, improving the efficiency of their management, and providing maintenance notifications at appropriate times. In the past, it was difficult to effectively manage the battery life of robots in factories and perform appropriate maintenance, which could result in an impact on the operation of the robots. Furthermore, there was a need for a method for providing notifications efficiently while reducing the burden on maintenance personnel.

[1932] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1933] In this invention, the server includes means for collecting base station monitoring data, means for filtering battery-related data from the collected monitoring data, means for acquiring past inspection result data, means for evaluating battery life by analyzing the filtered data and the past inspection result data, means for listing base stations requiring on-site inspection based on the evaluation results, means for notifying the user of the list of base stations requiring on-site inspection, and means for analyzing the user's emotions and optimizing the content and transmission timing of the notification message. This enables accurate evaluation of the robot's battery life, optimal timing for on-site inspection, and efficient maintenance.

[1934] A "base station" is a device that is a relay point in a communication network and provides monitoring data.

[1935] "Monitoring data" refers to data such as voltage, temperature, and current collected from the base station.

[1936] "Battery-related data" refers to information from the monitoring data that relates to the state and lifespan of the battery.

[1937] "Filtering" refers to the process of extracting data that meets specific conditions from collected monitoring data.

[1938] "Inspection result data" refers to records of past inspections and data related to the results of those inspections.

[1939] "Analysis" refers to the process of performing calculations and evaluations based on data to predict the battery's condition and lifespan.

[1940] "Battery life assessment" refers to predicting the remaining life of a battery based on data analyzed by the server.

[1941] "On-site inspection" refers to actually visiting a base station to replace or perform maintenance on batteries.

[1942] "Emotion analysis" refers to extracting and analyzing the emotions of a user based on the user's emotional data.

[1943] An embodiment of the present invention is described in detail below. The present invention relates to a battery management system for robots in a factory. The system includes multiple robots, a server, a user, and an emotion analysis engine. This system can accurately evaluate the battery life of the robots and enable timely on-site inspection and maintenance.

[1944] System Configuration

[1945] This system consists of a robot, a server, a user, and a sentiment analysis engine. The robot operates in the factory and provides monitoring data. The server is the main device that processes and analyzes the monitoring data and evaluates battery life. The user receives notifications and performs on-site inspections. The sentiment analysis engine analyzes user emotions and optimizes the content and timing of notifications.

[1946] Program Operation

[1947] Data collection

[1948] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[1949] The server also retrieves past inspection result data from the database, including battery replacement history and detailed inspection results.

[1950] Data Filtering

[1951] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[1952] Time Series Analysis

[1953] The server analyzes the filtered alarm data in chronological order to extract its frequency and patterns, and confirms that "low voltage" alarms have occurred five times in the past month.

[1954] Inspection history analysis

[1955] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[1956] Battery Life Rating

[1957] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[1958] If the server determines that the battery life is below a standard value (e.g., less than three months remaining), it lists the robot as one that requires on-site inspection.

[1959] Field survey list generation and notification

[1960] The server generates a list of robots that are assessed as nearing the end of their lifespan, making it clear which robots need to be investigated.

[1961] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[1962] The user (person in charge) receives and confirms the notification message from the server.

[1963] Emotion analysis using an emotion analysis engine

[1964] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[1965] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[1966] Preparation and implementation of on-site surveys

[1967] The user (person in charge) receives the notification and prepares the on-site investigation, sets the investigation schedule, and prepares the necessary tools and equipment.

[1968] The user (person in charge) visits the site, inspects the batteries of the listed robots, replaces the batteries as necessary, and updates the database with the results.

[1969] Specific examples

[1970] For example, the server collects and analyzes the following data for Robot A in a factory: Five "low voltage" alarms occurred in the past month, and the results of the last inspection indicated battery degradation. The server determines that the battery has three months or less of life left and adds Robot A to the on-site inspection list. The sentiment analysis engine recognizes how busy the user (person in charge) is and sends a notification at the optimal time saying, "Robot A's battery life is three months remaining. Please schedule an on-site inspection." The person in charge checks the notification, prepares for the on-site inspection, and actually inspects Robot A. System stability is ensured by checking the battery status on-site and replacing it if necessary.

[1971] Prompt Sentence Examples

[1972] prompt:

[1973] "Please describe a system that combines battery life assessment for factory robots and optimal notification timing. Please include the following elements: data collection, data analysis, life assessment, notification generation, notification delivery, and sentiment analysis."

[1974] Expected output:

[1975] "The robots in the factory use sensors to collect monitoring data on battery voltage, temperature, and current, and send it to a server. The server analyzes the collected data and evaluates battery life. When a robot's lifespan is shortened, an emotion analysis engine analyzes the emotions of the person in charge and sends a maintenance notification at the optimal time. Once the maintenance is completed, the results are updated in the database to ensure the stability of the system."

[1976] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1977] Processing step flow

[1978] Step 1: Data collection

[1979] Specific behavior:

[1980] The server periodically collects monitoring data from each robot in the factory. The monitoring data includes information such as voltage, temperature, and current. For example, data is collected from Robot A every day and stored in the server's database.

[1981] Input: Monitoring data such as voltage, temperature, and current obtained from sensors inside the robot.

[1982] Output: Monitoring data stored in a database. The monitoring data is recorded in the database along with the date.

[1983] Step 2: Data filtering

[1984] Specific behavior:

[1985] The server filters the collected monitoring data for battery-related data, for example, extracting only "low voltage" alarms.

[1986] Input: All monitoring data stored in the database.

[1987] Output: Filtered battery related data. Data for "low voltage" alarms is extracted.

[1988] Step 3: Obtaining inspection result data

[1989] Specific behavior:

[1990] The server retrieves past inspection result data from a database, including battery replacement history and detailed inspection results.

[1991] Input: Inspection result data stored in the database.

[1992] Output: Obtained past inspection result data. The server reads the inspection result information into memory.

[1993] Step 4: Time series analysis

[1994] Specific behavior:

[1995] The server analyzes the filtered alarm data in chronological order to extract frequency and patterns, for example, checking that "low voltage" alarms have occurred five times in the past month.

[1996] Input: Filtered alarm data.

[1997] Output: Analysis results (alarm occurrence frequency and pattern). The server records the result that a "low voltage" alarm has occurred five times in the past month.

[1998] Step 5: Inspection history analysis

[1999] Specific behavior:

[2000] The server analyzes the collected inspection result data and evaluates the battery replacement history and status, for example, confirming that the battery has not been replaced for more than a year since the last inspection.

[2001] Input: Obtained inspection result data.

[2002] Output: Analysis results (battery replacement history and status). Information that the battery has not been replaced for over a year is recorded.

[2003] Step 6: Evaluate battery life

[2004] Specific behavior:

[2005] The server evaluates the battery life based on the results of time series analysis and inspection history analysis, and estimates the remaining life based on the frequency of alarms and inspection history.

[2006] Input: Time series analysis results and inspection history analysis results.

[2007] Output: Battery life assessment result. Information indicating that the remaining battery life is less than 3 months is recorded.

[2008] Step 7: Generate a site inspection list

[2009] Specific behavior:

[2010] The server generates a list of robots that are assessed to be nearing the end of their lifespan, making it clear which robots need to be investigated.

[2011] Input: Battery life assessment results.

[2012] Output: List of robots that require on-site investigation. A list of robots that require investigation is generated.

[2013] Step 8: Generate and send a notification message

[2014] Specific behavior:

[2015] The server generates a notification message based on the list of robots that require on-site inspection. For example, it creates a notification saying, "Robot A's battery life is 3 months. On-site inspection is required."

[2016] Input: List of robots that require on-site inspection.

[2017] Output: Notification message. A notification message is sent to the user's terminal.

[2018] Step 9: Sentiment analysis using a sentiment analysis engine

[2019] Specific behavior:

[2020] The emotion analysis engine analyzes the user's reaction to the notification and extracts the user's emotion. For example, if the user feels stressed by the notification, the emotion analysis engine will recognize that.

[2021] Input: User response data.

[2022] Output: Parsed emotion data. Information that the user is feeling stressed is recorded.

[2023] Step 10: Optimize notification timing

[2024] Specific behavior:

[2025] The emotion analysis engine adjusts the content and timing of notification messages based on the analyzed emotion data. For example, if the user feels busy, the timing of the next notification will be adjusted to reduce stress.

[2026] Input: Parsed emotion data.

[2027] Output: Optimized notification timing. Notifications are sent at the best possible time for the user.

[2028] Step 11: Prepare and conduct the site survey

[2029] Specific behavior:

[2030] The user (person in charge) receives the notification and prepares for the on-site inspection. They set up an inspection schedule and prepare the necessary tools and equipment. The user then goes to the site and checks the batteries of the listed robots. They replace the batteries as necessary and update the database with the records.

[2031] Input: Notification message and required investigation tools.

[2032] Output: Updated inspection result data. The results of the on-site inspection and battery replacement are recorded in the database.

[2033] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2034] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2035] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2036] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2037] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2038] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2039] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2040] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2041] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2042] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the em...

Claims

1. means for collecting base station monitoring data; means for filtering data relating to the battery from the collected monitoring data; A means for obtaining past inspection result data; a means for analyzing the filtered data and past inspection result data to assess the lifespan of the battery; A means for listing base stations that require on-site inspection based on the evaluation results; a means for notifying a list of base stations that require on-site inspection; A system including:

2. 2. The system of claim 1, wherein the monitoring data is collected periodically.

3. 10. The system of claim 1, further comprising an algorithm for estimating battery life.

Images